diff --git a/preprocess/analysedonnees.ipynb b/preprocess/analysedonnees.ipynb
index 59d3a0e471ea66a8cd20cc7e6952e3985ad06b86..4a98caa046eea6863f783107f0788c1421bfe231 100644
--- a/preprocess/analysedonnees.ipynb
+++ b/preprocess/analysedonnees.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -10,7 +10,40 @@
"\n",
"X = pd.read_csv('data/X_train_6ZIKlTY.csv')\n",
"y = pd.read_csv('data/y_train_lXj6X5y.csv')\n",
- "X_challenge = pd.read_csv('data/X_test_oiZ2ukx.csv')"
+ "X_challenge = pd.read_csv('data/X_test_oiZ2ukx.csv')\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index 0\n",
+ "patient_id 0\n",
+ "cohort 0\n",
+ "sexM 0\n",
+ "gene 7763\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "ledd 8865\n",
+ "time_since_intake_on 11196\n",
+ "time_since_intake_off 18641\n",
+ "on 7264\n",
+ "off 9770\n",
+ "time_since_diagnosis 0\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_challenge.isna().sum()"
]
},
{
diff --git a/preprocess/enfinpeutetre.csv b/preprocess/enfinpeutetre.csv
new file mode 100644
index 0000000000000000000000000000000000000000..f8408f9c8e7fe1b1db75a79edd40621e0ec40e04
--- /dev/null
+++ b/preprocess/enfinpeutetre.csv
@@ -0,0 +1,23673 @@
+Index,target
+0,41.35045
+1,43.303
+2,44.069
+3,48.014694
+4,50.621983
+5,53.705776
+6,56.259987
+7,59.443783
+8,59.55727
+9,60.49054
+10,66.43864
+11,64.12637
+12,17.43744
+13,23.829592
+14,26.577875
+15,24.867691
+16,44.47344
+17,48.366028
+18,50.361763
+19,48.049446
+20,25.16687
+21,28.091026
+22,34.362846
+23,46.27726
+24,8.466401
+25,9.200819
+26,8.290071
+27,11.486822
+28,27.681717
+29,28.273903
+30,32.1877
+31,34.3969
+32,39.088375
+33,37.897728
+34,40.984535
+35,39.970047
+36,45.03779
+37,50.04254
+38,56.402626
+39,60.558304
+40,12.061905
+41,14.139614
+42,18.01417
+43,21.519726
+44,24.16504
+45,25.401379
+46,26.588541
+47,32.65162
+48,38.11237
+49,39.259823
+50,44.106655
+51,35.63301
+52,38.29442
+53,37.517746
+54,44.656784
+55,51.954067
+56,59.02542
+57,57.99025
+58,60.224823
+59,62.794846
+60,64.75348
+61,70.104416
+62,13.861122
+63,17.351187
+64,19.367607
+65,20.702963
+66,25.504602
+67,26.0498
+68,27.986176
+69,33.718304
+70,35.21089
+71,40.903774
+72,41.726868
+73,49.46301
+74,22.48182
+75,24.239668
+76,25.553293
+77,28.555204
+78,24.128939
+79,30.092861
+80,30.656246
+81,35.650887
+82,40.784756
+83,45.850822
+84,49.517776
+85,50.20489
+86,51.94616
+87,56.525906
+88,57.167953
+89,61.25274
+90,41.71733
+91,46.942955
+92,48.921764
+93,49.923107
+94,53.003677
+95,56.857826
+96,57.01244
+97,58.01691
+98,61.358513
+99,61.74778
+100,62.31282
+101,65.553406
+102,25.609802
+103,28.969242
+104,30.546078
+105,34.929443
+106,38.893936
+107,41.12555
+108,44.146797
+109,49.245316
+110,50.53435
+111,52.46841
+112,56.1988
+113,60.16512
+114,20.188911
+115,21.516462
+116,23.47515
+117,24.155258
+118,28.154266
+119,27.378872
+120,30.845743
+121,32.34512
+122,33.122284
+123,35.969738
+124,40.35344
+125,41.22037
+126,27.009653
+127,31.086452
+128,31.952827
+129,33.026894
+130,35.18383
+131,38.868343
+132,41.362488
+133,45.185192
+134,45.838585
+135,50.25444
+136,51.406506
+137,57.96224
+138,15.375208
+139,17.302021
+140,20.687569
+141,21.06535
+142,25.617966
+143,27.601656
+144,29.049732
+145,32.764793
+146,35.128983
+147,37.520523
+148,37.603054
+149,37.95673
+150,26.66668
+151,29.633629
+152,29.212475
+153,32.699898
+154,31.983149
+155,34.81964
+156,35.093952
+157,39.917297
+158,43.038654
+159,51.01702
+160,51.18418
+161,57.236866
+162,25.40978
+163,28.322376
+164,27.31635
+165,31.33274
+166,33.54664
+167,39.515812
+168,43.322456
+169,47.275494
+170,44.817112
+171,47.34939
+172,53.163128
+173,25.481857
+174,34.71269
+175,39.37292
+176,41.75401
+177,8.403828
+178,11.329926
+179,12.997315
+180,16.175926
+181,19.334332
+182,18.344666
+183,23.059065
+184,23.643364
+185,25.56799
+186,32.87428
+187,34.557896
+188,37.10363
+189,1.6052858
+190,4.3646154
+191,6.96739
+192,8.995832
+193,11.510779
+194,15.400359
+195,17.239664
+196,20.234812
+197,17.73435
+198,22.764664
+199,26.82936
+200,30.964367
+201,11.004606
+202,12.341604
+203,14.024992
+204,13.998241
+205,17.527618
+206,20.343555
+207,21.87934
+208,23.101583
+209,25.54884
+210,28.8395
+211,28.507088
+212,45.230152
+213,46.39695
+214,47.98372
+215,52.39849
+216,28.168352
+217,30.440392
+218,29.495028
+219,35.981144
+220,35.04254
+221,36.747143
+222,38.50762
+223,44.156754
+224,48.514156
+225,49.46022
+226,22.283993
+227,25.553999
+228,28.964842
+229,30.39058
+230,31.504702
+231,35.864315
+232,35.740257
+233,37.71904
+234,36.560616
+235,11.093397
+236,11.909581
+237,14.165369
+238,16.546844
+239,18.640862
+240,27.635057
+241,33.758736
+242,30.862688
+243,39.93164
+244,46.51139
+245,47.425556
+246,52.27748
+247,52.884056
+248,56.577045
+249,63.25326
+250,21.698093
+251,28.04613
+252,30.254349
+253,31.502457
+254,35.261326
+255,36.198853
+256,37.25781
+257,42.134457
+258,48.614655
+259,44.477036
+260,47.551575
+261,46.755775
+262,48.954453
+263,52.014935
+264,15.604825
+265,20.055237
+266,22.234825
+267,26.973507
+268,27.35696
+269,29.98497
+270,29.896969
+271,38.00113
+272,21.483173
+273,27.345753
+274,31.647224
+275,31.31476
+276,35.198265
+277,34.696587
+278,29.412672
+279,33.53931
+280,37.52876
+281,41.65535
+282,40.653797
+283,44.888393
+284,46.443626
+285,48.4857
+286,51.032887
+287,50.246475
+288,52.17982
+289,48.854183
+290,52.91808
+291,55.03618
+292,53.80305
+293,54.968098
+294,58.513046
+295,58.64997
+296,60.003773
+297,62.64585
+298,65.880165
+299,40.16924
+300,45.53936
+301,45.439106
+302,50.534267
+303,51.247665
+304,51.70364
+305,56.493397
+306,58.029095
+307,61.043247
+308,61.534897
+309,29.383423
+310,31.287636
+311,34.17364
+312,39.58407
+313,41.34355
+314,48.31243
+315,49.36892
+316,11.404193
+317,15.075922
+318,16.754436
+319,30.484184
+320,4.7442245
+321,6.0790234
+322,10.704405
+323,14.29994
+324,19.691336
+325,40.24455
+326,43.2704
+327,54.16089
+328,57.515427
+329,16.992844
+330,19.918364
+331,21.409739
+332,23.512585
+333,56.90043
+334,61.766518
+335,65.91023
+336,64.62369
+337,8.647163
+338,12.63042
+339,16.953463
+340,14.935176
+341,24.14219
+342,25.080383
+343,23.844774
+344,30.496363
+345,27.25182
+346,29.6431
+347,32.46492
+348,31.683125
+349,47.551712
+350,46.95631
+351,48.43118
+352,51.60665
+353,51.89543
+354,49.63134
+355,52.86489
+356,49.845627
+357,51.893238
+358,54.675797
+359,54.986206
+360,50.717827
+361,57.55528
+362,57.183113
+363,60.72805
+364,59.561123
+365,25.435635
+366,26.686089
+367,27.452236
+368,35.381382
+369,28.489319
+370,35.029015
+371,43.433937
+372,50.699543
+373,37.204025
+374,38.447212
+375,37.160404
+376,40.81465
+377,15.011646
+378,17.125744
+379,18.682148
+380,18.611359
+381,20.109758
+382,31.476683
+383,33.34429
+384,29.731075
+385,32.495213
+386,36.356667
+387,36.94244
+388,41.725872
+389,26.366463
+390,28.969051
+391,39.777985
+392,41.43234
+393,42.409298
+394,46.96374
+395,48.317513
+396,51.405537
+397,51.295853
+398,54.9265
+399,56.939903
+400,59.300575
+401,28.820934
+402,30.688726
+403,31.306438
+404,34.332424
+405,38.577072
+406,36.672256
+407,37.76117
+408,42.22583
+409,47.017902
+410,52.039875
+411,20.567188
+412,24.258406
+413,27.629585
+414,31.021652
+415,28.974384
+416,30.640171
+417,34.02695
+418,24.665058
+419,30.576143
+420,35.553925
+421,37.78826
+422,41.12107
+423,14.778872
+424,19.575417
+425,22.786068
+426,20.983986
+427,23.73701
+428,37.66414
+429,45.496605
+430,48.560818
+431,48.303055
+432,54.282658
+433,32.118053
+434,33.089504
+435,32.692955
+436,35.52895
+437,34.935944
+438,35.89037
+439,35.504425
+440,38.09708
+441,39.04489
+442,41.441315
+443,42.68371
+444,42.671143
+445,46.15631
+446,5.1757417
+447,8.191668
+448,12.619269
+449,14.803829
+450,15.709034
+451,16.29726
+452,19.435959
+453,24.65739
+454,41.61605
+455,45.714912
+456,50.07417
+457,52.572037
+458,53.328056
+459,54.080063
+460,56.430923
+461,58.537987
+462,37.662083
+463,42.33995
+464,46.16606
+465,50.3464
+466,62.098644
+467,63.33751
+468,66.23889
+469,68.74345
+470,69.92894
+471,67.8818
+472,72.51202
+473,73.29658
+474,74.97259
+475,74.980934
+476,76.10034
+477,78.02125
+478,22.07281
+479,28.160591
+480,29.380146
+481,35.374996
+482,38.01513
+483,34.13017
+484,37.725143
+485,40.677994
+486,26.825932
+487,33.031197
+488,40.506844
+489,46.881798
+490,27.052382
+491,31.667418
+492,35.270405
+493,37.339085
+494,39.572777
+495,30.01094
+496,42.255646
+497,46.257362
+498,40.200333
+499,43.166832
+500,46.7707
+501,48.43003
+502,49.92195
+503,52.53
+504,55.499386
+505,54.540367
+506,59.719604
+507,7.190899
+508,7.8643036
+509,9.048094
+510,15.63074
+511,31.08384
+512,32.42964
+513,33.663193
+514,36.560593
+515,35.634174
+516,40.350113
+517,44.92826
+518,46.42929
+519,44.490814
+520,47.624615
+521,52.145023
+522,53.762493
+523,22.62545
+524,24.623032
+525,29.537895
+526,35.8176
+527,38.948616
+528,39.635124
+529,44.33017
+530,46.711548
+531,54.97283
+532,59.773296
+533,62.10396
+534,65.34957
+535,67.96083
+536,66.86126
+537,69.26163
+538,72.39214
+539,72.13255
+540,30.768652
+541,30.325039
+542,34.7962
+543,36.4575
+544,6.2495437
+545,9.003016
+546,12.103296
+547,17.015673
+548,19.925125
+549,17.416418
+550,24.023285
+551,35.774292
+552,42.39541
+553,34.223015
+554,36.541325
+555,41.785553
+556,46.824528
+557,47.380165
+558,52.820724
+559,51.392963
+560,53.39842
+561,58.86836
+562,61.513428
+563,60.6512
+564,59.848537
+565,15.745135
+566,14.683944
+567,15.716909
+568,22.755028
+569,26.684599
+570,52.058533
+571,51.422813
+572,52.326855
+573,54.81338
+574,55.669907
+575,61.37581
+576,26.818716
+577,30.579834
+578,32.89301
+579,36.752842
+580,37.472717
+581,38.588444
+582,44.28554
+583,47.20748
+584,13.767373
+585,21.598951
+586,25.170555
+587,25.147242
+588,28.37762
+589,50.12864
+590,52.358414
+591,54.531322
+592,56.547993
+593,58.6483
+594,59.20329
+595,60.83886
+596,61.353317
+597,63.302868
+598,64.95856
+599,67.09034
+600,68.7943
+601,43.029263
+602,51.347134
+603,53.81809
+604,55.668617
+605,35.73692
+606,40.689182
+607,42.546494
+608,46.57386
+609,48.992607
+610,42.651283
+611,48.277664
+612,46.99553
+613,48.17366
+614,53.007374
+615,51.859394
+616,55.183926
+617,56.55483
+618,19.991077
+619,20.773054
+620,23.437906
+621,27.089369
+622,26.271044
+623,28.279957
+624,28.577196
+625,25.168486
+626,34.614117
+627,37.358875
+628,39.61038
+629,0.89035916
+630,1.8183206
+631,4.885182
+632,7.3414097
+633,8.71186
+634,11.756801
+635,14.223604
+636,17.469564
+637,20.059334
+638,20.073387
+639,21.666784
+640,27.31821
+641,1.0660062
+642,0.7773156
+643,2.3923173
+644,3.407948
+645,9.71581
+646,16.202644
+647,20.02955
+648,20.736298
+649,24.79069
+650,20.728392
+651,25.181581
+652,26.910704
+653,30.9044
+654,32.195415
+655,34.77986
+656,36.338104
+657,40.259727
+658,37.26899
+659,40.684853
+660,48.390903
+661,50.61133
+662,43.139328
+663,41.010315
+664,40.32777
+665,41.74421
+666,41.779156
+667,42.173183
+668,46.68127
+669,46.413895
+670,47.22966
+671,24.981045
+672,28.864645
+673,39.98678
+674,38.851784
+675,36.36017
+676,40.25929
+677,42.24153
+678,46.88893
+679,42.77775
+680,44.828106
+681,47.668068
+682,50.911575
+683,25.628355
+684,26.67144
+685,31.278072
+686,33.399155
+687,32.723293
+688,37.237846
+689,38.82228
+690,39.088547
+691,43.56362
+692,45.99958
+693,45.56907
+694,47.94567
+695,21.747677
+696,31.45427
+697,31.548182
+698,31.489372
+699,33.179604
+700,43.5627
+701,42.8374
+702,45.52833
+703,49.301476
+704,51.108326
+705,54.12089
+706,58.75786
+707,42.08725
+708,45.82606
+709,52.7995
+710,56.711258
+711,52.28937
+712,53.76389
+713,55.60752
+714,58.15837
+715,59.00763
+716,60.191307
+717,61.814854
+718,63.7665
+719,62.51199
+720,68.26699
+721,66.77277
+722,65.93163
+723,40.192574
+724,46.303352
+725,47.59333
+726,50.6105
+727,7.5182133
+728,15.484402
+729,20.906483
+730,24.485386
+731,29.57314
+732,39.64634
+733,47.548077
+734,51.90992
+735,59.148315
+736,63.24061
+737,11.8737755
+738,12.957703
+739,15.6643095
+740,20.89826
+741,24.754122
+742,26.582731
+743,28.101871
+744,31.120098
+745,35.89708
+746,38.63272
+747,40.062363
+748,50.15505
+749,42.228683
+750,44.37339
+751,47.717815
+752,49.63067
+753,12.79421
+754,13.838559
+755,15.32079
+756,17.026775
+757,21.05618
+758,23.155779
+759,25.917831
+760,27.561749
+761,40.730076
+762,41.46278
+763,40.262638
+764,45.566963
+765,11.058015
+766,12.100565
+767,11.585045
+768,15.08191
+769,16.250193
+770,22.98453
+771,24.876274
+772,22.154324
+773,23.969555
+774,26.087898
+775,27.693283
+776,27.466314
+777,0.09685577
+778,0.61274946
+779,0.9912815
+780,6.436222
+781,29.518309
+782,38.848625
+783,43.160362
+784,42.884518
+785,26.164791
+786,26.477953
+787,28.321651
+788,32.039818
+789,33.631065
+790,39.61207
+791,43.10189
+792,42.30345
+793,48.261604
+794,6.7143326
+795,9.381642
+796,14.609254
+797,16.23507
+798,17.652739
+799,20.170736
+800,28.718151
+801,32.968254
+802,34.14389
+803,35.735332
+804,34.46495
+805,38.80522
+806,36.083706
+807,36.454605
+808,37.44242
+809,40.108875
+810,2.0227506
+811,2.4166675
+812,3.4854279
+813,7.982171
+814,43.236523
+815,49.229233
+816,50.778404
+817,58.162666
+818,11.173294
+819,16.695734
+820,21.862156
+821,26.035925
+822,43.493046
+823,52.187237
+824,55.382812
+825,53.04277
+826,54.293663
+827,56.366943
+828,56.181423
+829,57.493027
+830,61.20716
+831,61.230095
+832,60.327286
+833,63.569153
+834,24.726738
+835,30.522879
+836,36.459675
+837,46.00892
+838,37.952217
+839,39.764442
+840,41.225563
+841,42.99658
+842,46.013992
+843,48.872467
+844,49.944477
+845,51.09245
+846,51.327038
+847,52.1466
+848,55.905144
+849,57.793167
+850,32.373013
+851,32.63843
+852,35.460205
+853,37.21495
+854,43.219666
+855,49.113842
+856,50.032852
+857,55.429752
+858,57.862305
+859,56.72582
+860,61.985123
+861,62.5955
+862,25.068806
+863,27.692986
+864,27.524017
+865,33.25787
+866,35.28908
+867,32.900696
+868,35.942257
+869,38.38671
+870,43.328568
+871,49.664993
+872,51.86093
+873,54.17955
+874,20.95195
+875,25.166756
+876,28.38073
+877,33.021217
+878,35.393425
+879,36.60151
+880,36.631817
+881,41.758377
+882,41.868057
+883,46.579582
+884,49.58132
+885,50.762222
+886,52.220726
+887,53.452824
+888,54.920414
+889,55.888332
+890,38.278854
+891,44.5068
+892,47.10633
+893,47.23439
+894,40.906242
+895,39.70453
+896,39.47325
+897,42.73864
+898,12.129745
+899,12.321188
+900,14.53477
+901,11.362302
+902,13.317281
+903,31.134302
+904,37.452255
+905,39.99031
+906,38.740166
+907,40.895203
+908,45.230858
+909,50.514587
+910,51.008636
+911,56.560806
+912,55.20394
+913,55.684227
+914,16.303944
+915,17.764416
+916,19.663471
+917,23.78033
+918,26.361902
+919,30.910334
+920,31.31688
+921,42.139183
+922,45.24091
+923,46.54241
+924,50.391804
+925,52.548294
+926,57.399952
+927,57.858715
+928,59.88453
+929,60.84307
+930,62.731197
+931,63.501865
+932,65.105515
+933,5.358291
+934,7.0547314
+935,10.400194
+936,19.406586
+937,24.049978
+938,27.502165
+939,32.505245
+940,36.46299
+941,37.609795
+942,1.1479268
+943,0.7064705
+944,4.0306206
+945,5.3300242
+946,9.333704
+947,37.315952
+948,43.344402
+949,47.85025
+950,51.847054
+951,54.320683
+952,36.482304
+953,38.99501
+954,40.069416
+955,41.873997
+956,48.835995
+957,49.704662
+958,53.350506
+959,53.54886
+960,55.469868
+961,55.96792
+962,59.42262
+963,16.153233
+964,19.230576
+965,21.181835
+966,31.766623
+967,42.656876
+968,52.4694
+969,55.3394
+970,58.58773
+971,27.452984
+972,26.767365
+973,28.231956
+974,30.615538
+975,41.02255
+976,41.945415
+977,41.539116
+978,44.719482
+979,24.662745
+980,24.806103
+981,25.098717
+982,27.771751
+983,53.093353
+984,54.364788
+985,55.05503
+986,58.151157
+987,63.317406
+988,60.07586
+989,62.45799
+990,63.66935
+991,61.34299
+992,66.90862
+993,67.12216
+994,69.93979
+995,1.8439087
+996,3.825645
+997,7.241151
+998,9.975937
+999,10.959907
+1000,19.454554
+1001,23.976448
+1002,25.311403
+1003,30.89551
+1004,37.374905
+1005,14.724349
+1006,17.269068
+1007,22.357944
+1008,25.389568
+1009,24.526781
+1010,27.291344
+1011,16.695309
+1012,16.363071
+1013,22.621073
+1014,24.237871
+1015,26.988564
+1016,33.450863
+1017,42.542866
+1018,44.764885
+1019,45.13758
+1020,46.37037
+1021,47.446434
+1022,51.46652
+1023,52.402134
+1024,58.70578
+1025,55.754295
+1026,17.206413
+1027,21.205555
+1028,23.424902
+1029,23.68649
+1030,27.827953
+1031,33.147404
+1032,32.93333
+1033,36.23959
+1034,37.57904
+1035,42.57044
+1036,44.30061
+1037,46.68692
+1038,47.41246
+1039,50.65192
+1040,51.423897
+1041,54.93441
+1042,54.745285
+1043,48.34952
+1044,50.713253
+1045,49.986645
+1046,55.595367
+1047,60.659462
+1048,60.855633
+1049,60.00215
+1050,61.643276
+1051,63.63637
+1052,63.499947
+1053,66.0634
+1054,69.46393
+1055,28.839418
+1056,34.284187
+1057,36.091995
+1058,37.21415
+1059,33.260715
+1060,39.313354
+1061,43.29974
+1062,49.51645
+1063,54.58464
+1064,53.081318
+1065,56.128296
+1066,58.74118
+1067,31.382662
+1068,36.160854
+1069,39.771507
+1070,42.641212
+1071,37.674587
+1072,43.253437
+1073,50.35176
+1074,54.70582
+1075,29.007093
+1076,30.650581
+1077,31.54826
+1078,44.699295
+1079,26.257053
+1080,29.402378
+1081,29.49686
+1082,30.981905
+1083,7.890425
+1084,10.869828
+1085,11.1656
+1086,12.310913
+1087,15.172628
+1088,16.911022
+1089,17.922794
+1090,23.125141
+1091,21.64654
+1092,30.884384
+1093,33.46396
+1094,33.920662
+1095,30.366028
+1096,34.95713
+1097,37.374413
+1098,40.27253
+1099,41.516716
+1100,44.85028
+1101,45.22352
+1102,49.078655
+1103,51.682373
+1104,51.877045
+1105,55.387245
+1106,58.83323
+1107,18.60548
+1108,28.172947
+1109,32.233044
+1110,31.988632
+1111,19.500883
+1112,22.950155
+1113,23.829754
+1114,29.243076
+1115,29.035677
+1116,34.746696
+1117,36.151623
+1118,39.620308
+1119,44.29504
+1120,46.09589
+1121,50.133736
+1122,53.960724
+1123,55.80429
+1124,57.44069
+1125,58.694763
+1126,59.06352
+1127,62.40678
+1128,64.14761
+1129,56.97402
+1130,66.3023
+1131,66.02425
+1132,67.07458
+1133,21.277378
+1134,23.72953
+1135,30.767605
+1136,32.59996
+1137,32.04837
+1138,32.652714
+1139,33.913048
+1140,42.20935
+1141,43.370552
+1142,47.66249
+1143,57.800858
+1144,51.747173
+1145,29.644697
+1146,31.224838
+1147,35.4386
+1148,43.650436
+1149,44.53989
+1150,45.312035
+1151,47.710987
+1152,32.974274
+1153,35.902245
+1154,37.804283
+1155,40.57941
+1156,22.32456
+1157,23.423046
+1158,25.48246
+1159,29.733648
+1160,32.686607
+1161,35.312973
+1162,37.658356
+1163,41.80619
+1164,27.686615
+1165,30.71957
+1166,36.813896
+1167,42.409668
+1168,46.452293
+1169,9.70591
+1170,9.970783
+1171,10.726667
+1172,13.269481
+1173,17.873917
+1174,18.271097
+1175,19.822226
+1176,21.829962
+1177,24.802145
+1178,28.559559
+1179,28.720564
+1180,30.803337
+1181,37.3521
+1182,36.45174
+1183,42.47759
+1184,38.086807
+1185,44.087734
+1186,17.865055
+1187,21.684229
+1188,25.280922
+1189,31.303753
+1190,34.102783
+1191,45.51086
+1192,54.54507
+1193,61.95656
+1194,20.537376
+1195,20.456257
+1196,22.225359
+1197,24.155731
+1198,29.452995
+1199,35.623146
+1200,41.63194
+1201,43.030533
+1202,-0.10683804
+1203,0.79824346
+1204,0.63020164
+1205,2.8638742
+1206,6.238479
+1207,7.7226286
+1208,9.637768
+1209,10.496704
+1210,13.97491
+1211,11.582126
+1212,10.676216
+1213,12.680576
+1214,13.849954
+1215,19.292603
+1216,19.977392
+1217,24.301672
+1218,27.037224
+1219,29.827671
+1220,38.439617
+1221,28.71732
+1222,35.121796
+1223,23.60625
+1224,27.904322
+1225,28.47065
+1226,30.76121
+1227,35.479973
+1228,36.962112
+1229,39.748894
+1230,44.347206
+1231,46.39084
+1232,49.606754
+1233,51.513226
+1234,52.15582
+1235,32.12421
+1236,35.29451
+1237,37.28114
+1238,43.51985
+1239,13.065634
+1240,13.925455
+1241,19.146101
+1242,22.47089
+1243,17.46054
+1244,18.510223
+1245,19.653378
+1246,21.545216
+1247,24.846067
+1248,24.234947
+1249,29.669117
+1250,35.805546
+1251,31.18064
+1252,32.40382
+1253,33.58368
+1254,35.005478
+1255,37.27677
+1256,40.994167
+1257,39.385033
+1258,43.204422
+1259,43.054688
+1260,19.402748
+1261,20.784126
+1262,22.360725
+1263,26.720707
+1264,28.887693
+1265,32.572666
+1266,35.35087
+1267,37.839855
+1268,41.212814
+1269,47.025726
+1270,50.880325
+1271,47.38376
+1272,33.538746
+1273,34.751884
+1274,37.091736
+1275,39.3079
+1276,42.26289
+1277,43.68965
+1278,47.375454
+1279,50.328716
+1280,51.000343
+1281,54.801487
+1282,56.506256
+1283,11.605175
+1284,16.48713
+1285,19.005186
+1286,20.433653
+1287,26.133104
+1288,24.374187
+1289,25.546318
+1290,30.422142
+1291,30.325285
+1292,31.518936
+1293,32.059376
+1294,33.779045
+1295,25.938137
+1296,32.390835
+1297,35.44281
+1298,37.78904
+1299,23.974918
+1300,22.72881
+1301,27.85268
+1302,40.51951
+1303,41.7717
+1304,39.092583
+1305,46.06013
+1306,49.344944
+1307,50.909424
+1308,51.82405
+1309,55.695972
+1310,58.629646
+1311,23.45345
+1312,27.282642
+1313,31.508314
+1314,33.257507
+1315,31.753756
+1316,40.17926
+1317,43.922325
+1318,44.485065
+1319,46.789375
+1320,44.95938
+1321,49.641014
+1322,53.80426
+1323,23.04822
+1324,23.942436
+1325,27.006836
+1326,29.468456
+1327,30.51768
+1328,34.56461
+1329,39.816025
+1330,43.7109
+1331,16.734198
+1332,19.107296
+1333,22.333378
+1334,24.361935
+1335,31.20973
+1336,19.190903
+1337,19.917446
+1338,22.16409
+1339,26.243008
+1340,29.871565
+1341,28.62554
+1342,30.973454
+1343,36.23448
+1344,41.688293
+1345,44.944748
+1346,47.10634
+1347,49.140507
+1348,50.911728
+1349,54.980877
+1350,54.81021
+1351,56.445255
+1352,57.21552
+1353,61.027424
+1354,64.972725
+1355,65.39951
+1356,66.21976
+1357,69.79528
+1358,70.49614
+1359,73.02154
+1360,72.5181
+1361,75.01248
+1362,73.831184
+1363,75.916756
+1364,75.00834
+1365,29.00866
+1366,30.521772
+1367,43.10173
+1368,45.466423
+1369,47.92689
+1370,18.069532
+1371,18.629276
+1372,20.767014
+1373,21.945423
+1374,13.654039
+1375,14.093866
+1376,18.093882
+1377,18.156534
+1378,24.834734
+1379,14.052538
+1380,17.006454
+1381,22.748709
+1382,24.93414
+1383,26.31779
+1384,28.9485
+1385,30.835913
+1386,31.379765
+1387,42.52208
+1388,42.332893
+1389,49.55974
+1390,15.649696
+1391,20.548029
+1392,23.038357
+1393,25.026777
+1394,30.271542
+1395,34.557896
+1396,50.133194
+1397,55.61076
+1398,56.97637
+1399,60.644962
+1400,62.855194
+1401,63.60569
+1402,61.230362
+1403,65.251434
+1404,69.69872
+1405,69.83833
+1406,71.48081
+1407,72.71974
+1408,15.601191
+1409,19.535898
+1410,21.867144
+1411,25.122288
+1412,24.873957
+1413,25.222267
+1414,34.627033
+1415,13.864289
+1416,14.568326
+1417,17.265762
+1418,19.672562
+1419,24.616474
+1420,26.420843
+1421,26.31976
+1422,29.114964
+1423,33.87967
+1424,35.48225
+1425,36.83127
+1426,39.307358
+1427,35.3424
+1428,39.900627
+1429,40.076103
+1430,43.550995
+1431,44.152733
+1432,48.62394
+1433,53.175247
+1434,51.746735
+1435,56.339676
+1436,50.30377
+1437,57.755558
+1438,63.223946
+1439,63.881603
+1440,33.04359
+1441,33.228554
+1442,34.89337
+1443,36.082478
+1444,38.877663
+1445,39.67661
+1446,13.3752165
+1447,15.008129
+1448,16.513662
+1449,18.505968
+1450,26.067652
+1451,32.86087
+1452,57.241417
+1453,60.38578
+1454,58.48024
+1455,64.96516
+1456,65.00395
+1457,66.46399
+1458,68.821884
+1459,69.8241
+1460,71.74461
+1461,71.42547
+1462,73.063255
+1463,73.248695
+1464,23.41828
+1465,25.480577
+1466,31.173605
+1467,39.48303
+1468,42.33282
+1469,39.187828
+1470,45.314587
+1471,54.8433
+1472,56.416897
+1473,63.86841
+1474,43.336845
+1475,44.22774
+1476,50.891914
+1477,53.941925
+1478,57.671967
+1479,54.628826
+1480,59.047054
+1481,59.769386
+1482,59.88852
+1483,65.59326
+1484,60.63534
+1485,63.881065
+1486,4.855432
+1487,6.165496
+1488,11.876641
+1489,14.728905
+1490,16.386524
+1491,17.680292
+1492,24.493406
+1493,28.735992
+1494,25.049805
+1495,27.520752
+1496,41.139767
+1497,54.704174
+1498,56.487694
+1499,59.12217
+1500,59.25797
+1501,61.58489
+1502,25.03237
+1503,31.011322
+1504,30.174406
+1505,34.57292
+1506,48.607826
+1507,49.186405
+1508,50.35059
+1509,54.30094
+1510,59.24502
+1511,64.98342
+1512,67.38393
+1513,67.54805
+1514,68.017784
+1515,69.60203
+1516,73.60511
+1517,74.13523
+1518,0.25651288
+1519,2.7652047
+1520,3.376545
+1521,4.3283625
+1522,8.210907
+1523,8.770229
+1524,11.538495
+1525,12.192167
+1526,19.512249
+1527,42.838425
+1528,48.032646
+1529,51.172897
+1530,55.34801
+1531,60.07504
+1532,59.444134
+1533,26.65794
+1534,27.65864
+1535,28.742073
+1536,28.61206
+1537,20.113398
+1538,20.665863
+1539,22.70554
+1540,29.668568
+1541,33.31288
+1542,35.767582
+1543,40.50235
+1544,44.18274
+1545,44.741272
+1546,45.584915
+1547,45.134342
+1548,51.20514
+1549,31.536304
+1550,37.053318
+1551,37.436264
+1552,50.004215
+1553,28.507788
+1554,44.47183
+1555,47.598232
+1556,47.77562
+1557,21.450232
+1558,21.506233
+1559,21.787777
+1560,25.181019
+1561,29.155436
+1562,30.673542
+1563,12.537016
+1564,15.925012
+1565,18.422855
+1566,23.450457
+1567,25.741692
+1568,26.95173
+1569,29.737545
+1570,31.959068
+1571,33.825806
+1572,36.045685
+1573,34.639233
+1574,35.68763
+1575,29.050175
+1576,29.156685
+1577,28.247524
+1578,30.521076
+1579,23.744183
+1580,29.39305
+1581,31.079279
+1582,33.007965
+1583,37.690865
+1584,39.281265
+1585,43.094433
+1586,46.17797
+1587,48.3384
+1588,51.91196
+1589,52.666195
+1590,54.84266
+1591,44.239433
+1592,46.343304
+1593,49.32491
+1594,52.525455
+1595,13.941093
+1596,15.148655
+1597,25.283157
+1598,27.68662
+1599,30.210632
+1600,36.22678
+1601,33.07566
+1602,38.552284
+1603,42.607826
+1604,41.94876
+1605,45.01786
+1606,50.51016
+1607,26.453188
+1608,31.374367
+1609,32.345245
+1610,34.671677
+1611,38.599533
+1612,40.515785
+1613,42.836502
+1614,47.42961
+1615,49.122616
+1616,51.681812
+1617,52.38683
+1618,54.4051
+1619,9.796341
+1620,14.041068
+1621,20.740166
+1622,25.640137
+1623,26.286789
+1624,33.113205
+1625,34.55157
+1626,35.58614
+1627,41.306637
+1628,48.470085
+1629,51.65055
+1630,49.41951
+1631,51.402603
+1632,53.7493
+1633,56.716667
+1634,63.152977
+1635,61.83377
+1636,14.419274
+1637,14.595572
+1638,16.180841
+1639,19.688293
+1640,20.671656
+1641,24.204388
+1642,26.4057
+1643,28.413784
+1644,32.06868
+1645,33.83411
+1646,34.132126
+1647,35.324394
+1648,17.20989
+1649,18.126333
+1650,28.746143
+1651,33.403557
+1652,38.153816
+1653,41.26336
+1654,42.140217
+1655,47.805504
+1656,49.448746
+1657,50.43888
+1658,51.52395
+1659,5.5126147
+1660,9.70388
+1661,12.975566
+1662,14.574112
+1663,16.656483
+1664,20.661173
+1665,2.9900193
+1666,3.928374
+1667,5.359599
+1668,4.5605326
+1669,5.9355884
+1670,33.556053
+1671,36.833076
+1672,41.27915
+1673,51.076897
+1674,53.136776
+1675,53.941925
+1676,56.123444
+1677,58.867004
+1678,59.832012
+1679,49.610493
+1680,48.879253
+1681,44.658634
+1682,47.174526
+1683,52.39459
+1684,46.753635
+1685,53.265778
+1686,52.062183
+1687,56.813908
+1688,57.57937
+1689,61.015312
+1690,59.675667
+1691,26.461765
+1692,28.986242
+1693,31.191526
+1694,34.741272
+1695,37.891262
+1696,38.350018
+1697,40.89733
+1698,44.34137
+1699,45.253223
+1700,46.546337
+1701,48.691193
+1702,52.91936
+1703,17.049353
+1704,18.442987
+1705,20.596155
+1706,28.092056
+1707,32.188072
+1708,15.575721
+1709,19.939295
+1710,22.567488
+1711,25.144524
+1712,24.731571
+1713,30.799006
+1714,30.184542
+1715,30.353706
+1716,32.240204
+1717,32.753334
+1718,1.7514918
+1719,2.5840864
+1720,7.1305504
+1721,7.224984
+1722,12.016257
+1723,15.051068
+1724,-0.59444714
+1725,-0.2129987
+1726,1.0040257
+1727,2.6742864
+1728,5.827091
+1729,7.052149
+1730,10.348889
+1731,15.769499
+1732,10.674109
+1733,12.05294
+1734,13.700837
+1735,14.653944
+1736,42.671265
+1737,47.420353
+1738,48.16777
+1739,49.54422
+1740,30.41064
+1741,35.54746
+1742,35.887817
+1743,35.93107
+1744,35.045033
+1745,36.760384
+1746,39.209576
+1747,41.632
+1748,36.338444
+1749,38.35873
+1750,37.678146
+1751,41.19074
+1752,40.895996
+1753,43.39059
+1754,44.32436
+1755,47.542065
+1756,48.06035
+1757,50.684914
+1758,51.79576
+1759,55.563328
+1760,49.211002
+1761,49.668385
+1762,53.34221
+1763,57.761562
+1764,60.469166
+1765,61.32591
+1766,63.45634
+1767,65.1039
+1768,67.02719
+1769,69.57948
+1770,71.98464
+1771,73.13249
+1772,14.561484
+1773,17.956907
+1774,18.44513
+1775,21.80554
+1776,26.001215
+1777,28.070314
+1778,29.888935
+1779,43.61563
+1780,44.0345
+1781,45.51012
+1782,47.889156
+1783,34.224968
+1784,38.180862
+1785,44.396004
+1786,47.91236
+1787,31.560722
+1788,46.266632
+1789,50.386543
+1790,52.592815
+1791,29.910374
+1792,33.860126
+1793,37.106842
+1794,37.86183
+1795,46.751854
+1796,48.05465
+1797,46.549423
+1798,47.299835
+1799,49.06333
+1800,50.091316
+1801,0.34652388
+1802,0.22293751
+1803,1.6190443
+1804,4.9115257
+1805,6.5453897
+1806,6.9803033
+1807,12.202242
+1808,13.9351225
+1809,16.152971
+1810,18.169079
+1811,18.561272
+1812,19.401436
+1813,21.037361
+1814,22.338322
+1815,25.3544
+1816,29.662148
+1817,32.327473
+1818,31.89177
+1819,34.72787
+1820,39.634373
+1821,42.471695
+1822,35.829746
+1823,45.521652
+1824,48.54561
+1825,42.01861
+1826,43.772217
+1827,48.48835
+1828,52.074127
+1829,4.7946877
+1830,6.188262
+1831,7.038304
+1832,11.40911
+1833,11.300571
+1834,14.727648
+1835,42.54278
+1836,52.153984
+1837,49.300247
+1838,53.984894
+1839,56.54306
+1840,59.675903
+1841,62.8182
+1842,63.04457
+1843,62.94063
+1844,65.66282
+1845,66.37102
+1846,66.26743
+1847,36.02296
+1848,37.859627
+1849,42.859085
+1850,46.108776
+1851,54.736176
+1852,0.121157855
+1853,0.7488666
+1854,0.646974
+1855,3.2972503
+1856,34.201263
+1857,35.288586
+1858,39.062263
+1859,43.664932
+1860,46.05181
+1861,54.592983
+1862,55.249794
+1863,56.93424
+1864,55.881706
+1865,61.079334
+1866,61.024082
+1867,62.022095
+1868,46.677532
+1869,46.639572
+1870,48.84214
+1871,51.812702
+1872,15.355992
+1873,20.35004
+1874,22.653862
+1875,24.71632
+1876,30.34026
+1877,34.167267
+1878,30.835947
+1879,34.252663
+1880,39.225136
+1881,39.241966
+1882,40.684303
+1883,41.452915
+1884,22.213053
+1885,21.569931
+1886,22.956757
+1887,23.961527
+1888,63.99154
+1889,69.336784
+1890,68.083084
+1891,69.82683
+1892,70.72565
+1893,72.142105
+1894,73.40296
+1895,73.27418
+1896,21.740002
+1897,21.873161
+1898,25.605087
+1899,22.85106
+1900,24.107075
+1901,27.839027
+1902,31.4778
+1903,35.601128
+1904,38.057343
+1905,40.77695
+1906,28.081202
+1907,30.258934
+1908,38.824276
+1909,42.813145
+1910,40.608902
+1911,43.672688
+1912,47.448616
+1913,48.01644
+1914,50.429615
+1915,51.49294
+1916,51.970554
+1917,55.503162
+1918,12.665856
+1919,23.115765
+1920,24.688955
+1921,28.009703
+1922,28.456032
+1923,24.906979
+1924,29.490845
+1925,32.62812
+1926,33.135555
+1927,34.30513
+1928,38.441254
+1929,42.92263
+1930,42.108356
+1931,43.713833
+1932,15.180262
+1933,20.481354
+1934,24.902273
+1935,27.372639
+1936,28.65519
+1937,31.631472
+1938,35.897614
+1939,38.808052
+1940,41.796844
+1941,48.776005
+1942,46.74224
+1943,50.297066
+1944,15.390614
+1945,16.39692
+1946,21.390455
+1947,30.848484
+1948,21.388668
+1949,20.87024
+1950,23.93774
+1951,23.487085
+1952,28.326153
+1953,32.132317
+1954,33.96788
+1955,34.16434
+1956,34.54661
+1957,36.2947
+1958,37.412975
+1959,46.70266
+1960,46.44029
+1961,48.964577
+1962,52.043903
+1963,49.604874
+1964,56.38629
+1965,21.049095
+1966,22.14775
+1967,28.897982
+1968,30.523874
+1969,33.962864
+1970,22.813736
+1971,27.147678
+1972,35.250435
+1973,34.433853
+1974,37.023144
+1975,40.388344
+1976,38.536133
+1977,44.322693
+1978,49.114105
+1979,49.19795
+1980,53.74575
+1981,54.340405
+1982,15.6989355
+1983,17.944555
+1984,17.263777
+1985,25.211685
+1986,13.637697
+1987,15.454601
+1988,18.604874
+1989,18.547712
+1990,26.01676
+1991,28.620857
+1992,32.68145
+1993,36.281334
+1994,36.379074
+1995,42.127922
+1996,47.027378
+1997,50.403404
+1998,2.0345635
+1999,5.6694946
+2000,9.217777
+2001,6.4237823
+2002,9.5845785
+2003,12.430112
+2004,14.504973
+2005,23.965412
+2006,22.769522
+2007,24.475197
+2008,25.17622
+2009,26.624662
+2010,35.905205
+2011,39.231964
+2012,42.076866
+2013,43.049747
+2014,44.954964
+2015,39.2553
+2016,41.50075
+2017,40.543617
+2018,51.49817
+2019,53.906986
+2020,54.748142
+2021,58.083023
+2022,58.361595
+2023,26.248516
+2024,29.197876
+2025,32.607185
+2026,36.24238
+2027,39.01706
+2028,40.58628
+2029,44.53906
+2030,48.105553
+2031,47.865685
+2032,48.640335
+2033,51.035385
+2034,53.562473
+2035,61.63909
+2036,61.72986
+2037,62.86654
+2038,67.6055
+2039,67.133354
+2040,48.813107
+2041,46.868885
+2042,52.65295
+2043,50.3331
+2044,11.053725
+2045,13.77345
+2046,18.781496
+2047,23.040613
+2048,20.496132
+2049,22.787003
+2050,22.920124
+2051,0.37974572
+2052,2.1331468
+2053,4.1937823
+2054,10.571676
+2055,32.00728
+2056,30.229105
+2057,33.622913
+2058,34.311646
+2059,35.518032
+2060,14.850317
+2061,16.879702
+2062,18.990545
+2063,24.036638
+2064,30.109917
+2065,39.59713
+2066,47.7558
+2067,50.47616
+2068,53.204823
+2069,54.382412
+2070,55.00714
+2071,55.34904
+2072,57.418648
+2073,61.903145
+2074,63.594677
+2075,65.24624
+2076,65.49191
+2077,31.165953
+2078,32.040596
+2079,34.349064
+2080,35.379524
+2081,37.023293
+2082,40.41559
+2083,43.320385
+2084,43.612827
+2085,45.58897
+2086,50.824013
+2087,51.078064
+2088,52.789074
+2089,9.698361
+2090,15.981023
+2091,19.042309
+2092,18.573847
+2093,21.60423
+2094,24.22093
+2095,28.079472
+2096,38.60964
+2097,38.37093
+2098,41.493713
+2099,46.337208
+2100,56.255997
+2101,14.18713
+2102,14.96506
+2103,15.388535
+2104,22.52501
+2105,24.65788
+2106,24.915312
+2107,26.582186
+2108,27.542011
+2109,30.566776
+2110,33.11676
+2111,34.097515
+2112,33.804596
+2113,38.83749
+2114,39.46298
+2115,43.651226
+2116,46.242916
+2117,48.09575
+2118,47.726624
+2119,15.337989
+2120,17.259764
+2121,18.913828
+2122,23.258423
+2123,22.07935
+2124,27.146448
+2125,28.265182
+2126,31.126627
+2127,31.754265
+2128,18.771362
+2129,20.07013
+2130,20.255568
+2131,21.930252
+2132,24.082418
+2133,26.023918
+2134,41.373474
+2135,42.60795
+2136,45.278435
+2137,42.90191
+2138,46.685616
+2139,17.35295
+2140,18.421038
+2141,22.01738
+2142,25.926096
+2143,18.202898
+2144,23.60687
+2145,26.339241
+2146,26.134409
+2147,16.028841
+2148,25.06923
+2149,28.982182
+2150,28.845589
+2151,29.178438
+2152,33.353607
+2153,33.578457
+2154,38.83471
+2155,38.13408
+2156,40.29285
+2157,41.373795
+2158,42.911877
+2159,14.699961
+2160,15.117874
+2161,15.077209
+2162,16.892002
+2163,20.254213
+2164,1.1273817
+2165,6.242645
+2166,7.2904124
+2167,8.407149
+2168,59.76527
+2169,61.382744
+2170,63.09
+2171,66.79007
+2172,64.6471
+2173,65.50618
+2174,68.47213
+2175,70.41203
+2176,71.795555
+2177,73.691376
+2178,71.04482
+2179,71.03944
+2180,40.014572
+2181,43.94807
+2182,45.8872
+2183,50.550213
+2184,55.750237
+2185,65.1505
+2186,66.05204
+2187,66.805534
+2188,68.73815
+2189,70.83776
+2190,70.70495
+2191,70.77164
+2192,74.46165
+2193,75.75536
+2194,78.121925
+2195,31.570272
+2196,36.79819
+2197,42.603294
+2198,50.311604
+2199,12.789858
+2200,15.552046
+2201,17.82852
+2202,20.235104
+2203,19.524227
+2204,26.134748
+2205,31.810436
+2206,34.074978
+2207,32.417374
+2208,39.92541
+2209,41.94418
+2210,39.179077
+2211,42.560337
+2212,47.298172
+2213,56.163696
+2214,59.493034
+2215,64.848175
+2216,63.482872
+2217,63.508045
+2218,22.526634
+2219,33.58972
+2220,32.15705
+2221,33.99858
+2222,35.54426
+2223,36.76619
+2224,43.766445
+2225,45.578762
+2226,49.874462
+2227,51.340176
+2228,54.014374
+2229,57.44282
+2230,21.854507
+2231,31.494267
+2232,33.995445
+2233,30.303717
+2234,32.374413
+2235,38.7491
+2236,38.66103
+2237,41.60706
+2238,34.767796
+2239,34.92476
+2240,37.124187
+2241,40.914093
+2242,41.973145
+2243,43.522457
+2244,49.5326
+2245,50.913567
+2246,52.639946
+2247,50.487118
+2248,51.89207
+2249,41.954704
+2250,42.751163
+2251,43.677353
+2252,44.43615
+2253,46.799637
+2254,48.668304
+2255,48.590523
+2256,50.51242
+2257,52.827095
+2258,52.444267
+2259,54.640755
+2260,55.032566
+2261,27.260077
+2262,30.520458
+2263,33.815865
+2264,37.182076
+2265,24.174244
+2266,35.11445
+2267,36.728043
+2268,32.657036
+2269,33.47461
+2270,34.757122
+2271,32.32871
+2272,39.71499
+2273,42.98145
+2274,43.675262
+2275,46.882816
+2276,47.74051
+2277,47.514153
+2278,49.205357
+2279,52.27937
+2280,55.48866
+2281,54.01407
+2282,56.98587
+2283,58.41739
+2284,58.991695
+2285,62.35831
+2286,62.044693
+2287,60.174263
+2288,60.602074
+2289,30.920958
+2290,37.059303
+2291,39.363144
+2292,42.407932
+2293,22.729813
+2294,25.2526
+2295,25.91557
+2296,29.157684
+2297,22.086493
+2298,24.464508
+2299,24.458097
+2300,31.40063
+2301,37.662838
+2302,36.481148
+2303,39.798115
+2304,41.53934
+2305,46.15264
+2306,48.204613
+2307,52.287685
+2308,59.52854
+2309,16.178513
+2310,19.089275
+2311,20.679356
+2312,24.485815
+2313,27.973045
+2314,33.411472
+2315,31.324516
+2316,34.71033
+2317,51.467876
+2318,55.11118
+2319,54.12293
+2320,57.321022
+2321,56.80334
+2322,62.327522
+2323,61.891212
+2324,5.6926785
+2325,6.718072
+2326,8.942735
+2327,15.895253
+2328,17.62143
+2329,13.813156
+2330,18.318607
+2331,20.064367
+2332,22.51984
+2333,29.43541
+2334,30.360382
+2335,30.701508
+2336,5.887619
+2337,5.211538
+2338,9.563541
+2339,11.269642
+2340,12.97961
+2341,16.26737
+2342,18.43481
+2343,21.375881
+2344,21.799639
+2345,26.222935
+2346,29.496367
+2347,30.359293
+2348,44.129505
+2349,46.296024
+2350,51.915894
+2351,51.246414
+2352,54.387486
+2353,53.220284
+2354,54.29435
+2355,56.15306
+2356,57.936615
+2357,58.138092
+2358,57.988045
+2359,59.309402
+2360,30.413591
+2361,37.519745
+2362,42.2931
+2363,46.643044
+2364,14.350542
+2365,16.839668
+2366,24.059536
+2367,27.28987
+2368,18.349152
+2369,19.675587
+2370,25.58875
+2371,28.483097
+2372,28.04206
+2373,33.4571
+2374,36.963005
+2375,36.98427
+2376,38.969658
+2377,40.845886
+2378,42.83765
+2379,45.54109
+2380,43.21811
+2381,43.571335
+2382,40.74843
+2383,42.904083
+2384,40.116676
+2385,44.481697
+2386,47.049095
+2387,47.726524
+2388,52.541817
+2389,49.09771
+2390,50.38369
+2391,52.494423
+2392,29.075426
+2393,33.060844
+2394,38.53661
+2395,41.441692
+2396,19.426163
+2397,24.449448
+2398,24.702072
+2399,27.106504
+2400,34.1632
+2401,39.667416
+2402,41.43547
+2403,48.037388
+2404,45.64805
+2405,47.41446
+2406,49.71293
+2407,56.983032
+2408,53.99856
+2409,55.063812
+2410,57.959347
+2411,61.403175
+2412,64.76337
+2413,64.14756
+2414,25.210163
+2415,28.879063
+2416,33.88528
+2417,40.154774
+2418,52.401474
+2419,38.13998
+2420,35.45954
+2421,38.40948
+2422,37.742973
+2423,38.735428
+2424,41.709286
+2425,43.267017
+2426,47.73371
+2427,44.831444
+2428,46.487167
+2429,57.08204
+2430,63.017715
+2431,27.662275
+2432,26.958204
+2433,28.365095
+2434,31.557116
+2435,33.756615
+2436,36.544888
+2437,39.1897
+2438,42.633125
+2439,42.582275
+2440,23.950562
+2441,25.900457
+2442,33.437603
+2443,40.825138
+2444,38.496204
+2445,42.646576
+2446,44.867233
+2447,50.097343
+2448,51.93094
+2449,58.487774
+2450,58.692444
+2451,57.86931
+2452,35.613335
+2453,36.31295
+2454,37.326366
+2455,40.22794
+2456,43.6883
+2457,45.074146
+2458,47.566296
+2459,53.134968
+2460,53.872646
+2461,55.59279
+2462,58.67145
+2463,57.63921
+2464,39.7618
+2465,39.353783
+2466,42.441017
+2467,45.648125
+2468,47.131496
+2469,46.32684
+2470,47.585346
+2471,50.026134
+2472,53.37289
+2473,13.871006
+2474,20.320118
+2475,23.30084
+2476,26.263567
+2477,25.749506
+2478,29.238937
+2479,34.211014
+2480,21.994123
+2481,23.081408
+2482,29.965218
+2483,34.902275
+2484,32.730022
+2485,33.771286
+2486,34.946854
+2487,37.62716
+2488,43.695404
+2489,43.79345
+2490,48.12775
+2491,47.986565
+2492,47.175755
+2493,48.686306
+2494,44.764587
+2495,50.948418
+2496,15.476379
+2497,22.42613
+2498,24.604748
+2499,25.283274
+2500,21.841497
+2501,27.040539
+2502,32.05963
+2503,33.170734
+2504,36.1363
+2505,36.784504
+2506,40.907825
+2507,42.739357
+2508,45.444283
+2509,45.296375
+2510,45.027607
+2511,21.48193
+2512,25.356304
+2513,28.956156
+2514,34.959774
+2515,27.37485
+2516,27.605972
+2517,30.745852
+2518,29.98668
+2519,32.12539
+2520,30.885956
+2521,32.52726
+2522,33.532173
+2523,37.727562
+2524,37.55832
+2525,39.779724
+2526,41.29195
+2527,45.297848
+2528,45.1121
+2529,51.596077
+2530,51.194004
+2531,52.200874
+2532,33.573383
+2533,34.178093
+2534,39.77372
+2535,43.5076
+2536,46.485054
+2537,48.14142
+2538,47.781593
+2539,51.11803
+2540,52.227795
+2541,55.336533
+2542,56.856773
+2543,57.105667
+2544,12.326353
+2545,15.968057
+2546,17.29038
+2547,17.585442
+2548,49.22206
+2549,49.22051
+2550,55.760403
+2551,54.44583
+2552,61.000008
+2553,36.97858
+2554,38.017776
+2555,39.482506
+2556,39.284035
+2557,13.038802
+2558,14.8145895
+2559,13.194932
+2560,17.979492
+2561,18.68591
+2562,19.066086
+2563,23.566542
+2564,25.696066
+2565,30.08974
+2566,31.843014
+2567,34.162468
+2568,38.929348
+2569,9.671858
+2570,12.783162
+2571,14.453928
+2572,14.103484
+2573,13.689002
+2574,14.652223
+2575,15.527396
+2576,15.893736
+2577,29.849886
+2578,32.993393
+2579,50.943386
+2580,51.130383
+2581,15.8784485
+2582,14.786033
+2583,25.210157
+2584,27.099724
+2585,60.78224
+2586,63.609806
+2587,65.26736
+2588,68.61691
+2589,69.67585
+2590,69.80531
+2591,69.447754
+2592,70.939835
+2593,71.96249
+2594,74.87989
+2595,74.81745
+2596,75.920006
+2597,40.199574
+2598,41.55074
+2599,43.282993
+2600,50.041412
+2601,50.637527
+2602,54.52764
+2603,55.250786
+2604,57.358482
+2605,58.145054
+2606,61.109596
+2607,60.390194
+2608,64.592415
+2609,30.041836
+2610,30.648571
+2611,34.796528
+2612,35.025265
+2613,37.380795
+2614,37.973106
+2615,42.048157
+2616,42.221752
+2617,33.318226
+2618,38.1507
+2619,45.92317
+2620,51.3236
+2621,13.918771
+2622,15.49152
+2623,18.154558
+2624,23.622269
+2625,26.897015
+2626,28.719702
+2627,31.450333
+2628,20.828213
+2629,33.863537
+2630,35.466194
+2631,36.226334
+2632,37.812622
+2633,18.810192
+2634,23.010006
+2635,23.156742
+2636,25.939104
+2637,29.578043
+2638,28.758465
+2639,34.928642
+2640,36.119476
+2641,37.920193
+2642,38.9359
+2643,40.115368
+2644,39.728832
+2645,54.119076
+2646,52.853355
+2647,53.53181
+2648,55.769234
+2649,58.062836
+2650,58.024055
+2651,61.31201
+2652,62.934402
+2653,62.65786
+2654,30.347267
+2655,34.179604
+2656,33.08296
+2657,34.418495
+2658,28.022675
+2659,29.024694
+2660,31.139925
+2661,31.70761
+2662,12.329795
+2663,16.561571
+2664,22.425291
+2665,24.264141
+2666,26.91934
+2667,20.077185
+2668,22.439583
+2669,23.581833
+2670,26.173347
+2671,26.58778
+2672,29.92092
+2673,31.922195
+2674,32.77978
+2675,12.258289
+2676,12.405928
+2677,17.749454
+2678,22.69682
+2679,27.138584
+2680,29.814957
+2681,31.08992
+2682,35.152695
+2683,38.63177
+2684,37.812984
+2685,42.828304
+2686,40.86136
+2687,30.773098
+2688,44.86834
+2689,49.950603
+2690,56.344685
+2691,17.547117
+2692,23.577065
+2693,26.284357
+2694,29.160973
+2695,30.009706
+2696,32.21604
+2697,23.728664
+2698,26.080122
+2699,26.173132
+2700,28.050903
+2701,34.19851
+2702,35.345173
+2703,38.430252
+2704,18.061735
+2705,20.1865
+2706,22.164906
+2707,24.193527
+2708,24.209526
+2709,27.446152
+2710,29.67218
+2711,33.033752
+2712,31.927244
+2713,34.52536
+2714,35.97338
+2715,36.889393
+2716,25.867977
+2717,32.40323
+2718,37.061657
+2719,48.544926
+2720,12.163664
+2721,18.637428
+2722,20.435017
+2723,23.265905
+2724,22.846865
+2725,25.257864
+2726,28.524372
+2727,28.353086
+2728,32.467487
+2729,34.42983
+2730,37.333694
+2731,40.22561
+2732,36.783047
+2733,37.353626
+2734,40.602615
+2735,44.185303
+2736,48.03791
+2737,50.554398
+2738,53.5634
+2739,55.93691
+2740,58.78938
+2741,60.440712
+2742,64.30038
+2743,64.04253
+2744,6.0047054
+2745,6.7430153
+2746,8.688723
+2747,10.688402
+2748,13.668983
+2749,18.035267
+2750,20.647495
+2751,23.630276
+2752,24.082151
+2753,35.143738
+2754,42.303276
+2755,39.374016
+2756,7.323699
+2757,8.515384
+2758,10.160137
+2759,16.778788
+2760,17.193222
+2761,18.462847
+2762,17.363739
+2763,21.827116
+2764,23.349607
+2765,24.718256
+2766,25.100426
+2767,23.770657
+2768,47.081406
+2769,49.651665
+2770,52.321533
+2771,57.129436
+2772,58.239124
+2773,57.11241
+2774,60.023624
+2775,19.354765
+2776,23.524988
+2777,21.59193
+2778,23.25387
+2779,27.504662
+2780,28.353611
+2781,29.782188
+2782,32.7454
+2783,34.120773
+2784,33.295326
+2785,34.795135
+2786,38.76519
+2787,27.378304
+2788,32.010662
+2789,35.820835
+2790,35.085236
+2791,40.353794
+2792,43.05908
+2793,48.695473
+2794,48.94339
+2795,50.17365
+2796,53.556824
+2797,54.69192
+2798,59.59729
+2799,15.702995
+2800,16.08209
+2801,18.4784
+2802,19.11673
+2803,19.940731
+2804,22.828354
+2805,26.058018
+2806,27.990692
+2807,27.602287
+2808,29.744196
+2809,30.306736
+2810,30.913605
+2811,9.702015
+2812,12.54854
+2813,14.016623
+2814,15.613456
+2815,16.304344
+2816,13.379534
+2817,14.623972
+2818,17.798035
+2819,19.496058
+2820,23.292713
+2821,24.178902
+2822,28.243614
+2823,31.95153
+2824,33.35531
+2825,34.213924
+2826,35.995564
+2827,36.083115
+2828,19.150965
+2829,20.007998
+2830,21.904346
+2831,24.596899
+2832,32.000336
+2833,34.75698
+2834,31.428617
+2835,30.717165
+2836,36.15453
+2837,42.214233
+2838,44.964214
+2839,49.256947
+2840,21.176802
+2841,23.823784
+2842,26.7828
+2843,31.288378
+2844,50.956886
+2845,61.80227
+2846,64.25279
+2847,64.28848
+2848,34.464546
+2849,39.11051
+2850,42.623207
+2851,45.438423
+2852,52.563744
+2853,53.56964
+2854,4.3439946
+2855,5.9500027
+2856,6.478506
+2857,10.414046
+2858,14.001605
+2859,13.426161
+2860,15.567652
+2861,18.175508
+2862,22.164595
+2863,22.48638
+2864,19.44485
+2865,23.950237
+2866,24.66489
+2867,35.562824
+2868,38.766438
+2869,44.333115
+2870,48.350967
+2871,49.247032
+2872,51.988792
+2873,54.024323
+2874,62.91204
+2875,64.97801
+2876,64.85967
+2877,66.55493
+2878,13.283884
+2879,17.908497
+2880,20.499325
+2881,16.364042
+2882,23.090347
+2883,2.6717117
+2884,3.7892182
+2885,7.2850213
+2886,8.457039
+2887,13.653944
+2888,15.351715
+2889,17.068102
+2890,18.731163
+2891,20.900524
+2892,22.988186
+2893,24.393227
+2894,26.680883
+2895,2.0547094
+2896,5.080961
+2897,8.499564
+2898,10.280905
+2899,15.237986
+2900,19.37134
+2901,55.474354
+2902,58.695618
+2903,64.15751
+2904,67.16212
+2905,8.810858
+2906,14.063138
+2907,13.537273
+2908,15.016409
+2909,22.784454
+2910,1.9972309
+2911,2.374558
+2912,3.661006
+2913,6.9768806
+2914,9.347608
+2915,16.218636
+2916,19.238003
+2917,20.995262
+2918,21.042961
+2919,23.1559
+2920,25.926416
+2921,25.97409
+2922,15.530312
+2923,16.278864
+2924,16.625635
+2925,19.513054
+2926,17.505854
+2927,22.307323
+2928,22.431108
+2929,26.292763
+2930,24.877655
+2931,27.217848
+2932,30.893219
+2933,33.50347
+2934,35.404
+2935,41.743877
+2936,43.723923
+2937,50.004448
+2938,51.23515
+2939,57.18194
+2940,59.187866
+2941,62.455734
+2942,7.4143305
+2943,8.343793
+2944,10.638979
+2945,13.880556
+2946,14.016834
+2947,17.52958
+2948,23.711706
+2949,27.125225
+2950,32.373707
+2951,32.313877
+2952,34.843094
+2953,38.01
+2954,42.178154
+2955,44.11818
+2956,45.87031
+2957,45.351032
+2958,48.018764
+2959,50.188503
+2960,50.663948
+2961,52.653053
+2962,53.754147
+2963,57.256165
+2964,57.31543
+2965,60.446167
+2966,24.781824
+2967,24.55095
+2968,26.752377
+2969,32.152943
+2970,37.622124
+2971,46.94597
+2972,48.349842
+2973,51.8253
+2974,56.95095
+2975,43.48454
+2976,42.67241
+2977,40.92282
+2978,43.26818
+2979,42.828213
+2980,35.511463
+2981,35.932884
+2982,38.718075
+2983,38.44105
+2984,40.270233
+2985,38.447853
+2986,41.90812
+2987,41.07979
+2988,46.050102
+2989,47.275726
+2990,48.960598
+2991,49.573067
+2992,8.961809
+2993,14.649853
+2994,17.480452
+2995,17.309368
+2996,20.388588
+2997,23.988667
+2998,23.552052
+2999,25.82019
+3000,26.45221
+3001,27.608194
+3002,28.369526
+3003,29.396435
+3004,1.4813337
+3005,2.1201892
+3006,3.6036296
+3007,6.8870025
+3008,11.587017
+3009,11.83027
+3010,14.168793
+3011,17.36104
+3012,17.61495
+3013,18.418533
+3014,20.872517
+3015,22.848906
+3016,36.835026
+3017,38.47293
+3018,39.662014
+3019,42.35863
+3020,41.95555
+3021,45.207912
+3022,45.355328
+3023,48.38095
+3024,15.661018
+3025,19.89943
+3026,23.39307
+3027,23.15161
+3028,46.544704
+3029,48.905197
+3030,48.915615
+3031,53.01174
+3032,56.4436
+3033,59.61241
+3034,59.885532
+3035,60.768208
+3036,64.20328
+3037,63.13283
+3038,67.1256
+3039,71.87423
+3040,39.345345
+3041,39.504047
+3042,41.287964
+3043,44.294487
+3044,21.899246
+3045,23.542044
+3046,22.150143
+3047,25.008602
+3048,20.951822
+3049,22.622156
+3050,26.595636
+3051,30.467821
+3052,32.208942
+3053,35.36291
+3054,38.69249
+3055,41.67871
+3056,42.25604
+3057,43.451878
+3058,45.450787
+3059,48.46709
+3060,48.104034
+3061,49.727093
+3062,52.121017
+3063,55.636017
+3064,61.44401
+3065,61.214558
+3066,64.56591
+3067,66.48612
+3068,69.25167
+3069,69.35664
+3070,71.69177
+3071,0.14138778
+3072,2.169852
+3073,4.148897
+3074,6.9554987
+3075,10.434446
+3076,13.225559
+3077,16.814358
+3078,17.903656
+3079,20.147234
+3080,21.100922
+3081,22.797012
+3082,22.40685
+3083,25.403954
+3084,26.159725
+3085,30.116055
+3086,37.03724
+3087,42.819786
+3088,25.080454
+3089,28.019442
+3090,33.70752
+3091,36.037083
+3092,34.845734
+3093,38.255993
+3094,40.35145
+3095,41.724464
+3096,42.190613
+3097,43.90861
+3098,9.313049
+3099,11.820633
+3100,13.4104395
+3101,13.300929
+3102,15.153142
+3103,17.27375
+3104,24.942854
+3105,24.311632
+3106,27.823273
+3107,29.764082
+3108,32.457657
+3109,34.6727
+3110,33.592026
+3111,33.219357
+3112,41.09419
+3113,46.155334
+3114,48.807926
+3115,52.566574
+3116,48.503036
+3117,55.13389
+3118,58.447346
+3119,10.476299
+3120,13.237203
+3121,18.73672
+3122,23.955948
+3123,32.465893
+3124,10.541112
+3125,16.355509
+3126,17.722473
+3127,22.282026
+3128,18.899021
+3129,30.336563
+3130,35.313744
+3131,31.719011
+3132,31.568403
+3133,32.74987
+3134,39.891518
+3135,39.99685
+3136,46.98271
+3137,46.84845
+3138,42.37617
+3139,30.958134
+3140,43.452316
+3141,50.984974
+3142,48.040707
+3143,17.283892
+3144,20.129873
+3145,23.176533
+3146,25.445555
+3147,35.225883
+3148,37.56978
+3149,38.269493
+3150,44.533894
+3151,47.62635
+3152,46.930176
+3153,50.539192
+3154,53.490303
+3155,56.424095
+3156,57.615658
+3157,58.806885
+3158,60.29934
+3159,18.326813
+3160,20.7724
+3161,28.12844
+3162,29.960257
+3163,31.169277
+3164,32.77244
+3165,34.524544
+3166,38.369682
+3167,40.06427
+3168,43.36637
+3169,45.00777
+3170,48.650146
+3171,41.695114
+3172,44.53202
+3173,46.93542
+3174,49.885933
+3175,13.191466
+3176,16.324375
+3177,23.491398
+3178,27.537832
+3179,22.010609
+3180,23.587654
+3181,24.536577
+3182,33.009365
+3183,36.592888
+3184,34.692276
+3185,41.500477
+3186,40.395576
+3187,44.814114
+3188,48.155235
+3189,49.066402
+3190,23.532986
+3191,29.062145
+3192,28.497292
+3193,32.918324
+3194,37.281136
+3195,40.536797
+3196,46.0283
+3197,48.36792
+3198,49.349564
+3199,54.329193
+3200,55.666782
+3201,55.78205
+3202,27.9099
+3203,29.192133
+3204,37.236202
+3205,42.37009
+3206,44.668392
+3207,46.443684
+3208,27.589622
+3209,36.845657
+3210,37.975353
+3211,34.49652
+3212,39.309204
+3213,40.610676
+3214,43.6548
+3215,45.00206
+3216,46.99035
+3217,49.487392
+3218,51.136986
+3219,54.81794
+3220,17.313538
+3221,18.658314
+3222,23.084589
+3223,32.948627
+3224,34.480007
+3225,33.475548
+3226,36.42348
+3227,39.41258
+3228,42.50283
+3229,43.443916
+3230,48.069954
+3231,47.243298
+3232,32.738674
+3233,32.524208
+3234,34.741425
+3235,43.253605
+3236,43.39324
+3237,47.21952
+3238,43.12337
+3239,45.89361
+3240,48.223747
+3241,50.33947
+3242,51.57943
+3243,53.254555
+3244,23.90753
+3245,24.650791
+3246,28.755928
+3247,34.281094
+3248,43.52413
+3249,42.821068
+3250,43.129982
+3251,44.099094
+3252,34.891716
+3253,41.147713
+3254,45.392372
+3255,54.10033
+3256,28.928303
+3257,30.36507
+3258,34.852013
+3259,33.22828
+3260,42.851505
+3261,46.03832
+3262,44.015163
+3263,46.77344
+3264,49.906857
+3265,52.316723
+3266,53.711376
+3267,56.670525
+3268,26.433928
+3269,27.158182
+3270,27.705288
+3271,27.1906
+3272,40.152252
+3273,57.278996
+3274,58.86312
+3275,58.68899
+3276,44.55161
+3277,48.99459
+3278,51.95256
+3279,54.93966
+3280,37.806538
+3281,44.653637
+3282,50.61283
+3283,53.908283
+3284,27.971031
+3285,34.322826
+3286,38.065872
+3287,49.233723
+3288,53.07135
+3289,48.456833
+3290,52.947433
+3291,55.087395
+3292,56.143982
+3293,56.551163
+3294,61.918236
+3295,66.113655
+3296,34.240856
+3297,40.03714
+3298,44.864876
+3299,42.992764
+3300,47.72908
+3301,49.528217
+3302,48.82612
+3303,52.045612
+3304,53.978725
+3305,55.942757
+3306,55.176094
+3307,56.57001
+3308,39.002903
+3309,45.1668
+3310,52.10495
+3311,59.35753
+3312,3.8776135
+3313,5.1090317
+3314,8.712946
+3315,11.312104
+3316,10.372432
+3317,16.188084
+3318,17.187305
+3319,19.215536
+3320,22.781548
+3321,25.803831
+3322,35.70155
+3323,36.57547
+3324,38.693287
+3325,57.044796
+3326,59.353283
+3327,61.05662
+3328,61.913544
+3329,36.920437
+3330,41.04742
+3331,41.480885
+3332,48.946873
+3333,6.546627
+3334,8.140552
+3335,10.321226
+3336,12.213347
+3337,16.245686
+3338,22.111767
+3339,22.3823
+3340,22.158901
+3341,24.133535
+3342,27.198368
+3343,26.722431
+3344,33.291664
+3345,35.960762
+3346,38.905655
+3347,45.2437
+3348,45.820274
+3349,52.804924
+3350,53.051136
+3351,57.28862
+3352,58.433952
+3353,60.37168
+3354,62.528286
+3355,63.037155
+3356,66.19064
+3357,28.433283
+3358,42.31402
+3359,44.316288
+3360,39.722294
+3361,41.930885
+3362,42.908745
+3363,48.093113
+3364,57.793697
+3365,46.483555
+3366,51.656425
+3367,55.98239
+3368,52.186306
+3369,53.54702
+3370,55.416126
+3371,54.53971
+3372,56.313965
+3373,48.14687
+3374,55.056866
+3375,58.652782
+3376,57.148087
+3377,14.917115
+3378,17.047993
+3379,17.201132
+3380,21.484158
+3381,21.032852
+3382,24.206854
+3383,28.65159
+3384,30.598358
+3385,32.647076
+3386,36.1746
+3387,25.92504
+3388,30.61438
+3389,33.82528
+3390,35.726883
+3391,36.52501
+3392,40.83396
+3393,40.60921
+3394,44.17139
+3395,44.502716
+3396,48.846767
+3397,48.933685
+3398,51.462215
+3399,51.851055
+3400,53.018932
+3401,52.91994
+3402,54.11042
+3403,31.215527
+3404,35.22495
+3405,46.05404
+3406,51.65892
+3407,0.69995105
+3408,1.0397962
+3409,1.7382842
+3410,5.0921335
+3411,8.560541
+3412,9.429518
+3413,13.828211
+3414,20.73415
+3415,23.819723
+3416,26.236721
+3417,28.666126
+3418,43.278606
+3419,49.53502
+3420,48.358154
+3421,49.202568
+3422,52.510323
+3423,53.295105
+3424,55.447548
+3425,57.159554
+3426,58.035244
+3427,56.888325
+3428,61.4857
+3429,60.59645
+3430,21.787594
+3431,23.41837
+3432,26.607023
+3433,29.800102
+3434,33.88784
+3435,38.336414
+3436,40.489285
+3437,40.813965
+3438,41.671753
+3439,45.26547
+3440,47.77726
+3441,48.96543
+3442,24.31371
+3443,24.77503
+3444,25.349852
+3445,29.30876
+3446,37.490253
+3447,42.365185
+3448,45.722572
+3449,42.407177
+3450,53.456085
+3451,54.191395
+3452,61.07833
+3453,47.601494
+3454,50.96517
+3455,51.950386
+3456,54.516464
+3457,57.537735
+3458,58.09481
+3459,59.531048
+3460,59.16909
+3461,60.57241
+3462,64.01255
+3463,62.20501
+3464,61.72453
+3465,35.171104
+3466,37.892647
+3467,42.52503
+3468,41.99086
+3469,21.006268
+3470,23.219751
+3471,23.442804
+3472,21.673897
+3473,23.988018
+3474,27.223488
+3475,35.581394
+3476,36.97549
+3477,39.642036
+3478,41.938328
+3479,46.74067
+3480,48.172142
+3481,53.018814
+3482,52.70247
+3483,57.710922
+3484,56.47337
+3485,56.05081
+3486,61.061993
+3487,7.2123528
+3488,11.6432905
+3489,12.369755
+3490,14.531979
+3491,17.652395
+3492,19.838451
+3493,22.376087
+3494,22.42296
+3495,26.424137
+3496,30.620256
+3497,29.98521
+3498,31.710995
+3499,18.652899
+3500,20.527216
+3501,33.604454
+3502,33.0388
+3503,35.9786
+3504,59.44636
+3505,67.89453
+3506,67.15811
+3507,66.65434
+3508,71.17216
+3509,72.88217
+3510,72.501305
+3511,73.09513
+3512,7.1662993
+3513,12.302368
+3514,13.235896
+3515,25.047237
+3516,30.445042
+3517,34.076393
+3518,23.905405
+3519,30.239023
+3520,35.764595
+3521,46.70795
+3522,33.941826
+3523,39.252125
+3524,40.680447
+3525,41.50012
+3526,45.489315
+3527,49.364815
+3528,50.801136
+3529,53.10125
+3530,60.029114
+3531,58.33494
+3532,26.442398
+3533,31.61492
+3534,33.356224
+3535,39.451103
+3536,37.718533
+3537,45.406464
+3538,47.083076
+3539,49.021217
+3540,49.96996
+3541,52.04996
+3542,56.144436
+3543,57.630836
+3544,20.970253
+3545,23.646515
+3546,26.26242
+3547,32.502113
+3548,37.670006
+3549,36.976658
+3550,38.798138
+3551,40.090137
+3552,42.471893
+3553,47.95522
+3554,47.834446
+3555,48.68798
+3556,7.8664913
+3557,9.619838
+3558,11.714869
+3559,16.98298
+3560,17.52999
+3561,21.24524
+3562,23.065313
+3563,25.166393
+3564,26.104671
+3565,27.084896
+3566,29.34652
+3567,34.822998
+3568,38.930565
+3569,36.634567
+3570,38.102306
+3571,42.45694
+3572,44.318356
+3573,49.080948
+3574,61.834282
+3575,64.6221
+3576,61.618313
+3577,68.2379
+3578,35.192497
+3579,45.383797
+3580,48.965244
+3581,48.754173
+3582,50.792233
+3583,51.885136
+3584,56.273758
+3585,56.726353
+3586,59.566513
+3587,61.16475
+3588,62.767735
+3589,65.85678
+3590,45.695442
+3591,52.81225
+3592,48.007183
+3593,49.064377
+3594,48.28079
+3595,49.904327
+3596,53.695488
+3597,58.056362
+3598,57.23982
+3599,59.649975
+3600,63.787346
+3601,63.23148
+3602,16.106674
+3603,15.408187
+3604,18.597185
+3605,22.866747
+3606,23.126228
+3607,11.094875
+3608,13.499408
+3609,14.733231
+3610,22.937914
+3611,29.556747
+3612,35.038513
+3613,40.96895
+3614,44.792618
+3615,45.116356
+3616,50.18431
+3617,53.472435
+3618,47.168915
+3619,48.34957
+3620,54.15634
+3621,53.396797
+3622,58.69582
+3623,62.897522
+3624,58.96721
+3625,62.29591
+3626,64.28134
+3627,66.150345
+3628,66.98814
+3629,66.07357
+3630,11.930256
+3631,9.6824875
+3632,13.87333
+3633,14.58307
+3634,24.38019
+3635,26.369867
+3636,24.849602
+3637,27.938343
+3638,33.725952
+3639,35.526478
+3640,33.73317
+3641,37.379757
+3642,49.631954
+3643,51.8884
+3644,51.612907
+3645,53.485317
+3646,79.78506
+3647,80.45256
+3648,80.71636
+3649,83.35698
+3650,84.8869
+3651,85.39242
+3652,86.04517
+3653,13.773672
+3654,15.128512
+3655,14.859861
+3656,17.749344
+3657,19.043402
+3658,22.272655
+3659,28.863064
+3660,28.983559
+3661,29.751629
+3662,31.366558
+3663,33.806767
+3664,38.960873
+3665,10.91804
+3666,12.203213
+3667,14.953262
+3668,20.127632
+3669,23.023188
+3670,25.39938
+3671,31.37629
+3672,28.66567
+3673,31.972385
+3674,33.1038
+3675,36.55557
+3676,41.100693
+3677,45.326298
+3678,9.801537
+3679,12.847907
+3680,18.891851
+3681,19.790997
+3682,17.31712
+3683,20.676716
+3684,23.297537
+3685,27.229862
+3686,28.186377
+3687,32.576603
+3688,31.700752
+3689,32.635204
+3690,32.417973
+3691,40.69839
+3692,42.977386
+3693,45.494236
+3694,49.849953
+3695,34.298874
+3696,40.879612
+3697,44.802425
+3698,47.3598
+3699,13.916399
+3700,15.101379
+3701,14.806505
+3702,17.073212
+3703,49.83158
+3704,50.045315
+3705,50.675446
+3706,51.985535
+3707,55.96938
+3708,54.736076
+3709,0.7076731
+3710,1.7651907
+3711,4.516474
+3712,5.9293327
+3713,42.728004
+3714,51.155655
+3715,57.359386
+3716,58.70339
+3717,60.95485
+3718,33.58378
+3719,39.74597
+3720,42.09496
+3721,46.410492
+3722,0.15035889
+3723,0.44086072
+3724,0.17563024
+3725,0.45375067
+3726,24.708885
+3727,29.463993
+3728,28.900835
+3729,31.083368
+3730,35.778492
+3731,38.14928
+3732,41.03959
+3733,44.656155
+3734,46.116737
+3735,51.449306
+3736,53.75885
+3737,55.262646
+3738,5.708992
+3739,10.454224
+3740,12.792724
+3741,14.9984665
+3742,17.62968
+3743,23.682327
+3744,25.81899
+3745,25.481718
+3746,23.761902
+3747,27.173748
+3748,28.690834
+3749,28.60448
+3750,15.350587
+3751,19.677145
+3752,25.067429
+3753,32.71512
+3754,13.8853655
+3755,18.956656
+3756,20.858953
+3757,22.641111
+3758,22.677114
+3759,23.571049
+3760,26.797842
+3761,28.1633
+3762,32.137657
+3763,34.93222
+3764,37.10569
+3765,31.82906
+3766,30.907238
+3767,38.26207
+3768,45.639755
+3769,45.60455
+3770,45.776978
+3771,51.0229
+3772,55.718994
+3773,43.272003
+3774,47.071762
+3775,46.894547
+3776,49.980183
+3777,56.144367
+3778,61.0475
+3779,72.00702
+3780,69.52649
+3781,68.29165
+3782,68.87169
+3783,74.71462
+3784,75.77603
+3785,8.450944
+3786,10.140924
+3787,11.693811
+3788,20.120352
+3789,23.755604
+3790,31.390896
+3791,34.47359
+3792,33.074783
+3793,33.75433
+3794,38.989456
+3795,39.261215
+3796,42.760544
+3797,43.10943
+3798,45.584507
+3799,45.812458
+3800,47.93179
+3801,43.911163
+3802,46.724518
+3803,51.281395
+3804,54.381367
+3805,58.040356
+3806,61.90785
+3807,62.51157
+3808,64.30537
+3809,70.18408
+3810,69.50528
+3811,69.51558
+3812,71.30229
+3813,21.583675
+3814,24.228676
+3815,27.898262
+3816,29.066227
+3817,36.012417
+3818,38.20588
+3819,40.91028
+3820,23.147182
+3821,27.318155
+3822,39.911278
+3823,53.112152
+3824,35.614376
+3825,35.463127
+3826,38.754097
+3827,39.85756
+3828,40.30295
+3829,20.985828
+3830,23.055473
+3831,28.844053
+3832,31.799995
+3833,30.917028
+3834,33.503117
+3835,36.994274
+3836,37.814713
+3837,37.493866
+3838,40.60789
+3839,41.277985
+3840,45.21831
+3841,24.673706
+3842,25.961096
+3843,25.98864
+3844,27.681879
+3845,28.753996
+3846,31.797949
+3847,33.498577
+3848,34.102955
+3849,37.809464
+3850,36.52591
+3851,36.82331
+3852,38.558315
+3853,43.818333
+3854,44.783363
+3855,45.71901
+3856,50.11197
+3857,51.946304
+3858,54.704697
+3859,53.916443
+3860,53.68966
+3861,60.365875
+3862,55.945457
+3863,56.85877
+3864,57.037926
+3865,0.5358791
+3866,1.0897688
+3867,2.6629364
+3868,5.7720346
+3869,7.912761
+3870,6.966157
+3871,7.9129415
+3872,10.324358
+3873,40.46437
+3874,46.635765
+3875,48.731052
+3876,54.914783
+3877,58.52493
+3878,61.492844
+3879,59.982563
+3880,61.40638
+3881,62.27098
+3882,64.36813
+3883,69.97545
+3884,67.38286
+3885,44.260628
+3886,46.401527
+3887,49.03587
+3888,54.948387
+3889,56.42541
+3890,59.67438
+3891,60.651997
+3892,61.90599
+3893,61.650852
+3894,63.386654
+3895,64.00218
+3896,64.823906
+3897,11.907589
+3898,13.826758
+3899,15.367916
+3900,19.586554
+3901,29.61345
+3902,36.488586
+3903,33.16054
+3904,39.471073
+3905,43.87806
+3906,42.449955
+3907,41.438236
+3908,53.3434
+3909,0.9411748
+3910,1.2405581
+3911,4.7467985
+3912,9.0833645
+3913,20.667862
+3914,22.611332
+3915,32.957214
+3916,35.149223
+3917,33.725418
+3918,37.17117
+3919,9.696904
+3920,12.734044
+3921,13.396267
+3922,15.449084
+3923,20.18101
+3924,22.530075
+3925,24.36248
+3926,25.906815
+3927,28.135141
+3928,29.059734
+3929,30.81169
+3930,12.657793
+3931,18.37033
+3932,18.982452
+3933,21.127316
+3934,22.973667
+3935,24.14978
+3936,33.407764
+3937,38.177593
+3938,2.014858
+3939,5.604248
+3940,7.54942
+3941,10.307018
+3942,12.054206
+3943,13.195887
+3944,14.172273
+3945,22.657623
+3946,27.138302
+3947,28.016132
+3948,28.879295
+3949,21.736687
+3950,27.938932
+3951,32.66119
+3952,36.252747
+3953,41.72855
+3954,8.937433
+3955,12.213317
+3956,15.137403
+3957,18.36597
+3958,20.731625
+3959,22.43942
+3960,23.035328
+3961,25.51334
+3962,28.707634
+3963,36.172836
+3964,35.889614
+3965,37.180046
+3966,35.14342
+3967,41.28927
+3968,47.899006
+3969,49.078953
+3970,50.991524
+3971,25.77235
+3972,32.696457
+3973,34.66903
+3974,33.718826
+3975,38.133835
+3976,41.950134
+3977,42.644466
+3978,47.239174
+3979,48.505325
+3980,53.19001
+3981,54.940884
+3982,53.463104
+3983,20.023277
+3984,21.594707
+3985,24.95559
+3986,32.884033
+3987,37.75808
+3988,38.60865
+3989,40.35666
+3990,45.25208
+3991,47.772503
+3992,48.878567
+3993,49.534542
+3994,52.42945
+3995,30.734978
+3996,36.840992
+3997,32.52211
+3998,35.538635
+3999,37.262566
+4000,39.95009
+4001,17.907148
+4002,21.945967
+4003,25.67445
+4004,33.019547
+4005,33.086693
+4006,34.6965
+4007,38.097652
+4008,44.50578
+4009,44.030834
+4010,46.588585
+4011,50.617867
+4012,51.62559
+4013,36.110874
+4014,37.71503
+4015,37.22226
+4016,42.143337
+4017,45.967293
+4018,48.501038
+4019,54.301918
+4020,54.34181
+4021,57.28173
+4022,58.305748
+4023,61.598877
+4024,43.021194
+4025,47.9988
+4026,50.737118
+4027,57.028786
+4028,20.705462
+4029,22.113235
+4030,23.90892
+4031,26.226416
+4032,53.503853
+4033,56.29083
+4034,56.015785
+4035,58.947975
+4036,61.142136
+4037,62.388386
+4038,61.485596
+4039,67.28714
+4040,67.22552
+4041,66.89258
+4042,66.91949
+4043,68.377975
+4044,47.709793
+4045,51.677486
+4046,53.092216
+4047,57.16468
+4048,22.222652
+4049,23.125267
+4050,25.16598
+4051,24.252789
+4052,29.481173
+4053,30.633837
+4054,30.743504
+4055,36.291634
+4056,37.17342
+4057,39.539265
+4058,37.620804
+4059,40.17948
+4060,23.293306
+4061,26.60213
+4062,31.126793
+4063,37.557938
+4064,26.750519
+4065,28.481377
+4066,31.109028
+4067,31.85161
+4068,36.376488
+4069,41.12122
+4070,42.828873
+4071,44.577316
+4072,46.42517
+4073,48.280834
+4074,49.6984
+4075,54.55818
+4076,11.667178
+4077,15.3866625
+4078,16.92749
+4079,18.015461
+4080,35.293934
+4081,34.54457
+4082,36.854263
+4083,38.355255
+4084,39.51963
+4085,42.08861
+4086,42.849346
+4087,49.422356
+4088,45.999306
+4089,47.363052
+4090,49.40829
+4091,53.119118
+4092,17.291122
+4093,16.174423
+4094,20.670599
+4095,21.83981
+4096,22.202019
+4097,23.701406
+4098,19.797363
+4099,20.606148
+4100,22.58481
+4101,26.684101
+4102,28.895725
+4103,31.026302
+4104,37.33051
+4105,40.801937
+4106,18.519562
+4107,19.882843
+4108,26.018253
+4109,26.911005
+4110,47.298813
+4111,47.775604
+4112,50.415947
+4113,53.476894
+4114,54.01339
+4115,16.453684
+4116,21.144854
+4117,24.045185
+4118,22.633793
+4119,25.062315
+4120,28.238735
+4121,30.083975
+4122,32.44629
+4123,34.181232
+4124,37.665092
+4125,38.17187
+4126,40.20918
+4127,20.078629
+4128,20.214027
+4129,28.59109
+4130,32.811516
+4131,48.4444
+4132,48.309093
+4133,53.519554
+4134,55.40858
+4135,58.161446
+4136,59.888344
+4137,61.05033
+4138,63.211197
+4139,63.6732
+4140,66.89814
+4141,68.79782
+4142,70.80713
+4143,0.1296221
+4144,2.2120337
+4145,6.145605
+4146,11.179798
+4147,7.1993885
+4148,9.762377
+4149,19.016048
+4150,21.404
+4151,20.26464
+4152,22.795832
+4153,25.527706
+4154,28.584843
+4155,30.692429
+4156,35.42876
+4157,37.57767
+4158,42.32498
+4159,44.957153
+4160,46.49631
+4161,12.044096
+4162,13.16344
+4163,17.307148
+4164,21.195988
+4165,24.49001
+4166,27.061432
+4167,30.981464
+4168,35.133167
+4169,33.365982
+4170,35.21496
+4171,35.497208
+4172,36.594986
+4173,51.25414
+4174,56.163994
+4175,58.0447
+4176,59.365612
+4177,61.796543
+4178,62.903465
+4179,66.58271
+4180,65.744644
+4181,66.68402
+4182,66.660194
+4183,68.971794
+4184,70.42222
+4185,32.14276
+4186,33.200653
+4187,39.897507
+4188,43.21232
+4189,45.923347
+4190,48.957306
+4191,50.7631
+4192,53.663067
+4193,53.97907
+4194,55.98748
+4195,59.547825
+4196,59.78807
+4197,16.03141
+4198,24.092598
+4199,26.639921
+4200,25.29697
+4201,23.679615
+4202,25.621742
+4203,31.785332
+4204,35.685497
+4205,38.61892
+4206,37.44956
+4207,38.83903
+4208,42.974346
+4209,0.17118664
+4210,0.7645921
+4211,1.0170473
+4212,1.8189985
+4213,6.271348
+4214,8.858791
+4215,13.879326
+4216,13.105867
+4217,15.082232
+4218,15.401957
+4219,44.45139
+4220,45.0811
+4221,47.94172
+4222,49.759064
+4223,53.7651
+4224,54.718525
+4225,56.532173
+4226,57.624794
+4227,60.313152
+4228,62.588882
+4229,64.50569
+4230,67.7993
+4231,32.390892
+4232,34.488697
+4233,37.57044
+4234,39.868332
+4235,40.563286
+4236,40.244774
+4237,48.1639
+4238,51.0927
+4239,50.537697
+4240,52.943222
+4241,56.3293
+4242,60.084843
+4243,0.46239302
+4244,0.52107936
+4245,0.45955855
+4246,0.7117965
+4247,22.441257
+4248,24.772076
+4249,24.533314
+4250,28.584648
+4251,29.179106
+4252,30.007795
+4253,36.488644
+4254,41.449146
+4255,40.52076
+4256,43.4449
+4257,43.681755
+4258,47.983917
+4259,24.852842
+4260,34.538555
+4261,41.715267
+4262,46.44343
+4263,26.018478
+4264,31.263317
+4265,31.337933
+4266,31.70766
+4267,34.33039
+4268,38.216827
+4269,41.475414
+4270,42.28705
+4271,55.273537
+4272,57.449974
+4273,61.52388
+4274,63.36237
+4275,64.75929
+4276,66.13171
+4277,70.381355
+4278,70.49971
+4279,68.78372
+4280,73.6452
+4281,71.29312
+4282,72.83419
+4283,32.77844
+4284,37.919952
+4285,42.474663
+4286,44.182602
+4287,48.212753
+4288,52.670933
+4289,51.226845
+4290,54.333324
+4291,57.341812
+4292,1.1077309
+4293,0.83186835
+4294,2.1206965
+4295,2.7427707
+4296,7.4554653
+4297,10.163578
+4298,7.2295966
+4299,13.964868
+4300,14.3475685
+4301,17.90334
+4302,22.135885
+4303,24.29974
+4304,21.590918
+4305,22.394297
+4306,25.366503
+4307,26.427973
+4308,24.957268
+4309,25.92907
+4310,27.410667
+4311,30.94573
+4312,30.632534
+4313,32.98272
+4314,34.929108
+4315,35.26369
+4316,-0.09447573
+4317,-0.24132392
+4318,1.1985967
+4319,3.8655114
+4320,7.3415747
+4321,6.6773944
+4322,13.221059
+4323,13.122242
+4324,14.957663
+4325,16.61172
+4326,21.711279
+4327,25.26027
+4328,33.87838
+4329,36.927437
+4330,34.764965
+4331,37.81612
+4332,40.573467
+4333,42.006195
+4334,43.63486
+4335,45.11985
+4336,47.755577
+4337,48.12539
+4338,47.57874
+4339,34.8474
+4340,34.23317
+4341,38.375618
+4342,44.470398
+4343,42.009842
+4344,41.647774
+4345,46.23226
+4346,50.572548
+4347,55.54348
+4348,34.82339
+4349,39.425465
+4350,41.58335
+4351,44.061085
+4352,46.63127
+4353,49.62857
+4354,50.583008
+4355,32.177002
+4356,34.035625
+4357,37.81975
+4358,51.076572
+4359,58.46449
+4360,18.142944
+4361,20.196022
+4362,21.76474
+4363,23.17509
+4364,25.941996
+4365,27.245499
+4366,27.729925
+4367,28.918314
+4368,43.67924
+4369,45.754215
+4370,45.65683
+4371,51.229652
+4372,27.738123
+4373,28.724554
+4374,31.207878
+4375,32.902245
+4376,34.440475
+4377,41.462517
+4378,41.90123
+4379,46.168953
+4380,45.477432
+4381,45.40369
+4382,49.35496
+4383,53.292885
+4384,14.30875
+4385,20.324394
+4386,22.991367
+4387,22.138126
+4388,23.333584
+4389,23.571743
+4390,30.096329
+4391,33.9627
+4392,34.428116
+4393,29.766893
+4394,30.654213
+4395,31.478035
+4396,36.957966
+4397,39.295567
+4398,40.03138
+4399,40.192585
+4400,41.77375
+4401,41.03658
+4402,43.803806
+4403,43.318928
+4404,43.20407
+4405,39.579494
+4406,44.962452
+4407,51.06814
+4408,54.281475
+4409,16.843693
+4410,20.81614
+4411,26.048557
+4412,29.959093
+4413,21.162636
+4414,25.54196
+4415,28.835022
+4416,35.585342
+4417,38.432404
+4418,27.109594
+4419,27.056953
+4420,28.393257
+4421,29.089539
+4422,29.991798
+4423,32.167477
+4424,5.787956
+4425,8.516348
+4426,7.7757587
+4427,13.6170845
+4428,19.642904
+4429,23.856579
+4430,21.641329
+4431,23.92649
+4432,36.160538
+4433,46.538574
+4434,51.21727
+4435,45.700928
+4436,51.37709
+4437,58.784805
+4438,47.27914
+4439,49.56553
+4440,50.185253
+4441,50.245537
+4442,25.9799
+4443,28.124939
+4444,29.634895
+4445,35.48164
+4446,36.737244
+4447,38.910088
+4448,43.17739
+4449,19.575716
+4450,30.578712
+4451,30.703226
+4452,32.304928
+4453,42.99322
+4454,50.769703
+4455,54.197063
+4456,59.012817
+4457,57.184605
+4458,60.678886
+4459,61.8228
+4460,39.316387
+4461,48.89668
+4462,50.677265
+4463,56.451416
+4464,15.433604
+4465,21.544512
+4466,26.466673
+4467,27.19112
+4468,39.53426
+4469,44.20976
+4470,47.75135
+4471,48.360764
+4472,52.434917
+4473,14.2883415
+4474,20.342945
+4475,21.200123
+4476,23.324703
+4477,26.36697
+4478,31.08544
+4479,32.95305
+4480,33.610435
+4481,42.014977
+4482,44.08052
+4483,50.040405
+4484,52.79975
+4485,13.533332
+4486,16.921368
+4487,19.335403
+4488,22.331745
+4489,16.354935
+4490,17.130934
+4491,16.03452
+4492,17.304333
+4493,18.209946
+4494,10.3381
+4495,16.532352
+4496,19.925173
+4497,19.36022
+4498,24.371716
+4499,28.487803
+4500,30.433983
+4501,32.201
+4502,33.11116
+4503,31.06527
+4504,43.97712
+4505,48.86531
+4506,49.872574
+4507,31.832802
+4508,40.488182
+4509,39.524345
+4510,45.22088
+4511,44.90781
+4512,49.466335
+4513,52.86011
+4514,54.085514
+4515,54.18705
+4516,53.87902
+4517,57.353912
+4518,55.259903
+4519,1.0273035
+4520,1.9270918
+4521,4.076442
+4522,10.28244
+4523,36.01215
+4524,35.56521
+4525,37.018948
+4526,43.33662
+4527,38.207706
+4528,40.6599
+4529,41.725
+4530,43.7122
+4531,18.774338
+4532,26.024185
+4533,28.538593
+4534,31.554628
+4535,19.575573
+4536,22.009602
+4537,26.941126
+4538,32.609486
+4539,33.58497
+4540,33.342724
+4541,34.812267
+4542,37.03791
+4543,42.94974
+4544,40.864407
+4545,41.50806
+4546,45.328377
+4547,32.115936
+4548,36.169292
+4549,37.837967
+4550,37.806297
+4551,38.905186
+4552,44.15189
+4553,22.646215
+4554,25.477911
+4555,25.015854
+4556,26.082691
+4557,27.995861
+4558,35.545513
+4559,36.522858
+4560,32.539223
+4561,38.31272
+4562,39.439743
+4563,42.969463
+4564,45.340626
+4565,23.225006
+4566,27.873255
+4567,30.840246
+4568,31.734026
+4569,52.02501
+4570,50.075264
+4571,51.030643
+4572,50.674606
+4573,55.6609
+4574,10.392675
+4575,12.389964
+4576,15.486698
+4577,15.819946
+4578,26.154068
+4579,26.615257
+4580,29.230974
+4581,32.243965
+4582,37.683514
+4583,38.25671
+4584,41.716923
+4585,47.40709
+4586,49.05634
+4587,55.769547
+4588,58.520275
+4589,59.376087
+4590,61.28961
+4591,63.698593
+4592,62.979507
+4593,66.70024
+4594,66.07281
+4595,67.6654
+4596,69.22569
+4597,46.674248
+4598,52.246643
+4599,50.855793
+4600,56.35417
+4601,9.472614
+4602,8.132129
+4603,13.665728
+4604,17.331993
+4605,20.810104
+4606,23.611643
+4607,25.626709
+4608,27.515583
+4609,34.478626
+4610,34.144787
+4611,35.78422
+4612,37.46622
+4613,45.561195
+4614,50.65722
+4615,51.986446
+4616,57.488564
+4617,61.620277
+4618,62.48863
+4619,63.60964
+4620,64.61905
+4621,67.68145
+4622,70.24887
+4623,68.58749
+4624,71.914505
+4625,33.302902
+4626,37.182373
+4627,43.845078
+4628,44.51508
+4629,48.595642
+4630,50.617367
+4631,54.312073
+4632,55.693157
+4633,56.71228
+4634,59.76378
+4635,37.442623
+4636,42.202908
+4637,43.732594
+4638,45.112564
+4639,50.156433
+4640,47.69051
+4641,55.000977
+4642,56.505173
+4643,54.999073
+4644,53.861626
+4645,56.71935
+4646,59.924088
+4647,35.15044
+4648,38.516304
+4649,48.08248
+4650,48.33314
+4651,46.95594
+4652,49.342598
+4653,55.24352
+4654,53.9414
+4655,57.811996
+4656,59.572388
+4657,67.14244
+4658,68.22768
+4659,9.498931
+4660,13.696766
+4661,16.207237
+4662,14.115963
+4663,17.681269
+4664,22.570494
+4665,22.402914
+4666,25.789606
+4667,23.829498
+4668,26.335878
+4669,27.305006
+4670,28.792383
+4671,60.79551
+4672,64.739586
+4673,66.78563
+4674,67.20938
+4675,39.67001
+4676,41.75823
+4677,46.79544
+4678,50.36896
+4679,52.603004
+4680,53.679924
+4681,56.719593
+4682,57.655556
+4683,58.634735
+4684,60.130646
+4685,62.159134
+4686,62.9471
+4687,46.509136
+4688,47.357014
+4689,45.91182
+4690,49.52848
+4691,51.992798
+4692,41.019573
+4693,44.79996
+4694,44.795746
+4695,44.945892
+4696,48.219437
+4697,48.5128
+4698,50.413666
+4699,52.564987
+4700,52.741608
+4701,54.596523
+4702,55.696854
+4703,58.7502
+4704,37.036907
+4705,40.06738
+4706,44.548454
+4707,45.532394
+4708,47.053207
+4709,51.212418
+4710,53.393425
+4711,56.189507
+4712,55.662148
+4713,58.55515
+4714,59.69286
+4715,58.66775
+4716,20.229918
+4717,25.903234
+4718,26.341688
+4719,28.078888
+4720,30.649982
+4721,46.148216
+4722,49.277214
+4723,53.4612
+4724,55.983383
+4725,58.1757
+4726,59.78267
+4727,59.738327
+4728,22.758638
+4729,21.853046
+4730,23.560654
+4731,24.536987
+4732,24.085049
+4733,28.55452
+4734,29.47397
+4735,43.979298
+4736,47.100197
+4737,50.098614
+4738,51.121452
+4739,54.92723
+4740,27.338636
+4741,30.951082
+4742,32.33842
+4743,35.456
+4744,37.694195
+4745,38.279865
+4746,9.007454
+4747,12.15745
+4748,16.376408
+4749,18.831898
+4750,17.685623
+4751,28.10232
+4752,31.026577
+4753,30.30944
+4754,37.83576
+4755,42.644516
+4756,29.669733
+4757,35.884853
+4758,36.62901
+4759,36.01676
+4760,41.228344
+4761,44.01927
+4762,47.173462
+4763,46.341007
+4764,49.688103
+4765,50.603695
+4766,38.025314
+4767,37.84525
+4768,41.961163
+4769,45.95066
+4770,48.090916
+4771,51.439438
+4772,55.71704
+4773,55.162807
+4774,57.687454
+4775,58.099895
+4776,64.83362
+4777,62.4629
+4778,52.062378
+4779,59.391357
+4780,60.439987
+4781,61.193245
+4782,48.020466
+4783,49.85447
+4784,47.32565
+4785,46.620193
+4786,49.317703
+4787,51.247154
+4788,49.947655
+4789,53.418045
+4790,31.964256
+4791,33.427532
+4792,36.895153
+4793,41.776947
+4794,42.187626
+4795,43.32822
+4796,46.814365
+4797,50.750515
+4798,55.428917
+4799,56.499973
+4800,59.71834
+4801,60.391926
+4802,26.797533
+4803,29.793732
+4804,36.01303
+4805,37.54827
+4806,38.861546
+4807,41.9261
+4808,43.692574
+4809,47.444614
+4810,48.689514
+4811,49.973816
+4812,55.011826
+4813,41.101627
+4814,43.937523
+4815,47.312115
+4816,50.015076
+4817,51.334106
+4818,54.10639
+4819,55.865753
+4820,56.49398
+4821,57.594532
+4822,59.996048
+4823,58.493843
+4824,60.00016
+4825,16.189186
+4826,19.50578
+4827,18.918427
+4828,25.28095
+4829,27.089731
+4830,28.007956
+4831,33.459732
+4832,34.42078
+4833,36.405476
+4834,38.74482
+4835,39.21035
+4836,42.740105
+4837,10.437942
+4838,14.397852
+4839,19.324047
+4840,19.077229
+4841,28.906378
+4842,30.57185
+4843,31.81971
+4844,31.139015
+4845,34.871674
+4846,36.955307
+4847,41.441986
+4848,43.137928
+4849,41.8252
+4850,43.62148
+4851,46.11551
+4852,46.815483
+4853,25.7244
+4854,26.014322
+4855,25.357733
+4856,28.503368
+4857,51.423916
+4858,52.967392
+4859,54.036625
+4860,58.35563
+4861,24.275837
+4862,24.454178
+4863,29.52591
+4864,32.17109
+4865,34.630676
+4866,36.3623
+4867,37.48781
+4868,40.731987
+4869,47.365112
+4870,35.694912
+4871,37.78089
+4872,39.084507
+4873,42.855335
+4874,46.16063
+4875,50.84476
+4876,24.170542
+4877,27.319016
+4878,27.753632
+4879,28.680065
+4880,29.58032
+4881,13.556135
+4882,14.615773
+4883,18.94454
+4884,21.21363
+4885,51.044476
+4886,54.090576
+4887,59.500744
+4888,60.20716
+4889,63.774677
+4890,62.951942
+4891,16.046661
+4892,20.131458
+4893,31.82071
+4894,32.967987
+4895,26.387466
+4896,28.942966
+4897,32.5255
+4898,33.93194
+4899,37.24224
+4900,39.74493
+4901,41.784817
+4902,47.157272
+4903,0.99875003
+4904,1.8916177
+4905,8.664005
+4906,7.004011
+4907,19.968515
+4908,23.916656
+4909,31.744064
+4910,33.73945
+4911,39.425674
+4912,38.43016
+4913,41.293797
+4914,45.46792
+4915,45.295113
+4916,47.877674
+4917,46.50717
+4918,-0.66063297
+4919,-0.2725725
+4920,1.095259
+4921,2.539687
+4922,6.9517674
+4923,9.476982
+4924,14.333645
+4925,10.886864
+4926,17.130888
+4927,19.984129
+4928,24.490225
+4929,30.32604
+4930,45.146774
+4931,46.385303
+4932,45.17893
+4933,46.189148
+4934,46.897457
+4935,49.00372
+4936,49.554195
+4937,34.045555
+4938,37.98504
+4939,40.590504
+4940,44.149883
+4941,47.484486
+4942,52.048885
+4943,20.075275
+4944,21.78652
+4945,24.021894
+4946,32.807053
+4947,36.34856
+4948,35.63137
+4949,7.5470657
+4950,8.812565
+4951,10.016032
+4952,13.053526
+4953,39.255257
+4954,37.722385
+4955,38.85897
+4956,40.820698
+4957,43.165897
+4958,5.7530704
+4959,5.5363483
+4960,7.7995358
+4961,7.650652
+4962,15.595077
+4963,18.979704
+4964,17.205036
+4965,17.465591
+4966,22.366053
+4967,24.410898
+4968,26.892357
+4969,28.586985
+4970,5.7861223
+4971,7.6994777
+4972,10.673319
+4973,13.345248
+4974,11.444452
+4975,15.043998
+4976,15.950153
+4977,16.88644
+4978,34.319553
+4979,37.484722
+4980,41.038826
+4981,43.02269
+4982,44.612926
+4983,47.713753
+4984,52.068325
+4985,52.75613
+4986,54.395596
+4987,54.886063
+4988,57.438385
+4989,59.35528
+4990,11.750891
+4991,13.062095
+4992,16.123024
+4993,21.91794
+4994,24.98772
+4995,26.041868
+4996,33.301563
+4997,37.76703
+4998,38.061375
+4999,41.53862
+5000,46.183228
+5001,46.62479
+5002,51.25218
+5003,53.587162
+5004,55.9448
+5005,55.202595
+5006,57.10367
+5007,58.220627
+5008,15.887412
+5009,19.26904
+5010,19.398516
+5011,21.271488
+5012,22.327831
+5013,27.701128
+5014,34.13073
+5015,35.0801
+5016,42.188385
+5017,49.06401
+5018,42.802624
+5019,48.479664
+5020,52.474007
+5021,50.99862
+5022,56.57189
+5023,59.28788
+5024,32.641407
+5025,42.399105
+5026,46.182808
+5027,38.819386
+5028,44.565025
+5029,47.593452
+5030,51.026245
+5031,53.350536
+5032,53.29435
+5033,55.86119
+5034,57.309883
+5035,55.93384
+5036,22.22048
+5037,25.115786
+5038,29.588589
+5039,29.787367
+5040,18.596272
+5041,23.764772
+5042,24.762564
+5043,28.025778
+5044,30.694962
+5045,31.00579
+5046,35.154327
+5047,36.42871
+5048,37.37507
+5049,38.169445
+5050,40.303173
+5051,41.563484
+5052,19.249624
+5053,23.067333
+5054,22.473837
+5055,23.180973
+5056,29.489758
+5057,27.223484
+5058,30.789604
+5059,34.896683
+5060,38.11453
+5061,43.720818
+5062,47.10319
+5063,51.48616
+5064,0.99608153
+5065,1.4446323
+5066,1.8379878
+5067,2.8448076
+5068,5.722802
+5069,6.6273975
+5070,11.245944
+5071,14.4031315
+5072,15.165043
+5073,26.47889
+5074,26.768505
+5075,29.348894
+5076,29.039545
+5077,39.952297
+5078,43.70166
+5079,40.692924
+5080,42.835682
+5081,45.925114
+5082,49.661674
+5083,49.58248
+5084,53.900368
+5085,4.085636
+5086,6.091758
+5087,8.687083
+5088,13.065989
+5089,15.784179
+5090,18.385517
+5091,20.215233
+5092,23.053255
+5093,26.903385
+5094,28.038195
+5095,29.7061
+5096,30.874367
+5097,50.323536
+5098,52.117447
+5099,55.608906
+5100,52.120647
+5101,52.86178
+5102,55.557117
+5103,57.19994
+5104,56.87224
+5105,58.333973
+5106,58.99698
+5107,63.303276
+5108,64.15788
+5109,35.74647
+5110,35.365383
+5111,35.937286
+5112,38.844257
+5113,39.81215
+5114,39.125084
+5115,40.961926
+5116,38.682556
+5117,43.939823
+5118,46.32468
+5119,48.553337
+5120,1.5012674
+5121,2.6315212
+5122,3.8097932
+5123,5.34552
+5124,6.2489605
+5125,10.939499
+5126,53.09171
+5127,52.927326
+5128,56.67646
+5129,56.232784
+5130,57.181282
+5131,55.486343
+5132,57.07791
+5133,61.197815
+5134,58.550797
+5135,58.969265
+5136,62.164642
+5137,64.40462
+5138,19.163866
+5139,20.730427
+5140,22.03336
+5141,29.55124
+5142,34.81402
+5143,26.769787
+5144,33.57772
+5145,35.855804
+5146,40.02083
+5147,28.790134
+5148,34.24904
+5149,36.57263
+5150,42.752533
+5151,40.261963
+5152,48.282436
+5153,51.76232
+5154,54.462658
+5155,34.676205
+5156,38.650234
+5157,40.856167
+5158,43.201637
+5159,46.037262
+5160,50.44524
+5161,53.70017
+5162,57.48218
+5163,22.869383
+5164,25.478615
+5165,25.45322
+5166,33.505188
+5167,37.11702
+5168,34.370346
+5169,39.597824
+5170,42.021477
+5171,44.084736
+5172,44.881657
+5173,46.86913
+5174,47.183884
+5175,9.005111
+5176,14.857062
+5177,21.912928
+5178,23.686613
+5179,37.899635
+5180,42.187637
+5181,47.283585
+5182,47.773808
+5183,50.29941
+5184,46.387283
+5185,50.883812
+5186,50.98192
+5187,54.742203
+5188,56.820595
+5189,59.664925
+5190,60.868286
+5191,62.55092
+5192,63.311386
+5193,67.51697
+5194,66.565796
+5195,67.18487
+5196,8.8420515
+5197,9.5976715
+5198,9.139552
+5199,9.861275
+5200,24.428228
+5201,32.518517
+5202,32.94459
+5203,34.575405
+5204,36.68581
+5205,40.081097
+5206,45.261208
+5207,46.62982
+5208,51.49717
+5209,26.48044
+5210,26.282896
+5211,25.376558
+5212,27.49631
+5213,29.952362
+5214,21.789978
+5215,25.68827
+5216,29.552505
+5217,35.130123
+5218,38.1688
+5219,55.082027
+5220,54.735207
+5221,54.055088
+5222,56.196423
+5223,56.00352
+5224,57.489807
+5225,0.2026788
+5226,0.9336445
+5227,1.6969187
+5228,3.3125453
+5229,9.131085
+5230,33.899807
+5231,36.477203
+5232,42.716892
+5233,44.977318
+5234,22.955355
+5235,30.834116
+5236,29.851181
+5237,32.904892
+5238,23.087978
+5239,30.434906
+5240,34.64133
+5241,44.600174
+5242,26.49504
+5243,28.331459
+5244,34.09306
+5245,35.835266
+5246,35.608055
+5247,38.27237
+5248,38.90789
+5249,38.78755
+5250,10.853229
+5251,11.937262
+5252,12.4227
+5253,14.832168
+5254,15.966238
+5255,17.399149
+5256,19.658066
+5257,25.350002
+5258,28.114384
+5259,31.517778
+5260,31.056988
+5261,33.46567
+5262,23.127094
+5263,26.638626
+5264,29.55166
+5265,35.407627
+5266,38.824093
+5267,37.81768
+5268,40.514755
+5269,42.073498
+5270,45.79005
+5271,48.187107
+5272,27.697044
+5273,31.253538
+5274,30.84431
+5275,29.809406
+5276,33.38696
+5277,33.06605
+5278,38.200024
+5279,38.77572
+5280,39.631645
+5281,42.703236
+5282,45.121765
+5283,50.109673
+5284,42.879883
+5285,50.25498
+5286,52.36354
+5287,53.335827
+5288,60.62217
+5289,59.65191
+5290,62.591198
+5291,65.05213
+5292,64.00572
+5293,67.56538
+5294,65.878746
+5295,67.50263
+5296,12.503494
+5297,17.708426
+5298,22.780476
+5299,24.843416
+5300,27.167492
+5301,22.645758
+5302,27.57374
+5303,28.726715
+5304,30.022345
+5305,31.57999
+5306,35.82824
+5307,37.294575
+5308,41.711384
+5309,42.806076
+5310,43.68364
+5311,46.945374
+5312,47.374146
+5313,35.827946
+5314,48.368484
+5315,53.667324
+5316,58.28345
+5317,14.727568
+5318,24.165728
+5319,28.644196
+5320,29.037403
+5321,54.203213
+5322,54.020855
+5323,56.675034
+5324,55.557087
+5325,58.643623
+5326,60.05949
+5327,61.274666
+5328,65.65271
+5329,64.803345
+5330,65.43484
+5331,66.01863
+5332,69.5708
+5333,37.368443
+5334,43.07149
+5335,44.865032
+5336,45.939117
+5337,50.05024
+5338,55.07954
+5339,51.78356
+5340,54.735294
+5341,55.421207
+5342,56.060715
+5343,56.985546
+5344,59.97283
+5345,40.57464
+5346,41.07472
+5347,47.65971
+5348,48.90541
+5349,53.29329
+5350,55.352993
+5351,55.03599
+5352,58.261307
+5353,58.89682
+5354,60.757294
+5355,61.594257
+5356,63.478928
+5357,12.911118
+5358,23.677362
+5359,24.945068
+5360,26.209215
+5361,87.662926
+5362,90.13987
+5363,92.31691
+5364,96.995804
+5365,95.69664
+5366,95.02064
+5367,97.78381
+5368,100.67758
+5369,101.52363
+5370,100.31499
+5371,100.60615
+5372,100.35594
+5373,37.63221
+5374,39.426872
+5375,45.469646
+5376,48.958504
+5377,52.442223
+5378,52.78965
+5379,52.792248
+5380,59.779156
+5381,57.349255
+5382,58.78025
+5383,58.40757
+5384,60.81837
+5385,17.26152
+5386,16.448685
+5387,25.011976
+5388,25.990595
+5389,26.421593
+5390,20.908377
+5391,23.457691
+5392,23.235306
+5393,26.65281
+5394,27.51577
+5395,30.12098
+5396,34.61362
+5397,35.870686
+5398,36.041397
+5399,39.00759
+5400,41.070396
+5401,46.392464
+5402,20.850344
+5403,27.020027
+5404,32.049538
+5405,42.15105
+5406,24.704811
+5407,24.398476
+5408,25.94598
+5409,25.737864
+5410,45.63321
+5411,47.843323
+5412,49.094223
+5413,42.737404
+5414,44.89094
+5415,51.76906
+5416,30.430862
+5417,33.85801
+5418,35.07846
+5419,41.07135
+5420,40.90916
+5421,44.95585
+5422,18.766174
+5423,26.22917
+5424,27.87125
+5425,29.20484
+5426,32.313507
+5427,33.351936
+5428,16.978678
+5429,17.443542
+5430,20.177479
+5431,27.874317
+5432,29.849457
+5433,26.411842
+5434,28.894127
+5435,33.73677
+5436,18.324457
+5437,19.885395
+5438,22.111387
+5439,23.177528
+5440,23.334497
+5441,26.206152
+5442,28.400288
+5443,37.163452
+5444,40.14426
+5445,37.825333
+5446,37.8607
+5447,46.97899
+5448,19.223581
+5449,23.848143
+5450,24.734007
+5451,29.681599
+5452,30.429802
+5453,25.082048
+5454,29.874252
+5455,30.878002
+5456,33.477448
+5457,33.983727
+5458,36.69475
+5459,37.929886
+5460,23.505013
+5461,26.313267
+5462,29.382551
+5463,33.85132
+5464,41.402863
+5465,39.05993
+5466,43.41554
+5467,46.584717
+5468,49.154305
+5469,51.471573
+5470,53.984715
+5471,36.92053
+5472,41.380054
+5473,42.514153
+5474,44.64247
+5475,44.255566
+5476,47.70011
+5477,52.09885
+5478,51.477676
+5479,55.645866
+5480,55.69335
+5481,61.069588
+5482,62.591503
+5483,63.39618
+5484,64.61271
+5485,65.47686
+5486,68.83968
+5487,68.675476
+5488,72.24459
+5489,73.9458
+5490,71.93375
+5491,10.138273
+5492,15.611011
+5493,16.55278
+5494,17.299963
+5495,19.580177
+5496,23.932343
+5497,28.455782
+5498,35.66993
+5499,36.146843
+5500,40.254475
+5501,39.412548
+5502,42.85608
+5503,54.20428
+5504,54.642075
+5505,59.128277
+5506,62.162712
+5507,65.50251
+5508,62.183983
+5509,66.22068
+5510,65.91283
+5511,65.18713
+5512,67.2731
+5513,71.28137
+5514,71.650314
+5515,14.415353
+5516,17.655186
+5517,24.57356
+5518,31.630993
+5519,40.610577
+5520,15.891061
+5521,17.813503
+5522,21.09061
+5523,27.596159
+5524,28.158737
+5525,31.062447
+5526,33.32461
+5527,39.22377
+5528,45.245213
+5529,41.87496
+5530,44.062943
+5531,49.368504
+5532,51.705723
+5533,52.668583
+5534,56.532417
+5535,55.872974
+5536,53.396988
+5537,58.304634
+5538,57.30719
+5539,60.498848
+5540,65.59678
+5541,60.82576
+5542,61.378036
+5543,65.54229
+5544,42.043423
+5545,41.85597
+5546,42.31055
+5547,44.4005
+5548,46.477932
+5549,17.455944
+5550,23.95772
+5551,26.083115
+5552,25.279007
+5553,31.117405
+5554,34.61895
+5555,32.16517
+5556,34.045895
+5557,34.622936
+5558,36.318577
+5559,38.989067
+5560,38.999878
+5561,24.505579
+5562,32.168243
+5563,31.847427
+5564,31.454784
+5565,33.822987
+5566,37.936634
+5567,41.731716
+5568,46.759983
+5569,50.495064
+5570,8.00531
+5571,9.986237
+5572,13.144668
+5573,15.376482
+5574,17.233004
+5575,20.657904
+5576,25.211231
+5577,18.414383
+5578,18.218895
+5579,20.044025
+5580,21.413769
+5581,20.424345
+5582,22.932928
+5583,25.937624
+5584,28.90012
+5585,29.615652
+5586,34.40964
+5587,41.548874
+5588,34.60247
+5589,46.399433
+5590,51.087963
+5591,52.70227
+5592,64.495735
+5593,31.469097
+5594,33.72458
+5595,35.477203
+5596,39.080345
+5597,40.974
+5598,12.935823
+5599,15.116006
+5600,20.417324
+5601,23.096245
+5602,23.151049
+5603,56.52912
+5604,61.284687
+5605,64.09628
+5606,67.62668
+5607,64.57634
+5608,65.43877
+5609,66.62617
+5610,67.255585
+5611,68.96862
+5612,70.26769
+5613,70.2855
+5614,71.697464
+5615,19.178846
+5616,20.494745
+5617,22.95769
+5618,30.841516
+5619,21.606102
+5620,25.768593
+5621,28.91303
+5622,34.035835
+5623,33.529114
+5624,35.575405
+5625,40.461468
+5626,44.361683
+5627,42.475334
+5628,47.487476
+5629,47.24616
+5630,55.938717
+5631,48.643806
+5632,51.545746
+5633,55.01805
+5634,59.109783
+5635,62.7673
+5636,60.504642
+5637,63.109722
+5638,66.174065
+5639,21.555752
+5640,26.902534
+5641,31.820648
+5642,33.976166
+5643,45.12106
+5644,50.188313
+5645,52.175858
+5646,47.183056
+5647,52.445778
+5648,55.55982
+5649,55.91846
+5650,59.932594
+5651,59.21057
+5652,58.573387
+5653,61.63663
+5654,62.607956
+5655,20.094957
+5656,22.68014
+5657,27.027699
+5658,31.946556
+5659,33.59736
+5660,36.30698
+5661,57.604496
+5662,59.29444
+5663,61.789906
+5664,63.633015
+5665,68.626785
+5666,5.467551
+5667,12.135695
+5668,14.977297
+5669,16.045685
+5670,42.292763
+5671,44.72264
+5672,43.00468
+5673,46.833908
+5674,47.11142
+5675,51.857704
+5676,50.16496
+5677,51.54496
+5678,53.512432
+5679,55.29622
+5680,55.012966
+5681,17.10615
+5682,22.862389
+5683,24.165066
+5684,24.066593
+5685,24.150368
+5686,24.715332
+5687,25.640333
+5688,29.709015
+5689,29.1706
+5690,31.649761
+5691,34.16874
+5692,34.778404
+5693,12.85352
+5694,27.390446
+5695,28.146482
+5696,25.472496
+5697,28.120993
+5698,27.6762
+5699,28.831074
+5700,29.977522
+5701,32.568375
+5702,34.275414
+5703,38.790592
+5704,40.605595
+5705,38.98792
+5706,41.165913
+5707,46.94412
+5708,44.70465
+5709,49.442894
+5710,50.32965
+5711,55.439552
+5712,55.56867
+5713,56.51758
+5714,58.85683
+5715,60.37419
+5716,64.41392
+5717,34.533886
+5718,36.827118
+5719,43.04806
+5720,50.112057
+5721,55.27296
+5722,0.29229328
+5723,1.1162335
+5724,1.0396907
+5725,2.9127874
+5726,5.3147244
+5727,5.015425
+5728,8.262843
+5729,12.775593
+5730,16.183939
+5731,16.811954
+5732,17.337234
+5733,18.62841
+5734,21.69574
+5735,37.518993
+5736,52.222343
+5737,56.72679
+5738,57.67071
+5739,43.3224
+5740,47.078293
+5741,50.56594
+5742,55.989082
+5743,57.60912
+5744,59.250282
+5745,62.462242
+5746,65.05822
+5747,67.62924
+5748,67.10202
+5749,68.50514
+5750,77.88977
+5751,22.978912
+5752,27.34076
+5753,33.234364
+5754,37.355553
+5755,34.569107
+5756,37.99254
+5757,39.0292
+5758,42.96085
+5759,7.5858593
+5760,13.6478
+5761,18.249603
+5762,22.841915
+5763,25.91629
+5764,31.657372
+5765,34.210136
+5766,35.500866
+5767,39.199986
+5768,45.54332
+5769,44.561886
+5770,46.378403
+5771,50.469666
+5772,48.188583
+5773,53.99804
+5774,55.885445
+5775,16.572144
+5776,21.295437
+5777,27.337027
+5778,30.318449
+5779,30.248566
+5780,30.641926
+5781,35.266327
+5782,38.98345
+5783,35.450882
+5784,41.793865
+5785,45.23504
+5786,44.43732
+5787,39.711666
+5788,43.088337
+5789,48.088604
+5790,52.221207
+5791,52.41647
+5792,54.96115
+5793,57.829967
+5794,59.96455
+5795,61.28814
+5796,63.32893
+5797,67.15752
+5798,67.977196
+5799,22.844486
+5800,22.325096
+5801,23.16654
+5802,26.13499
+5803,19.436296
+5804,20.050564
+5805,20.255814
+5806,19.271141
+5807,19.533623
+5808,50.48569
+5809,53.68782
+5810,57.580746
+5811,62.81422
+5812,41.106533
+5813,44.53179
+5814,46.12656
+5815,55.052498
+5816,31.871136
+5817,32.0273
+5818,34.709976
+5819,36.45532
+5820,16.689674
+5821,19.324392
+5822,22.675907
+5823,23.823896
+5824,27.077627
+5825,30.826328
+5826,37.3004
+5827,43.05168
+5828,42.703266
+5829,28.555607
+5830,27.109987
+5831,27.516148
+5832,31.613531
+5833,31.906109
+5834,73.8967
+5835,72.903725
+5836,77.284164
+5837,77.84314
+5838,75.327545
+5839,76.64207
+5840,77.06647
+5841,78.92765
+5842,78.38905
+5843,80.15936
+5844,79.32925
+5845,80.68572
+5846,22.358126
+5847,25.84219
+5848,27.839775
+5849,28.786718
+5850,30.484005
+5851,36.464382
+5852,34.7044
+5853,37.843
+5854,38.35449
+5855,1.1332549
+5856,2.6012733
+5857,4.221462
+5858,7.103189
+5859,9.968122
+5860,12.805527
+5861,17.928864
+5862,22.322742
+5863,23.018623
+5864,23.845587
+5865,24.601452
+5866,27.948135
+5867,15.426281
+5868,15.496033
+5869,22.085073
+5870,31.954594
+5871,39.610523
+5872,40.41387
+5873,46.070786
+5874,45.903267
+5875,50.721592
+5876,54.839542
+5877,55.030663
+5878,54.824738
+5879,57.017174
+5880,58.526703
+5881,58.46145
+5882,58.77629
+5883,36.91672
+5884,39.732758
+5885,40.606262
+5886,52.60397
+5887,50.820034
+5888,53.435684
+5889,53.67592
+5890,54.823517
+5891,56.56656
+5892,60.32194
+5893,61.75966
+5894,61.56097
+5895,2.496168
+5896,2.9763527
+5897,5.11713
+5898,8.320236
+5899,7.7460437
+5900,18.221233
+5901,19.3989
+5902,23.26845
+5903,20.943638
+5904,22.704306
+5905,22.038595
+5906,23.097696
+5907,10.628886
+5908,12.726667
+5909,13.098516
+5910,15.164896
+5911,15.509346
+5912,17.81183
+5913,20.16652
+5914,17.654524
+5915,19.515575
+5916,25.08274
+5917,29.155962
+5918,31.644283
+5919,34.750397
+5920,23.596848
+5921,26.462118
+5922,29.226942
+5923,37.25452
+5924,37.848858
+5925,39.338192
+5926,42.554993
+5927,46.927544
+5928,49.17961
+5929,53.89026
+5930,56.710335
+5931,58.78814
+5932,1.6647456
+5933,3.0417628
+5934,7.1200886
+5935,9.554399
+5936,10.96734
+5937,28.75539
+5938,32.131107
+5939,34.640995
+5940,32.45066
+5941,22.902414
+5942,27.01585
+5943,32.327366
+5944,30.345264
+5945,33.72138
+5946,37.810585
+5947,41.455986
+5948,42.76906
+5949,39.1118
+5950,41.446762
+5951,42.25548
+5952,44.939438
+5953,20.646275
+5954,26.367702
+5955,30.072966
+5956,29.369936
+5957,30.140282
+5958,32.08846
+5959,36.448242
+5960,39.884727
+5961,42.212822
+5962,42.0618
+5963,40.091606
+5964,42.691177
+5965,33.575844
+5966,34.9178
+5967,38.869644
+5968,45.247585
+5969,47.936302
+5970,51.506134
+5971,52.527313
+5972,54.24983
+5973,57.40313
+5974,60.069374
+5975,58.08024
+5976,59.899437
+5977,31.947521
+5978,39.82162
+5979,43.877254
+5980,42.68551
+5981,48.311146
+5982,48.07368
+5983,51.338753
+5984,53.9327
+5985,56.111343
+5986,59.040802
+5987,63.642654
+5988,63.124012
+5989,32.852432
+5990,35.718586
+5991,38.337955
+5992,41.99144
+5993,44.936428
+5994,37.650997
+5995,38.782993
+5996,44.38475
+5997,50.395145
+5998,54.615337
+5999,54.506706
+6000,29.24136
+6001,29.687119
+6002,30.919504
+6003,33.23904
+6004,41.47264
+6005,38.528854
+6006,38.715065
+6007,46.103695
+6008,49.370956
+6009,50.79516
+6010,55.586555
+6011,58.47393
+6012,39.8725
+6013,41.972034
+6014,41.96252
+6015,42.852913
+6016,42.815422
+6017,46.167946
+6018,47.835453
+6019,47.433132
+6020,46.040215
+6021,51.439804
+6022,53.78168
+6023,51.49452
+6024,27.086683
+6025,35.3071
+6026,39.42669
+6027,42.508904
+6028,24.260277
+6029,25.739216
+6030,33.38405
+6031,35.972008
+6032,42.061802
+6033,43.474392
+6034,44.942276
+6035,46.44428
+6036,49.28594
+6037,52.500008
+6038,54.17244
+6039,56.680813
+6040,1.7827613
+6041,3.3131838
+6042,5.284245
+6043,5.499449
+6044,7.3568544
+6045,8.662376
+6046,14.37186
+6047,14.46859
+6048,16.65291
+6049,21.726025
+6050,25.939327
+6051,28.726988
+6052,34.623135
+6053,35.61014
+6054,37.661106
+6055,41.476833
+6056,44.52742
+6057,35.859615
+6058,41.27767
+6059,42.265892
+6060,49.61643
+6061,26.135601
+6062,27.422705
+6063,32.55809
+6064,35.380123
+6065,38.901085
+6066,38.50639
+6067,39.458813
+6068,42.702164
+6069,44.50654
+6070,46.37767
+6071,52.161148
+6072,55.527725
+6073,21.798204
+6074,22.683935
+6075,27.724949
+6076,26.143324
+6077,28.090973
+6078,27.531511
+6079,45.155518
+6080,45.960205
+6081,47.542812
+6082,51.827118
+6083,54.057465
+6084,55.85265
+6085,56.057068
+6086,58.73943
+6087,58.522015
+6088,61.16049
+6089,62.32482
+6090,65.12485
+6091,12.77528
+6092,17.937977
+6093,22.127249
+6094,23.017685
+6095,-0.6939118
+6096,-0.08510779
+6097,1.6510353
+6098,3.543939
+6099,7.800023
+6100,8.604275
+6101,9.998718
+6102,12.4331665
+6103,12.227895
+6104,14.690788
+6105,14.198304
+6106,18.69508
+6107,21.219158
+6108,24.038334
+6109,25.620811
+6110,30.405994
+6111,35.250854
+6112,38.19249
+6113,41.45035
+6114,44.06202
+6115,42.526474
+6116,48.170383
+6117,48.62672
+6118,52.097046
+6119,23.666304
+6120,26.270908
+6121,28.673548
+6122,35.238964
+6123,36.99533
+6124,36.860985
+6125,39.234287
+6126,41.281067
+6127,44.587776
+6128,49.715656
+6129,50.13235
+6130,52.446526
+6131,44.714317
+6132,50.407898
+6133,52.82549
+6134,53.73514
+6135,55.649445
+6136,34.082996
+6137,34.906845
+6138,33.295685
+6139,36.616257
+6140,34.587044
+6141,37.74641
+6142,39.97702
+6143,40.298557
+6144,42.46501
+6145,40.580147
+6146,39.48934
+6147,42.232765
+6148,39.018456
+6149,41.438786
+6150,42.459698
+6151,43.20979
+6152,45.3685
+6153,46.431713
+6154,42.88188
+6155,47.299187
+6156,45.528797
+6157,16.95042
+6158,23.105856
+6159,27.073599
+6160,27.683512
+6161,29.754154
+6162,41.266777
+6163,43.863605
+6164,46.347202
+6165,49.191498
+6166,51.368446
+6167,52.161884
+6168,56.121403
+6169,59.075405
+6170,25.274424
+6171,27.427914
+6172,29.242743
+6173,32.37191
+6174,33.892963
+6175,34.184135
+6176,18.702393
+6177,22.492655
+6178,27.285824
+6179,29.63345
+6180,26.220997
+6181,26.89708
+6182,31.304413
+6183,42.538357
+6184,16.504646
+6185,18.192331
+6186,19.441734
+6187,26.938087
+6188,28.579075
+6189,34.187313
+6190,34.00586
+6191,38.39499
+6192,41.300797
+6193,44.483444
+6194,44.708252
+6195,51.475845
+6196,36.539536
+6197,41.380474
+6198,43.308475
+6199,45.1363
+6200,49.33395
+6201,48.248833
+6202,55.93834
+6203,56.212234
+6204,58.214703
+6205,61.363754
+6206,61.70585
+6207,61.231445
+6208,13.167904
+6209,13.28577
+6210,14.119899
+6211,18.213926
+6212,20.213194
+6213,23.40412
+6214,29.720219
+6215,33.017994
+6216,36.632946
+6217,38.17533
+6218,40.257614
+6219,40.377922
+6220,1.730427
+6221,2.5860496
+6222,3.8395886
+6223,5.5375037
+6224,26.62597
+6225,32.82731
+6226,31.16959
+6227,36.245415
+6228,47.19942
+6229,51.82706
+6230,20.32216
+6231,20.284618
+6232,22.422306
+6233,25.953518
+6234,27.367126
+6235,31.268236
+6236,35.920418
+6237,38.752487
+6238,42.318874
+6239,41.808556
+6240,42.269314
+6241,45.513412
+6242,39.141636
+6243,42.042156
+6244,43.80053
+6245,43.08197
+6246,43.867767
+6247,45.103294
+6248,47.507446
+6249,22.476055
+6250,25.367798
+6251,27.393593
+6252,27.216146
+6253,42.787354
+6254,46.377457
+6255,50.899773
+6256,54.76906
+6257,57.124928
+6258,17.248598
+6259,18.98154
+6260,19.493748
+6261,20.100515
+6262,22.213518
+6263,22.538847
+6264,23.420113
+6265,26.782326
+6266,27.581743
+6267,28.105766
+6268,29.600296
+6269,30.904316
+6270,33.50932
+6271,38.157997
+6272,35.451843
+6273,34.805824
+6274,12.675624
+6275,14.912866
+6276,18.081661
+6277,20.181662
+6278,23.731161
+6279,24.487793
+6280,26.15886
+6281,33.37671
+6282,36.194107
+6283,37.317696
+6284,36.71412
+6285,38.944042
+6286,35.875984
+6287,38.244003
+6288,48.690823
+6289,54.293766
+6290,54.116768
+6291,45.884674
+6292,49.31913
+6293,51.226074
+6294,55.191174
+6295,56.615963
+6296,57.30029
+6297,61.959362
+6298,65.85153
+6299,66.93889
+6300,64.880135
+6301,68.94569
+6302,69.357765
+6303,32.8265
+6304,34.129597
+6305,43.26047
+6306,48.152496
+6307,4.1721835
+6308,6.226288
+6309,14.505844
+6310,18.273106
+6311,3.8154159
+6312,10.419086
+6313,15.702781
+6314,19.693312
+6315,24.479126
+6316,17.651001
+6317,30.476326
+6318,31.454239
+6319,34.33033
+6320,8.895168
+6321,16.073877
+6322,19.334919
+6323,15.283291
+6324,15.827719
+6325,20.174904
+6326,25.856941
+6327,30.00654
+6328,37.407104
+6329,36.63675
+6330,37.901264
+6331,37.97213
+6332,35.302845
+6333,39.384834
+6334,40.416214
+6335,17.298443
+6336,19.067
+6337,26.525202
+6338,30.660748
+6339,33.91673
+6340,32.2241
+6341,36.189568
+6342,40.541233
+6343,41.20774
+6344,42.811794
+6345,46.180984
+6346,49.24915
+6347,44.036217
+6348,45.03589
+6349,47.34088
+6350,51.19072
+6351,56.608345
+6352,57.58581
+6353,60.793896
+6354,61.51143
+6355,64.19566
+6356,70.7173
+6357,68.92648
+6358,72.88497
+6359,23.471924
+6360,29.074488
+6361,31.38121
+6362,29.781157
+6363,29.967445
+6364,32.41722
+6365,35.690742
+6366,37.32488
+6367,40.905426
+6368,41.65548
+6369,45.32099
+6370,45.593132
+6371,21.005941
+6372,35.09662
+6373,34.83351
+6374,28.078682
+6375,36.350655
+6376,40.381615
+6377,42.523415
+6378,43.9329
+6379,42.67505
+6380,50.21261
+6381,46.961452
+6382,48.273888
+6383,61.697685
+6384,62.029564
+6385,66.22219
+6386,63.376038
+6387,67.29784
+6388,66.26406
+6389,63.435223
+6390,66.464714
+6391,65.87912
+6392,65.34135
+6393,69.01631
+6394,23.096924
+6395,22.941292
+6396,23.4005
+6397,28.793701
+6398,27.440952
+6399,28.532578
+6400,32.88548
+6401,33.640198
+6402,36.821766
+6403,36.19767
+6404,37.33624
+6405,37.711647
+6406,35.848064
+6407,37.99315
+6408,38.307716
+6409,37.839325
+6410,37.765747
+6411,38.934727
+6412,38.06169
+6413,39.394203
+6414,39.134884
+6415,40.17926
+6416,43.30374
+6417,20.329773
+6418,26.721523
+6419,27.517227
+6420,40.843826
+6421,24.853407
+6422,30.335144
+6423,30.96796
+6424,29.990068
+6425,32.824505
+6426,33.116524
+6427,39.727875
+6428,41.461258
+6429,43.38781
+6430,45.376686
+6431,47.08373
+6432,48.428123
+6433,72.4418
+6434,74.89615
+6435,74.236916
+6436,78.87453
+6437,11.399383
+6438,17.717737
+6439,22.200148
+6440,25.470646
+6441,23.079178
+6442,33.100586
+6443,35.873173
+6444,30.7134
+6445,32.31334
+6446,34.74516
+6447,39.686096
+6448,38.235226
+6449,39.852634
+6450,42.66987
+6451,42.870384
+6452,44.17984
+6453,39.459095
+6454,45.62267
+6455,52.331215
+6456,54.401943
+6457,13.726839
+6458,22.566769
+6459,23.53458
+6460,23.838913
+6461,24.387316
+6462,26.600307
+6463,30.549656
+6464,36.209553
+6465,38.8205
+6466,42.06938
+6467,42.218643
+6468,19.391901
+6469,29.800056
+6470,32.171127
+6471,37.58112
+6472,15.068211
+6473,18.218805
+6474,21.150465
+6475,24.85986
+6476,46.64916
+6477,47.47308
+6478,53.580853
+6479,54.384777
+6480,56.684185
+6481,59.219734
+6482,26.084522
+6483,29.17215
+6484,37.85205
+6485,43.67623
+6486,45.81611
+6487,33.774548
+6488,36.335007
+6489,37.750862
+6490,45.454117
+6491,49.305958
+6492,50.13119
+6493,54.03137
+6494,54.08748
+6495,54.84723
+6496,56.152855
+6497,56.60209
+6498,60.39739
+6499,37.579704
+6500,39.933064
+6501,43.622704
+6502,45.72108
+6503,51.315395
+6504,50.673763
+6505,54.099346
+6506,54.123554
+6507,57.253735
+6508,56.445305
+6509,20.511335
+6510,26.415709
+6511,28.756886
+6512,31.222525
+6513,3.2397375
+6514,4.9330077
+6515,5.9331484
+6516,6.8410244
+6517,6.7206893
+6518,7.7778854
+6519,9.741283
+6520,10.447903
+6521,47.84832
+6522,48.47516
+6523,48.6204
+6524,52.538662
+6525,25.376883
+6526,31.486872
+6527,32.780613
+6528,33.83787
+6529,38.31991
+6530,41.657352
+6531,45.479763
+6532,47.856964
+6533,50.70318
+6534,51.54796
+6535,52.042763
+6536,56.03
+6537,57.16325
+6538,59.768814
+6539,63.190735
+6540,64.24239
+6541,67.866394
+6542,67.68115
+6543,67.64473
+6544,70.585625
+6545,71.16563
+6546,73.65953
+6547,72.86444
+6548,52.031677
+6549,59.644695
+6550,62.761356
+6551,65.00623
+6552,41.44416
+6553,45.093853
+6554,43.43749
+6555,46.35211
+6556,48.223892
+6557,44.909096
+6558,46.224907
+6559,47.67899
+6560,49.253613
+6561,53.760654
+6562,53.69512
+6563,35.704662
+6564,40.3113
+6565,43.244465
+6566,47.541664
+6567,48.128277
+6568,49.37508
+6569,50.912136
+6570,54.989708
+6571,52.298367
+6572,55.35199
+6573,54.153152
+6574,56.43476
+6575,42.010414
+6576,48.27829
+6577,50.02291
+6578,45.678165
+6579,46.2083
+6580,47.02958
+6581,49.558342
+6582,52.557293
+6583,55.76745
+6584,56.329903
+6585,54.764366
+6586,57.255432
+6587,27.124823
+6588,33.246258
+6589,38.089493
+6590,40.449085
+6591,46.494385
+6592,48.828568
+6593,49.987366
+6594,52.734444
+6595,16.223507
+6596,16.889843
+6597,20.860312
+6598,27.22814
+6599,31.262568
+6600,28.401287
+6601,30.38001
+6602,28.757233
+6603,33.265762
+6604,54.016834
+6605,53.417336
+6606,55.387604
+6607,56.728924
+6608,37.05004
+6609,38.879314
+6610,46.30974
+6611,48.4845
+6612,25.034172
+6613,26.77982
+6614,29.914093
+6615,36.576633
+6616,40.59639
+6617,41.941437
+6618,42.94761
+6619,47.156116
+6620,49.103012
+6621,54.27005
+6622,54.786446
+6623,61.109863
+6624,44.009586
+6625,47.847034
+6626,53.508636
+6627,48.94041
+6628,47.29117
+6629,48.5261
+6630,53.557762
+6631,52.486702
+6632,54.725586
+6633,53.70425
+6634,53.813435
+6635,57.46356
+6636,56.831665
+6637,59.88984
+6638,60.180862
+6639,65.29246
+6640,61.978535
+6641,68.03369
+6642,69.66043
+6643,70.583206
+6644,72.291794
+6645,45.64651
+6646,46.409286
+6647,48.34678
+6648,52.103283
+6649,54.779415
+6650,54.605534
+6651,57.55353
+6652,56.92921
+6653,59.89718
+6654,59.86734
+6655,13.904413
+6656,18.151562
+6657,25.185318
+6658,30.74841
+6659,36.712795
+6660,17.619354
+6661,17.3586
+6662,17.830803
+6663,17.825716
+6664,20.512413
+6665,18.251993
+6666,19.146511
+6667,21.10972
+6668,22.909502
+6669,25.538921
+6670,26.00121
+6671,29.669283
+6672,31.228506
+6673,33.227707
+6674,32.498123
+6675,35.109764
+6676,1.7269104
+6677,4.461016
+6678,5.639722
+6679,8.381756
+6680,32.96753
+6681,32.31248
+6682,32.943115
+6683,36.465775
+6684,29.092634
+6685,32.626965
+6686,33.04316
+6687,35.212536
+6688,31.726091
+6689,35.299232
+6690,37.134037
+6691,40.802654
+6692,41.50541
+6693,41.049595
+6694,44.072334
+6695,46.228
+6696,14.383754
+6697,16.269976
+6698,17.45071
+6699,18.13277
+6700,21.275482
+6701,26.073505
+6702,31.074705
+6703,28.71936
+6704,30.810371
+6705,34.391327
+6706,36.394093
+6707,42.391945
+6708,28.202564
+6709,32.455364
+6710,33.365723
+6711,38.86051
+6712,48.867935
+6713,12.570394
+6714,14.430665
+6715,20.672218
+6716,24.646479
+6717,13.066587
+6718,15.779228
+6719,16.675543
+6720,19.221346
+6721,21.69722
+6722,25.60492
+6723,26.203955
+6724,32.331295
+6725,31.965614
+6726,36.02682
+6727,37.573547
+6728,36.95305
+6729,40.422363
+6730,50.884155
+6731,55.69385
+6732,58.744778
+6733,62.91354
+6734,62.21913
+6735,64.27244
+6736,65.369286
+6737,68.457504
+6738,68.14006
+6739,22.502972
+6740,24.799154
+6741,27.472305
+6742,32.957035
+6743,38.911346
+6744,40.380966
+6745,42.465363
+6746,45.543476
+6747,50.24741
+6748,51.39602
+6749,51.215496
+6750,56.992092
+6751,38.399612
+6752,46.006172
+6753,50.43956
+6754,47.784492
+6755,52.991394
+6756,57.10838
+6757,32.622364
+6758,34.722565
+6759,35.035034
+6760,38.05854
+6761,40.020996
+6762,43.58515
+6763,46.644604
+6764,48.630093
+6765,50.534363
+6766,53.002354
+6767,54.399757
+6768,56.433174
+6769,30.264786
+6770,30.192385
+6771,33.226166
+6772,39.929714
+6773,38.72696
+6774,40.837048
+6775,45.40953
+6776,46.72657
+6777,21.708101
+6778,22.64025
+6779,24.089931
+6780,26.083294
+6781,30.462269
+6782,33.415157
+6783,37.572502
+6784,40.948303
+6785,40.533936
+6786,41.720066
+6787,45.423645
+6788,47.68535
+6789,47.266712
+6790,59.276394
+6791,61.179836
+6792,66.448044
+6793,66.690025
+6794,66.14273
+6795,67.664856
+6796,66.10038
+6797,67.89778
+6798,73.4446
+6799,68.23846
+6800,67.23177
+6801,71.68572
+6802,73.02671
+6803,69.471
+6804,47.18147
+6805,47.444553
+6806,45.925606
+6807,50.476818
+6808,47.178635
+6809,52.383022
+6810,52.68646
+6811,51.33986
+6812,54.606606
+6813,57.953056
+6814,59.44117
+6815,60.172535
+6816,40.28719
+6817,41.274765
+6818,43.60248
+6819,47.082764
+6820,48.974426
+6821,53.25315
+6822,57.31141
+6823,57.323383
+6824,59.8313
+6825,61.55405
+6826,61.917137
+6827,64.79713
+6828,2.3388577
+6829,5.0125847
+6830,2.6443484
+6831,5.1225395
+6832,6.85627
+6833,8.792601
+6834,9.500095
+6835,11.842296
+6836,13.279423
+6837,16.09699
+6838,39.969048
+6839,44.53514
+6840,49.33013
+6841,56.387
+6842,62.69185
+6843,45.117214
+6844,45.56129
+6845,45.086666
+6846,50.578465
+6847,64.428215
+6848,67.74234
+6849,67.66376
+6850,69.35838
+6851,68.506065
+6852,72.62176
+6853,70.75421
+6854,74.53465
+6855,74.36813
+6856,78.15853
+6857,9.441797
+6858,11.1484585
+6859,14.077257
+6860,12.565402
+6861,17.277765
+6862,18.041212
+6863,19.441124
+6864,21.070843
+6865,28.755253
+6866,31.313763
+6867,30.522963
+6868,30.73543
+6869,8.95275
+6870,11.729031
+6871,13.829159
+6872,17.443441
+6873,16.1515
+6874,15.03358
+6875,22.116627
+6876,24.537466
+6877,27.04895
+6878,28.519295
+6879,29.299948
+6880,0.6250344
+6881,1.4303983
+6882,2.2486663
+6883,3.4389546
+6884,14.559273
+6885,18.034266
+6886,21.833782
+6887,25.449867
+6888,30.437492
+6889,32.519096
+6890,31.594414
+6891,35.819115
+6892,33.59395
+6893,37.08711
+6894,36.25397
+6895,37.034622
+6896,40.462402
+6897,43.281715
+6898,44.600677
+6899,44.87147
+6900,48.376896
+6901,51.449787
+6902,53.743835
+6903,54.42241
+6904,1.3884809
+6905,5.3952045
+6906,9.092508
+6907,13.245911
+6908,17.86825
+6909,15.602734
+6910,17.339943
+6911,22.477188
+6912,24.664524
+6913,28.224524
+6914,31.467104
+6915,35.810413
+6916,38.864693
+6917,43.75325
+6918,44.790436
+6919,47.572765
+6920,59.26229
+6921,37.044197
+6922,46.544
+6923,51.158566
+6924,52.797657
+6925,53.918015
+6926,19.229471
+6927,21.896818
+6928,34.8632
+6929,36.85041
+6930,36.576733
+6931,40.999115
+6932,34.17595
+6933,47.504215
+6934,47.21837
+6935,48.16941
+6936,27.63821
+6937,29.836538
+6938,35.91585
+6939,44.940742
+6940,45.489178
+6941,21.790276
+6942,24.696352
+6943,28.525692
+6944,30.419464
+6945,34.37278
+6946,39.490215
+6947,44.58236
+6948,46.514557
+6949,51.304077
+6950,52.096832
+6951,51.81595
+6952,56.970055
+6953,38.191013
+6954,41.692368
+6955,48.830643
+6956,53.924408
+6957,54.33661
+6958,6.736468
+6959,6.548357
+6960,8.240675
+6961,8.544018
+6962,20.594345
+6963,35.12945
+6964,37.604
+6965,34.10817
+6966,37.33398
+6967,38.307823
+6968,40.261932
+6969,40.183662
+6970,45.77072
+6971,46.107067
+6972,27.131662
+6973,28.308115
+6974,29.46925
+6975,30.29811
+6976,30.33769
+6977,32.693707
+6978,35.089355
+6979,36.36138
+6980,14.328409
+6981,16.293919
+6982,19.611406
+6983,21.716053
+6984,20.643864
+6985,25.003471
+6986,30.286255
+6987,44.23411
+6988,43.49768
+6989,50.743652
+6990,48.805687
+6991,51.94666
+6992,53.90973
+6993,55.954075
+6994,57.040108
+6995,1.0117602
+6996,1.4072626
+6997,3.5180335
+6998,4.1782055
+6999,9.97022
+7000,11.441524
+7001,19.51411
+7002,24.993557
+7003,31.881638
+7004,38.84368
+7005,47.817036
+7006,48.174114
+7007,53.057648
+7008,57.053944
+7009,36.670723
+7010,38.937553
+7011,41.252357
+7012,40.88848
+7013,43.003887
+7014,47.773773
+7015,49.954006
+7016,50.281845
+7017,51.285934
+7018,53.707294
+7019,52.604355
+7020,50.39496
+7021,27.401596
+7022,32.221653
+7023,37.20125
+7024,44.36541
+7025,3.2870336
+7026,3.6690085
+7027,7.6466274
+7028,7.719224
+7029,9.6143875
+7030,8.235145
+7031,10.464019
+7032,15.011633
+7033,20.7587
+7034,20.441614
+7035,22.876812
+7036,28.694914
+7037,13.215651
+7038,13.267603
+7039,17.607819
+7040,17.440128
+7041,21.185364
+7042,25.201439
+7043,31.033302
+7044,31.339941
+7045,38.650906
+7046,36.708427
+7047,40.93136
+7048,47.631287
+7049,20.036049
+7050,24.091879
+7051,31.318974
+7052,36.601345
+7053,41.272923
+7054,15.751903
+7055,19.861532
+7056,23.691109
+7057,26.773506
+7058,47.797455
+7059,50.175735
+7060,54.0804
+7061,59.009094
+7062,60.99121
+7063,61.837475
+7064,64.257744
+7065,65.07388
+7066,66.12702
+7067,66.3447
+7068,68.33293
+7069,68.3644
+7070,9.953443
+7071,14.294951
+7072,16.02362
+7073,18.727757
+7074,38.97401
+7075,42.508316
+7076,44.57964
+7077,46.94789
+7078,50.628044
+7079,56.352222
+7080,55.598648
+7081,60.528164
+7082,62.24283
+7083,60.901752
+7084,63.030827
+7085,21.025343
+7086,23.69188
+7087,25.821938
+7088,28.437275
+7089,10.684455
+7090,12.248835
+7091,14.564299
+7092,16.519688
+7093,16.741302
+7094,19.47854
+7095,21.03143
+7096,24.786182
+7097,25.787943
+7098,29.562115
+7099,31.714207
+7100,40.243122
+7101,42.91536
+7102,48.414433
+7103,49.600677
+7104,54.50978
+7105,40.815914
+7106,39.613297
+7107,42.01577
+7108,47.161987
+7109,55.99877
+7110,54.251907
+7111,57.352467
+7112,57.619045
+7113,61.72744
+7114,62.336437
+7115,60.967167
+7116,65.348656
+7117,8.803875
+7118,13.117273
+7119,15.458277
+7120,23.52316
+7121,27.692284
+7122,29.904905
+7123,30.66503
+7124,31.550661
+7125,33.918556
+7126,34.678997
+7127,38.40106
+7128,41.25844
+7129,41.31446
+7130,46.563778
+7131,44.209694
+7132,44.384064
+7133,61.09526
+7134,65.404495
+7135,67.701416
+7136,67.962135
+7137,69.71969
+7138,71.091835
+7139,71.13986
+7140,72.34719
+7141,75.86685
+7142,75.31167
+7143,75.77723
+7144,77.18161
+7145,34.176895
+7146,35.66534
+7147,37.77467
+7148,40.79753
+7149,42.309097
+7150,1.0020007
+7151,5.03651
+7152,8.218029
+7153,11.145715
+7154,14.203501
+7155,18.32283
+7156,18.849667
+7157,21.51437
+7158,24.17295
+7159,26.567806
+7160,28.085732
+7161,28.462473
+7162,34.71366
+7163,36.18347
+7164,39.70912
+7165,42.32663
+7166,46.09629
+7167,46.703552
+7168,50.64852
+7169,50.218147
+7170,54.5915
+7171,55.499634
+7172,58.056168
+7173,59.079597
+7174,25.991587
+7175,27.608276
+7176,26.425512
+7177,35.519005
+7178,1.4297953
+7179,2.7038393
+7180,3.3047278
+7181,4.29033
+7182,4.728722
+7183,15.016489
+7184,18.9329
+7185,17.351646
+7186,21.427462
+7187,22.911686
+7188,26.898422
+7189,20.28092
+7190,21.406672
+7191,23.24085
+7192,28.111286
+7193,28.8274
+7194,29.423943
+7195,27.565777
+7196,34.28682
+7197,34.149582
+7198,38.867043
+7199,38.570286
+7200,45.177578
+7201,9.557486
+7202,11.694818
+7203,10.109024
+7204,15.461809
+7205,17.761427
+7206,18.148342
+7207,20.189463
+7208,25.61728
+7209,29.136684
+7210,29.281548
+7211,26.808449
+7212,29.19677
+7213,28.876396
+7214,35.739265
+7215,33.552624
+7216,35.976826
+7217,39.96626
+7218,42.95807
+7219,43.908028
+7220,48.82621
+7221,52.64126
+7222,52.030403
+7223,11.468082
+7224,14.218216
+7225,17.900751
+7226,26.345654
+7227,51.608864
+7228,54.03009
+7229,56.854507
+7230,63.28323
+7231,14.123333
+7232,17.68816
+7233,20.116022
+7234,24.686354
+7235,34.225033
+7236,38.663853
+7237,41.45584
+7238,50.25318
+7239,57.176258
+7240,15.445255
+7241,16.964365
+7242,24.746332
+7243,26.151363
+7244,49.83721
+7245,54.309395
+7246,55.53194
+7247,56.572784
+7248,8.714227
+7249,11.068967
+7250,11.764742
+7251,12.719002
+7252,14.682522
+7253,16.762068
+7254,20.849554
+7255,24.29308
+7256,26.405933
+7257,28.117037
+7258,32.781475
+7259,32.470844
+7260,23.138773
+7261,24.963646
+7262,27.723614
+7263,30.083471
+7264,34.928715
+7265,41.12822
+7266,42.010014
+7267,45.898315
+7268,45.258217
+7269,46.496544
+7270,49.186577
+7271,52.896275
+7272,15.377848
+7273,16.242992
+7274,18.812305
+7275,20.418373
+7276,22.809048
+7277,32.60754
+7278,37.33025
+7279,39.07133
+7280,40.618446
+7281,38.967014
+7282,46.41944
+7283,49.60949
+7284,30.20294
+7285,52.39282
+7286,58.590626
+7287,58.57406
+7288,66.26196
+7289,21.582022
+7290,22.927929
+7291,22.712772
+7292,26.3978
+7293,32.36569
+7294,35.52702
+7295,37.300938
+7296,39.429646
+7297,41.69708
+7298,43.3236
+7299,46.9717
+7300,47.395626
+7301,7.313244
+7302,9.198421
+7303,9.854588
+7304,10.535715
+7305,55.969627
+7306,57.238876
+7307,57.83684
+7308,63.706062
+7309,64.56372
+7310,66.70561
+7311,67.00528
+7312,67.85923
+7313,65.754395
+7314,67.56586
+7315,70.63397
+7316,73.41608
+7317,7.490701
+7318,8.660373
+7319,15.104985
+7320,17.612646
+7321,24.860764
+7322,26.76804
+7323,31.869865
+7324,32.61142
+7325,32.246338
+7326,39.157364
+7327,42.24786
+7328,48.104992
+7329,49.852364
+7330,53.083874
+7331,50.434917
+7332,52.20559
+7333,55.943134
+7334,60.592735
+7335,60.744835
+7336,62.035156
+7337,63.081036
+7338,64.18525
+7339,65.07931
+7340,40.4696
+7341,45.147835
+7342,47.36315
+7343,52.135323
+7344,52.987953
+7345,52.06405
+7346,57.683372
+7347,57.969437
+7348,62.845383
+7349,60.595795
+7350,62.020313
+7351,64.13211
+7352,25.408167
+7353,30.604553
+7354,30.065323
+7355,40.119717
+7356,42.49961
+7357,42.87594
+7358,46.41049
+7359,46.76694
+7360,49.237656
+7361,55.950058
+7362,53.5113
+7363,53.944565
+7364,22.122995
+7365,27.514595
+7366,29.664858
+7367,29.02584
+7368,30.439852
+7369,33.390175
+7370,36.33214
+7371,39.506332
+7372,46.653496
+7373,52.26673
+7374,48.524086
+7375,51.948963
+7376,19.700912
+7377,19.500921
+7378,21.252413
+7379,24.797255
+7380,31.602129
+7381,28.592457
+7382,35.91578
+7383,38.554264
+7384,39.703148
+7385,49.60761
+7386,52.333668
+7387,49.555435
+7388,22.64973
+7389,27.269083
+7390,32.205776
+7391,36.048935
+7392,44.338455
+7393,40.073776
+7394,45.12601
+7395,49.731056
+7396,53.013893
+7397,51.844673
+7398,51.937107
+7399,54.452686
+7400,6.9314485
+7401,8.580475
+7402,15.101351
+7403,18.193165
+7404,22.652946
+7405,20.12426
+7406,23.547869
+7407,27.64571
+7408,34.080643
+7409,38.744003
+7410,32.74319
+7411,40.501606
+7412,46.466824
+7413,48.697994
+7414,4.497946
+7415,5.241663
+7416,10.235189
+7417,11.954222
+7418,15.002722
+7419,16.167332
+7420,18.76264
+7421,21.064396
+7422,25.39239
+7423,26.558651
+7424,40.518517
+7425,44.31553
+7426,48.691765
+7427,51.3621
+7428,55.854538
+7429,53.453087
+7430,54.169483
+7431,56.55411
+7432,53.23048
+7433,57.8652
+7434,58.500835
+7435,59.211952
+7436,61.80015
+7437,60.568813
+7438,35.527195
+7439,37.21207
+7440,36.216026
+7441,40.058266
+7442,42.02337
+7443,42.85188
+7444,47.11429
+7445,47.731762
+7446,50.143486
+7447,50.429104
+7448,54.199623
+7449,56.806885
+7450,14.6152115
+7451,16.589226
+7452,19.769567
+7453,32.22678
+7454,37.059227
+7455,35.751156
+7456,39.71578
+7457,41.793285
+7458,40.08655
+7459,42.453682
+7460,48.008648
+7461,49.4177
+7462,27.429914
+7463,29.806322
+7464,31.589384
+7465,44.21317
+7466,44.095127
+7467,42.207756
+7468,45.33077
+7469,49.37564
+7470,52.03119
+7471,54.83186
+7472,56.324493
+7473,56.466633
+7474,20.742027
+7475,25.539022
+7476,31.885456
+7477,36.332603
+7478,27.114944
+7479,34.638405
+7480,35.92621
+7481,36.409363
+7482,40.62157
+7483,34.965195
+7484,41.20549
+7485,43.997334
+7486,46.993023
+7487,51.95878
+7488,53.320984
+7489,54.703983
+7490,57.325356
+7491,60.183235
+7492,60.496506
+7493,62.122364
+7494,64.32272
+7495,22.96389
+7496,31.039043
+7497,31.341988
+7498,33.644413
+7499,43.320904
+7500,47.473507
+7501,47.138565
+7502,46.526558
+7503,52.826523
+7504,53.509277
+7505,52.289303
+7506,54.766197
+7507,21.0318
+7508,22.72649
+7509,22.51176
+7510,25.211248
+7511,32.084633
+7512,36.416878
+7513,35.568947
+7514,38.139984
+7515,39.77986
+7516,11.659324
+7517,12.270572
+7518,15.4848175
+7519,18.693188
+7520,17.71484
+7521,20.095755
+7522,25.917578
+7523,27.443588
+7524,28.440012
+7525,32.86072
+7526,23.80333
+7527,28.197617
+7528,28.3538
+7529,31.325798
+7530,39.38969
+7531,42.750725
+7532,47.776848
+7533,48.015278
+7534,51.070385
+7535,50.378963
+7536,51.26814
+7537,52.343697
+7538,55.551094
+7539,9.994704
+7540,11.425632
+7541,19.648329
+7542,23.324604
+7543,49.319607
+7544,51.268715
+7545,55.07572
+7546,58.553753
+7547,60.57168
+7548,61.530556
+7549,64.12098
+7550,65.17095
+7551,65.82486
+7552,68.21621
+7553,68.44328
+7554,69.17405
+7555,2.278562
+7556,4.6945634
+7557,6.171061
+7558,12.126435
+7559,30.998812
+7560,37.579357
+7561,41.225986
+7562,46.703247
+7563,18.89469
+7564,21.117949
+7565,31.407736
+7566,35.1037
+7567,38.477524
+7568,34.859367
+7569,36.312157
+7570,42.99749
+7571,43.890503
+7572,44.958244
+7573,48.818726
+7574,50.870274
+7575,28.017195
+7576,30.584312
+7577,30.754192
+7578,33.251137
+7579,38.447758
+7580,36.746834
+7581,41.19093
+7582,46.562737
+7583,41.76709
+7584,48.132698
+7585,54.191654
+7586,54.789482
+7587,13.767481
+7588,14.858904
+7589,21.140392
+7590,25.561384
+7591,23.389462
+7592,26.10191
+7593,27.565125
+7594,29.040224
+7595,30.949802
+7596,34.51779
+7597,39.292114
+7598,39.32498
+7599,28.434744
+7600,28.380972
+7601,29.901234
+7602,31.792507
+7603,30.457983
+7604,32.067238
+7605,32.782223
+7606,36.732048
+7607,43.170708
+7608,25.695303
+7609,26.59496
+7610,31.464403
+7611,36.55507
+7612,53.61211
+7613,53.614994
+7614,57.4343
+7615,60.170586
+7616,62.85782
+7617,64.599495
+7618,65.162094
+7619,65.76424
+7620,70.08805
+7621,73.20431
+7622,18.853758
+7623,21.998878
+7624,23.105139
+7625,29.097225
+7626,32.937237
+7627,3.1397438
+7628,3.5957656
+7629,4.1077056
+7630,21.592691
+7631,0.37995845
+7632,1.1342952
+7633,3.1263545
+7634,6.098612
+7635,35.681313
+7636,45.523766
+7637,56.395805
+7638,50.02167
+7639,46.878067
+7640,50.424004
+7641,56.745594
+7642,61.16928
+7643,63.13997
+7644,67.14682
+7645,24.18936
+7646,27.45109
+7647,25.740429
+7648,31.948864
+7649,30.459509
+7650,31.975784
+7651,35.293816
+7652,38.08049
+7653,40.654404
+7654,44.78933
+7655,30.125141
+7656,33.117058
+7657,35.257736
+7658,41.171047
+7659,44.895523
+7660,50.380016
+7661,53.95435
+7662,53.19651
+7663,54.55555
+7664,59.26339
+7665,59.68238
+7666,18.123114
+7667,21.353931
+7668,24.97192
+7669,33.99031
+7670,38.709217
+7671,28.117634
+7672,27.245672
+7673,29.68395
+7674,29.24987
+7675,30.951921
+7676,32.258617
+7677,30.634254
+7678,31.143179
+7679,33.465813
+7680,33.683853
+7681,34.65334
+7682,38.654613
+7683,39.489956
+7684,42.007557
+7685,44.68751
+7686,45.571495
+7687,47.155045
+7688,49.220062
+7689,17.889986
+7690,20.077862
+7691,24.026943
+7692,27.737114
+7693,30.858196
+7694,30.687551
+7695,38.52688
+7696,41.182777
+7697,37.551517
+7698,43.020752
+7699,44.237503
+7700,48.766323
+7701,18.249512
+7702,19.758425
+7703,21.112762
+7704,23.48189
+7705,26.35112
+7706,23.22539
+7707,28.553835
+7708,31.111347
+7709,31.54813
+7710,36.0814
+7711,40.824413
+7712,44.818398
+7713,34.12992
+7714,40.032307
+7715,43.029278
+7716,39.932213
+7717,46.506508
+7718,49.556637
+7719,54.60927
+7720,57.632072
+7721,60.01711
+7722,62.21786
+7723,61.791462
+7724,65.143776
+7725,67.3398
+7726,66.06758
+7727,66.807144
+7728,68.41221
+7729,66.52417
+7730,10.784563
+7731,14.907487
+7732,16.278725
+7733,14.967088
+7734,17.12804
+7735,18.368687
+7736,24.18398
+7737,28.120707
+7738,30.799633
+7739,28.348757
+7740,31.286186
+7741,35.19552
+7742,18.815802
+7743,19.51973
+7744,19.9282
+7745,22.824913
+7746,27.0012
+7747,28.64719
+7748,25.428238
+7749,31.54271
+7750,33.56299
+7751,33.781902
+7752,40.0069
+7753,40.99716
+7754,29.890085
+7755,38.868614
+7756,44.098568
+7757,46.147987
+7758,32.240414
+7759,31.67748
+7760,33.263863
+7761,32.574066
+7762,35.40771
+7763,36.322525
+7764,43.380688
+7765,46.459297
+7766,51.659836
+7767,54.269104
+7768,55.93705
+7769,59.335686
+7770,61.171257
+7771,63.6391
+7772,63.159508
+7773,63.222645
+7774,65.8788
+7775,67.24962
+7776,24.473837
+7777,26.28096
+7778,28.334759
+7779,30.346207
+7780,36.14917
+7781,37.573853
+7782,41.962696
+7783,45.085938
+7784,29.221613
+7785,28.164469
+7786,30.790077
+7787,30.071447
+7788,35.035156
+7789,37.451813
+7790,39.28362
+7791,12.423501
+7792,14.328366
+7793,15.244518
+7794,14.930445
+7795,16.373129
+7796,33.58331
+7797,34.436127
+7798,34.641052
+7799,36.209965
+7800,29.188309
+7801,34.8362
+7802,38.41545
+7803,37.514774
+7804,43.496796
+7805,44.71394
+7806,48.29651
+7807,38.196644
+7808,40.625793
+7809,41.73449
+7810,44.651573
+7811,45.69608
+7812,54.470978
+7813,53.045364
+7814,33.0549
+7815,35.801292
+7816,36.06926
+7817,35.94478
+7818,16.449192
+7819,26.191204
+7820,28.733437
+7821,28.528152
+7822,21.533447
+7823,24.463263
+7824,26.977901
+7825,28.346584
+7826,32.59919
+7827,34.717796
+7828,38.12198
+7829,43.939117
+7830,46.021385
+7831,45.577957
+7832,49.580345
+7833,51.589504
+7834,-0.087009564
+7835,-0.7617169
+7836,0.33174592
+7837,1.094024
+7838,2.8410378
+7839,7.0530524
+7840,9.819706
+7841,14.003002
+7842,17.266335
+7843,20.664013
+7844,16.527346
+7845,22.826971
+7846,25.013884
+7847,25.679949
+7848,28.45811
+7849,29.19337
+7850,29.578133
+7851,33.57579
+7852,36.21132
+7853,11.68396
+7854,13.4865265
+7855,14.4968605
+7856,21.309572
+7857,39.430065
+7858,45.26178
+7859,54.11741
+7860,59.985428
+7861,60.688404
+7862,61.797764
+7863,25.964832
+7864,31.743675
+7865,35.95626
+7866,35.907715
+7867,25.456154
+7868,26.714708
+7869,27.059483
+7870,30.038815
+7871,31.12269
+7872,35.0178
+7873,36.388405
+7874,38.83574
+7875,44.908546
+7876,47.68289
+7877,51.95613
+7878,53.862583
+7879,25.166842
+7880,27.014927
+7881,30.963144
+7882,32.761536
+7883,37.243973
+7884,39.14364
+7885,42.974884
+7886,43.972282
+7887,46.326622
+7888,46.45306
+7889,49.107227
+7890,50.764706
+7891,40.41139
+7892,39.534378
+7893,46.111763
+7894,44.651882
+7895,9.649988
+7896,13.04393
+7897,14.087416
+7898,15.952185
+7899,18.93901
+7900,23.32103
+7901,22.51694
+7902,26.108057
+7903,28.61465
+7904,33.51398
+7905,39.543377
+7906,40.269955
+7907,8.915722
+7908,12.548197
+7909,14.093714
+7910,17.189037
+7911,19.935192
+7912,25.444141
+7913,21.26736
+7914,23.412926
+7915,4.6742735
+7916,5.0861907
+7917,6.3200088
+7918,10.216053
+7919,14.743665
+7920,12.773156
+7921,15.584263
+7922,23.917185
+7923,28.563328
+7924,34.38251
+7925,38.878113
+7926,30.736427
+7927,34.488213
+7928,38.814987
+7929,41.979416
+7930,44.04464
+7931,47.77833
+7932,52.209545
+7933,27.726118
+7934,27.116291
+7935,30.177158
+7936,31.053574
+7937,38.212185
+7938,21.2333
+7939,27.943512
+7940,28.930216
+7941,31.530981
+7942,33.85808
+7943,35.146652
+7944,38.084198
+7945,42.368176
+7946,26.895744
+7947,30.69205
+7948,37.473026
+7949,41.006496
+7950,45.82763
+7951,12.361071
+7952,15.3725195
+7953,15.8803
+7954,18.178959
+7955,22.113285
+7956,25.417234
+7957,27.189718
+7958,27.055439
+7959,31.28581
+7960,24.921883
+7961,27.372765
+7962,27.259848
+7963,39.11068
+7964,27.585878
+7965,31.339392
+7966,33.370777
+7967,37.974854
+7968,17.68975
+7969,20.028309
+7970,25.599695
+7971,29.445126
+7972,29.588749
+7973,33.47242
+7974,38.27778
+7975,41.426613
+7976,41.671745
+7977,45.035294
+7978,48.802723
+7979,53.5499
+7980,18.449818
+7981,24.808054
+7982,27.73606
+7983,27.003994
+7984,28.467121
+7985,30.597
+7986,35.76564
+7987,39.88989
+7988,39.098896
+7989,40.414497
+7990,43.16346
+7991,47.869324
+7992,11.071897
+7993,10.029224
+7994,14.710212
+7995,20.833637
+7996,25.523544
+7997,24.08182
+7998,33.917397
+7999,35.910255
+8000,35.444893
+8001,37.262356
+8002,37.050804
+8003,34.383617
+8004,37.5759
+8005,40.159016
+8006,51.657116
+8007,7.5168753
+8008,7.237563
+8009,9.863876
+8010,11.899865
+8011,14.011915
+8012,17.263836
+8013,19.103207
+8014,19.189913
+8015,29.239998
+8016,30.399862
+8017,30.810274
+8018,34.786312
+8019,23.580477
+8020,27.902534
+8021,31.986916
+8022,36.985817
+8023,44.17527
+8024,47.012928
+8025,46.108215
+8026,47.775505
+8027,52.70758
+8028,32.80986
+8029,33.115658
+8030,38.00361
+8031,39.084663
+8032,47.146587
+8033,51.64767
+8034,51.713276
+8035,54.4254
+8036,57.01129
+8037,31.045982
+8038,33.293884
+8039,34.466675
+8040,40.87229
+8041,43.953125
+8042,47.02952
+8043,52.833206
+8044,56.081093
+8045,56.084415
+8046,58.07714
+8047,62.567734
+8048,26.239918
+8049,27.523499
+8050,29.812595
+8051,32.878082
+8052,36.378708
+8053,36.672752
+8054,39.33168
+8055,44.94935
+8056,46.164803
+8057,45.91475
+8058,49.17944
+8059,53.635284
+8060,33.450047
+8061,33.083214
+8062,39.35472
+8063,46.3637
+8064,49.89547
+8065,50.141502
+8066,53.271038
+8067,54.862194
+8068,48.796127
+8069,51.14953
+8070,52.025463
+8071,57.174072
+8072,58.444954
+8073,61.0772
+8074,62.951176
+8075,65.42255
+8076,64.422585
+8077,67.12875
+8078,68.35977
+8079,67.34746
+8080,26.79421
+8081,28.031067
+8082,29.153988
+8083,32.257336
+8084,37.074368
+8085,39.466187
+8086,39.964386
+8087,43.064415
+8088,42.499
+8089,43.212498
+8090,45.35434
+8091,44.743687
+8092,52.192154
+8093,54.11508
+8094,60.211704
+8095,66.80479
+8096,68.93133
+8097,23.40985
+8098,25.396929
+8099,25.615122
+8100,30.463573
+8101,52.21212
+8102,55.563507
+8103,56.12017
+8104,58.8728
+8105,60.01018
+8106,60.682976
+8107,62.569927
+8108,63.590324
+8109,64.88962
+8110,65.83746
+8111,69.21627
+8112,67.59926
+8113,18.254978
+8114,20.38255
+8115,22.823763
+8116,26.936237
+8117,28.528177
+8118,32.26663
+8119,36.35014
+8120,37.96599
+8121,40.73987
+8122,43.758186
+8123,48.504997
+8124,51.3459
+8125,67.43791
+8126,67.0071
+8127,67.221054
+8128,73.78265
+8129,73.1531
+8130,74.13046
+8131,73.42612
+8132,76.46639
+8133,78.78349
+8134,78.479355
+8135,78.11941
+8136,19.776508
+8137,20.08186
+8138,24.726742
+8139,27.238056
+8140,25.67235
+8141,28.240686
+8142,27.57467
+8143,30.686977
+8144,18.184729
+8145,18.24135
+8146,22.013601
+8147,29.026169
+8148,1.9695652
+8149,4.6167717
+8150,5.5496874
+8151,10.478331
+8152,39.30472
+8153,40.705875
+8154,43.07656
+8155,47.094303
+8156,7.3904414
+8157,9.765535
+8158,12.57299
+8159,21.463371
+8160,27.543167
+8161,28.505716
+8162,32.893963
+8163,37.656536
+8164,4.5456505
+8165,5.2382655
+8166,6.977956
+8167,9.064703
+8168,14.186008
+8169,20.088783
+8170,21.93027
+8171,38.079178
+8172,24.8625
+8173,23.99044
+8174,25.956291
+8175,27.608437
+8176,2.1344032
+8177,4.0447264
+8178,9.258602
+8179,10.261019
+8180,16.401524
+8181,49.1632
+8182,47.52168
+8183,51.110588
+8184,53.1571
+8185,22.132847
+8186,30.681429
+8187,35.65417
+8188,37.79438
+8189,40.395138
+8190,33.97542
+8191,36.713585
+8192,38.280876
+8193,38.804672
+8194,42.690704
+8195,43.439667
+8196,45.648613
+8197,20.352177
+8198,24.094078
+8199,30.157795
+8200,34.006626
+8201,23.914429
+8202,28.400616
+8203,29.4426
+8204,28.286205
+8205,34.86183
+8206,35.261234
+8207,36.512867
+8208,37.294117
+8209,40.890137
+8210,42.55382
+8211,46.582485
+8212,47.001633
+8213,20.03127
+8214,22.186436
+8215,22.280819
+8216,25.62222
+8217,29.391594
+8218,34.46104
+8219,35.289112
+8220,44.98668
+8221,46.189735
+8222,58.662086
+8223,16.236433
+8224,19.57823
+8225,22.023537
+8226,21.597805
+8227,23.52865
+8228,31.15563
+8229,32.787415
+8230,34.47384
+8231,38.22429
+8232,43.388012
+8233,41.351406
+8234,46.55323
+8235,9.508655
+8236,13.4049015
+8237,14.717784
+8238,14.403756
+8239,17.52631
+8240,18.614754
+8241,11.999956
+8242,15.8636675
+8243,16.159882
+8244,17.936794
+8245,20.71364
+8246,22.866968
+8247,26.585423
+8248,32.616753
+8249,33.28926
+8250,39.74109
+8251,46.994095
+8252,40.126957
+8253,43.339516
+8254,45.243427
+8255,44.246197
+8256,50.924652
+8257,50.212433
+8258,24.89424
+8259,27.037487
+8260,34.62803
+8261,38.268078
+8262,39.08364
+8263,42.67631
+8264,41.445515
+8265,43.780304
+8266,46.856194
+8267,46.97878
+8268,50.58806
+8269,53.068516
+8270,19.496363
+8271,21.575314
+8272,22.16273
+8273,27.067844
+8274,30.112368
+8275,33.84403
+8276,36.152847
+8277,37.888382
+8278,38.990597
+8279,39.868076
+8280,40.419083
+8281,20.488026
+8282,24.396252
+8283,27.245775
+8284,30.749674
+8285,32.8389
+8286,32.857697
+8287,39.810844
+8288,42.626297
+8289,39.776794
+8290,42.646637
+8291,47.011425
+8292,47.698067
+8293,11.546282
+8294,12.402383
+8295,12.949042
+8296,13.857242
+8297,16.974966
+8298,20.467686
+8299,24.185282
+8300,27.54211
+8301,29.235806
+8302,31.854862
+8303,37.689583
+8304,39.217224
+8305,42.66339
+8306,47.858063
+8307,49.23489
+8308,48.616276
+8309,13.244101
+8310,14.67155
+8311,18.732998
+8312,19.052387
+8313,27.410103
+8314,28.147678
+8315,29.80682
+8316,32.142574
+8317,41.000538
+8318,46.169422
+8319,54.946503
+8320,56.720608
+8321,61.97707
+8322,62.461197
+8323,62.552418
+8324,63.572624
+8325,67.47784
+8326,65.4266
+8327,70.14482
+8328,69.39393
+8329,70.01533
+8330,49.864716
+8331,54.611465
+8332,53.036324
+8333,53.576366
+8334,55.179924
+8335,53.77855
+8336,53.81196
+8337,58.224335
+8338,60.465996
+8339,56.978912
+8340,61.33563
+8341,62.3897
+8342,29.203552
+8343,34.785088
+8344,38.561165
+8345,37.981068
+8346,46.140903
+8347,45.83712
+8348,53.306
+8349,54.803505
+8350,55.502575
+8351,56.79513
+8352,16.03643
+8353,19.193752
+8354,26.25332
+8355,32.944157
+8356,33.936802
+8357,35.98191
+8358,38.201668
+8359,44.47045
+8360,13.749939
+8361,14.047873
+8362,21.175123
+8363,23.873322
+8364,13.98683
+8365,16.397533
+8366,22.249798
+8367,25.955322
+8368,12.470697
+8369,16.489265
+8370,19.55461
+8371,19.51879
+8372,24.997562
+8373,27.584696
+8374,40.760597
+8375,40.234238
+8376,36.41202
+8377,40.495735
+8378,3.580624
+8379,4.963828
+8380,5.99328
+8381,8.656826
+8382,11.04808
+8383,12.759745
+8384,14.537078
+8385,34.627525
+8386,33.665634
+8387,39.969437
+8388,43.153053
+8389,48.31153
+8390,50.588352
+8391,52.60695
+8392,57.392563
+8393,60.4032
+8394,60.780296
+8395,62.53766
+8396,62.01625
+8397,13.4740305
+8398,14.840089
+8399,20.69987
+8400,21.62651
+8401,22.5693
+8402,26.481825
+8403,27.99733
+8404,29.371983
+8405,31.832987
+8406,35.23372
+8407,39.061615
+8408,39.8633
+8409,38.571247
+8410,40.805416
+8411,39.897015
+8412,30.8121
+8413,33.766068
+8414,45.93883
+8415,53.596127
+8416,18.266783
+8417,19.464514
+8418,20.419922
+8419,22.175617
+8420,20.798931
+8421,23.321793
+8422,24.575329
+8423,26.5285
+8424,28.432755
+8425,27.439556
+8426,26.913876
+8427,28.066717
+8428,31.421455
+8429,30.866875
+8430,35.47564
+8431,35.21675
+8432,37.38501
+8433,39.132706
+8434,41.056084
+8435,44.13459
+8436,47.639626
+8437,25.106373
+8438,28.677818
+8439,30.892078
+8440,32.437477
+8441,39.025814
+8442,41.073586
+8443,31.15957
+8444,38.085033
+8445,41.148438
+8446,51.3207
+8447,52.595642
+8448,48.765175
+8449,52.421974
+8450,53.68418
+8451,57.588154
+8452,61.25832
+8453,6.512759
+8454,7.0660524
+8455,7.943876
+8456,8.513039
+8457,11.159259
+8458,14.01836
+8459,17.235672
+8460,17.517677
+8461,19.63799
+8462,25.755806
+8463,30.147318
+8464,31.989035
+8465,12.230503
+8466,19.652004
+8467,20.94252
+8468,20.708416
+8469,24.313
+8470,27.580904
+8471,30.361238
+8472,34.4996
+8473,39.2556
+8474,42.573975
+8475,45.062294
+8476,46.688114
+8477,39.821632
+8478,41.835785
+8479,45.02304
+8480,48.47539
+8481,51.97676
+8482,51.897984
+8483,52.772026
+8484,57.364708
+8485,57.222393
+8486,57.241474
+8487,57.837475
+8488,61.422432
+8489,72.75981
+8490,73.59892
+8491,72.117035
+8492,72.1498
+8493,74.42798
+8494,71.46957
+8495,75.76174
+8496,77.188515
+8497,76.114136
+8498,77.18525
+8499,24.213896
+8500,26.89202
+8501,28.873413
+8502,30.595371
+8503,36.82051
+8504,42.337208
+8505,45.040066
+8506,52.933918
+8507,54.031162
+8508,55.090492
+8509,56.622902
+8510,53.78905
+8511,57.884758
+8512,55.231155
+8513,58.752575
+8514,62.490395
+8515,60.33603
+8516,61.226273
+8517,61.11398
+8518,21.398323
+8519,23.775198
+8520,23.746773
+8521,29.885265
+8522,33.89796
+8523,36.32847
+8524,40.023445
+8525,44.77203
+8526,45.661972
+8527,48.168633
+8528,48.492306
+8529,52.2239
+8530,19.080492
+8531,20.082714
+8532,21.234827
+8533,21.915606
+8534,55.608486
+8535,55.813248
+8536,60.942177
+8537,61.348755
+8538,50.26579
+8539,53.62494
+8540,55.687508
+8541,57.193066
+8542,55.161118
+8543,56.78955
+8544,58.071594
+8545,59.88763
+8546,59.785725
+8547,66.76142
+8548,49.9285
+8549,54.148857
+8550,58.515446
+8551,58.710545
+8552,60.78683
+8553,64.47211
+8554,64.260315
+8555,65.28784
+8556,68.81601
+8557,68.58144
+8558,71.727516
+8559,73.09835
+8560,34.64628
+8561,37.600746
+8562,43.079826
+8563,48.655666
+8564,51.045982
+8565,54.31644
+8566,51.933533
+8567,57.83489
+8568,60.363434
+8569,59.268635
+8570,60.109886
+8571,62.234367
+8572,40.69631
+8573,46.25042
+8574,47.42219
+8575,45.69729
+8576,47.626892
+8577,49.611137
+8578,51.181858
+8579,56.996445
+8580,55.2726
+8581,55.992558
+8582,57.15579
+8583,57.41584
+8584,22.71502
+8585,24.503857
+8586,23.496758
+8587,25.45779
+8588,21.291233
+8589,28.067373
+8590,33.324562
+8591,42.471092
+8592,27.120306
+8593,32.356327
+8594,35.15367
+8595,37.120552
+8596,40.042675
+8597,40.158424
+8598,9.119524
+8599,15.144472
+8600,21.046347
+8601,24.35203
+8602,40.580746
+8603,46.05062
+8604,47.49418
+8605,53.62433
+8606,56.745285
+8607,56.31129
+8608,57.504433
+8609,60.908405
+8610,62.74803
+8611,62.98944
+8612,67.16591
+8613,71.8117
+8614,21.201828
+8615,22.860039
+8616,24.792019
+8617,24.693481
+8618,29.912075
+8619,29.369839
+8620,35.140667
+8621,38.62633
+8622,42.92365
+8623,43.17638
+8624,47.406273
+8625,53.187943
+8626,14.830065
+8627,24.629656
+8628,28.468824
+8629,28.028036
+8630,33.348057
+8631,36.57354
+8632,32.875298
+8633,35.15722
+8634,41.568504
+8635,39.343456
+8636,40.94759
+8637,43.704643
+8638,31.697418
+8639,34.31428
+8640,36.95579
+8641,40.593998
+8642,42.38579
+8643,45.46565
+8644,47.981247
+8645,49.710358
+8646,50.78265
+8647,53.165363
+8648,56.415806
+8649,57.94743
+8650,14.657388
+8651,17.3546
+8652,16.741505
+8653,16.278452
+8654,19.31904
+8655,52.271793
+8656,55.816048
+8657,58.367146
+8658,60.180313
+8659,63.76628
+8660,65.69058
+8661,69.2877
+8662,68.94015
+8663,70.504234
+8664,71.8403
+8665,72.15757
+8666,73.28368
+8667,23.375853
+8668,24.267258
+8669,27.823698
+8670,30.116247
+8671,3.0283585
+8672,4.870226
+8673,9.526766
+8674,11.414629
+8675,12.405195
+8676,13.343989
+8677,18.897915
+8678,20.341259
+8679,16.315844
+8680,18.710615
+8681,20.659184
+8682,30.601032
+8683,44.90485
+8684,51.896286
+8685,51.908154
+8686,55.8241
+8687,56.571045
+8688,63.033985
+8689,64.17442
+8690,66.6138
+8691,27.169233
+8692,28.260986
+8693,28.75628
+8694,32.836273
+8695,33.126
+8696,34.42046
+8697,21.180326
+8698,20.235895
+8699,23.633423
+8700,27.426086
+8701,45.992855
+8702,45.707058
+8703,46.36953
+8704,48.322437
+8705,49.450302
+8706,50.500687
+8707,48.418816
+8708,52.865654
+8709,53.503822
+8710,54.81555
+8711,59.443058
+8712,61.802917
+8713,23.772057
+8714,32.931286
+8715,34.945366
+8716,36.480885
+8717,29.982067
+8718,34.171204
+8719,40.580048
+8720,43.993263
+8721,33.73169
+8722,44.72226
+8723,50.809986
+8724,55.677143
+8725,44.290398
+8726,47.614834
+8727,53.68453
+8728,60.0657
+8729,63.441536
+8730,65.7571
+8731,65.70023
+8732,69.94359
+8733,75.19324
+8734,28.136478
+8735,31.518024
+8736,31.823765
+8737,34.70215
+8738,37.048958
+8739,40.878727
+8740,42.789852
+8741,47.55423
+8742,48.410862
+8743,50.829468
+8744,53.922318
+8745,56.303364
+8746,12.052646
+8747,12.826558
+8748,13.849989
+8749,18.041864
+8750,21.391998
+8751,38.967285
+8752,40.30683
+8753,41.436184
+8754,43.013634
+8755,44.452156
+8756,21.014631
+8757,27.74279
+8758,35.8339
+8759,39.76879
+8760,31.5924
+8761,38.5549
+8762,39.349022
+8763,42.582684
+8764,43.750366
+8765,48.037247
+8766,52.395214
+8767,55.173
+8768,40.24787
+8769,40.850426
+8770,42.774406
+8771,47.08857
+8772,53.07028
+8773,52.907764
+8774,55.072094
+8775,55.4857
+8776,55.65361
+8777,61.265953
+8778,64.79094
+8779,63.99712
+8780,11.566694
+8781,13.272169
+8782,19.843693
+8783,20.47694
+8784,23.454529
+8785,27.569658
+8786,32.739124
+8787,37.455532
+8788,47.615288
+8789,45.19883
+8790,42.944515
+8791,52.73459
+8792,10.047285
+8793,12.156755
+8794,12.66684
+8795,13.704262
+8796,15.280774
+8797,19.013144
+8798,31.136595
+8799,30.635223
+8800,31.338509
+8801,25.35562
+8802,29.996109
+8803,31.4128
+8804,40.723396
+8805,42.27978
+8806,44.723557
+8807,18.9262
+8808,21.791292
+8809,27.433247
+8810,28.468674
+8811,38.145668
+8812,39.62558
+8813,43.566723
+8814,5.6106224
+8815,8.064075
+8816,11.106598
+8817,12.893174
+8818,12.529187
+8819,16.823818
+8820,19.237053
+8821,25.561352
+8822,25.846912
+8823,28.600754
+8824,29.707256
+8825,29.707561
+8826,30.411167
+8827,8.991737
+8828,11.141133
+8829,11.4597
+8830,10.986386
+8831,13.090378
+8832,14.483496
+8833,18.694796
+8834,20.256752
+8835,18.43676
+8836,19.977757
+8837,20.8984
+8838,29.795681
+8839,32.80011
+8840,35.340603
+8841,38.820953
+8842,43.89759
+8843,44.083466
+8844,45.151123
+8845,16.616358
+8846,20.952055
+8847,23.537851
+8848,24.311445
+8849,27.604778
+8850,24.76161
+8851,32.87216
+8852,33.583252
+8853,35.439266
+8854,36.59038
+8855,39.73899
+8856,39.385296
+8857,29.071512
+8858,29.012497
+8859,31.650475
+8860,33.70677
+8861,36.72384
+8862,37.749134
+8863,41.77506
+8864,41.704697
+8865,33.69238
+8866,33.754208
+8867,36.588333
+8868,40.898167
+8869,40.07558
+8870,40.716663
+8871,41.53681
+8872,44.208744
+8873,46.260296
+8874,44.977726
+8875,49.6326
+8876,51.960983
+8877,52.01042
+8878,52.14422
+8879,54.851406
+8880,58.275475
+8881,61.700565
+8882,60.98591
+8883,65.51925
+8884,67.410255
+8885,69.308914
+8886,71.42726
+8887,70.75747
+8888,73.659904
+8889,12.092631
+8890,14.665099
+8891,17.88556
+8892,22.939192
+8893,30.133156
+8894,33.027588
+8895,33.33471
+8896,38.04381
+8897,37.398777
+8898,39.17253
+8899,40.993088
+8900,44.95517
+8901,0.613298
+8902,1.4531583
+8903,2.4787447
+8904,4.4566593
+8905,5.4582677
+8906,6.3287406
+8907,9.636827
+8908,12.075639
+8909,34.28783
+8910,44.608364
+8911,48.93423
+8912,54.78917
+8913,59.850716
+8914,19.678593
+8915,23.128012
+8916,26.064077
+8917,37.46069
+8918,20.317293
+8919,23.501513
+8920,24.658407
+8921,28.888374
+8922,33.060127
+8923,35.984455
+8924,47.323143
+8925,50.888336
+8926,53.606388
+8927,54.44585
+8928,63.431965
+8929,62.450073
+8930,61.496845
+8931,63.868084
+8932,63.94361
+8933,70.15079
+8934,67.335014
+8935,69.96152
+8936,42.47305
+8937,41.871017
+8938,48.041607
+8939,50.17088
+8940,56.811592
+8941,61.06223
+8942,62.836006
+8943,17.36734
+8944,18.498432
+8945,20.99911
+8946,19.405153
+8947,20.135296
+8948,46.118748
+8949,50.928787
+8950,51.935776
+8951,58.911953
+8952,64.03564
+8953,62.78948
+8954,46.253468
+8955,47.18957
+8956,48.22545
+8957,52.765354
+8958,54.852654
+8959,56.61842
+8960,58.04811
+8961,58.022205
+8962,59.50961
+8963,62.078575
+8964,59.548298
+8965,61.14849
+8966,47.28491
+8967,48.288445
+8968,45.08098
+8969,48.97
+8970,43.964497
+8971,44.63643
+8972,47.521404
+8973,55.282295
+8974,57.988888
+8975,61.506397
+8976,60.95462
+8977,61.93441
+8978,63.195843
+8979,62.43696
+8980,64.24917
+8981,64.61279
+8982,28.42864
+8983,30.061472
+8984,34.373116
+8985,37.80334
+8986,40.22991
+8987,44.589653
+8988,47.191612
+8989,50.406376
+8990,41.56707
+8991,43.56434
+8992,44.94985
+8993,49.156395
+8994,51.880936
+8995,52.459225
+8996,56.217823
+8997,57.71728
+8998,62.87036
+8999,59.89199
+9000,61.234512
+9001,63.111965
+9002,11.538986
+9003,15.291985
+9004,16.819427
+9005,21.447659
+9006,23.485607
+9007,22.299711
+9008,23.963137
+9009,28.413923
+9010,31.717144
+9011,31.083597
+9012,31.131332
+9013,33.99781
+9014,18.924839
+9015,22.31135
+9016,27.90846
+9017,38.267937
+9018,18.876179
+9019,20.140854
+9020,21.571848
+9021,25.28418
+9022,23.99898
+9023,27.678028
+9024,18.354994
+9025,20.63103
+9026,21.85476
+9027,27.88651
+9028,38.925247
+9029,30.837364
+9030,36.520466
+9031,34.88518
+9032,33.837105
+9033,37.971176
+9034,40.64785
+9035,35.51805
+9036,39.11462
+9037,44.15627
+9038,49.47308
+9039,52.139874
+9040,54.89648
+9041,57.64367
+9042,57.808083
+9043,60.721912
+9044,60.85066
+9045,64.92444
+9046,64.83905
+9047,10.891494
+9048,12.163159
+9049,11.762643
+9050,23.081152
+9051,15.636286
+9052,13.710623
+9053,17.741365
+9054,17.402235
+9055,21.219814
+9056,23.507412
+9057,23.79861
+9058,28.469515
+9059,29.989738
+9060,30.318645
+9061,36.809814
+9062,36.1476
+9063,56.778343
+9064,56.750843
+9065,57.31142
+9066,61.143143
+9067,12.9419
+9068,14.952518
+9069,21.048338
+9070,24.304192
+9071,0.92379975
+9072,1.0310543
+9073,0.6162602
+9074,7.552737
+9075,30.010828
+9076,33.580456
+9077,35.287613
+9078,37.728806
+9079,42.670338
+9080,43.51512
+9081,46.469402
+9082,11.456256
+9083,15.629599
+9084,17.436953
+9085,21.946016
+9086,26.011473
+9087,10.447905
+9088,13.646767
+9089,15.129178
+9090,26.399925
+9091,6.0974436
+9092,8.722952
+9093,9.411659
+9094,10.88534
+9095,12.889132
+9096,15.5756
+9097,16.495943
+9098,21.125872
+9099,19.780138
+9100,22.479963
+9101,33.05826
+9102,32.171818
+9103,29.902342
+9104,33.87575
+9105,35.815098
+9106,37.999714
+9107,37.576805
+9108,39.061058
+9109,43.093147
+9110,47.540306
+9111,49.273544
+9112,16.731354
+9113,22.71846
+9114,27.908363
+9115,29.600542
+9116,28.571478
+9117,31.447289
+9118,14.508265
+9119,16.505804
+9120,20.025469
+9121,21.88633
+9122,22.23444
+9123,26.611517
+9124,29.269218
+9125,30.338747
+9126,33.24846
+9127,34.760765
+9128,32.84262
+9129,35.3592
+9130,7.6101494
+9131,9.392502
+9132,10.711548
+9133,12.137537
+9134,13.793816
+9135,15.56288
+9136,16.208614
+9137,22.562788
+9138,24.254627
+9139,24.646696
+9140,27.149437
+9141,30.060432
+9142,18.159887
+9143,18.34496
+9144,25.821928
+9145,28.777866
+9146,31.464994
+9147,35.867638
+9148,37.780758
+9149,43.363087
+9150,47.83081
+9151,44.223057
+9152,45.565853
+9153,50.740475
+9154,18.71811
+9155,22.043522
+9156,26.389433
+9157,34.485977
+9158,37.63218
+9159,40.24063
+9160,31.949245
+9161,33.463505
+9162,34.251984
+9163,37.66113
+9164,38.198776
+9165,40.93444
+9166,48.138058
+9167,46.87359
+9168,50.61508
+9169,53.642746
+9170,58.912544
+9171,55.06109
+9172,36.80281
+9173,36.39847
+9174,39.18504
+9175,40.850983
+9176,30.2717
+9177,36.48439
+9178,37.166718
+9179,38.986526
+9180,40.87125
+9181,13.758608
+9182,14.27434
+9183,22.239729
+9184,23.474377
+9185,26.615835
+9186,28.407078
+9187,30.974531
+9188,35.92462
+9189,39.993454
+9190,37.392506
+9191,41.19858
+9192,44.07621
+9193,44.007103
+9194,45.50866
+9195,45.357758
+9196,48.6598
+9197,30.170925
+9198,32.497192
+9199,28.28824
+9200,45.97219
+9201,48.618153
+9202,47.09633
+9203,54.62904
+9204,56.190365
+9205,61.94029
+9206,65.78877
+9207,63.11763
+9208,63.58013
+9209,16.947071
+9210,18.294413
+9211,21.741161
+9212,26.59657
+9213,29.954922
+9214,29.781643
+9215,35.064438
+9216,37.643963
+9217,39.660263
+9218,41.18124
+9219,44.229187
+9220,43.56644
+9221,37.671177
+9222,43.670406
+9223,46.889904
+9224,48.121616
+9225,50.73847
+9226,51.261086
+9227,54.11591
+9228,54.35246
+9229,55.27021
+9230,57.827057
+9231,58.873074
+9232,59.12895
+9233,4.036973
+9234,5.5364256
+9235,8.814178
+9236,11.054441
+9237,10.527884
+9238,10.332546
+9239,11.523497
+9240,13.797645
+9241,23.356993
+9242,29.666565
+9243,40.465225
+9244,45.166794
+9245,34.562996
+9246,38.75721
+9247,43.853355
+9248,40.06063
+9249,40.92706
+9250,44.491455
+9251,52.698067
+9252,48.58187
+9253,0.12698656
+9254,0.500728
+9255,0.800649
+9256,2.3303962
+9257,4.190097
+9258,6.1327314
+9259,32.215744
+9260,39.55008
+9261,48.557884
+9262,53.40433
+9263,11.425604
+9264,15.67926
+9265,19.812199
+9266,25.653446
+9267,28.140665
+9268,27.812035
+9269,35.16965
+9270,37.711052
+9271,37.87137
+9272,37.8066
+9273,42.19396
+9274,45.89239
+9275,34.754803
+9276,38.399147
+9277,39.63639
+9278,43.877434
+9279,45.431355
+9280,47.428097
+9281,49.605053
+9282,15.2234535
+9283,16.05616
+9284,18.378618
+9285,18.415352
+9286,20.415426
+9287,26.29111
+9288,16.871796
+9289,20.586842
+9290,22.44012
+9291,27.321411
+9292,28.525425
+9293,31.40434
+9294,34.037018
+9295,36.03239
+9296,39.17128
+9297,40.467766
+9298,40.01676
+9299,43.629234
+9300,3.528189
+9301,4.557432
+9302,8.011173
+9303,9.658045
+9304,11.164929
+9305,18.393383
+9306,18.13517
+9307,22.999441
+9308,26.40302
+9309,31.347702
+9310,30.001833
+9311,34.633797
+9312,45.155727
+9313,50.923985
+9314,52.25846
+9315,54.24745
+9316,55.48
+9317,56.42535
+9318,58.83448
+9319,60.601795
+9320,62.006256
+9321,63.29967
+9322,64.85209
+9323,67.43775
+9324,1.6428809
+9325,2.471977
+9326,3.306882
+9327,5.335432
+9328,29.624233
+9329,30.385174
+9330,36.60349
+9331,39.385086
+9332,44.39705
+9333,45.68354
+9334,49.85765
+9335,53.09172
+9336,56.00952
+9337,57.952778
+9338,57.526184
+9339,59.222874
+9340,30.006283
+9341,36.511734
+9342,38.615078
+9343,39.455505
+9344,29.748566
+9345,35.022106
+9346,39.675392
+9347,42.336548
+9348,36.54622
+9349,36.00135
+9350,40.516304
+9351,40.13728
+9352,43.073807
+9353,41.913105
+9354,44.60215
+9355,44.869785
+9356,47.611343
+9357,51.81381
+9358,54.032394
+9359,54.727383
+9360,10.069503
+9361,13.456495
+9362,14.098596
+9363,27.316187
+9364,33.46727
+9365,10.236517
+9366,11.388886
+9367,15.164356
+9368,20.37894
+9369,18.681858
+9370,20.512375
+9371,22.452736
+9372,24.011253
+9373,26.831932
+9374,30.882008
+9375,31.090525
+9376,35.276787
+9377,38.59532
+9378,36.979984
+9379,38.299538
+9380,40.816566
+9381,26.46237
+9382,26.650263
+9383,32.496136
+9384,34.37511
+9385,35.27393
+9386,38.545788
+9387,38.993065
+9388,42.16021
+9389,43.059734
+9390,44.191376
+9391,46.01738
+9392,48.40733
+9393,5.3902225
+9394,7.9600496
+9395,9.065224
+9396,12.378272
+9397,18.400341
+9398,18.602306
+9399,22.226805
+9400,23.190094
+9401,34.587273
+9402,30.948734
+9403,31.649593
+9404,39.054665
+9405,38.674843
+9406,39.85569
+9407,41.905983
+9408,20.358978
+9409,22.078121
+9410,27.411516
+9411,29.834963
+9412,27.72179
+9413,26.208994
+9414,31.953773
+9415,33.899036
+9416,36.36467
+9417,36.293945
+9418,38.72535
+9419,40.603653
+9420,30.876993
+9421,33.99338
+9422,37.446968
+9423,39.32992
+9424,47.66759
+9425,54.15408
+9426,58.884274
+9427,57.57498
+9428,57.046566
+9429,59.3548
+9430,63.779247
+9431,67.3701
+9432,25.581139
+9433,27.073912
+9434,28.88953
+9435,32.647797
+9436,36.29501
+9437,40.637753
+9438,38.637566
+9439,44.29185
+9440,52.211227
+9441,49.724617
+9442,54.36582
+9443,49.708206
+9444,6.050631
+9445,10.275157
+9446,14.94902
+9447,16.636312
+9448,38.624584
+9449,40.99139
+9450,39.282623
+9451,50.030823
+9452,4.261571
+9453,4.7681513
+9454,6.380198
+9455,7.8996134
+9456,10.090027
+9457,12.493172
+9458,15.22054
+9459,54.455708
+9460,59.95363
+9461,65.73779
+9462,67.07875
+9463,72.94594
+9464,72.994736
+9465,73.152916
+9466,78.24299
+9467,76.43305
+9468,78.44632
+9469,82.531586
+9470,80.27202
+9471,34.615166
+9472,35.891594
+9473,38.517857
+9474,43.290787
+9475,45.041424
+9476,45.306892
+9477,49.557106
+9478,49.715908
+9479,51.596962
+9480,53.536663
+9481,55.28484
+9482,56.4416
+9483,21.886835
+9484,26.871866
+9485,28.705908
+9486,28.496605
+9487,30.327969
+9488,32.71371
+9489,31.451738
+9490,36.797825
+9491,39.942207
+9492,43.500854
+9493,44.228302
+9494,44.447468
+9495,22.09778
+9496,27.13883
+9497,32.94027
+9498,38.309845
+9499,20.329517
+9500,21.856148
+9501,22.064457
+9502,30.989927
+9503,33.06093
+9504,37.122223
+9505,38.18866
+9506,38.415592
+9507,43.087147
+9508,45.70195
+9509,46.95583
+9510,47.958412
+9511,27.58325
+9512,29.458178
+9513,32.587875
+9514,33.046867
+9515,38.53582
+9516,42.85115
+9517,45.472458
+9518,41.780815
+9519,45.560062
+9520,47.80629
+9521,50.560123
+9522,54.830467
+9523,18.740782
+9524,17.7783
+9525,20.065224
+9526,21.18166
+9527,24.36174
+9528,27.318363
+9529,30.013592
+9530,33.30979
+9531,39.192436
+9532,34.716034
+9533,40.27276
+9534,40.959435
+9535,47.976173
+9536,56.706703
+9537,59.807037
+9538,55.610718
+9539,60.124367
+9540,61.54167
+9541,62.751625
+9542,64.31628
+9543,65.37365
+9544,67.52078
+9545,68.4861
+9546,70.83147
+9547,12.748136
+9548,12.720862
+9549,13.960261
+9550,19.099743
+9551,21.513655
+9552,23.832268
+9553,25.903147
+9554,27.534151
+9555,31.320343
+9556,31.497374
+9557,34.078754
+9558,35.285477
+9559,0.6306225
+9560,1.3255002
+9561,2.7570055
+9562,3.8088925
+9563,6.5779934
+9564,9.774041
+9565,10.751847
+9566,11.734246
+9567,15.148433
+9568,16.56791
+9569,16.23241
+9570,19.851786
+9571,8.510898
+9572,17.079538
+9573,20.084965
+9574,24.020151
+9575,27.059195
+9576,36.561203
+9577,36.369617
+9578,39.431473
+9579,41.2806
+9580,41.82893
+9581,40.810444
+9582,42.742332
+9583,45.06729
+9584,45.577137
+9585,46.82223
+9586,48.55389
+9587,52.633232
+9588,19.58152
+9589,26.617914
+9590,35.480217
+9591,34.453644
+9592,32.767056
+9593,35.535805
+9594,40.45877
+9595,41.25196
+9596,43.865437
+9597,48.23172
+9598,49.600826
+9599,31.42513
+9600,36.876118
+9601,40.456474
+9602,39.581352
+9603,44.249447
+9604,46.197166
+9605,68.32452
+9606,70.682976
+9607,70.91906
+9608,74.82024
+9609,53.950443
+9610,55.464573
+9611,60.592598
+9612,60.721092
+9613,63.900536
+9614,66.58152
+9615,67.58483
+9616,67.955025
+9617,70.33563
+9618,71.77522
+9619,72.40174
+9620,74.21875
+9621,45.918224
+9622,48.766605
+9623,48.466175
+9624,51.23871
+9625,53.764435
+9626,55.1888
+9627,56.94742
+9628,58.15015
+9629,61.09805
+9630,61.41343
+9631,62.771664
+9632,14.608709
+9633,19.091337
+9634,21.306274
+9635,24.325745
+9636,28.626959
+9637,36.97423
+9638,38.245174
+9639,38.68245
+9640,42.361794
+9641,48.75196
+9642,51.645554
+9643,53.55171
+9644,55.959267
+9645,58.207123
+9646,57.678875
+9647,62.4372
+9648,33.907593
+9649,34.413506
+9650,34.598312
+9651,36.465492
+9652,5.8712344
+9653,6.211864
+9654,8.331427
+9655,8.103953
+9656,11.529995
+9657,12.693301
+9658,14.773179
+9659,0.63726205
+9660,1.6858587
+9661,2.56178
+9662,3.8056808
+9663,6.0806704
+9664,12.177773
+9665,16.081118
+9666,13.084613
+9667,14.966778
+9668,23.711235
+9669,41.7068
+9670,38.16452
+9671,40.377373
+9672,34.62608
+9673,44.473816
+9674,45.442932
+9675,18.650518
+9676,26.91014
+9677,29.399532
+9678,28.216938
+9679,32.54153
+9680,32.398956
+9681,35.121574
+9682,38.41362
+9683,41.949234
+9684,43.2631
+9685,45.9958
+9686,47.25142
+9687,4.896119
+9688,4.661868
+9689,7.6646104
+9690,10.327232
+9691,13.0386505
+9692,16.710466
+9693,16.060694
+9694,24.228897
+9695,20.967983
+9696,27.870226
+9697,35.459866
+9698,43.846024
+9699,39.92967
+9700,39.502235
+9701,38.908684
+9702,42.24784
+9703,44.08044
+9704,43.43363
+9705,46.766933
+9706,53.548416
+9707,58.133144
+9708,56.382248
+9709,25.625916
+9710,28.520845
+9711,27.979359
+9712,32.12628
+9713,32.472122
+9714,38.554085
+9715,40.767693
+9716,45.89718
+9717,13.918112
+9718,18.032898
+9719,20.618095
+9720,25.807068
+9721,28.74213
+9722,0.018036004
+9723,1.1143677
+9724,4.284804
+9725,7.141738
+9726,14.744914
+9727,17.50388
+9728,22.483427
+9729,27.50611
+9730,34.068237
+9731,35.552834
+9732,32.60835
+9733,40.139816
+9734,41.454388
+9735,41.108955
+9736,46.938126
+9737,45.698692
+9738,48.637985
+9739,11.665201
+9740,15.351865
+9741,22.256147
+9742,24.338772
+9743,21.029812
+9744,23.373123
+9745,24.998108
+9746,29.178923
+9747,31.432074
+9748,10.943832
+9749,11.412611
+9750,13.817433
+9751,15.194499
+9752,17.64015
+9753,17.685661
+9754,21.533392
+9755,28.042076
+9756,31.935226
+9757,25.164108
+9758,32.468044
+9759,34.52072
+9760,9.944638
+9761,10.163975
+9762,12.186133
+9763,15.775987
+9764,19.17118
+9765,22.478783
+9766,25.34225
+9767,27.901611
+9768,28.767273
+9769,31.781021
+9770,30.079985
+9771,33.344555
+9772,34.38793
+9773,37.588192
+9774,39.47448
+9775,46.00158
+9776,47.45339
+9777,52.524242
+9778,53.205746
+9779,56.44866
+9780,3.0193553
+9781,4.3128033
+9782,5.2957125
+9783,6.943757
+9784,37.360428
+9785,42.815517
+9786,43.07047
+9787,45.514137
+9788,18.168331
+9789,22.556927
+9790,22.058924
+9791,23.124405
+9792,27.988842
+9793,30.191498
+9794,35.320312
+9795,35.071938
+9796,39.272675
+9797,40.694447
+9798,39.89003
+9799,42.48703
+9800,32.57636
+9801,34.553974
+9802,36.171406
+9803,39.607315
+9804,45.88256
+9805,46.2943
+9806,50.607525
+9807,50.728176
+9808,51.74221
+9809,52.185368
+9810,53.813015
+9811,55.39361
+9812,28.207747
+9813,34.285168
+9814,36.695385
+9815,36.661667
+9816,39.790264
+9817,42.751656
+9818,46.034286
+9819,44.929916
+9820,0.7824064
+9821,3.4154763
+9822,5.7912493
+9823,7.6475463
+9824,52.02487
+9825,48.44022
+9826,51.18001
+9827,51.57759
+9828,50.91405
+9829,37.396774
+9830,41.638184
+9831,46.919006
+9832,45.55316
+9833,47.68867
+9834,51.303818
+9835,50.707153
+9836,54.70313
+9837,54.5052
+9838,54.689198
+9839,55.924866
+9840,57.756557
+9841,24.743338
+9842,28.529856
+9843,31.056644
+9844,32.428688
+9845,34.085243
+9846,26.608488
+9847,28.00885
+9848,40.981277
+9849,46.065514
+9850,43.080193
+9851,43.59337
+9852,47.68696
+9853,50.284912
+9854,50.524715
+9855,53.34379
+9856,53.167595
+9857,55.88148
+9858,1.3769825
+9859,2.518002
+9860,3.9739237
+9861,5.2265067
+9862,44.527332
+9863,54.00144
+9864,58.077206
+9865,59.7325
+9866,28.360018
+9867,28.826056
+9868,30.710289
+9869,34.39241
+9870,36.373013
+9871,37.12657
+9872,42.77122
+9873,43.058823
+9874,46.36427
+9875,47.964066
+9876,50.14723
+9877,52.23546
+9878,20.992088
+9879,24.244267
+9880,25.879978
+9881,30.475054
+9882,33.084354
+9883,35.246677
+9884,38.919327
+9885,45.839577
+9886,43.795635
+9887,46.251938
+9888,47.630993
+9889,45.7798
+9890,11.660702
+9891,14.939352
+9892,17.405628
+9893,19.089294
+9894,28.672615
+9895,30.505949
+9896,29.88916
+9897,36.30902
+9898,34.657017
+9899,39.61004
+9900,33.035465
+9901,36.994392
+9902,10.564294
+9903,12.780362
+9904,14.100605
+9905,15.037796
+9906,20.337921
+9907,25.955235
+9908,26.971283
+9909,29.425655
+9910,31.60242
+9911,35.571133
+9912,40.264275
+9913,45.655685
+9914,30.855503
+9915,31.17621
+9916,30.521145
+9917,32.331467
+9918,32.187267
+9919,34.595837
+9920,34.479034
+9921,42.32284
+9922,43.307816
+9923,43.770687
+9924,47.08111
+9925,58.646194
+9926,60.655617
+9927,62.780586
+9928,66.218666
+9929,65.57054
+9930,69.47608
+9931,69.58724
+9932,71.41406
+9933,21.039806
+9934,25.1656
+9935,27.882793
+9936,26.368427
+9937,29.80813
+9938,29.43528
+9939,33.562378
+9940,39.957115
+9941,38.291428
+9942,38.277798
+9943,40.10868
+9944,43.5458
+9945,28.410385
+9946,31.021544
+9947,33.298187
+9948,34.56813
+9949,39.95037
+9950,43.26245
+9951,48.797382
+9952,50.405556
+9953,51.70779
+9954,54.364902
+9955,55.919308
+9956,60.138863
+9957,35.06325
+9958,38.991653
+9959,46.29995
+9960,48.389664
+9961,50.993595
+9962,46.627388
+9963,49.90659
+9964,53.35346
+9965,61.277336
+9966,41.57182
+9967,44.38054
+9968,50.630966
+9969,49.681187
+9970,56.273636
+9971,53.683334
+9972,58.587296
+9973,58.34331
+9974,58.122158
+9975,60.13854
+9976,62.643578
+9977,67.45127
+9978,28.748499
+9979,30.318054
+9980,32.41059
+9981,34.083313
+9982,35.41919
+9983,38.294453
+9984,37.79731
+9985,29.384762
+9986,36.104893
+9987,44.882088
+9988,50.0438
+9989,52.187393
+9990,26.583874
+9991,29.943743
+9992,32.311832
+9993,37.33326
+9994,22.60262
+9995,23.248234
+9996,25.279015
+9997,27.374487
+9998,28.422525
+9999,30.49621
+10000,33.808083
+10001,37.06361
+10002,37.625713
+10003,41.894318
+10004,44.371956
+10005,47.332153
+10006,4.268548
+10007,5.5151353
+10008,6.047552
+10009,6.7499123
+10010,8.83344
+10011,15.976371
+10012,19.273548
+10013,73.99677
+10014,79.24155
+10015,78.68468
+10016,77.580055
+10017,44.580914
+10018,46.11634
+10019,48.719414
+10020,47.619503
+10021,52.061035
+10022,6.1444874
+10023,8.443475
+10024,10.379987
+10025,10.741753
+10026,16.337404
+10027,18.54332
+10028,18.964478
+10029,24.21806
+10030,25.247988
+10031,27.643885
+10032,31.514982
+10033,30.288506
+10034,80.08078
+10035,88.16662
+10036,90.94758
+10037,93.923096
+10038,96.78362
+10039,97.76682
+10040,98.57215
+10041,103.14134
+10042,102.13298
+10043,104.04673
+10044,105.404106
+10045,106.35665
+10046,44.941334
+10047,47.02453
+10048,52.771507
+10049,59.79148
+10050,61.224075
+10051,63.6002
+10052,66.261444
+10053,67.33086
+10054,70.16112
+10055,68.99447
+10056,74.41425
+10057,76.765884
+10058,17.019064
+10059,18.5668
+10060,25.13293
+10061,28.784681
+10062,26.084152
+10063,33.772198
+10064,34.51631
+10065,43.43711
+10066,43.662315
+10067,47.59228
+10068,49.15118
+10069,46.125355
+10070,21.877457
+10071,24.752226
+10072,28.553473
+10073,31.269087
+10074,34.58626
+10075,36.79232
+10076,37.437675
+10077,16.777082
+10078,23.057919
+10079,26.971664
+10080,33.13504
+10081,12.364744
+10082,13.584036
+10083,16.360283
+10084,18.042572
+10085,24.09178
+10086,25.721603
+10087,22.877874
+10088,24.589138
+10089,26.884878
+10090,33.996803
+10091,36.22142
+10092,34.463478
+10093,36.80881
+10094,37.778305
+10095,39.151104
+10096,40.047203
+10097,43.240566
+10098,43.46761
+10099,27.460596
+10100,28.670765
+10101,29.299894
+10102,32.45562
+10103,43.571144
+10104,47.459255
+10105,48.866432
+10106,49.790405
+10107,50.26068
+10108,42.790794
+10109,49.604042
+10110,54.147453
+10111,51.399128
+10112,54.050217
+10113,56.472282
+10114,57.64142
+10115,10.405406
+10116,12.42969
+10117,13.738196
+10118,17.814653
+10119,42.514496
+10120,42.311077
+10121,43.338623
+10122,48.19223
+10123,47.86431
+10124,22.772392
+10125,35.0516
+10126,35.97224
+10127,39.023613
+10128,6.370371
+10129,7.598114
+10130,12.770441
+10131,18.240301
+10132,21.331554
+10133,-0.16048914
+10134,0.8002105
+10135,0.9002979
+10136,6.616626
+10137,41.31512
+10138,43.012005
+10139,46.32954
+10140,50.559074
+10141,51.728783
+10142,52.377884
+10143,55.82115
+10144,58.61254
+10145,59.959866
+10146,62.24926
+10147,62.420593
+10148,66.53818
+10149,29.659609
+10150,37.447693
+10151,46.466496
+10152,54.98532
+10153,54.75781
+10154,28.192139
+10155,29.553423
+10156,35.178913
+10157,35.39647
+10158,34.031574
+10159,40.03356
+10160,45.680607
+10161,40.887367
+10162,46.756924
+10163,51.77475
+10164,51.368607
+10165,55.067207
+10166,57.75136
+10167,61.087097
+10168,61.902874
+10169,49.57739
+10170,49.72074
+10171,46.556202
+10172,51.30511
+10173,53.810917
+10174,51.74138
+10175,55.05089
+10176,55.90798
+10177,56.95986
+10178,58.291862
+10179,58.689114
+10180,16.186699
+10181,23.707846
+10182,28.303272
+10183,29.172047
+10184,25.812605
+10185,28.284039
+10186,32.97848
+10187,35.801037
+10188,35.942154
+10189,38.515984
+10190,41.87882
+10191,43.199234
+10192,28.05499
+10193,30.078875
+10194,31.6926
+10195,34.544193
+10196,34.89327
+10197,52.687336
+10198,55.600574
+10199,57.309334
+10200,59.82363
+10201,56.63625
+10202,64.634766
+10203,61.100594
+10204,62.196445
+10205,62.718613
+10206,66.99945
+10207,65.40922
+10208,25.869482
+10209,32.56388
+10210,44.047405
+10211,47.42919
+10212,22.4581
+10213,35.283867
+10214,37.231743
+10215,32.039524
+10216,38.788223
+10217,39.16382
+10218,42.72431
+10219,46.227432
+10220,49.544174
+10221,54.30216
+10222,60.584118
+10223,62.544064
+10224,32.309067
+10225,40.546196
+10226,42.19193
+10227,42.27472
+10228,48.748096
+10229,50.06634
+10230,54.804733
+10231,54.03887
+10232,53.89339
+10233,56.957714
+10234,56.47559
+10235,56.200157
+10236,21.028004
+10237,28.980137
+10238,33.281986
+10239,38.329674
+10240,45.379395
+10241,27.41098
+10242,28.81697
+10243,30.065804
+10244,29.788439
+10245,28.779636
+10246,30.56471
+10247,31.661278
+10248,36.668743
+10249,38.493416
+10250,38.39146
+10251,41.649963
+10252,41.64289
+10253,57.85421
+10254,60.672832
+10255,66.776794
+10256,64.79917
+10257,69.81572
+10258,69.967224
+10259,72.16181
+10260,76.16516
+10261,73.7334
+10262,75.660866
+10263,76.350945
+10264,79.02282
+10265,0.6143909
+10266,1.2126021
+10267,0.5066552
+10268,0.71664137
+10269,0.29856706
+10270,0.8146398
+10271,1.5795634
+10272,2.5597723
+10273,36.36762
+10274,38.095844
+10275,43.26311
+10276,48.46095
+10277,49.616028
+10278,54.21958
+10279,53.58819
+10280,58.403282
+10281,56.898018
+10282,63.435246
+10283,63.6244
+10284,64.07254
+10285,34.02558
+10286,35.20291
+10287,43.06095
+10288,52.32255
+10289,55.750835
+10290,51.697075
+10291,57.32525
+10292,58.199135
+10293,60.22116
+10294,65.24185
+10295,65.839905
+10296,64.55528
+10297,11.339587
+10298,11.342751
+10299,13.741142
+10300,14.986676
+10301,19.281443
+10302,21.365633
+10303,24.64338
+10304,25.826286
+10305,28.21785
+10306,30.142544
+10307,35.06776
+10308,39.002045
+10309,39.4497
+10310,40.257347
+10311,45.26268
+10312,42.004932
+10313,47.189236
+10314,50.442307
+10315,51.019783
+10316,55.534103
+10317,57.73468
+10318,59.806217
+10319,59.32391
+10320,62.914734
+10321,61.777435
+10322,62.4182
+10323,65.84798
+10324,67.043465
+10325,32.07248
+10326,39.288902
+10327,40.630127
+10328,44.79009
+10329,70.6992
+10330,74.55852
+10331,74.16006
+10332,78.1486
+10333,82.290245
+10334,84.240654
+10335,87.05361
+10336,29.907839
+10337,34.665604
+10338,35.470356
+10339,36.41639
+10340,40.86336
+10341,49.643795
+10342,54.180763
+10343,56.959236
+10344,58.935776
+10345,61.66126
+10346,62.635494
+10347,67.717926
+10348,66.70034
+10349,42.74721
+10350,49.171677
+10351,56.29559
+10352,54.364807
+10353,57.687954
+10354,59.156586
+10355,65.6527
+10356,65.19592
+10357,66.982834
+10358,68.23526
+10359,67.59633
+10360,33.98604
+10361,34.07905
+10362,37.586094
+10363,42.498238
+10364,22.689587
+10365,29.64845
+10366,32.73548
+10367,32.319946
+10368,19.753775
+10369,22.59542
+10370,23.978878
+10371,29.483772
+10372,32.612057
+10373,30.77148
+10374,36.024506
+10375,37.599365
+10376,37.850655
+10377,38.914356
+10378,39.792885
+10379,35.380474
+10380,38.842773
+10381,39.504715
+10382,41.2475
+10383,46.095947
+10384,46.61886
+10385,50.07978
+10386,47.82669
+10387,52.330032
+10388,51.960503
+10389,18.486277
+10390,22.834618
+10391,28.082705
+10392,31.121307
+10393,39.087452
+10394,21.173397
+10395,26.75487
+10396,28.169525
+10397,26.596825
+10398,33.040302
+10399,36.19725
+10400,36.746384
+10401,44.605362
+10402,45.07528
+10403,47.197556
+10404,49.866314
+10405,48.31709
+10406,19.442657
+10407,20.870926
+10408,22.403131
+10409,23.928019
+10410,26.834206
+10411,34.993607
+10412,36.96935
+10413,36.86653
+10414,38.88572
+10415,37.38748
+10416,40.389465
+10417,41.852337
+10418,36.82231
+10419,37.641624
+10420,40.351204
+10421,43.150562
+10422,42.772583
+10423,45.111046
+10424,46.856113
+10425,48.249054
+10426,47.368637
+10427,50.28878
+10428,50.84734
+10429,53.021454
+10430,52.97004
+10431,55.47621
+10432,59.505398
+10433,59.392975
+10434,60.275856
+10435,59.48164
+10436,65.76248
+10437,68.01428
+10438,69.83468
+10439,67.78471
+10440,73.74263
+10441,71.13916
+10442,25.352621
+10443,28.61379
+10444,28.630507
+10445,30.112171
+10446,36.506916
+10447,50.092438
+10448,55.858574
+10449,58.608593
+10450,32.68783
+10451,32.940956
+10452,34.00483
+10453,40.66052
+10454,41.00223
+10455,39.029526
+10456,46.341476
+10457,48.698982
+10458,43.869125
+10459,43.142456
+10460,50.146935
+10461,51.648254
+10462,18.48599
+10463,20.039892
+10464,20.035206
+10465,22.41273
+10466,23.629084
+10467,29.129856
+10468,31.429905
+10469,34.602722
+10470,29.012623
+10471,34.214493
+10472,38.291462
+10473,38.665474
+10474,25.147333
+10475,33.77782
+10476,39.80801
+10477,36.72649
+10478,40.511402
+10479,41.34185
+10480,44.30463
+10481,48.35544
+10482,49.281918
+10483,15.513415
+10484,16.474283
+10485,16.573778
+10486,17.35922
+10487,19.577469
+10488,7.89818
+10489,8.895947
+10490,9.475592
+10491,11.108303
+10492,13.401955
+10493,18.406912
+10494,21.608099
+10495,21.15097
+10496,22.537338
+10497,24.099222
+10498,25.904858
+10499,7.4448733
+10500,10.338029
+10501,10.568167
+10502,10.651812
+10503,11.891583
+10504,12.151498
+10505,28.65985
+10506,30.828842
+10507,36.02426
+10508,37.372444
+10509,27.600742
+10510,29.669037
+10511,32.86261
+10512,37.46947
+10513,40.68769
+10514,42.206417
+10515,50.827717
+10516,50.94133
+10517,52.326443
+10518,50.432877
+10519,58.163147
+10520,22.183056
+10521,22.047617
+10522,22.46251
+10523,27.062168
+10524,29.762764
+10525,33.79032
+10526,33.874638
+10527,35.691765
+10528,38.993492
+10529,40.233852
+10530,45.41358
+10531,50.1746
+10532,50.75066
+10533,54.800312
+10534,58.827374
+10535,59.839725
+10536,58.507545
+10537,61.814423
+10538,62.75063
+10539,42.644863
+10540,40.720665
+10541,40.346127
+10542,45.68557
+10543,29.148796
+10544,32.89617
+10545,32.816666
+10546,37.026253
+10547,31.467556
+10548,37.32502
+10549,39.772385
+10550,47.40851
+10551,48.24176
+10552,48.14616
+10553,50.587906
+10554,54.36704
+10555,59.31485
+10556,60.66064
+10557,62.639954
+10558,19.701286
+10559,22.220112
+10560,25.189396
+10561,29.435762
+10562,30.862003
+10563,36.243896
+10564,40.548946
+10565,40.659576
+10566,40.901867
+10567,46.350143
+10568,46.1936
+10569,48.943356
+10570,19.008167
+10571,23.04498
+10572,33.465485
+10573,36.12829
+10574,33.750793
+10575,34.81744
+10576,38.82185
+10577,41.359196
+10578,42.72171
+10579,44.272488
+10580,50.82023
+10581,49.721992
+10582,19.810024
+10583,22.159182
+10584,24.482231
+10585,22.417988
+10586,27.72213
+10587,30.493404
+10588,30.191149
+10589,40.15169
+10590,36.78733
+10591,39.89666
+10592,40.372593
+10593,42.05607
+10594,59.906918
+10595,59.150574
+10596,63.633396
+10597,63.908638
+10598,20.082972
+10599,21.719011
+10600,24.426285
+10601,25.719997
+10602,27.006104
+10603,20.27234
+10604,24.609684
+10605,23.540154
+10606,28.176228
+10607,30.567333
+10608,37.18183
+10609,38.443302
+10610,41.126358
+10611,39.028404
+10612,41.327675
+10613,48.354794
+10614,50.45879
+10615,51.83503
+10616,54.911736
+10617,58.620663
+10618,60.150562
+10619,62.271523
+10620,63.15847
+10621,67.393295
+10622,65.81189
+10623,37.057583
+10624,37.327766
+10625,40.72527
+10626,42.719723
+10627,46.720074
+10628,51.477966
+10629,48.266903
+10630,51.916687
+10631,57.0744
+10632,12.7422
+10633,18.221113
+10634,20.71191
+10635,20.641577
+10636,23.73026
+10637,24.852116
+10638,25.193483
+10639,25.697525
+10640,31.090582
+10641,35.402782
+10642,32.949966
+10643,36.55648
+10644,24.792507
+10645,26.443256
+10646,29.139193
+10647,31.593224
+10648,34.65649
+10649,33.960022
+10650,40.644913
+10651,39.515076
+10652,41.34687
+10653,43.830017
+10654,44.011536
+10655,46.875793
+10656,42.958336
+10657,46.396378
+10658,57.994804
+10659,60.936775
+10660,65.01215
+10661,18.445295
+10662,20.654531
+10663,23.823017
+10664,30.316917
+10665,32.746384
+10666,36.691578
+10667,39.44165
+10668,37.796185
+10669,40.13642
+10670,44.52883
+10671,43.2659
+10672,45.074753
+10673,31.106682
+10674,29.91428
+10675,39.388012
+10676,46.585434
+10677,45.733994
+10678,48.07451
+10679,49.277206
+10680,52.363724
+10681,53.964676
+10682,13.831647
+10683,16.0292
+10684,17.35852
+10685,18.816813
+10686,22.37264
+10687,22.89708
+10688,40.858448
+10689,50.696777
+10690,53.7383
+10691,53.05945
+10692,56.329006
+10693,61.505352
+10694,62.444237
+10695,61.3514
+10696,61.20495
+10697,66.12185
+10698,63.220688
+10699,68.35777
+10700,32.9427
+10701,36.64604
+10702,36.477875
+10703,40.03683
+10704,41.321407
+10705,43.20018
+10706,43.82894
+10707,44.54212
+10708,22.366655
+10709,22.657822
+10710,27.715778
+10711,35.52055
+10712,38.577957
+10713,37.42926
+10714,43.516426
+10715,41.87673
+10716,48.69604
+10717,49.209515
+10718,51.803074
+10719,14.305422
+10720,15.211705
+10721,22.03485
+10722,21.240295
+10723,25.575792
+10724,31.176634
+10725,28.296171
+10726,33.880116
+10727,35.225
+10728,38.651463
+10729,40.177063
+10730,43.91455
+10731,8.979962
+10732,10.451361
+10733,12.538458
+10734,15.0138035
+10735,51.11984
+10736,53.622875
+10737,54.961193
+10738,59.53936
+10739,59.749023
+10740,66.305595
+10741,61.103523
+10742,67.26056
+10743,66.53367
+10744,38.291866
+10745,39.12072
+10746,43.53936
+10747,48.74567
+10748,50.238888
+10749,55.73906
+10750,56.20872
+10751,57.611694
+10752,58.52701
+10753,60.63656
+10754,60.9912
+10755,61.59497
+10756,3.3484888
+10757,6.3612747
+10758,9.496159
+10759,8.134937
+10760,10.26081
+10761,12.278784
+10762,14.271938
+10763,15.893613
+10764,19.258572
+10765,36.291023
+10766,37.224934
+10767,40.24982
+10768,42.154705
+10769,44.744144
+10770,50.27703
+10771,51.571274
+10772,51.471085
+10773,53.01402
+10774,54.451893
+10775,56.603664
+10776,57.984455
+10777,18.969461
+10778,22.031963
+10779,23.675232
+10780,26.334944
+10781,28.769024
+10782,30.974089
+10783,34.502205
+10784,36.56551
+10785,41.262886
+10786,39.3832
+10787,42.744358
+10788,44.344543
+10789,12.413714
+10790,14.64292
+10791,15.704519
+10792,23.080194
+10793,14.10188
+10794,16.301435
+10795,17.387445
+10796,17.140268
+10797,18.273136
+10798,21.68423
+10799,21.51347
+10800,25.827415
+10801,28.306017
+10802,30.656883
+10803,30.554031
+10804,32.087677
+10805,43.980034
+10806,58.339554
+10807,58.758675
+10808,62.127018
+10809,29.46199
+10810,30.59273
+10811,30.089157
+10812,34.382244
+10813,27.262478
+10814,28.524147
+10815,29.558624
+10816,29.780352
+10817,17.042385
+10818,24.737064
+10819,26.400621
+10820,27.16974
+10821,27.799809
+10822,28.546768
+10823,35.4937
+10824,35.259487
+10825,38.584053
+10826,42.390263
+10827,45.6966
+10828,47.138905
+10829,19.474724
+10830,21.91148
+10831,21.964815
+10832,25.673313
+10833,27.86574
+10834,30.333496
+10835,34.39078
+10836,39.31472
+10837,-0.08337516
+10838,0.30667105
+10839,0.73343325
+10840,1.7712629
+10841,5.2692013
+10842,9.295656
+10843,10.8377495
+10844,19.536285
+10845,22.652296
+10846,30.851664
+10847,30.000473
+10848,31.145912
+10849,31.328218
+10850,4.1742215
+10851,5.2677736
+10852,5.9623966
+10853,8.815641
+10854,10.744892
+10855,13.970809
+10856,21.387829
+10857,23.333115
+10858,24.883968
+10859,22.521471
+10860,24.864603
+10861,27.332062
+10862,49.076477
+10863,51.622417
+10864,53.139008
+10865,58.79022
+10866,60.512054
+10867,62.977005
+10868,63.804478
+10869,65.33529
+10870,67.531334
+10871,70.04284
+10872,72.65287
+10873,74.30717
+10874,20.474022
+10875,22.509594
+10876,29.204346
+10877,39.028797
+10878,38.43976
+10879,39.739895
+10880,41.235367
+10881,42.3235
+10882,43.555916
+10883,45.218246
+10884,46.14571
+10885,49.146667
+10886,48.485703
+10887,48.71901
+10888,52.099155
+10889,53.647476
+10890,16.176088
+10891,18.2032
+10892,18.565477
+10893,23.564312
+10894,24.15709
+10895,25.478718
+10896,26.345491
+10897,29.80958
+10898,34.022964
+10899,36.42419
+10900,41.03879
+10901,43.125034
+10902,17.718456
+10903,19.348587
+10904,21.020947
+10905,24.77238
+10906,22.99422
+10907,24.774097
+10908,27.47509
+10909,34.343636
+10910,38.749367
+10911,38.59917
+10912,37.35169
+10913,39.549946
+10914,42.640617
+10915,38.65645
+10916,43.807404
+10917,46.054474
+10918,20.962004
+10919,20.978243
+10920,23.77756
+10921,23.206911
+10922,22.855362
+10923,27.230164
+10924,29.342775
+10925,29.769182
+10926,29.785366
+10927,33.86935
+10928,33.614796
+10929,39.370514
+10930,22.849194
+10931,33.33506
+10932,32.722874
+10933,30.03003
+10934,34.02152
+10935,36.78397
+10936,38.543953
+10937,16.412931
+10938,17.794025
+10939,20.052938
+10940,26.820827
+10941,27.46773
+10942,33.20228
+10943,39.320442
+10944,36.388348
+10945,39.104637
+10946,38.848797
+10947,41.306297
+10948,39.363705
+10949,32.63417
+10950,33.563374
+10951,39.659374
+10952,43.50921
+10953,44.4445
+10954,47.369022
+10955,44.803146
+10956,49.778366
+10957,48.821835
+10958,16.680014
+10959,18.560608
+10960,22.249664
+10961,23.056059
+10962,26.298613
+10963,32.268497
+10964,35.036068
+10965,39.02818
+10966,43.4124
+10967,49.68885
+10968,51.703926
+10969,50.200962
+10970,34.03297
+10971,34.808712
+10972,36.714687
+10973,43.53998
+10974,45.942795
+10975,48.665844
+10976,46.125412
+10977,52.09388
+10978,51.44457
+10979,50.665363
+10980,53.16345
+10981,54.132378
+10982,7.72214
+10983,8.8871975
+10984,9.518896
+10985,10.672656
+10986,13.80026
+10987,17.911102
+10988,22.279226
+10989,23.713688
+10990,19.481106
+10991,25.15863
+10992,27.189346
+10993,29.631922
+10994,37.88492
+10995,44.613476
+10996,46.993492
+10997,48.82361
+10998,53.66465
+10999,55.102993
+11000,54.387367
+11001,41.45995
+11002,42.84216
+11003,45.420677
+11004,48.597588
+11005,48.23063
+11006,50.422676
+11007,49.983276
+11008,55.15331
+11009,54.70858
+11010,55.951992
+11011,56.31971
+11012,58.779537
+11013,62.6099
+11014,66.01525
+11015,67.709
+11016,70.24504
+11017,18.47438
+11018,20.585152
+11019,21.82839
+11020,28.294468
+11021,30.107412
+11022,34.271236
+11023,33.735134
+11024,39.313133
+11025,41.31724
+11026,26.444986
+11027,29.779818
+11028,26.659496
+11029,31.438488
+11030,30.750317
+11031,29.719584
+11032,29.921719
+11033,50.483475
+11034,57.122913
+11035,57.59828
+11036,59.196198
+11037,58.64093
+11038,62.704704
+11039,23.838245
+11040,25.496754
+11041,29.878185
+11042,33.906075
+11043,37.970413
+11044,42.199734
+11045,41.29885
+11046,50.31472
+11047,48.24244
+11048,50.04661
+11049,52.265694
+11050,55.115295
+11051,9.445038
+11052,10.539621
+11053,14.62565
+11054,22.060368
+11055,15.018799
+11056,17.286346
+11057,19.685204
+11058,23.579433
+11059,24.86747
+11060,29.558884
+11061,33.88314
+11062,36.25264
+11063,36.826305
+11064,39.469006
+11065,45.5746
+11066,49.98639
+11067,39.60379
+11068,44.54234
+11069,47.71061
+11070,48.764538
+11071,54.00332
+11072,56.12956
+11073,54.427788
+11074,60.329887
+11075,61.071537
+11076,62.06848
+11077,65.269394
+11078,25.79804
+11079,26.724049
+11080,27.028786
+11081,31.911858
+11082,32.362045
+11083,33.1504
+11084,38.732773
+11085,40.714985
+11086,41.04575
+11087,46.012264
+11088,47.340134
+11089,50.668163
+11090,31.6748
+11091,32.24059
+11092,32.24156
+11093,35.828682
+11094,34.452465
+11095,36.439598
+11096,39.371487
+11097,41.79649
+11098,41.700405
+11099,46.479927
+11100,47.01746
+11101,49.685238
+11102,30.794981
+11103,32.395546
+11104,36.905678
+11105,38.099197
+11106,42.057335
+11107,43.183964
+11108,43.86569
+11109,47.051296
+11110,48.86242
+11111,51.71818
+11112,55.337666
+11113,52.8787
+11114,39.117832
+11115,42.39308
+11116,42.51889
+11117,46.14926
+11118,49.074074
+11119,51.495335
+11120,56.090675
+11121,56.09533
+11122,56.776497
+11123,60.66825
+11124,60.608322
+11125,63.432213
+11126,50.947308
+11127,52.125084
+11128,49.64061
+11129,52.47035
+11130,55.89871
+11131,59.831352
+11132,57.011497
+11133,59.576103
+11134,56.98132
+11135,59.78206
+11136,59.44097
+11137,63.403934
+11138,22.260178
+11139,26.358263
+11140,31.662563
+11141,34.19484
+11142,37.66672
+11143,42.312565
+11144,46.731136
+11145,45.8859
+11146,47.107204
+11147,50.800278
+11148,51.246826
+11149,52.239277
+11150,29.920225
+11151,30.414501
+11152,32.297646
+11153,35.890495
+11154,39.992622
+11155,33.42945
+11156,34.70705
+11157,43.65982
+11158,44.031887
+11159,41.88932
+11160,44.41392
+11161,46.209023
+11162,46.380745
+11163,47.99439
+11164,48.482384
+11165,50.257
+11166,13.79891
+11167,14.429443
+11168,16.74116
+11169,20.362299
+11170,23.128174
+11171,25.884876
+11172,28.436304
+11173,37.841835
+11174,41.016876
+11175,43.7977
+11176,44.88451
+11177,54.57207
+11178,57.52598
+11179,59.13866
+11180,60.90429
+11181,4.691183
+11182,15.607883
+11183,16.598858
+11184,19.023165
+11185,34.574047
+11186,34.892155
+11187,36.924538
+11188,42.952827
+11189,45.66105
+11190,52.084408
+11191,51.039608
+11192,49.600494
+11193,55.1613
+11194,56.23938
+11195,56.553444
+11196,18.368446
+11197,19.805058
+11198,20.837393
+11199,23.566631
+11200,28.432083
+11201,32.17453
+11202,27.3162
+11203,37.970444
+11204,42.26074
+11205,44.149227
+11206,47.705242
+11207,49.057102
+11208,50.700832
+11209,54.873165
+11210,55.683834
+11211,56.473743
+11212,58.956665
+11213,31.442024
+11214,33.96988
+11215,36.498543
+11216,40.437332
+11217,42.67207
+11218,47.150024
+11219,49.91262
+11220,53.34959
+11221,55.83432
+11222,57.02627
+11223,60.993687
+11224,61.62194
+11225,22.37397
+11226,27.121618
+11227,30.8201
+11228,31.33366
+11229,32.31982
+11230,30.324167
+11231,39.20546
+11232,43.638245
+11233,43.52924
+11234,47.03694
+11235,49.42168
+11236,49.595707
+11237,25.101397
+11238,26.738728
+11239,29.67777
+11240,31.19754
+11241,33.194294
+11242,33.545364
+11243,21.59322
+11244,22.627903
+11245,32.226513
+11246,37.480904
+11247,34.372555
+11248,35.307564
+11249,37.499653
+11250,39.88123
+11251,41.919044
+11252,45.33136
+11253,44.81272
+11254,45.790016
+11255,53.12111
+11256,47.94331
+11257,51.245056
+11258,54.630844
+11259,13.199228
+11260,17.33099
+11261,15.520569
+11262,19.306126
+11263,20.95022
+11264,28.565296
+11265,31.13937
+11266,29.758614
+11267,36.065548
+11268,38.743866
+11269,52.73401
+11270,55.367813
+11271,27.261652
+11272,28.631758
+11273,28.691462
+11274,31.000372
+11275,29.813011
+11276,32.55274
+11277,35.075813
+11278,38.425056
+11279,40.318314
+11280,39.72515
+11281,43.196922
+11282,43.855324
+11283,0.15780409
+11284,-0.18873596
+11285,0.5735654
+11286,1.5892609
+11287,1.822494
+11288,54.539207
+11289,55.11687
+11290,55.88322
+11291,60.87462
+11292,62.975075
+11293,63.5837
+11294,64.97268
+11295,24.602333
+11296,29.132902
+11297,31.690128
+11298,31.279888
+11299,38.336533
+11300,40.08507
+11301,42.712013
+11302,47.757008
+11303,46.709198
+11304,50.743176
+11305,50.483734
+11306,53.655315
+11307,20.822945
+11308,22.171036
+11309,27.250502
+11310,34.677513
+11311,36.146545
+11312,34.209095
+11313,37.119102
+11314,41.443268
+11315,42.312748
+11316,41.716305
+11317,43.92177
+11318,45.55983
+11319,3.8401756
+11320,3.4698317
+11321,10.11559
+11322,12.937949
+11323,15.105224
+11324,14.943628
+11325,14.4919815
+11326,16.500069
+11327,17.487282
+11328,21.784334
+11329,21.80542
+11330,24.522018
+11331,40.711052
+11332,41.65677
+11333,47.98915
+11334,47.36818
+11335,49.27772
+11336,53.937714
+11337,55.41211
+11338,55.932053
+11339,57.008713
+11340,58.505802
+11341,63.18729
+11342,59.724148
+11343,23.039333
+11344,26.485096
+11345,34.389027
+11346,38.07168
+11347,38.954647
+11348,45.997242
+11349,51.01372
+11350,53.075844
+11351,11.431078
+11352,13.62698
+11353,16.180819
+11354,24.479313
+11355,27.93237
+11356,70.337685
+11357,72.299
+11358,77.72834
+11359,87.57104
+11360,40.54532
+11361,47.41736
+11362,50.486595
+11363,57.50189
+11364,56.342842
+11365,60.303062
+11366,61.567387
+11367,62.485855
+11368,62.431366
+11369,65.32572
+11370,64.49773
+11371,65.46357
+11372,38.14613
+11373,41.69176
+11374,44.542965
+11375,50.262196
+11376,51.97925
+11377,55.919697
+11378,62.40947
+11379,60.220535
+11380,63.754784
+11381,65.80281
+11382,65.19267
+11383,67.21556
+11384,58.317863
+11385,60.384575
+11386,62.602295
+11387,62.012497
+11388,39.665634
+11389,44.47831
+11390,41.670105
+11391,43.78441
+11392,45.179375
+11393,48.953873
+11394,48.50969
+11395,51.353443
+11396,56.114372
+11397,56.51665
+11398,57.735603
+11399,14.073391
+11400,15.55199
+11401,16.189676
+11402,26.899609
+11403,30.08873
+11404,27.872725
+11405,35.278137
+11406,30.575262
+11407,26.590761
+11408,31.030022
+11409,33.200874
+11410,39.15842
+11411,51.417427
+11412,57.61609
+11413,57.10373
+11414,62.954887
+11415,64.457436
+11416,65.27173
+11417,64.64966
+11418,68.073685
+11419,67.01643
+11420,71.05915
+11421,68.66253
+11422,68.437836
+11423,10.602213
+11424,13.293
+11425,14.354513
+11426,15.139464
+11427,20.311802
+11428,21.837887
+11429,25.490166
+11430,28.746222
+11431,34.150078
+11432,35.537395
+11433,15.488052
+11434,19.183634
+11435,22.802982
+11436,25.73272
+11437,26.604355
+11438,32.63703
+11439,42.314697
+11440,43.1439
+11441,44.768692
+11442,47.107693
+11443,45.228928
+11444,53.604027
+11445,14.217308
+11446,18.346033
+11447,22.137447
+11448,23.768429
+11449,29.55907
+11450,28.632984
+11451,32.442616
+11452,36.63615
+11453,39.185707
+11454,40.443077
+11455,45.49324
+11456,51.34323
+11457,46.685165
+11458,48.68196
+11459,55.418507
+11460,57.18926
+11461,27.003101
+11462,29.08386
+11463,29.351515
+11464,31.328915
+11465,7.896501
+11466,13.4752445
+11467,14.813425
+11468,17.099815
+11469,14.520584
+11470,19.58707
+11471,21.26889
+11472,22.80359
+11473,17.082218
+11474,17.948284
+11475,20.649502
+11476,22.228922
+11477,24.745445
+11478,30.13054
+11479,34.229134
+11480,34.145035
+11481,41.24961
+11482,39.970592
+11483,45.116405
+11484,45.358013
+11485,12.567905
+11486,16.021162
+11487,23.491163
+11488,26.100899
+11489,25.385826
+11490,34.0262
+11491,36.16544
+11492,39.67218
+11493,39.746243
+11494,41.509064
+11495,39.678425
+11496,3.830868
+11497,5.7492924
+11498,8.829739
+11499,10.308929
+11500,13.632566
+11501,14.161769
+11502,14.578618
+11503,21.164194
+11504,23.102402
+11505,24.292006
+11506,26.457277
+11507,46.662163
+11508,48.511703
+11509,46.746128
+11510,48.12497
+11511,50.517223
+11512,51.794144
+11513,54.086155
+11514,51.719585
+11515,55.449287
+11516,55.292587
+11517,55.808006
+11518,58.89342
+11519,21.76729
+11520,23.008837
+11521,27.987898
+11522,35.17663
+11523,36.91423
+11524,34.61246
+11525,38.042603
+11526,41.99549
+11527,41.57549
+11528,45.698418
+11529,48.75939
+11530,49.776352
+11531,31.222801
+11532,35.80637
+11533,48.862656
+11534,49.47714
+11535,42.133167
+11536,45.029003
+11537,48.52584
+11538,48.878235
+11539,56.44902
+11540,54.905643
+11541,56.997715
+11542,59.606007
+11543,8.764466
+11544,8.807466
+11545,9.851316
+11546,17.88827
+11547,20.566753
+11548,24.223436
+11549,23.014118
+11550,18.560345
+11551,25.804523
+11552,27.718048
+11553,27.399681
+11554,28.619991
+11555,48.901897
+11556,48.564945
+11557,48.451416
+11558,49.516792
+11559,44.561428
+11560,44.127014
+11561,48.687584
+11562,53.62791
+11563,54.454967
+11564,18.438692
+11565,21.72519
+11566,21.661816
+11567,28.456135
+11568,29.928745
+11569,33.346653
+11570,32.887604
+11571,36.850327
+11572,37.350445
+11573,38.660233
+11574,40.842384
+11575,43.20198
+11576,51.25389
+11577,55.93212
+11578,54.40083
+11579,58.256607
+11580,66.64476
+11581,59.245724
+11582,63.872337
+11583,19.354975
+11584,20.571705
+11585,19.711893
+11586,21.990568
+11587,23.992981
+11588,23.339064
+11589,23.757397
+11590,25.675236
+11591,27.349783
+11592,31.27492
+11593,43.608547
+11594,42.376205
+11595,39.672234
+11596,43.86495
+11597,44.23991
+11598,50.707764
+11599,56.13367
+11600,23.382797
+11601,23.033817
+11602,28.966911
+11603,32.417435
+11604,35.687897
+11605,38.27959
+11606,41.610382
+11607,46.84736
+11608,49.227776
+11609,50.204716
+11610,55.605286
+11611,57.16935
+11612,29.153175
+11613,31.565727
+11614,37.32375
+11615,41.88833
+11616,44.1423
+11617,47.454254
+11618,50.953655
+11619,51.029877
+11620,51.867977
+11621,54.55621
+11622,58.062218
+11623,56.793877
+11624,41.831337
+11625,46.173016
+11626,50.480225
+11627,55.81969
+11628,56.99024
+11629,59.283714
+11630,62.53891
+11631,62.83097
+11632,63.25643
+11633,64.81942
+11634,65.839325
+11635,70.033325
+11636,29.141562
+11637,29.608545
+11638,31.338188
+11639,37.62526
+11640,34.68506
+11641,37.730892
+11642,44.1743
+11643,55.629906
+11644,66.603775
+11645,38.124855
+11646,39.867714
+11647,43.748657
+11648,42.929077
+11649,49.02974
+11650,56.27863
+11651,62.123844
+11652,64.914
+11653,67.059364
+11654,69.392685
+11655,71.275276
+11656,70.595215
+11657,22.466
+11658,27.078564
+11659,30.187565
+11660,31.830713
+11661,34.677822
+11662,37.20356
+11663,38.942146
+11664,48.78865
+11665,49.51097
+11666,49.712902
+11667,52.590122
+11668,53.82148
+11669,58.09262
+11670,56.891422
+11671,60.434963
+11672,65.13883
+11673,39.90954
+11674,41.986446
+11675,45.86843
+11676,48.390907
+11677,52.129795
+11678,54.811016
+11679,59.132812
+11680,59.92346
+11681,59.583614
+11682,61.194412
+11683,60.92442
+11684,62.86998
+11685,31.206884
+11686,36.2321
+11687,38.697693
+11688,40.951046
+11689,46.871635
+11690,50.41787
+11691,58.927357
+11692,15.714387
+11693,18.575272
+11694,25.785027
+11695,32.256805
+11696,28.208923
+11697,29.02728
+11698,29.976072
+11699,31.117517
+11700,32.418636
+11701,34.313107
+11702,32.549294
+11703,31.819813
+11704,33.326385
+11705,37.122787
+11706,36.984016
+11707,39.497604
+11708,25.42425
+11709,29.449886
+11710,32.059914
+11711,35.761578
+11712,45.763855
+11713,49.313705
+11714,52.495865
+11715,58.5963
+11716,63.311497
+11717,63.985672
+11718,65.73012
+11719,68.51143
+11720,67.53019
+11721,70.53846
+11722,72.55963
+11723,72.18167
+11724,9.560768
+11725,10.172817
+11726,18.751118
+11727,21.71106
+11728,20.95739
+11729,24.396723
+11730,25.40286
+11731,28.688408
+11732,33.524296
+11733,29.975557
+11734,38.373737
+11735,42.837067
+11736,38.846596
+11737,41.91006
+11738,47.63977
+11739,45.30191
+11740,48.097305
+11741,51.18198
+11742,49.952427
+11743,52.601143
+11744,55.301464
+11745,22.917656
+11746,29.329586
+11747,30.150017
+11748,34.585503
+11749,39.762047
+11750,37.621494
+11751,41.589634
+11752,45.39366
+11753,50.837627
+11754,8.112312
+11755,11.654395
+11756,13.858396
+11757,15.154186
+11758,18.157944
+11759,19.674551
+11760,44.424026
+11761,47.668873
+11762,51.17822
+11763,55.803734
+11764,54.83681
+11765,59.11554
+11766,60.78756
+11767,61.616055
+11768,62.918888
+11769,63.379112
+11770,67.750114
+11771,66.312004
+11772,18.105694
+11773,23.319283
+11774,24.083384
+11775,23.37318
+11776,26.634033
+11777,38.32893
+11778,39.581543
+11779,40.55293
+11780,45.182014
+11781,47.74042
+11782,49.729916
+11783,14.461699
+11784,17.554647
+11785,18.34562
+11786,22.682497
+11787,30.874557
+11788,37.918774
+11789,33.761826
+11790,33.706356
+11791,36.995796
+11792,43.193462
+11793,45.90172
+11794,42.800793
+11795,23.021254
+11796,32.039894
+11797,32.97287
+11798,36.682564
+11799,19.766642
+11800,24.189116
+11801,27.525742
+11802,32.633034
+11803,38.216965
+11804,39.454296
+11805,43.17417
+11806,45.41028
+11807,51.08089
+11808,33.682228
+11809,32.528175
+11810,36.02687
+11811,40.059406
+11812,42.56052
+11813,42.38521
+11814,41.852566
+11815,45.833412
+11816,46.550007
+11817,46.54359
+11818,49.879192
+11819,22.480915
+11820,23.92443
+11821,25.973217
+11822,27.168852
+11823,34.820362
+11824,36.60285
+11825,38.187153
+11826,41.886726
+11827,43.878883
+11828,45.581673
+11829,45.555668
+11830,47.79748
+11831,17.492971
+11832,22.397005
+11833,26.812876
+11834,30.724371
+11835,37.233814
+11836,12.253428
+11837,11.7003975
+11838,12.68162
+11839,11.847364
+11840,13.497737
+11841,4.9312153
+11842,6.7180705
+11843,12.337909
+11844,13.620836
+11845,20.181894
+11846,23.166552
+11847,24.812101
+11848,25.829014
+11849,28.876558
+11850,28.532393
+11851,31.24504
+11852,3.4262352
+11853,9.233494
+11854,11.563584
+11855,11.92741
+11856,16.993122
+11857,19.867632
+11858,21.952553
+11859,22.649584
+11860,22.151567
+11861,28.173952
+11862,31.59766
+11863,33.289864
+11864,33.221607
+11865,37.687046
+11866,39.73819
+11867,41.123947
+11868,42.076496
+11869,43.047943
+11870,44.709988
+11871,47.80409
+11872,48.20286
+11873,49.95686
+11874,49.942757
+11875,51.112236
+11876,6.7726707
+11877,8.059229
+11878,11.246431
+11879,13.999967
+11880,15.816837
+11881,39.93431
+11882,40.128487
+11883,42.80371
+11884,44.90444
+11885,50.891376
+11886,52.170788
+11887,60.87547
+11888,64.91357
+11889,59.208
+11890,63.012875
+11891,65.06633
+11892,70.52547
+11893,17.93447
+11894,26.243193
+11895,28.626064
+11896,22.373468
+11897,28.137255
+11898,33.959698
+11899,44.68071
+11900,32.21635
+11901,36.787163
+11902,38.504837
+11903,40.265762
+11904,41.734795
+11905,46.600613
+11906,48.28576
+11907,49.27585
+11908,48.79822
+11909,54.785408
+11910,51.624336
+11911,53.910866
+11912,8.201463
+11913,10.377005
+11914,15.04889
+11915,18.74899
+11916,22.24741
+11917,24.536037
+11918,26.65956
+11919,29.671185
+11920,30.449993
+11921,36.322395
+11922,39.70057
+11923,43.69355
+11924,47.03592
+11925,46.679565
+11926,48.653687
+11927,49.99244
+11928,20.844631
+11929,28.737135
+11930,32.738625
+11931,34.847233
+11932,16.465063
+11933,19.178123
+11934,23.343979
+11935,37.842705
+11936,21.641794
+11937,21.369516
+11938,21.778112
+11939,23.207193
+11940,23.392105
+11941,28.374823
+11942,29.55786
+11943,30.911009
+11944,33.50886
+11945,34.55631
+11946,38.162136
+11947,38.75943
+11948,10.770661
+11949,13.036555
+11950,15.40682
+11951,17.804508
+11952,20.580595
+11953,28.514565
+11954,28.972158
+11955,34.457417
+11956,33.29905
+11957,37.68357
+11958,36.808834
+11959,37.788757
+11960,1.2499316
+11961,1.6699595
+11962,4.2276344
+11963,7.5817337
+11964,10.1120205
+11965,45.97935
+11966,52.320942
+11967,58.03769
+11968,60.04402
+11969,63.424072
+11970,9.123457
+11971,13.806177
+11972,21.17521
+11973,25.360043
+11974,35.578278
+11975,17.628437
+11976,18.812012
+11977,23.476263
+11978,28.119692
+11979,33.81526
+11980,0.4774116
+11981,2.7824914
+11982,5.054901
+11983,12.243189
+11984,39.84307
+11985,41.623104
+11986,43.615414
+11987,44.991035
+11988,45.735542
+11989,46.629875
+11990,30.20264
+11991,35.08744
+11992,35.383175
+11993,44.342003
+11994,46.481815
+11995,20.253902
+11996,20.127335
+11997,24.35232
+11998,26.0485
+11999,35.63084
+12000,41.907604
+12001,46.198246
+12002,51.06079
+12003,54.421783
+12004,56.9186
+12005,22.338367
+12006,27.348732
+12007,30.249443
+12008,30.757101
+12009,34.077217
+12010,33.63495
+12011,33.153328
+12012,36.907463
+12013,40.979885
+12014,39.86177
+12015,40.654396
+12016,14.345321
+12017,17.710688
+12018,19.614298
+12019,24.730928
+12020,26.814564
+12021,26.781267
+12022,29.297756
+12023,32.54401
+12024,34.5458
+12025,37.98888
+12026,38.29231
+12027,41.81413
+12028,15.704973
+12029,19.184248
+12030,22.49745
+12031,23.41624
+12032,26.255985
+12033,27.035719
+12034,33.601746
+12035,36.22061
+12036,41.11863
+12037,41.370758
+12038,42.63832
+12039,47.682262
+12040,42.766632
+12041,48.548615
+12042,52.651844
+12043,54.309517
+12044,53.888966
+12045,59.82214
+12046,62.128998
+12047,63.117874
+12048,66.14904
+12049,65.667984
+12050,66.59955
+12051,67.05771
+12052,7.697152
+12053,10.693933
+12054,11.648582
+12055,13.788285
+12056,23.892673
+12057,26.064655
+12058,25.83135
+12059,28.358505
+12060,32.829624
+12061,37.697517
+12062,36.167374
+12063,40.763832
+12064,43.20595
+12065,45.365818
+12066,45.89603
+12067,45.768867
+12068,38.443237
+12069,48.92978
+12070,58.132507
+12071,56.792503
+12072,11.22068
+12073,13.692574
+12074,13.170365
+12075,22.455524
+12076,7.7793045
+12077,8.609194
+12078,8.533653
+12079,10.978533
+12080,10.491646
+12081,12.548301
+12082,13.69557
+12083,15.993661
+12084,16.4567
+12085,8.482718
+12086,9.631977
+12087,11.760941
+12088,12.447042
+12089,13.857527
+12090,17.151224
+12091,18.775728
+12092,19.76862
+12093,24.058895
+12094,28.850689
+12095,25.694141
+12096,29.284245
+12097,28.017876
+12098,36.119778
+12099,39.91982
+12100,42.96288
+12101,34.717255
+12102,38.357502
+12103,42.884354
+12104,44.17668
+12105,5.073614
+12106,7.361162
+12107,10.611427
+12108,11.163023
+12109,14.5178385
+12110,17.66571
+12111,20.949703
+12112,20.291798
+12113,27.631973
+12114,32.687798
+12115,35.794964
+12116,36.82431
+12117,38.046543
+12118,38.911842
+12119,38.7443
+12120,40.761955
+12121,43.217636
+12122,42.444878
+12123,44.764015
+12124,47.02284
+12125,48.285763
+12126,51.366432
+12127,54.238167
+12128,56.032223
+12129,24.161768
+12130,30.028067
+12131,31.659094
+12132,31.08631
+12133,10.851885
+12134,14.186997
+12135,16.6332
+12136,22.6995
+12137,18.73584
+12138,24.965313
+12139,27.551302
+12140,27.633038
+12141,31.389862
+12142,31.783743
+12143,36.60302
+12144,38.62562
+12145,39.94474
+12146,47.464165
+12147,45.731148
+12148,49.785572
+12149,1.0227222
+12150,3.0059147
+12151,4.7632117
+12152,5.6971145
+12153,10.58814
+12154,9.638332
+12155,38.41227
+12156,41.896286
+12157,43.417427
+12158,44.49602
+12159,30.236881
+12160,37.399555
+12161,40.11461
+12162,35.457424
+12163,40.894684
+12164,39.152428
+12165,43.15883
+12166,46.81874
+12167,52.168217
+12168,53.3028
+12169,57.836006
+12170,10.79189
+12171,11.937646
+12172,14.375113
+12173,15.667197
+12174,19.181602
+12175,19.603611
+12176,18.650082
+12177,23.206936
+12178,23.863123
+12179,25.979425
+12180,25.958176
+12181,31.741062
+12182,10.853584
+12183,12.543552
+12184,14.289371
+12185,19.40835
+12186,22.511574
+12187,20.726463
+12188,21.74207
+12189,29.021614
+12190,30.51444
+12191,29.665855
+12192,33.179134
+12193,38.034267
+12194,26.087667
+12195,29.055481
+12196,33.55403
+12197,37.94552
+12198,42.31585
+12199,42.98809
+12200,45.35978
+12201,47.105427
+12202,47.91929
+12203,52.5042
+12204,56.05998
+12205,57.64235
+12206,18.431108
+12207,22.67115
+12208,25.020344
+12209,26.679539
+12210,28.258745
+12211,33.350353
+12212,36.997784
+12213,40.927116
+12214,43.223827
+12215,42.950104
+12216,48.536526
+12217,53.86441
+12218,37.06951
+12219,40.095634
+12220,42.075253
+12221,43.801483
+12222,23.834143
+12223,26.45697
+12224,28.571331
+12225,30.700369
+12226,35.283848
+12227,51.91179
+12228,54.547714
+12229,56.223824
+12230,58.507027
+12231,60.50879
+12232,64.580124
+12233,65.170135
+12234,64.04306
+12235,66.956085
+12236,66.66047
+12237,69.76996
+12238,68.19956
+12239,44.86754
+12240,51.125923
+12241,50.350723
+12242,51.158585
+12243,50.94954
+12244,52.472065
+12245,54.173088
+12246,57.722588
+12247,56.35886
+12248,59.024193
+12249,59.28165
+12250,61.481796
+12251,33.484764
+12252,42.85041
+12253,46.66127
+12254,44.707745
+12255,45.858135
+12256,48.890312
+12257,53.717937
+12258,55.777786
+12259,54.248055
+12260,56.420605
+12261,58.273544
+12262,58.36006
+12263,25.826973
+12264,27.454453
+12265,29.156654
+12266,31.363966
+12267,34.993828
+12268,37.849255
+12269,37.13459
+12270,37.67376
+12271,38.06057
+12272,42.850163
+12273,45.077255
+12274,45.069984
+12275,20.40042
+12276,22.299116
+12277,21.32825
+12278,26.13708
+12279,28.889072
+12280,31.088331
+12281,36.36991
+12282,41.116158
+12283,42.691624
+12284,43.561035
+12285,58.37484
+12286,59.075813
+12287,29.915163
+12288,29.489258
+12289,31.550158
+12290,31.478685
+12291,33.37935
+12292,12.809973
+12293,20.806675
+12294,21.17041
+12295,18.400473
+12296,20.182686
+12297,23.285435
+12298,25.210327
+12299,27.310627
+12300,29.496414
+12301,29.1189
+12302,29.444862
+12303,32.086735
+12304,14.555842
+12305,18.619112
+12306,21.461798
+12307,23.089218
+12308,22.116302
+12309,27.228144
+12310,31.848225
+12311,34.587563
+12312,37.134148
+12313,38.680046
+12314,43.633846
+12315,44.175735
+12316,25.195992
+12317,29.385597
+12318,31.978691
+12319,38.577618
+12320,8.419758
+12321,10.412909
+12322,12.207042
+12323,18.210283
+12324,28.861752
+12325,8.949483
+12326,14.903669
+12327,23.100647
+12328,25.460594
+12329,22.939903
+12330,27.426603
+12331,32.343666
+12332,33.417282
+12333,37.24624
+12334,38.77596
+12335,39.395805
+12336,39.24913
+12337,31.62825
+12338,34.17097
+12339,36.848763
+12340,38.52089
+12341,42.913197
+12342,44.199673
+12343,47.319305
+12344,21.925518
+12345,27.788334
+12346,31.84307
+12347,33.55615
+12348,32.98694
+12349,21.826488
+12350,26.008852
+12351,37.732006
+12352,44.519424
+12353,22.001423
+12354,23.497385
+12355,25.78236
+12356,31.475689
+12357,36.005173
+12358,39.78375
+12359,28.37476
+12360,32.191612
+12361,32.407654
+12362,35.4567
+12363,36.72899
+12364,42.43418
+12365,54.728546
+12366,53.663967
+12367,56.74418
+12368,59.445652
+12369,34.805626
+12370,40.276917
+12371,44.409676
+12372,48.19685
+12373,52.707954
+12374,31.421803
+12375,37.825253
+12376,41.17404
+12377,45.74401
+12378,48.321842
+12379,53.242996
+12380,54.94844
+12381,59.227894
+12382,59.963043
+12383,64.14501
+12384,64.476135
+12385,66.71046
+12386,24.375916
+12387,22.507063
+12388,23.579617
+12389,22.375647
+12390,24.367493
+12391,24.892014
+12392,24.698378
+12393,24.562286
+12394,24.51502
+12395,27.609993
+12396,30.151423
+12397,52.31285
+12398,52.451218
+12399,53.533897
+12400,59.147617
+12401,0.36604103
+12402,0.6822517
+12403,0.44468787
+12404,0.4531631
+12405,25.001217
+12406,30.373468
+12407,32.878258
+12408,34.778465
+12409,40.282364
+12410,43.600773
+12411,47.383377
+12412,15.371448
+12413,12.964991
+12414,14.877983
+12415,20.31013
+12416,26.300701
+12417,30.2476
+12418,26.0363
+12419,29.72992
+12420,31.965714
+12421,37.636787
+12422,37.013794
+12423,37.380302
+12424,4.1476383
+12425,5.6722918
+12426,9.011908
+12427,9.785299
+12428,14.26996
+12429,17.033926
+12430,16.519787
+12431,21.210217
+12432,22.924236
+12433,23.95149
+12434,24.876486
+12435,47.539574
+12436,48.640198
+12437,51.20562
+12438,54.16808
+12439,33.811646
+12440,32.3275
+12441,34.63237
+12442,34.871887
+12443,34.267994
+12444,40.020195
+12445,35.423584
+12446,38.836678
+12447,38.09579
+12448,41.668297
+12449,14.256176
+12450,16.48275
+12451,20.502375
+12452,21.469707
+12453,28.309351
+12454,34.2112
+12455,30.066254
+12456,34.28522
+12457,34.893135
+12458,42.38707
+12459,45.511993
+12460,50.01237
+12461,58.558502
+12462,63.86128
+12463,65.79106
+12464,68.36802
+12465,71.47747
+12466,74.36047
+12467,73.591866
+12468,79.43135
+12469,79.38954
+12470,27.798702
+12471,31.926676
+12472,37.725945
+12473,40.006584
+12474,50.19703
+12475,31.224325
+12476,43.85068
+12477,45.155285
+12478,48.151634
+12479,49.1146
+12480,52.212784
+12481,50.80254
+12482,53.021027
+12483,53.93917
+12484,55.442417
+12485,60.244083
+12486,59.50941
+12487,60.544086
+12488,61.743484
+12489,63.414658
+12490,63.98926
+12491,67.46305
+12492,68.74909
+12493,11.559419
+12494,15.187118
+12495,17.30443
+12496,20.247246
+12497,22.028908
+12498,26.032492
+12499,26.26526
+12500,24.96444
+12501,30.0285
+12502,28.173555
+12503,34.85753
+12504,33.511948
+12505,34.09205
+12506,41.218334
+12507,39.98194
+12508,48.816685
+12509,36.203865
+12510,40.561394
+12511,43.394924
+12512,46.567467
+12513,47.0311
+12514,50.27975
+12515,54.41343
+12516,59.401337
+12517,54.116566
+12518,56.199364
+12519,58.584324
+12520,64.19906
+12521,63.903397
+12522,65.591385
+12523,67.66705
+12524,69.42791
+12525,69.47203
+12526,68.741135
+12527,72.132706
+12528,72.463684
+12529,21.209927
+12530,24.34858
+12531,26.320276
+12532,29.560724
+12533,35.596306
+12534,37.95088
+12535,42.30478
+12536,50.004314
+12537,52.110287
+12538,50.166687
+12539,53.941933
+12540,58.425247
+12541,59.800266
+12542,62.046066
+12543,63.072353
+12544,65.23567
+12545,66.10721
+12546,65.673096
+12547,49.80031
+12548,53.499893
+12549,62.102734
+12550,68.24935
+12551,23.38617
+12552,33.404774
+12553,34.606888
+12554,41.20694
+12555,47.422874
+12556,49.385868
+12557,51.069813
+12558,52.211277
+12559,50.60495
+12560,50.991295
+12561,55.946808
+12562,57.08807
+12563,57.787388
+12564,23.77321
+12565,30.533825
+12566,34.81201
+12567,32.59605
+12568,35.382454
+12569,37.71528
+12570,39.27249
+12571,42.079914
+12572,44.59845
+12573,47.080696
+12574,46.04358
+12575,49.43586
+12576,27.185017
+12577,31.717293
+12578,32.92946
+12579,37.482925
+12580,43.445103
+12581,50.90938
+12582,49.67897
+12583,51.904976
+12584,55.655983
+12585,-0.6066588
+12586,-0.4370569
+12587,0.74025
+12588,3.6800451
+12589,5.672944
+12590,6.947052
+12591,7.545349
+12592,7.4297724
+12593,8.828308
+12594,15.473173
+12595,20.40595
+12596,20.692093
+12597,38.596237
+12598,41.85785
+12599,45.410366
+12600,47.121426
+12601,46.821854
+12602,49.32268
+12603,50.63887
+12604,55.46244
+12605,33.305275
+12606,38.852398
+12607,40.74145
+12608,41.204277
+12609,42.703316
+12610,47.406036
+12611,26.797678
+12612,27.533974
+12613,29.459639
+12614,29.839548
+12615,31.372635
+12616,39.884758
+12617,45.013092
+12618,48.056107
+12619,48.834667
+12620,50.225407
+12621,34.329304
+12622,36.454887
+12623,38.676884
+12624,40.22574
+12625,47.918865
+12626,48.56812
+12627,50.164566
+12628,53.600418
+12629,54.62415
+12630,52.9346
+12631,60.01015
+12632,58.197235
+12633,68.52356
+12634,69.431145
+12635,72.05852
+12636,76.129944
+12637,41.787163
+12638,42.8293
+12639,47.11071
+12640,48.948986
+12641,49.864647
+12642,53.667606
+12643,55.55137
+12644,54.5312
+12645,56.286774
+12646,58.055843
+12647,59.626152
+12648,59.042347
+12649,61.31783
+12650,63.60109
+12651,64.55455
+12652,65.6291
+12653,65.429184
+12654,64.861244
+12655,69.898056
+12656,69.64329
+12657,67.108284
+12658,69.18245
+12659,72.14877
+12660,74.47034
+12661,31.286644
+12662,39.26111
+12663,46.0455
+12664,48.31875
+12665,16.12769
+12666,21.09499
+12667,21.851242
+12668,26.410156
+12669,32.362747
+12670,33.61272
+12671,38.368343
+12672,41.46008
+12673,43.68926
+12674,47.969948
+12675,44.296844
+12676,46.733295
+12677,24.276775
+12678,25.911963
+12679,29.165318
+12680,32.102238
+12681,33.47294
+12682,2.3482203
+12683,3.0581207
+12684,6.149416
+12685,7.5468645
+12686,22.664186
+12687,27.630625
+12688,35.657013
+12689,40.233124
+12690,28.755
+12691,40.9838
+12692,44.64271
+12693,41.096462
+12694,45.83717
+12695,49.799988
+12696,57.73127
+12697,54.567154
+12698,54.195118
+12699,59.66252
+12700,56.99096
+12701,63.164402
+12702,34.490356
+12703,36.977432
+12704,41.09436
+12705,43.920914
+12706,45.99955
+12707,50.292458
+12708,53.773033
+12709,52.32321
+12710,55.447704
+12711,56.215603
+12712,57.29032
+12713,58.294086
+12714,8.737013
+12715,12.3007765
+12716,13.412186
+12717,21.388494
+12718,24.66504
+12719,25.616053
+12720,28.380192
+12721,27.812338
+12722,34.67758
+12723,36.145153
+12724,11.6188755
+12725,14.701621
+12726,17.228357
+12727,18.431028
+12728,21.188236
+12729,22.67115
+12730,16.58047
+12731,18.330431
+12732,20.679514
+12733,22.716732
+12734,25.466415
+12735,25.205431
+12736,25.776836
+12737,26.963045
+12738,29.801884
+12739,29.203909
+12740,32.709873
+12741,27.038433
+12742,33.887947
+12743,35.5599
+12744,34.31594
+12745,38.99214
+12746,39.92611
+12747,42.48047
+12748,49.985233
+12749,53.58904
+12750,52.653946
+12751,56.98704
+12752,63.515953
+12753,84.24292
+12754,89.31381
+12755,87.68208
+12756,89.27762
+12757,90.518265
+12758,93.30711
+12759,93.96625
+12760,95.61305
+12761,98.47347
+12762,96.69153
+12763,96.633
+12764,99.56632
+12765,32.63802
+12766,31.158863
+12767,39.00286
+12768,42.704147
+12769,42.219093
+12770,44.776543
+12771,47.447994
+12772,47.501026
+12773,50.35845
+12774,54.607338
+12775,55.694237
+12776,59.984306
+12777,44.068825
+12778,42.39688
+12779,47.983944
+12780,52.19172
+12781,55.73132
+12782,57.05165
+12783,61.358
+12784,62.268265
+12785,61.547134
+12786,63.69633
+12787,64.897644
+12788,66.75768
+12789,3.706642
+12790,5.5527644
+12791,7.815538
+12792,9.625377
+12793,10.345921
+12794,13.4468775
+12795,13.981543
+12796,16.635616
+12797,18.42871
+12798,21.776983
+12799,28.793276
+12800,28.297953
+12801,28.616936
+12802,27.461418
+12803,30.417706
+12804,35.692474
+12805,43.839077
+12806,47.49724
+12807,52.574066
+12808,10.16016
+12809,13.640119
+12810,15.407473
+12811,15.356008
+12812,20.165071
+12813,20.586817
+12814,23.24101
+12815,30.031784
+12816,30.946949
+12817,32.006405
+12818,32.228302
+12819,36.552635
+12820,16.454079
+12821,22.769024
+12822,25.58648
+12823,24.295437
+12824,62.172825
+12825,63.74913
+12826,64.508736
+12827,66.83059
+12828,66.71637
+12829,65.69074
+12830,69.37603
+12831,69.893486
+12832,72.84718
+12833,74.493004
+12834,73.05924
+12835,76.76202
+12836,23.0688
+12837,25.50683
+12838,27.580515
+12839,28.781414
+12840,61.24407
+12841,64.441025
+12842,65.92985
+12843,69.13213
+12844,34.00656
+12845,33.668823
+12846,35.497955
+12847,39.939674
+12848,41.405735
+12849,42.937172
+12850,43.98706
+12851,46.87935
+12852,45.98284
+12853,32.24583
+12854,34.493237
+12855,41.485683
+12856,44.22022
+12857,45.684395
+12858,1.235548
+12859,0.55152476
+12860,6.015499
+12861,6.3395243
+12862,8.268723
+12863,7.599988
+12864,11.812723
+12865,15.145465
+12866,17.165443
+12867,17.50125
+12868,21.228424
+12869,24.279453
+12870,30.937279
+12871,32.128304
+12872,36.019295
+12873,41.129425
+12874,37.09654
+12875,38.640774
+12876,40.848053
+12877,42.5431
+12878,45.640503
+12879,45.849564
+12880,47.433083
+12881,49.25474
+12882,7.8929462
+12883,11.578491
+12884,13.505737
+12885,15.406104
+12886,32.050777
+12887,44.691845
+12888,48.486412
+12889,44.592224
+12890,44.21963
+12891,48.25848
+12892,49.923523
+12893,52.481842
+12894,55.775093
+12895,60.352116
+12896,60.903404
+12897,62.60788
+12898,62.816525
+12899,65.74241
+12900,65.603226
+12901,66.871376
+12902,38.305622
+12903,54.554295
+12904,63.43776
+12905,70.10919
+12906,34.023434
+12907,36.46592
+12908,35.51317
+12909,40.31997
+12910,19.662561
+12911,33.23175
+12912,36.672573
+12913,35.74551
+12914,24.246426
+12915,23.709972
+12916,25.455963
+12917,29.952602
+12918,33.151688
+12919,29.48913
+12920,30.591213
+12921,31.73799
+12922,18.091433
+12923,18.889763
+12924,22.496984
+12925,23.128191
+12926,21.840223
+12927,26.346909
+12928,29.937328
+12929,34.402668
+12930,44.649975
+12931,47.176765
+12932,46.806557
+12933,46.88603
+12934,49.44135
+12935,13.989977
+12936,17.181932
+12937,22.25013
+12938,24.084774
+12939,25.937588
+12940,32.992786
+12941,34.884544
+12942,38.660778
+12943,19.237299
+12944,19.784492
+12945,19.69186
+12946,21.059807
+12947,22.307688
+12948,32.45063
+12949,33.562183
+12950,34.008144
+12951,36.735085
+12952,23.45938
+12953,30.340347
+12954,33.030865
+12955,32.853085
+12956,37.431473
+12957,42.732567
+12958,40.996124
+12959,44.805122
+12960,47.948048
+12961,50.616505
+12962,53.699165
+12963,53.681526
+12964,12.170024
+12965,13.755751
+12966,23.249565
+12967,24.913612
+12968,22.191051
+12969,26.936924
+12970,30.35556
+12971,29.976406
+12972,34.154118
+12973,33.73191
+12974,36.732857
+12975,13.206959
+12976,14.96713
+12977,19.316463
+12978,21.692684
+12979,24.57943
+12980,24.78584
+12981,27.122719
+12982,30.277431
+12983,33.106476
+12984,34.20552
+12985,39.46477
+12986,36.792305
+12987,40.36479
+12988,6.047782
+12989,6.7818103
+12990,11.859109
+12991,14.5118265
+12992,15.729435
+12993,16.552128
+12994,21.38801
+12995,7.3166094
+12996,9.284439
+12997,7.52629
+12998,11.506316
+12999,13.254623
+13000,15.230905
+13001,16.543613
+13002,21.41731
+13003,21.350452
+13004,25.419607
+13005,26.715988
+13006,26.190914
+13007,54.955666
+13008,56.08285
+13009,57.043804
+13010,62.491734
+13011,45.045338
+13012,50.409367
+13013,51.823177
+13014,49.190327
+13015,50.047253
+13016,56.007465
+13017,58.558598
+13018,57.458427
+13019,60.937122
+13020,60.033646
+13021,21.866907
+13022,23.13797
+13023,26.087954
+13024,25.924852
+13025,30.364803
+13026,29.387222
+13027,33.67288
+13028,37.728592
+13029,41.727806
+13030,46.58971
+13031,34.251007
+13032,32.90223
+13033,35.621605
+13034,37.341206
+13035,37.489895
+13036,37.960777
+13037,41.6968
+13038,44.85579
+13039,44.21264
+13040,49.087395
+13041,50.675484
+13042,51.42103
+13043,7.686846
+13044,12.591672
+13045,16.694704
+13046,19.193985
+13047,16.884197
+13048,18.941692
+13049,20.250841
+13050,23.192514
+13051,21.58831
+13052,23.266394
+13053,25.567776
+13054,26.607988
+13055,27.393776
+13056,27.669413
+13057,29.10544
+13058,19.326536
+13059,22.2251
+13060,23.374504
+13061,32.505547
+13062,30.827827
+13063,31.099468
+13064,36.388058
+13065,33.574326
+13066,37.619175
+13067,43.039455
+13068,15.927168
+13069,21.104847
+13070,21.908918
+13071,22.85463
+13072,30.478462
+13073,65.37197
+13074,63.33889
+13075,67.192566
+13076,66.65241
+13077,68.6358
+13078,1.5435281
+13079,2.2995
+13080,2.787961
+13081,3.5954025
+13082,6.443637
+13083,8.987819
+13084,9.397724
+13085,15.195249
+13086,21.256926
+13087,31.465136
+13088,37.982746
+13089,40.0008
+13090,42.16872
+13091,17.275496
+13092,18.390182
+13093,20.057285
+13094,20.824358
+13095,22.430841
+13096,30.624767
+13097,34.51574
+13098,37.025116
+13099,47.930397
+13100,50.20589
+13101,48.000576
+13102,49.084694
+13103,49.938156
+13104,51.561043
+13105,43.041374
+13106,47.987896
+13107,52.673378
+13108,54.311127
+13109,60.68361
+13110,26.223942
+13111,28.348701
+13112,32.153217
+13113,41.21209
+13114,46.023434
+13115,44.846706
+13116,48.970245
+13117,53.402298
+13118,58.038025
+13119,55.779957
+13120,34.89313
+13121,34.12798
+13122,34.105087
+13123,35.390373
+13124,36.960358
+13125,40.044598
+13126,8.743313
+13127,11.124047
+13128,12.37693
+13129,15.386834
+13130,18.371315
+13131,18.609852
+13132,22.308674
+13133,26.266134
+13134,29.448574
+13135,30.772667
+13136,29.675606
+13137,30.998783
+13138,24.516142
+13139,35.24003
+13140,42.036037
+13141,40.21409
+13142,34.760296
+13143,37.56035
+13144,44.517258
+13145,49.1156
+13146,51.54864
+13147,50.494957
+13148,54.731834
+13149,59.842842
+13150,39.156178
+13151,39.579964
+13152,42.92981
+13153,45.281754
+13154,37.00759
+13155,50.67722
+13156,55.614075
+13157,55.701015
+13158,21.370895
+13159,26.263031
+13160,27.682291
+13161,28.542442
+13162,31.965492
+13163,31.395206
+13164,34.580944
+13165,49.113976
+13166,50.45631
+13167,53.66084
+13168,57.458534
+13169,57.46811
+13170,61.146107
+13171,62.155167
+13172,63.36845
+13173,65.46723
+13174,68.32092
+13175,68.56481
+13176,69.24676
+13177,17.967333
+13178,21.079842
+13179,25.931406
+13180,29.154486
+13181,33.07173
+13182,33.963367
+13183,39.918858
+13184,43.48018
+13185,28.110783
+13186,29.666004
+13187,32.47176
+13188,35.206383
+13189,9.882249
+13190,14.209481
+13191,19.504038
+13192,21.690498
+13193,29.447916
+13194,32.6305
+13195,33.416237
+13196,36.289467
+13197,36.39392
+13198,37.78265
+13199,38.95161
+13200,38.68936
+13201,40.502216
+13202,40.05818
+13203,41.460777
+13204,42.625614
+13205,44.94975
+13206,49.02897
+13207,49.841553
+13208,55.02082
+13209,30.38733
+13210,35.93732
+13211,38.49446
+13212,41.382187
+13213,41.86145
+13214,46.06799
+13215,51.531574
+13216,52.616776
+13217,52.990498
+13218,56.56232
+13219,57.459724
+13220,57.349617
+13221,14.055258
+13222,16.42656
+13223,19.311134
+13224,25.460112
+13225,27.776623
+13226,32.51911
+13227,36.747776
+13228,33.434486
+13229,38.210716
+13230,39.924603
+13231,38.73295
+13232,24.835867
+13233,26.286541
+13234,32.711327
+13235,34.452972
+13236,35.867416
+13237,0.34600815
+13238,0.7937643
+13239,1.594418
+13240,2.936558
+13241,7.6469307
+13242,11.298592
+13243,30.364359
+13244,33.479877
+13245,33.3665
+13246,37.47669
+13247,33.474575
+13248,33.084484
+13249,35.026093
+13250,38.963776
+13251,21.020449
+13252,20.659607
+13253,23.174131
+13254,26.692514
+13255,29.488295
+13256,34.16152
+13257,37.365795
+13258,39.337513
+13259,40.90881
+13260,44.339584
+13261,44.6501
+13262,46.626083
+13263,49.769783
+13264,53.275223
+13265,52.97992
+13266,53.993843
+13267,56.18751
+13268,24.350906
+13269,27.415768
+13270,28.984865
+13271,36.118954
+13272,40.551983
+13273,41.197685
+13274,58.09031
+13275,61.274647
+13276,64.50488
+13277,67.843124
+13278,26.463083
+13279,26.83237
+13280,33.375282
+13281,39.74788
+13282,41.05758
+13283,46.80745
+13284,43.34997
+13285,53.44788
+13286,56.9381
+13287,60.601776
+13288,60.84534
+13289,64.982864
+13290,65.88881
+13291,64.844025
+13292,71.48999
+13293,69.18053
+13294,54.13883
+13295,54.91689
+13296,53.43138
+13297,57.48394
+13298,55.87135
+13299,59.175674
+13300,60.64482
+13301,11.354363
+13302,14.3598385
+13303,18.470415
+13304,24.388042
+13305,47.193504
+13306,46.668148
+13307,50.469555
+13308,50.174706
+13309,51.39187
+13310,50.83724
+13311,53.554726
+13312,16.136383
+13313,21.173193
+13314,31.455086
+13315,34.264957
+13316,34.333908
+13317,9.145515
+13318,12.917286
+13319,14.82691
+13320,15.884904
+13321,21.445158
+13322,22.58649
+13323,24.858505
+13324,29.596624
+13325,31.856785
+13326,28.77052
+13327,43.43799
+13328,47.59488
+13329,50.69709
+13330,53.7445
+13331,66.57047
+13332,69.79697
+13333,70.98895
+13334,36.242
+13335,44.738815
+13336,46.123497
+13337,47.44947
+13338,52.558094
+13339,54.15818
+13340,55.86326
+13341,57.49155
+13342,61.622066
+13343,62.758175
+13344,66.62271
+13345,25.310928
+13346,26.879215
+13347,36.497078
+13348,42.971745
+13349,45.427284
+13350,14.1743145
+13351,14.902496
+13352,18.565279
+13353,18.374384
+13354,36.71729
+13355,37.622524
+13356,38.14908
+13357,39.94042
+13358,44.782368
+13359,41.150524
+13360,43.556725
+13361,49.799812
+13362,51.170185
+13363,50.86573
+13364,54.26051
+13365,56.04394
+13366,56.180573
+13367,16.32989
+13368,20.069036
+13369,22.046276
+13370,26.022808
+13371,27.854858
+13372,31.352123
+13373,37.949966
+13374,42.429504
+13375,43.511887
+13376,47.77204
+13377,49.32282
+13378,50.363342
+13379,56.232643
+13380,54.44876
+13381,51.61627
+13382,51.777824
+13383,57.679558
+13384,63.541927
+13385,72.28708
+13386,14.084778
+13387,16.671293
+13388,23.016634
+13389,24.908905
+13390,27.085878
+13391,29.800941
+13392,31.576975
+13393,33.100327
+13394,36.06774
+13395,35.63075
+13396,18.15055
+13397,22.109325
+13398,27.884958
+13399,35.61548
+13400,64.47583
+13401,66.52489
+13402,68.23884
+13403,71.46284
+13404,70.37061
+13405,72.2283
+13406,75.45623
+13407,74.60368
+13408,17.17651
+13409,19.055267
+13410,20.342325
+13411,22.156109
+13412,29.234375
+13413,30.247984
+13414,31.819794
+13415,37.48118
+13416,40.193985
+13417,42.83851
+13418,42.269665
+13419,51.184845
+13420,1.2010592
+13421,4.615201
+13422,5.92432
+13423,9.160156
+13424,11.209181
+13425,15.349727
+13426,12.128305
+13427,14.282631
+13428,16.509853
+13429,22.064955
+13430,25.457182
+13431,31.037624
+13432,32.91016
+13433,30.743435
+13434,44.32274
+13435,47.089455
+13436,50.90431
+13437,54.1854
+13438,52.69061
+13439,55.618885
+13440,56.986553
+13441,58.687927
+13442,45.627693
+13443,48.576424
+13444,53.65748
+13445,57.72767
+13446,21.361822
+13447,28.760857
+13448,30.442749
+13449,32.48262
+13450,32.236423
+13451,33.516525
+13452,36.588184
+13453,42.124947
+13454,46.165
+13455,46.09362
+13456,52.213432
+13457,56.039627
+13458,32.698326
+13459,34.29599
+13460,36.20421
+13461,38.68336
+13462,41.61514
+13463,41.876644
+13464,44.631767
+13465,50.662033
+13466,48.144165
+13467,54.651924
+13468,60.58817
+13469,62.06116
+13470,28.014364
+13471,29.342659
+13472,31.473904
+13473,30.092224
+13474,36.312912
+13475,34.14249
+13476,35.597828
+13477,43.171352
+13478,52.670948
+13479,56.36891
+13480,58.402206
+13481,31.681828
+13482,32.06768
+13483,35.906742
+13484,40.274384
+13485,42.89968
+13486,46.696285
+13487,51.132378
+13488,52.840588
+13489,50.696907
+13490,54.667313
+13491,57.05677
+13492,59.58924
+13493,24.72776
+13494,24.026274
+13495,28.32923
+13496,28.169714
+13497,30.125666
+13498,33.144714
+13499,36.184135
+13500,38.780014
+13501,40.944393
+13502,41.61776
+13503,45.91849
+13504,50.09089
+13505,24.19532
+13506,25.057228
+13507,30.87107
+13508,34.044487
+13509,37.764584
+13510,39.347298
+13511,42.192657
+13512,32.70785
+13513,29.90157
+13514,32.413517
+13515,33.27699
+13516,36.94202
+13517,35.387592
+13518,38.269917
+13519,42.023247
+13520,42.50193
+13521,40.3955
+13522,51.776295
+13523,53.933712
+13524,11.611809
+13525,18.67971
+13526,19.171324
+13527,29.77372
+13528,34.144894
+13529,31.634748
+13530,35.77266
+13531,38.60057
+13532,40.567604
+13533,46.482697
+13534,47.821476
+13535,49.912376
+13536,24.805218
+13537,26.035662
+13538,27.62767
+13539,33.172634
+13540,44.131176
+13541,42.285057
+13542,45.96605
+13543,47.031963
+13544,54.611065
+13545,27.325047
+13546,28.224453
+13547,36.28607
+13548,38.41404
+13549,44.303078
+13550,43.688442
+13551,48.461926
+13552,49.698128
+13553,54.155174
+13554,55.433098
+13555,59.27155
+13556,60.321968
+13557,24.903158
+13558,40.030174
+13559,45.608044
+13560,40.005463
+13561,42.38392
+13562,45.207874
+13563,49.37341
+13564,53.11547
+13565,53.238743
+13566,56.19303
+13567,55.854286
+13568,60.069843
+13569,32.152115
+13570,35.642876
+13571,40.0493
+13572,48.22156
+13573,49.516808
+13574,6.4896345
+13575,6.9281354
+13576,11.539585
+13577,12.98125
+13578,16.215794
+13579,49.536304
+13580,52.21689
+13581,52.47638
+13582,56.690514
+13583,58.80083
+13584,58.96742
+13585,27.794731
+13586,25.918737
+13587,26.81062
+13588,27.318966
+13589,31.086498
+13590,29.860302
+13591,31.032158
+13592,37.764454
+13593,36.777493
+13594,36.31717
+13595,41.16886
+13596,45.22322
+13597,37.62452
+13598,47.206272
+13599,46.995262
+13600,45.989594
+13601,48.949368
+13602,50.327232
+13603,51.541336
+13604,54.804844
+13605,54.33596
+13606,59.02357
+13607,61.99509
+13608,60.952324
+13609,20.972824
+13610,24.959755
+13611,34.00102
+13612,39.635994
+13613,42.6024
+13614,17.898718
+13615,21.706528
+13616,25.65335
+13617,27.368015
+13618,27.570526
+13619,34.68974
+13620,35.36438
+13621,36.269566
+13622,38.477905
+13623,42.52034
+13624,45.028732
+13625,51.080048
+13626,58.97676
+13627,58.21159
+13628,62.362724
+13629,62.034855
+13630,65.81827
+13631,66.65569
+13632,66.26431
+13633,69.604034
+13634,71.135826
+13635,70.83467
+13636,71.196594
+13637,16.357979
+13638,20.047739
+13639,31.119076
+13640,33.21923
+13641,28.806822
+13642,30.684725
+13643,33.632545
+13644,33.922665
+13645,36.040672
+13646,39.4633
+13647,42.529415
+13648,41.509533
+13649,-0.88035417
+13650,-1.3230121
+13651,0.76566935
+13652,2.3368232
+13653,5.622655
+13654,5.4852924
+13655,7.4844875
+13656,10.63083
+13657,11.829856
+13658,14.755233
+13659,21.024607
+13660,8.46517
+13661,14.419977
+13662,18.213373
+13663,25.38457
+13664,8.274453
+13665,10.660002
+13666,13.936958
+13667,13.838718
+13668,16.56622
+13669,22.010876
+13670,29.27829
+13671,31.303452
+13672,27.067047
+13673,34.270546
+13674,28.6936
+13675,38.39267
+13676,41.54101
+13677,40.89947
+13678,43.814426
+13679,45.972748
+13680,46.82876
+13681,48.47464
+13682,50.9246
+13683,54.106606
+13684,51.513817
+13685,53.8751
+13686,41.56144
+13687,47.21233
+13688,52.279793
+13689,56.12307
+13690,59.710266
+13691,44.623
+13692,48.125195
+13693,49.8812
+13694,54.264153
+13695,58.281994
+13696,23.615637
+13697,24.31414
+13698,27.066626
+13699,25.94217
+13700,25.870943
+13701,28.117851
+13702,37.528748
+13703,40.968166
+13704,47.090187
+13705,50.73289
+13706,50.568745
+13707,53.325455
+13708,55.49577
+13709,56.233826
+13710,56.376183
+13711,58.64545
+13712,61.31801
+13713,58.412205
+13714,27.455097
+13715,31.200665
+13716,38.569153
+13717,42.419537
+13718,44.88674
+13719,46.05724
+13720,50.38766
+13721,49.54532
+13722,53.843758
+13723,55.26197
+13724,58.571964
+13725,60.22578
+13726,16.970524
+13727,16.674313
+13728,16.894796
+13729,21.516205
+13730,14.207842
+13731,16.047451
+13732,19.317762
+13733,21.35086
+13734,20.272911
+13735,25.697237
+13736,28.566181
+13737,33.85842
+13738,49.22294
+13739,49.968517
+13740,53.13769
+13741,53.5589
+13742,54.91829
+13743,59.608276
+13744,60.212532
+13745,62.48072
+13746,61.7285
+13747,38.261543
+13748,45.3937
+13749,48.005116
+13750,52.123123
+13751,37.249214
+13752,37.917107
+13753,42.291664
+13754,49.398987
+13755,58.287186
+13756,17.993149
+13757,17.812273
+13758,16.063248
+13759,20.795185
+13760,33.17039
+13761,32.902336
+13762,35.17871
+13763,38.10153
+13764,44.450836
+13765,47.868977
+13766,47.996635
+13767,44.702766
+13768,47.344193
+13769,51.831245
+13770,53.303604
+13771,54.709095
+13772,58.579807
+13773,25.715057
+13774,27.990166
+13775,31.804117
+13776,41.85966
+13777,27.146856
+13778,30.231405
+13779,32.272427
+13780,33.397343
+13781,32.34685
+13782,34.78699
+13783,36.964703
+13784,37.917145
+13785,61.424896
+13786,59.688194
+13787,61.380302
+13788,60.536713
+13789,67.96411
+13790,64.34997
+13791,63.162796
+13792,64.61082
+13793,66.16687
+13794,69.12871
+13795,66.98533
+13796,68.43346
+13797,41.132153
+13798,42.612816
+13799,44.835983
+13800,50.39626
+13801,53.53627
+13802,53.24288
+13803,53.492233
+13804,58.125908
+13805,57.84153
+13806,60.70709
+13807,61.964947
+13808,63.85748
+13809,12.964437
+13810,14.59741
+13811,17.221977
+13812,22.64324
+13813,25.493954
+13814,29.852505
+13815,14.147306
+13816,16.60962
+13817,17.387104
+13818,19.322445
+13819,19.149801
+13820,23.6963
+13821,24.55574
+13822,27.080257
+13823,29.470821
+13824,30.801327
+13825,32.213108
+13826,34.886574
+13827,5.170673
+13828,7.332558
+13829,8.387952
+13830,21.689995
+13831,25.0801
+13832,29.4902
+13833,35.2879
+13834,37.456993
+13835,39.054005
+13836,39.51146
+13837,41.43554
+13838,43.355976
+13839,41.651176
+13840,46.97678
+13841,45.696507
+13842,46.264168
+13843,22.920416
+13844,25.586739
+13845,36.08159
+13846,42.674297
+13847,42.385445
+13848,17.812174
+13849,27.378838
+13850,29.674816
+13851,25.127956
+13852,26.494572
+13853,30.506401
+13854,31.345058
+13855,35.388863
+13856,40.71167
+13857,47.536053
+13858,54.447647
+13859,52.48075
+13860,20.275593
+13861,22.726849
+13862,22.497793
+13863,25.171682
+13864,28.387922
+13865,31.354822
+13866,34.397717
+13867,39.837574
+13868,44.00931
+13869,42.934643
+13870,42.535725
+13871,45.771984
+13872,26.013784
+13873,27.873997
+13874,28.4723
+13875,35.384445
+13876,36.433956
+13877,39.289932
+13878,44.819386
+13879,47.444206
+13880,48.500443
+13881,39.064743
+13882,44.155872
+13883,45.21715
+13884,44.025692
+13885,22.240847
+13886,28.35642
+13887,27.676544
+13888,30.151138
+13889,23.552069
+13890,27.170567
+13891,28.628489
+13892,27.48888
+13893,23.582247
+13894,23.854961
+13895,28.286613
+13896,27.750965
+13897,29.37037
+13898,30.364292
+13899,33.516243
+13900,35.641945
+13901,36.95603
+13902,43.601433
+13903,41.686817
+13904,43.44389
+13905,1.1682653
+13906,1.9336338
+13907,3.2247024
+13908,4.5122914
+13909,7.487114
+13910,9.282088
+13911,10.132344
+13912,29.290346
+13913,30.165716
+13914,32.320663
+13915,32.32773
+13916,16.89805
+13917,21.500978
+13918,22.901814
+13919,24.947239
+13920,32.21077
+13921,34.80508
+13922,32.944614
+13923,34.889317
+13924,37.50505
+13925,38.84063
+13926,40.67867
+13927,41.672146
+13928,30.254358
+13929,34.11249
+13930,38.158195
+13931,43.50688
+13932,44.105083
+13933,47.89666
+13934,50.379395
+13935,61.96738
+13936,62.76258
+13937,64.44797
+13938,68.37727
+13939,5.4062324
+13940,10.085489
+13941,14.72168
+13942,11.540611
+13943,16.802387
+13944,19.372158
+13945,22.184385
+13946,27.402359
+13947,31.726181
+13948,34.859962
+13949,32.86177
+13950,35.71876
+13951,19.88536
+13952,24.906404
+13953,29.045738
+13954,34.040604
+13955,29.476929
+13956,31.950459
+13957,32.501564
+13958,34.62105
+13959,33.732864
+13960,37.948555
+13961,38.301956
+13962,41.438293
+13963,21.171034
+13964,25.283504
+13965,32.091957
+13966,40.552643
+13967,17.799988
+13968,20.542595
+13969,22.67436
+13970,24.305666
+13971,26.845497
+13972,29.909842
+13973,32.004154
+13974,35.567886
+13975,39.955353
+13976,39.500854
+13977,51.412457
+13978,55.471474
+13979,49.756874
+13980,54.617104
+13981,56.059525
+13982,62.081203
+13983,65.43942
+13984,34.38937
+13985,37.747463
+13986,41.871185
+13987,43.687492
+13988,47.035225
+13989,51.305298
+13990,53.888256
+13991,53.276844
+13992,55.79253
+13993,57.534786
+13994,59.85607
+13995,62.26773
+13996,21.835241
+13997,26.171013
+13998,27.139652
+13999,28.024689
+14000,31.913834
+14001,33.045204
+14002,36.67224
+14003,38.039642
+14004,7.4451766
+14005,9.690967
+14006,13.472347
+14007,14.092068
+14008,16.675951
+14009,18.450554
+14010,29.278429
+14011,31.638931
+14012,34.06939
+14013,36.888172
+14014,38.692513
+14015,44.4152
+14016,25.750092
+14017,30.12837
+14018,31.883173
+14019,35.61625
+14020,35.19706
+14021,42.476524
+14022,46.528095
+14023,50.092346
+14024,50.454582
+14025,58.376022
+14026,54.264862
+14027,31.996216
+14028,36.89679
+14029,42.649017
+14030,48.28916
+14031,54.47499
+14032,57.44069
+14033,62.65755
+14034,22.882145
+14035,24.734022
+14036,22.965702
+14037,27.62922
+14038,21.865631
+14039,22.92947
+14040,25.912413
+14041,25.586687
+14042,27.08052
+14043,28.243748
+14044,32.620823
+14045,37.142544
+14046,39.73849
+14047,38.86022
+14048,39.380875
+14049,43.754353
+14050,31.368387
+14051,48.191597
+14052,47.588142
+14053,41.58396
+14054,46.405983
+14055,50.14421
+14056,53.012222
+14057,54.49046
+14058,55.305325
+14059,57.81933
+14060,63.371048
+14061,63.64009
+14062,21.716625
+14063,21.962456
+14064,20.422672
+14065,30.991005
+14066,36.108826
+14067,43.047737
+14068,39.349052
+14069,46.48097
+14070,48.53885
+14071,34.9624
+14072,35.955547
+14073,40.67779
+14074,39.025604
+14075,43.447853
+14076,43.951912
+14077,44.06529
+14078,46.224117
+14079,46.09857
+14080,46.910713
+14081,49.49296
+14082,51.814484
+14083,35.344547
+14084,34.680283
+14085,37.751648
+14086,34.352097
+14087,38.163574
+14088,39.738907
+14089,15.062373
+14090,17.4099
+14091,20.320759
+14092,24.158615
+14093,29.794285
+14094,10.331204
+14095,12.321774
+14096,13.620791
+14097,20.8847
+14098,43.012794
+14099,46.715538
+14100,52.094852
+14101,54.90482
+14102,56.24989
+14103,59.342438
+14104,60.792164
+14105,62.391926
+14106,62.646797
+14107,64.22774
+14108,62.940136
+14109,64.24875
+14110,18.51529
+14111,20.931076
+14112,21.369942
+14113,24.017479
+14114,29.54277
+14115,31.036943
+14116,33.536568
+14117,36.803062
+14118,40.465828
+14119,45.68924
+14120,47.303272
+14121,13.425255
+14122,21.333649
+14123,22.158224
+14124,24.064295
+14125,13.282714
+14126,17.067251
+14127,18.841898
+14128,24.029598
+14129,27.953905
+14130,27.601595
+14131,30.541351
+14132,36.002544
+14133,33.351273
+14134,39.67493
+14135,43.893394
+14136,42.6283
+14137,31.444044
+14138,35.764946
+14139,38.59355
+14140,34.49974
+14141,39.023193
+14142,40.611946
+14143,42.943428
+14144,5.434229
+14145,11.259782
+14146,12.847118
+14147,11.71715
+14148,14.731104
+14149,16.850006
+14150,22.13826
+14151,24.383976
+14152,24.563286
+14153,28.7561
+14154,13.272474
+14155,18.13565
+14156,23.00996
+14157,29.67271
+14158,12.1813345
+14159,15.56399
+14160,17.64297
+14161,16.071667
+14162,36.57949
+14163,41.134903
+14164,40.764824
+14165,49.127098
+14166,51.12705
+14167,52.17079
+14168,54.384254
+14169,57.16703
+14170,55.42399
+14171,60.452034
+14172,12.102618
+14173,11.65535
+14174,14.396508
+14175,20.30397
+14176,23.731915
+14177,23.00317
+14178,29.497103
+14179,29.951338
+14180,34.308094
+14181,37.387375
+14182,38.733955
+14183,40.898636
+14184,40.3265
+14185,42.49151
+14186,40.651283
+14187,43.922203
+14188,8.074104
+14189,11.026739
+14190,13.628492
+14191,22.111954
+14192,46.975224
+14193,51.086468
+14194,53.209007
+14195,56.447227
+14196,58.44532
+14197,62.336346
+14198,29.030128
+14199,32.069122
+14200,36.18518
+14201,39.069347
+14202,44.001587
+14203,47.292633
+14204,49.535835
+14205,48.45429
+14206,51.576866
+14207,55.597355
+14208,57.423668
+14209,57.52721
+14210,59.344227
+14211,60.52057
+14212,63.55165
+14213,65.5478
+14214,0.09553836
+14215,1.2591608
+14216,2.1835158
+14217,6.1585355
+14218,59.939907
+14219,59.49347
+14220,61.20546
+14221,64.70796
+14222,65.39164
+14223,64.97544
+14224,66.10426
+14225,65.80021
+14226,65.99511
+14227,68.99128
+14228,73.20485
+14229,71.708885
+14230,13.726829
+14231,14.3999195
+14232,18.554846
+14233,22.041002
+14234,20.583426
+14235,27.77985
+14236,32.122063
+14237,3.4957976
+14238,6.7696486
+14239,8.09475
+14240,7.5639057
+14241,9.333229
+14242,8.74746
+14243,10.28128
+14244,57.894775
+14245,56.105957
+14246,57.23382
+14247,52.102734
+14248,59.471733
+14249,63.09548
+14250,61.992516
+14251,58.509785
+14252,62.339546
+14253,22.683695
+14254,27.680635
+14255,33.68673
+14256,34.362457
+14257,36.676643
+14258,40.87023
+14259,43.050392
+14260,45.36703
+14261,52.742565
+14262,56.24607
+14263,55.12813
+14264,58.82536
+14265,25.132387
+14266,28.00776
+14267,29.272858
+14268,34.162506
+14269,33.73115
+14270,33.728363
+14271,35.620506
+14272,34.09202
+14273,38.46713
+14274,39.861977
+14275,40.70406
+14276,42.204754
+14277,43.228287
+14278,42.03718
+14279,46.148727
+14280,48.782104
+14281,42.072243
+14282,44.282852
+14283,47.88
+14284,53.398384
+14285,21.140808
+14286,25.540121
+14287,25.145287
+14288,29.300423
+14289,28.337112
+14290,34.101273
+14291,33.48879
+14292,38.0409
+14293,35.759575
+14294,41.215614
+14295,42.193016
+14296,49.797523
+14297,23.793734
+14298,29.454138
+14299,34.1052
+14300,37.363
+14301,38.53696
+14302,41.52182
+14303,45.34588
+14304,45.96116
+14305,47.80278
+14306,50.55849
+14307,51.125904
+14308,55.811222
+14309,16.2723
+14310,17.748938
+14311,19.164993
+14312,19.200727
+14313,18.623178
+14314,23.445889
+14315,23.02535
+14316,24.880964
+14317,27.864529
+14318,26.978407
+14319,28.352455
+14320,31.203125
+14321,31.382679
+14322,31.309496
+14323,32.868904
+14324,34.429306
+14325,37.14742
+14326,40.080906
+14327,16.836462
+14328,22.184196
+14329,24.520329
+14330,27.006365
+14331,12.481746
+14332,17.429865
+14333,21.1283
+14334,22.069942
+14335,24.789349
+14336,26.056099
+14337,31.853695
+14338,32.500137
+14339,33.54133
+14340,36.68875
+14341,39.61862
+14342,38.710632
+14343,39.713165
+14344,42.593925
+14345,44.785717
+14346,46.939342
+14347,11.045931
+14348,12.261263
+14349,14.206268
+14350,17.260773
+14351,24.201956
+14352,37.136086
+14353,35.312386
+14354,33.721603
+14355,36.06868
+14356,38.698517
+14357,40.689907
+14358,47.24378
+14359,5.008003
+14360,6.1119814
+14361,7.2226496
+14362,6.816038
+14363,22.925892
+14364,26.128338
+14365,35.8812
+14366,38.533463
+14367,45.18621
+14368,29.17482
+14369,29.742645
+14370,30.553535
+14371,31.935951
+14372,31.800903
+14373,37.358124
+14374,39.86512
+14375,37.295395
+14376,39.882355
+14377,41.597923
+14378,42.7201
+14379,46.31034
+14380,9.862419
+14381,13.068109
+14382,18.223553
+14383,20.042604
+14384,22.179724
+14385,27.130291
+14386,28.767027
+14387,32.536095
+14388,33.10502
+14389,33.16853
+14390,39.47216
+14391,40.675385
+14392,33.638348
+14393,31.446054
+14394,32.806915
+14395,31.921844
+14396,35.778137
+14397,16.611568
+14398,16.986124
+14399,19.704174
+14400,21.8884
+14401,24.441254
+14402,26.454596
+14403,29.865665
+14404,29.530916
+14405,33.022934
+14406,34.882343
+14407,35.256317
+14408,34.29173
+14409,5.3744183
+14410,7.122699
+14411,8.947181
+14412,10.056688
+14413,13.133247
+14414,16.03673
+14415,4.663471
+14416,4.7907887
+14417,7.4553537
+14418,10.202425
+14419,13.413171
+14420,18.460682
+14421,20.627499
+14422,22.788956
+14423,26.447693
+14424,27.931026
+14425,30.877972
+14426,36.869938
+14427,0.6693147
+14428,0.5031838
+14429,3.994285
+14430,4.603321
+14431,8.009193
+14432,8.362419
+14433,11.885523
+14434,14.957925
+14435,17.348564
+14436,22.694904
+14437,24.261063
+14438,27.247501
+14439,48.549816
+14440,49.543972
+14441,51.194103
+14442,50.55046
+14443,54.988808
+14444,56.788513
+14445,56.33286
+14446,57.915398
+14447,60.092625
+14448,60.277668
+14449,61.79348
+14450,64.16795
+14451,48.89174
+14452,51.89821
+14453,50.587383
+14454,53.657852
+14455,56.681965
+14456,55.710354
+14457,56.180603
+14458,58.264652
+14459,58.67511
+14460,57.57613
+14461,47.390812
+14462,53.25265
+14463,57.35161
+14464,64.79397
+14465,34.435463
+14466,35.29725
+14467,37.221336
+14468,40.019978
+14469,42.647358
+14470,41.668533
+14471,42.59011
+14472,44.57681
+14473,45.796207
+14474,49.613663
+14475,50.394382
+14476,29.941147
+14477,34.022247
+14478,39.61951
+14479,44.31095
+14480,41.26055
+14481,46.062035
+14482,46.48494
+14483,50.490997
+14484,50.0988
+14485,59.19151
+14486,60.740017
+14487,60.496235
+14488,61.04579
+14489,65.15674
+14490,63.846912
+14491,7.811369
+14492,6.4658523
+14493,7.7281804
+14494,8.901346
+14495,10.638456
+14496,5.2460976
+14497,6.0952563
+14498,7.131432
+14499,9.329895
+14500,12.334636
+14501,17.040432
+14502,18.040876
+14503,19.934347
+14504,18.702766
+14505,25.623894
+14506,27.711117
+14507,27.252089
+14508,13.137437
+14509,16.919928
+14510,17.076832
+14511,21.052923
+14512,13.134598
+14513,24.363092
+14514,22.524534
+14515,21.6482
+14516,25.818478
+14517,32.682434
+14518,36.90164
+14519,41.540443
+14520,41.495502
+14521,51.807327
+14522,54.44017
+14523,87.308105
+14524,93.85861
+14525,102.143814
+14526,101.51552
+14527,102.32403
+14528,106.53493
+14529,108.231735
+14530,104.60439
+14531,106.495674
+14532,109.79502
+14533,110.130615
+14534,112.50654
+14535,56.302845
+14536,58.516647
+14537,58.583183
+14538,62.1995
+14539,63.99594
+14540,63.281456
+14541,67.06526
+14542,68.443794
+14543,67.303734
+14544,66.94828
+14545,68.8622
+14546,69.49068
+14547,23.408037
+14548,25.078964
+14549,26.313784
+14550,42.74726
+14551,13.993375
+14552,18.891678
+14553,21.015589
+14554,22.634523
+14555,16.82086
+14556,19.242735
+14557,22.049051
+14558,26.762863
+14559,27.94011
+14560,37.145966
+14561,38.760876
+14562,35.115593
+14563,41.357086
+14564,40.49642
+14565,47.293694
+14566,48.461998
+14567,47.5298
+14568,50.78007
+14569,54.330753
+14570,58.482796
+14571,60.565556
+14572,41.185776
+14573,45.264465
+14574,54.629883
+14575,59.813248
+14576,35.848454
+14577,39.232346
+14578,42.93696
+14579,45.581196
+14580,50.429462
+14581,52.488667
+14582,54.907097
+14583,60.20308
+14584,59.31187
+14585,61.479492
+14586,65.03354
+14587,64.71655
+14588,64.328766
+14589,66.40214
+14590,67.44969
+14591,71.30235
+14592,74.204475
+14593,75.32943
+14594,78.32045
+14595,77.069984
+14596,78.540726
+14597,80.99286
+14598,82.25109
+14599,82.865555
+14600,25.227648
+14601,26.288067
+14602,27.333382
+14603,33.81089
+14604,37.0356
+14605,43.122326
+14606,43.705975
+14607,50.2146
+14608,51.860596
+14609,2.3717978
+14610,8.237342
+14611,10.53557
+14612,11.880839
+14613,28.450016
+14614,34.04659
+14615,36.75301
+14616,42.359646
+14617,13.769543
+14618,17.386143
+14619,20.32144
+14620,19.254065
+14621,23.457153
+14622,54.677406
+14623,56.98011
+14624,55.6238
+14625,54.27816
+14626,57.004936
+14627,50.82892
+14628,58.49958
+14629,57.25762
+14630,57.07905
+14631,60.373352
+14632,61.576385
+14633,46.831417
+14634,48.8642
+14635,47.838867
+14636,49.04606
+14637,51.35325
+14638,38.224625
+14639,42.451775
+14640,46.26967
+14641,47.270863
+14642,52.59867
+14643,53.841457
+14644,59.06845
+14645,59.07985
+14646,60.771133
+14647,61.050316
+14648,65.88817
+14649,66.53325
+14650,65.17716
+14651,63.79997
+14652,68.20704
+14653,67.863525
+14654,69.085014
+14655,70.23836
+14656,70.71753
+14657,71.54553
+14658,72.47007
+14659,75.41839
+14660,74.77344
+14661,74.26634
+14662,18.247478
+14663,22.320557
+14664,26.851353
+14665,29.565666
+14666,27.873198
+14667,32.39927
+14668,35.649284
+14669,35.094193
+14670,37.994102
+14671,31.092873
+14672,32.62606
+14673,31.6932
+14674,33.57856
+14675,34.806427
+14676,6.482839
+14677,4.8324265
+14678,6.6892223
+14679,14.364302
+14680,16.892498
+14681,14.788046
+14682,18.30743
+14683,23.132433
+14684,23.828484
+14685,29.827658
+14686,28.87215
+14687,39.468674
+14688,19.02684
+14689,23.619576
+14690,25.061258
+14691,32.92479
+14692,30.981846
+14693,35.94214
+14694,39.374485
+14695,40.607346
+14696,45.864716
+14697,48.002525
+14698,50.273605
+14699,56.11651
+14700,13.160717
+14701,17.439934
+14702,24.62055
+14703,28.119022
+14704,29.868877
+14705,34.00729
+14706,35.440002
+14707,35.628414
+14708,38.647766
+14709,38.090652
+14710,24.664951
+14711,33.84214
+14712,39.313873
+14713,38.62018
+14714,39.29135
+14715,41.959206
+14716,48.557262
+14717,59.07804
+14718,57.68134
+14719,24.11482
+14720,27.06052
+14721,26.831526
+14722,28.493774
+14723,34.508812
+14724,42.170456
+14725,43.75145
+14726,40.47253
+14727,45.038845
+14728,46.173275
+14729,49.520546
+14730,51.247074
+14731,29.259268
+14732,28.923704
+14733,31.10048
+14734,32.551674
+14735,38.873695
+14736,45.70932
+14737,39.46945
+14738,42.369076
+14739,47.295483
+14740,44.620907
+14741,49.327347
+14742,53.09481
+14743,54.52589
+14744,57.74282
+14745,59.15969
+14746,63.68338
+14747,30.180489
+14748,34.10804
+14749,41.485844
+14750,43.75177
+14751,43.844727
+14752,46.054527
+14753,10.087868
+14754,9.891828
+14755,13.575125
+14756,17.585566
+14757,19.096516
+14758,24.373352
+14759,31.747242
+14760,28.239029
+14761,32.329216
+14762,38.879646
+14763,39.064644
+14764,43.62851
+14765,29.21746
+14766,29.275156
+14767,31.644756
+14768,37.025383
+14769,40.10869
+14770,9.931852
+14771,14.46084
+14772,15.367832
+14773,17.49567
+14774,19.294743
+14775,21.514595
+14776,22.286634
+14777,23.061434
+14778,23.63273
+14779,23.094925
+14780,33.32457
+14781,37.67524
+14782,40.316353
+14783,41.395576
+14784,46.379192
+14785,49.641502
+14786,54.354694
+14787,58.029255
+14788,19.57505
+14789,26.116018
+14790,33.128216
+14791,37.550297
+14792,18.17751
+14793,20.822897
+14794,22.44004
+14795,24.010414
+14796,30.411337
+14797,35.122906
+14798,39.191917
+14799,39.169647
+14800,44.366104
+14801,45.341038
+14802,48.59896
+14803,47.223457
+14804,26.371464
+14805,34.055664
+14806,36.01635
+14807,33.487362
+14808,37.14016
+14809,38.54316
+14810,40.402985
+14811,41.43267
+14812,9.290672
+14813,9.523384
+14814,10.2768135
+14815,10.875306
+14816,24.565025
+14817,25.801678
+14818,33.401905
+14819,36.926758
+14820,49.253937
+14821,50.394127
+14822,54.56239
+14823,58.35708
+14824,-0.16398019
+14825,-0.4017338
+14826,0.5761881
+14827,0.6526687
+14828,2.4960492
+14829,4.8700094
+14830,6.3050237
+14831,8.207423
+14832,7.453147
+14833,11.234304
+14834,11.705675
+14835,12.498701
+14836,35.7296
+14837,45.00928
+14838,46.327408
+14839,49.485092
+14840,55.161495
+14841,55.86645
+14842,61.921703
+14843,63.388763
+14844,67.46894
+14845,72.11254
+14846,67.639885
+14847,70.0916
+14848,29.238888
+14849,35.995342
+14850,38.269867
+14851,38.448845
+14852,41.94679
+14853,7.1293597
+14854,11.223365
+14855,14.723875
+14856,16.05793
+14857,16.583858
+14858,20.91457
+14859,24.597187
+14860,31.100502
+14861,15.397644
+14862,19.315195
+14863,21.843672
+14864,25.68484
+14865,28.3382
+14866,33.97147
+14867,40.89634
+14868,47.71022
+14869,29.019655
+14870,34.901405
+14871,40.58964
+14872,44.71175
+14873,46.87856
+14874,23.240265
+14875,25.593157
+14876,31.56955
+14877,35.61845
+14878,36.02585
+14879,44.570522
+14880,46.23316
+14881,51.64008
+14882,58.640297
+14883,58.87731
+14884,58.923027
+14885,59.626316
+14886,59.210907
+14887,64.16503
+14888,65.98093
+14889,65.441345
+14890,67.03515
+14891,34.261555
+14892,42.68299
+14893,50.06364
+14894,56.405045
+14895,29.726704
+14896,31.197325
+14897,36.697308
+14898,42.95908
+14899,45.846085
+14900,47.5642
+14901,49.59548
+14902,54.331047
+14903,54.792946
+14904,58.592453
+14905,58.00107
+14906,59.745983
+14907,23.619335
+14908,27.074757
+14909,32.14294
+14910,38.51786
+14911,7.144985
+14912,10.381854
+14913,12.297453
+14914,18.96471
+14915,21.844185
+14916,26.201376
+14917,27.335955
+14918,31.132086
+14919,32.817432
+14920,38.447712
+14921,39.494625
+14922,41.07171
+14923,35.187473
+14924,36.986816
+14925,39.71606
+14926,40.987408
+14927,41.190605
+14928,41.82114
+14929,45.577705
+14930,49.25974
+14931,50.271523
+14932,50.423218
+14933,51.762585
+14934,54.50643
+14935,22.162483
+14936,22.699469
+14937,24.558481
+14938,32.392963
+14939,34.130127
+14940,31.870655
+14941,31.225925
+14942,36.646683
+14943,38.22368
+14944,39.72839
+14945,42.782204
+14946,46.28293
+14947,31.800617
+14948,38.271954
+14949,44.24463
+14950,45.9479
+14951,34.377712
+14952,36.24311
+14953,40.57205
+14954,44.445847
+14955,36.749355
+14956,40.26334
+14957,41.93897
+14958,45.283302
+14959,47.890526
+14960,52.205803
+14961,52.31056
+14962,54.963673
+14963,57.75338
+14964,57.963894
+14965,59.63886
+14966,62.938465
+14967,3.3275754
+14968,5.9037013
+14969,9.330722
+14970,10.116066
+14971,43.7663
+14972,45.46631
+14973,46.49825
+14974,54.290703
+14975,54.521122
+14976,57.44676
+14977,59.12678
+14978,59.834602
+14979,60.703228
+14980,62.636288
+14981,62.401237
+14982,64.18267
+14983,34.87042
+14984,36.80914
+14985,41.538162
+14986,43.915173
+14987,46.837303
+14988,48.41823
+14989,49.25401
+14990,0.7644393
+14991,1.9729135
+14992,4.892304
+14993,4.262307
+14994,6.4895353
+14995,8.162025
+14996,10.76755
+14997,12.023344
+14998,18.204649
+14999,18.356617
+15000,26.962715
+15001,30.974842
+15002,51.91316
+15003,56.00051
+15004,59.636536
+15005,59.188763
+15006,15.194187
+15007,15.890179
+15008,17.01363
+15009,19.846684
+15010,0.58472717
+15011,1.603284
+15012,4.3135357
+15013,6.0907855
+15014,7.661498
+15015,9.385569
+15016,64.771805
+15017,69.57629
+15018,62.74781
+15019,66.93904
+15020,71.79581
+15021,70.88115
+15022,72.45581
+15023,72.50447
+15024,74.164444
+15025,73.352455
+15026,72.52858
+15027,75.91088
+15028,32.531597
+15029,40.71428
+15030,42.866535
+15031,41.781075
+15032,41.230038
+15033,48.603653
+15034,47.66193
+15035,16.21188
+15036,16.335152
+15037,17.744627
+15038,19.007164
+15039,33.55813
+15040,37.65593
+15041,40.796413
+15042,44.53875
+15043,36.740223
+15044,37.91218
+15045,42.516052
+15046,44.6748
+15047,44.32097
+15048,44.074192
+15049,45.493027
+15050,47.547756
+15051,48.089676
+15052,50.126503
+15053,50.936893
+15054,51.0929
+15055,16.977306
+15056,17.447771
+15057,18.85278
+15058,22.421879
+15059,7.175828
+15060,10.96725
+15061,12.386126
+15062,13.537177
+15063,9.941643
+15064,12.193275
+15065,19.924402
+15066,23.6106
+15067,30.348127
+15068,29.857006
+15069,29.69614
+15070,34.508656
+15071,0.34549657
+15072,1.5279373
+15073,2.0500956
+15074,1.4503009
+15075,3.438205
+15076,17.945583
+15077,21.434788
+15078,29.67112
+15079,36.48418
+15080,31.206324
+15081,32.39588
+15082,34.862396
+15083,39.001026
+15084,39.796356
+15085,45.971565
+15086,47.09661
+15087,49.16552
+15088,48.226944
+15089,8.259909
+15090,12.547029
+15091,16.29065
+15092,21.440302
+15093,24.59513
+15094,25.659946
+15095,28.20485
+15096,31.510258
+15097,34.867218
+15098,40.05051
+15099,43.614117
+15100,46.951508
+15101,52.170914
+15102,56.142204
+15103,64.32134
+15104,67.815994
+15105,35.14991
+15106,38.702297
+15107,44.447372
+15108,46.70577
+15109,17.840162
+15110,17.752762
+15111,22.3244
+15112,22.564316
+15113,23.81239
+15114,29.25969
+15115,44.33365
+15116,45.135857
+15117,49.05353
+15118,24.745855
+15119,26.17491
+15120,31.038393
+15121,40.480816
+15122,42.82502
+15123,42.55849
+15124,43.211155
+15125,45.657516
+15126,23.052557
+15127,31.907497
+15128,31.989365
+15129,32.95458
+15130,32.143402
+15131,37.29093
+15132,39.510876
+15133,42.11364
+15134,42.528294
+15135,43.005585
+15136,44.78155
+15137,47.585777
+15138,31.97325
+15139,36.049965
+15140,38.991295
+15141,42.30733
+15142,8.995134
+15143,10.659519
+15144,15.178984
+15145,18.111418
+15146,18.083502
+15147,25.599758
+15148,27.714926
+15149,28.227158
+15150,31.920898
+15151,34.747894
+15152,38.939438
+15153,39.545414
+15154,18.027843
+15155,21.512613
+15156,22.751324
+15157,25.881779
+15158,31.465984
+15159,34.63716
+15160,35.698746
+15161,39.500454
+15162,40.76072
+15163,44.571392
+15164,49.653214
+15165,56.58169
+15166,58.734093
+15167,55.674534
+15168,59.685154
+15169,58.380695
+15170,64.84883
+15171,64.05354
+15172,66.12829
+15173,64.599686
+15174,66.74073
+15175,65.45558
+15176,21.87306
+15177,29.881315
+15178,29.772835
+15179,31.320824
+15180,14.599278
+15181,22.812527
+15182,25.243645
+15183,35.552605
+15184,17.248463
+15185,21.853004
+15186,21.903517
+15187,26.336725
+15188,30.345226
+15189,30.274717
+15190,36.24485
+15191,40.533745
+15192,43.4738
+15193,31.320898
+15194,32.644432
+15195,45.130135
+15196,49.22205
+15197,37.411804
+15198,42.217297
+15199,45.82145
+15200,46.7144
+15201,52.080437
+15202,54.714127
+15203,56.9997
+15204,58.77645
+15205,61.996277
+15206,60.988216
+15207,59.902103
+15208,61.76245
+15209,15.740515
+15210,16.251217
+15211,20.652185
+15212,22.166147
+15213,19.085981
+15214,21.346268
+15215,25.887493
+15216,28.758488
+15217,29.177752
+15218,34.291626
+15219,37.951958
+15220,39.17081
+15221,43.23958
+15222,1.1451154
+15223,3.722753
+15224,5.1641383
+15225,8.292454
+15226,55.257557
+15227,55.684204
+15228,59.449085
+15229,62.91861
+15230,63.5187
+15231,37.397877
+15232,41.731194
+15233,43.712986
+15234,48.83984
+15235,55.803894
+15236,58.128616
+15237,51.896454
+15238,59.25532
+15239,58.619907
+15240,58.706284
+15241,60.704544
+15242,63.645683
+15243,18.284142
+15244,21.20654
+15245,29.299744
+15246,27.52811
+15247,30.004221
+15248,34.142548
+15249,37.211227
+15250,40.28884
+15251,40.188477
+15252,43.328224
+15253,40.658966
+15254,42.348747
+15255,36.245064
+15256,42.7403
+15257,44.859276
+15258,48.905487
+15259,7.730631
+15260,11.539255
+15261,11.308334
+15262,13.855329
+15263,16.1372
+15264,18.5401
+15265,20.42429
+15266,22.993073
+15267,26.329937
+15268,17.433645
+15269,20.235415
+15270,23.182356
+15271,32.41314
+15272,37.759872
+15273,21.736105
+15274,27.207842
+15275,27.161562
+15276,30.912857
+15277,41.78816
+15278,45.353474
+15279,48.258717
+15280,51.324234
+15281,54.79006
+15282,55.057266
+15283,40.259056
+15284,56.416172
+15285,58.18108
+15286,56.931828
+15287,60.778603
+15288,67.41717
+15289,62.371136
+15290,66.15637
+15291,68.67667
+15292,68.86689
+15293,71.03287
+15294,73.32727
+15295,50.30191
+15296,51.86281
+15297,51.930645
+15298,53.41905
+15299,52.823956
+15300,53.70378
+15301,55.98437
+15302,59.381493
+15303,60.61713
+15304,59.569427
+15305,58.8149
+15306,62.89544
+15307,24.463535
+15308,32.16824
+15309,27.552202
+15310,29.291027
+15311,22.33995
+15312,27.31136
+15313,31.829031
+15314,42.310356
+15315,14.008921
+15316,14.897891
+15317,16.784615
+15318,22.90153
+15319,29.73898
+15320,32.571613
+15321,37.756615
+15322,39.802334
+15323,45.28956
+15324,45.93013
+15325,49.378513
+15326,54.13743
+15327,53.95046
+15328,55.841816
+15329,58.59721
+15330,60.478386
+15331,0.54917806
+15332,0.25083408
+15333,1.3806291
+15334,3.4488702
+15335,5.5730815
+15336,39.057556
+15337,38.553482
+15338,43.003685
+15339,44.254036
+15340,47.446365
+15341,48.1373
+15342,50.842255
+15343,53.264977
+15344,54.22653
+15345,55.11761
+15346,59.970623
+15347,60.213486
+15348,6.1649556
+15349,9.493606
+15350,11.023509
+15351,13.258423
+15352,16.682137
+15353,19.4762
+15354,21.32909
+15355,22.23571
+15356,30.343784
+15357,33.652145
+15358,33.49718
+15359,38.92163
+15360,25.210617
+15361,31.226116
+15362,31.713783
+15363,33.52324
+15364,38.34135
+15365,39.812714
+15366,42.58009
+15367,43.516273
+15368,45.481827
+15369,46.538544
+15370,47.97096
+15371,50.389446
+15372,32.383427
+15373,37.361813
+15374,39.778675
+15375,42.246246
+15376,48.632202
+15377,53.876717
+15378,49.986786
+15379,50.883526
+15380,55.303326
+15381,57.959877
+15382,57.00682
+15383,64.34306
+15384,22.68672
+15385,25.199806
+15386,32.264793
+15387,36.931408
+15388,20.992989
+15389,22.99541
+15390,26.703848
+15391,30.014042
+15392,29.913403
+15393,36.497723
+15394,38.808804
+15395,38.109455
+15396,47.27349
+15397,49.727768
+15398,54.27398
+15399,57.441254
+15400,37.033607
+15401,38.54971
+15402,39.894268
+15403,50.511482
+15404,51.54651
+15405,49.290466
+15406,54.478416
+15407,57.149067
+15408,43.91673
+15409,44.767742
+15410,43.098114
+15411,47.47259
+15412,50.39212
+15413,52.339897
+15414,55.169956
+15415,54.625294
+15416,58.16162
+15417,59.65371
+15418,27.02332
+15419,31.0666
+15420,32.412178
+15421,36.898117
+15422,38.580875
+15423,43.049324
+15424,44.744198
+15425,47.019768
+15426,34.680515
+15427,39.43947
+15428,43.738106
+15429,49.458603
+15430,50.91669
+15431,55.74
+15432,56.610752
+15433,58.495518
+15434,58.44363
+15435,60.443863
+15436,62.47249
+15437,64.08526
+15438,8.6319475
+15439,11.081821
+15440,13.023555
+15441,12.302708
+15442,13.655026
+15443,14.06044
+15444,24.887
+15445,29.18105
+15446,31.114838
+15447,31.185299
+15448,37.11476
+15449,35.832012
+15450,24.35832
+15451,31.154058
+15452,33.8536
+15453,33.71546
+15454,38.523376
+15455,37.313732
+15456,38.5415
+15457,34.518597
+15458,35.926666
+15459,39.32975
+15460,40.02401
+15461,14.52362
+15462,16.468153
+15463,20.291328
+15464,24.273012
+15465,26.802206
+15466,25.793182
+15467,35.489872
+15468,38.862415
+15469,36.83831
+15470,39.92448
+15471,42.105312
+15472,47.328285
+15473,20.036282
+15474,25.160936
+15475,27.171051
+15476,29.665813
+15477,29.814232
+15478,34.269005
+15479,32.822178
+15480,33.783215
+15481,35.231777
+15482,20.765245
+15483,24.337255
+15484,25.64742
+15485,29.399746
+15486,32.5607
+15487,35.683266
+15488,38.220238
+15489,41.53903
+15490,44.43711
+15491,48.426716
+15492,48.56937
+15493,50.049248
+15494,42.743843
+15495,47.936146
+15496,52.051647
+15497,54.339214
+15498,11.010864
+15499,19.836782
+15500,20.74167
+15501,22.501654
+15502,1.1264545
+15503,2.560301
+15504,9.13932
+15505,14.436899
+15506,17.163622
+15507,16.241673
+15508,22.090527
+15509,23.520967
+15510,20.92844
+15511,23.030334
+15512,26.632269
+15513,27.26062
+15514,32.334183
+15515,33.314995
+15516,38.726555
+15517,39.52095
+15518,41.695473
+15519,16.11838
+15520,17.437668
+15521,19.775982
+15522,21.9024
+15523,29.886757
+15524,35.655354
+15525,20.496712
+15526,22.621836
+15527,24.12937
+15528,29.922983
+15529,30.7042
+15530,36.09419
+15531,37.290962
+15532,39.82635
+15533,39.71353
+15534,41.49186
+15535,44.41483
+15536,45.376644
+15537,20.075138
+15538,28.647388
+15539,29.5686
+15540,28.014568
+15541,31.793621
+15542,37.45703
+15543,29.731483
+15544,34.726955
+15545,34.80738
+15546,36.286625
+15547,20.858759
+15548,21.612293
+15549,24.602047
+15550,25.19735
+15551,28.575348
+15552,29.066196
+15553,29.89213
+15554,29.696064
+15555,30.363989
+15556,32.437874
+15557,7.4065676
+15558,8.845192
+15559,9.261076
+15560,13.7819805
+15561,17.266254
+15562,17.426018
+15563,40.73841
+15564,42.683582
+15565,46.435867
+15566,51.534306
+15567,52.11647
+15568,55.37945
+15569,55.849045
+15570,43.181965
+15571,48.182705
+15572,49.966667
+15573,46.54373
+15574,4.070601
+15575,6.8285923
+15576,8.194176
+15577,8.036993
+15578,10.553563
+15579,12.832678
+15580,16.051903
+15581,21.891409
+15582,23.727688
+15583,22.986635
+15584,24.851528
+15585,27.033236
+15586,50.622112
+15587,49.408485
+15588,50.87789
+15589,55.128017
+15590,53.60712
+15591,58.211105
+15592,27.35671
+15593,28.72834
+15594,31.174118
+15595,32.9002
+15596,39.68833
+15597,40.646122
+15598,40.952026
+15599,41.967655
+15600,44.678654
+15601,44.925125
+15602,43.370583
+15603,45.591537
+15604,30.840538
+15605,49.58372
+15606,47.200546
+15607,53.37388
+15608,55.63398
+15609,61.12548
+15610,61.43591
+15611,67.11563
+15612,64.57886
+15613,65.20234
+15614,64.344734
+15615,69.76755
+15616,30.430538
+15617,35.069233
+15618,35.842464
+15619,40.523796
+15620,43.995613
+15621,49.866196
+15622,49.573128
+15623,52.7486
+15624,54.20638
+15625,59.601074
+15626,59.112457
+15627,61.576374
+15628,49.747677
+15629,52.725285
+15630,51.11026
+15631,55.0383
+15632,38.708504
+15633,39.48905
+15634,40.038666
+15635,42.249275
+15636,44.074745
+15637,54.955223
+15638,58.64199
+15639,61.200283
+15640,63.825874
+15641,67.2524
+15642,36.714104
+15643,43.20234
+15644,45.473648
+15645,49.085106
+15646,53.4628
+15647,55.808964
+15648,55.184856
+15649,56.832233
+15650,60.4435
+15651,59.76878
+15652,9.353336
+15653,9.851372
+15654,11.737349
+15655,11.477831
+15656,13.352491
+15657,13.927589
+15658,14.070783
+15659,16.483295
+15660,17.82765
+15661,19.704689
+15662,21.190918
+15663,25.436152
+15664,26.817396
+15665,28.807425
+15666,34.088333
+15667,34.41124
+15668,36.442226
+15669,36.93377
+15670,42.082127
+15671,42.01004
+15672,48.3466
+15673,54.595356
+15674,51.66632
+15675,14.598892
+15676,17.019638
+15677,17.88433
+15678,23.511812
+15679,24.277365
+15680,24.979996
+15681,27.545273
+15682,40.536995
+15683,36.513306
+15684,36.6698
+15685,44.01597
+15686,17.885586
+15687,19.831308
+15688,24.054646
+15689,25.394249
+15690,28.808681
+15691,31.658419
+15692,30.647575
+15693,32.197014
+15694,34.412693
+15695,37.422325
+15696,39.86512
+15697,36.746033
+15698,31.139206
+15699,30.822716
+15700,29.701374
+15701,41.388317
+15702,46.55207
+15703,49.223408
+15704,51.684258
+15705,53.732273
+15706,56.698383
+15707,59.913456
+15708,60.77434
+15709,5.046187
+15710,6.9968195
+15711,9.141471
+15712,14.852681
+15713,17.424332
+15714,40.549404
+15715,42.094975
+15716,43.146183
+15717,45.336388
+15718,47.882683
+15719,49.01304
+15720,52.025978
+15721,51.63183
+15722,54.598267
+15723,57.042744
+15724,56.34558
+15725,56.30326
+15726,16.618317
+15727,20.863304
+15728,23.956602
+15729,23.955873
+15730,27.124428
+15731,31.460276
+15732,30.856512
+15733,21.343992
+15734,28.083057
+15735,29.081203
+15736,31.251387
+15737,18.116411
+15738,19.429665
+15739,20.55093
+15740,22.389269
+15741,24.586212
+15742,25.968773
+15743,29.005417
+15744,32.38163
+15745,36.24283
+15746,39.971233
+15747,36.585587
+15748,38.5671
+15749,16.215593
+15750,17.387272
+15751,20.885054
+15752,28.03003
+15753,29.246725
+15754,19.301037
+15755,20.819792
+15756,23.751162
+15757,26.360882
+15758,12.829411
+15759,16.632425
+15760,19.648441
+15761,23.919914
+15762,26.5246
+15763,34.13347
+15764,33.25212
+15765,34.910454
+15766,36.95961
+15767,38.678413
+15768,41.18901
+15769,45.123497
+15770,26.038702
+15771,35.82525
+15772,39.73755
+15773,41.88646
+15774,24.100002
+15775,25.09452
+15776,24.510262
+15777,27.719324
+15778,16.036922
+15779,15.019281
+15780,18.732445
+15781,20.058044
+15782,33.14093
+15783,34.859116
+15784,40.744854
+15785,47.315304
+15786,49.55887
+15787,51.81565
+15788,25.335367
+15789,32.105625
+15790,33.456947
+15791,33.544506
+15792,36.623535
+15793,41.09302
+15794,43.77836
+15795,45.440044
+15796,47.564064
+15797,50.64379
+15798,49.242393
+15799,50.623787
+15800,50.93487
+15801,51.449326
+15802,52.61378
+15803,55.928627
+15804,66.01763
+15805,67.34245
+15806,70.112045
+15807,83.77696
+15808,84.04467
+15809,84.44685
+15810,80.281265
+15811,85.515175
+15812,24.695013
+15813,27.42675
+15814,30.126257
+15815,30.927938
+15816,35.19811
+15817,37.262302
+15818,37.134865
+15819,40.340176
+15820,44.583702
+15821,46.667152
+15822,48.014336
+15823,51.08771
+15824,17.189917
+15825,16.916742
+15826,24.010292
+15827,27.644844
+15828,41.26402
+15829,44.420967
+15830,45.54674
+15831,48.188072
+15832,50.616035
+15833,53.247646
+15834,54.710526
+15835,56.910362
+15836,57.566376
+15837,11.112165
+15838,15.339484
+15839,15.853175
+15840,16.79394
+15841,19.51263
+15842,20.664488
+15843,30.154123
+15844,34.983128
+15845,20.765978
+15846,20.437506
+15847,27.875324
+15848,46.031704
+15849,49.08574
+15850,51.279903
+15851,53.353386
+15852,60.54062
+15853,63.406006
+15854,17.856247
+15855,24.663298
+15856,26.226398
+15857,28.232346
+15858,20.537483
+15859,23.30154
+15860,28.129656
+15861,32.310104
+15862,24.687958
+15863,32.504135
+15864,37.356125
+15865,35.04734
+15866,39.18638
+15867,42.72632
+15868,22.52897
+15869,24.837885
+15870,29.673006
+15871,31.457922
+15872,34.432728
+15873,35.948093
+15874,38.15193
+15875,40.53366
+15876,33.64132
+15877,35.96504
+15878,35.123672
+15879,38.04094
+15880,37.612225
+15881,38.862556
+15882,42.51864
+15883,44.563335
+15884,45.237045
+15885,45.751072
+15886,46.341393
+15887,30.851677
+15888,32.78191
+15889,34.80099
+15890,38.555275
+15891,37.487648
+15892,41.728016
+15893,45.04864
+15894,45.606544
+15895,47.858147
+15896,48.743233
+15897,51.30933
+15898,51.97133
+15899,40.225063
+15900,40.687435
+15901,44.065384
+15902,47.03899
+15903,51.691116
+15904,54.115345
+15905,53.585472
+15906,59.10551
+15907,59.65061
+15908,59.65516
+15909,61.40084
+15910,63.31791
+15911,63.46561
+15912,69.2804
+15913,66.35077
+15914,70.895584
+15915,72.59475
+15916,15.982987
+15917,16.796995
+15918,17.847345
+15919,19.786983
+15920,23.112137
+15921,33.07815
+15922,36.111732
+15923,33.55406
+15924,35.33878
+15925,38.81163
+15926,39.809578
+15927,42.02982
+15928,54.446724
+15929,55.423187
+15930,59.8773
+15931,63.01546
+15932,66.330864
+15933,67.715744
+15934,67.30237
+15935,69.33984
+15936,70.10156
+15937,72.053856
+15938,73.61587
+15939,77.20727
+15940,9.469662
+15941,16.527548
+15942,22.70293
+15943,22.709497
+15944,43.40915
+15945,44.398098
+15946,47.380013
+15947,53.483326
+15948,19.583551
+15949,21.640062
+15950,23.154446
+15951,27.06738
+15952,26.825203
+15953,32.405735
+15954,33.66596
+15955,38.09516
+15956,41.78276
+15957,42.046783
+15958,46.85657
+15959,48.11856
+15960,29.772425
+15961,36.17372
+15962,37.18351
+15963,53.08077
+15964,35.004524
+15965,35.419384
+15966,37.134888
+15967,36.81737
+15968,31.371534
+15969,35.909447
+15970,36.709015
+15971,38.676292
+15972,43.309177
+15973,45.779015
+15974,51.954617
+15975,57.42884
+15976,60.27465
+15977,61.082783
+15978,63.98705
+15979,69.067215
+15980,25.817242
+15981,30.549961
+15982,40.482502
+15983,50.38115
+15984,25.431778
+15985,36.208103
+15986,39.212193
+15987,39.04493
+15988,8.47202
+15989,11.4031515
+15990,12.830614
+15991,15.964945
+15992,40.304848
+15993,38.939484
+15994,39.285255
+15995,43.824097
+15996,42.47942
+15997,40.35168
+15998,42.170544
+15999,43.405655
+16000,44.665962
+16001,46.99751
+16002,45.26283
+16003,48.867195
+16004,40.77789
+16005,44.882538
+16006,54.036644
+16007,63.017677
+16008,40.31539
+16009,50.050392
+16010,48.54281
+16011,44.47422
+16012,45.287598
+16013,50.035446
+16014,46.3189
+16015,52.223557
+16016,43.00744
+16017,50.329124
+16018,53.92682
+16019,51.14332
+16020,44.41582
+16021,51.69511
+16022,55.535507
+16023,63.008003
+16024,23.21759
+16025,24.01339
+16026,25.26606
+16027,30.470543
+16028,39.120335
+16029,38.66078
+16030,43.504787
+16031,46.09945
+16032,43.704292
+16033,45.660606
+16034,49.550568
+16035,53.340855
+16036,11.785309
+16037,11.281282
+16038,14.338924
+16039,18.38576
+16040,29.598566
+16041,30.15911
+16042,27.401817
+16043,31.113817
+16044,32.52453
+16045,35.97017
+16046,36.204647
+16047,39.61523
+16048,19.973253
+16049,19.61782
+16050,20.825876
+16051,26.075056
+16052,21.489706
+16053,27.244446
+16054,28.577324
+16055,31.303383
+16056,18.400349
+16057,28.206617
+16058,30.051395
+16059,26.283978
+16060,29.108751
+16061,31.256365
+16062,33.90476
+16063,37.757862
+16064,38.544624
+16065,23.665379
+16066,24.089571
+16067,26.120193
+16068,28.85155
+16069,31.828983
+16070,31.392231
+16071,0.26641482
+16072,-0.0009584576
+16073,0.10043505
+16074,1.207359
+16075,2.8752503
+16076,8.480807
+16077,8.836723
+16078,9.5552845
+16079,11.017908
+16080,64.87895
+16081,66.4685
+16082,69.83455
+16083,70.462715
+16084,54.514275
+16085,51.34754
+16086,53.14281
+16087,55.46843
+16088,33.520428
+16089,32.94115
+16090,34.721676
+16091,36.251793
+16092,9.468141
+16093,11.717979
+16094,12.6938505
+16095,16.5449
+16096,15.527754
+16097,21.261177
+16098,25.554226
+16099,27.24206
+16100,28.073671
+16101,17.92312
+16102,19.065042
+16103,19.56019
+16104,22.73545
+16105,26.29575
+16106,31.420048
+16107,34.77753
+16108,26.670118
+16109,29.99689
+16110,31.609123
+16111,32.766792
+16112,34.63359
+16113,38.81981
+16114,40.15319
+16115,42.30748
+16116,42.362465
+16117,45.75774
+16118,49.927204
+16119,48.317684
+16120,41.309376
+16121,41.402348
+16122,40.944042
+16123,45.047333
+16124,48.326973
+16125,48.229965
+16126,52.09325
+16127,52.29821
+16128,52.23468
+16129,55.113983
+16130,54.662506
+16131,56.721226
+16132,4.6775627
+16133,7.619403
+16134,14.619229
+16135,15.394142
+16136,30.762957
+16137,34.1015
+16138,37.514336
+16139,42.795288
+16140,47.24606
+16141,15.10217
+16142,16.031067
+16143,16.885859
+16144,16.934237
+16145,19.474167
+16146,20.381355
+16147,27.748585
+16148,32.518593
+16149,25.89028
+16150,26.130306
+16151,27.524794
+16152,28.48143
+16153,29.649357
+16154,30.597912
+16155,19.497898
+16156,20.992138
+16157,25.110245
+16158,27.500536
+16159,27.624256
+16160,12.493107
+16161,13.998224
+16162,15.976952
+16163,19.57983
+16164,20.368164
+16165,21.885218
+16166,22.963932
+16167,25.991285
+16168,24.377796
+16169,29.04512
+16170,30.497974
+16171,31.991293
+16172,0.61560243
+16173,0.94862634
+16174,0.6263017
+16175,0.79016477
+16176,35.65661
+16177,38.429283
+16178,45.383907
+16179,49.427498
+16180,52.321854
+16181,24.38498
+16182,27.558561
+16183,30.530785
+16184,31.331799
+16185,37.459476
+16186,39.146107
+16187,20.386707
+16188,22.148859
+16189,28.206905
+16190,31.479364
+16191,32.422943
+16192,23.152071
+16193,26.768908
+16194,30.55415
+16195,35.171185
+16196,39.100487
+16197,40.364708
+16198,45.142
+16199,44.22091
+16200,48.718468
+16201,51.155678
+16202,51.82845
+16203,52.35315
+16204,23.177864
+16205,25.391188
+16206,22.785582
+16207,25.377077
+16208,24.563503
+16209,27.964668
+16210,30.486906
+16211,33.00574
+16212,35.06869
+16213,36.664536
+16214,43.356895
+16215,45.270325
+16216,29.531681
+16217,35.279884
+16218,37.68143
+16219,40.026455
+16220,39.937023
+16221,40.95915
+16222,41.88723
+16223,43.092422
+16224,48.912895
+16225,9.286336
+16226,10.2435465
+16227,11.073057
+16228,11.749873
+16229,15.9697075
+16230,16.349537
+16231,17.696056
+16232,18.568256
+16233,24.322105
+16234,28.864994
+16235,20.517971
+16236,19.065382
+16237,23.464863
+16238,26.102158
+16239,31.12842
+16240,33.899242
+16241,37.138542
+16242,38.1242
+16243,41.1194
+16244,43.71377
+16245,47.748013
+16246,50.249195
+16247,10.091554
+16248,10.959127
+16249,13.056893
+16250,15.29619
+16251,18.47467
+16252,21.885206
+16253,22.022251
+16254,25.905266
+16255,27.550444
+16256,35.16453
+16257,34.730255
+16258,36.76955
+16259,10.596926
+16260,12.336008
+16261,18.69393
+16262,20.901436
+16263,21.60519
+16264,23.872292
+16265,28.408096
+16266,31.865051
+16267,32.35869
+16268,33.267628
+16269,35.56096
+16270,33.857143
+16271,10.010189
+16272,13.875319
+16273,17.235174
+16274,24.11039
+16275,46.03308
+16276,50.74673
+16277,54.33151
+16278,54.299156
+16279,56.317947
+16280,57.432304
+16281,61.907227
+16282,64.89632
+16283,64.22806
+16284,65.31639
+16285,68.25663
+16286,70.71295
+16287,18.416824
+16288,21.968142
+16289,23.882133
+16290,26.047394
+16291,31.74751
+16292,35.06457
+16293,40.31945
+16294,40.491806
+16295,47.203163
+16296,48.424698
+16297,55.656364
+16298,46.70003
+16299,47.550594
+16300,49.625954
+16301,49.95423
+16302,53.188637
+16303,51.612217
+16304,53.82271
+16305,54.590065
+16306,56.175243
+16307,58.076653
+16308,60.455837
+16309,63.013805
+16310,21.630234
+16311,28.56021
+16312,32.49349
+16313,32.610855
+16314,52.075214
+16315,54.578735
+16316,58.46903
+16317,62.017433
+16318,64.31956
+16319,64.06058
+16320,67.93559
+16321,68.88248
+16322,68.99538
+16323,69.460976
+16324,71.71819
+16325,19.782366
+16326,24.532953
+16327,32.675488
+16328,37.489067
+16329,29.417562
+16330,33.384777
+16331,35.050766
+16332,32.656963
+16333,37.870335
+16334,7.1464305
+16335,10.615007
+16336,14.287686
+16337,16.702438
+16338,8.47285
+16339,7.2206216
+16340,13.87931
+16341,15.569515
+16342,16.430555
+16343,18.78643
+16344,26.103584
+16345,24.480616
+16346,27.911829
+16347,31.06948
+16348,34.804817
+16349,41.806004
+16350,27.222204
+16351,28.192774
+16352,30.092648
+16353,32.967087
+16354,39.45793
+16355,38.88749
+16356,43.9635
+16357,43.978127
+16358,45.56745
+16359,55.066658
+16360,59.193436
+16361,58.122833
+16362,17.382961
+16363,20.482359
+16364,18.575302
+16365,19.070652
+16366,22.253746
+16367,25.215816
+16368,27.419971
+16369,29.582167
+16370,31.600517
+16371,36.859974
+16372,43.42604
+16373,46.095005
+16374,48.926098
+16375,50.395424
+16376,57.818672
+16377,56.859253
+16378,61.402096
+16379,34.872116
+16380,40.215076
+16381,45.333366
+16382,46.81877
+16383,45.711334
+16384,15.498141
+16385,15.403291
+16386,20.18574
+16387,20.77901
+16388,16.962267
+16389,19.960825
+16390,24.15247
+16391,26.668324
+16392,28.271896
+16393,29.262465
+16394,30.517475
+16395,37.779873
+16396,45.688118
+16397,49.287598
+16398,49.064175
+16399,16.010584
+16400,17.340042
+16401,18.850212
+16402,19.67065
+16403,21.552216
+16404,21.70137
+16405,25.372553
+16406,29.100248
+16407,31.30115
+16408,34.43698
+16409,36.082615
+16410,38.656307
+16411,31.50747
+16412,32.206764
+16413,31.077759
+16414,31.33181
+16415,33.29313
+16416,34.57209
+16417,35.80336
+16418,37.30456
+16419,39.30197
+16420,42.725967
+16421,44.89524
+16422,46.7574
+16423,43.986347
+16424,46.31361
+16425,48.259212
+16426,49.18189
+16427,51.085167
+16428,52.662582
+16429,54.56613
+16430,58.993896
+16431,25.28517
+16432,26.413452
+16433,29.103188
+16434,28.135792
+16435,31.55166
+16436,39.375736
+16437,14.56847
+16438,16.714176
+16439,18.465132
+16440,21.115393
+16441,25.221348
+16442,25.621088
+16443,32.81507
+16444,31.167755
+16445,38.973892
+16446,41.213264
+16447,39.701527
+16448,48.14171
+16449,53.660095
+16450,57.69193
+16451,7.5553846
+16452,10.08057
+16453,12.378086
+16454,17.191319
+16455,21.367737
+16456,22.233107
+16457,26.763885
+16458,47.713146
+16459,48.92184
+16460,51.2229
+16461,52.67646
+16462,53.869484
+16463,54.93544
+16464,56.591103
+16465,58.479122
+16466,59.076157
+16467,59.90853
+16468,61.595963
+16469,63.604713
+16470,17.788288
+16471,21.317879
+16472,35.337242
+16473,39.897358
+16474,26.471733
+16475,30.20402
+16476,30.880508
+16477,37.662296
+16478,22.97036
+16479,24.547888
+16480,29.721176
+16481,35.220055
+16482,35.0979
+16483,42.730526
+16484,45.819546
+16485,43.43175
+16486,46.92603
+16487,55.130333
+16488,52.160088
+16489,57.789467
+16490,13.869881
+16491,15.765518
+16492,15.609619
+16493,17.868172
+16494,20.595959
+16495,22.841553
+16496,23.474579
+16497,26.324688
+16498,30.850676
+16499,31.479818
+16500,16.736519
+16501,19.125853
+16502,26.176588
+16503,30.376274
+16504,5.371456
+16505,6.6151495
+16506,12.100758
+16507,16.775698
+16508,14.379876
+16509,18.92892
+16510,22.741552
+16511,20.173157
+16512,21.00791
+16513,29.287485
+16514,31.59423
+16515,33.763412
+16516,12.206786
+16517,13.862836
+16518,14.95569
+16519,15.7760725
+16520,8.608191
+16521,9.392164
+16522,11.961378
+16523,15.078084
+16524,18.07523
+16525,21.34336
+16526,23.675322
+16527,24.363075
+16528,35.60574
+16529,40.63372
+16530,42.717
+16531,46.984615
+16532,48.88101
+16533,47.704838
+16534,50.291496
+16535,52.47343
+16536,52.343903
+16537,54.797974
+16538,54.006207
+16539,58.297226
+16540,58.645237
+16541,59.09301
+16542,57.28154
+16543,24.636631
+16544,26.043251
+16545,30.588339
+16546,35.181667
+16547,37.154964
+16548,44.46447
+16549,46.812008
+16550,45.437035
+16551,45.315407
+16552,50.37461
+16553,52.99275
+16554,56.48188
+16555,7.044345
+16556,8.93651
+16557,13.484304
+16558,17.634102
+16559,77.5384
+16560,80.82782
+16561,80.604675
+16562,80.23805
+16563,89.8
+16564,17.964924
+16565,18.268034
+16566,19.1714
+16567,24.09708
+16568,26.838892
+16569,30.57269
+16570,35.979336
+16571,37.124283
+16572,43.4746
+16573,42.87705
+16574,49.798462
+16575,48.945847
+16576,54.98345
+16577,58.49036
+16578,60.585552
+16579,63.50635
+16580,68.10964
+16581,69.63542
+16582,71.03835
+16583,74.203156
+16584,72.859886
+16585,73.686264
+16586,74.60034
+16587,76.547165
+16588,47.49724
+16589,45.467495
+16590,49.12169
+16591,53.203033
+16592,17.322033
+16593,21.103218
+16594,25.229769
+16595,25.768032
+16596,25.856588
+16597,30.475668
+16598,33.88184
+16599,36.293797
+16600,35.71049
+16601,41.32984
+16602,43.142044
+16603,42.354202
+16604,17.161776
+16605,19.728611
+16606,19.773718
+16607,21.193192
+16608,25.620258
+16609,23.737755
+16610,35.831993
+16611,39.367683
+16612,35.648506
+16613,40.237797
+16614,42.698784
+16615,43.214302
+16616,41.934685
+16617,49.218132
+16618,50.393715
+16619,47.661346
+16620,48.496048
+16621,51.117977
+16622,54.43621
+16623,55.134712
+16624,54.908875
+16625,56.27138
+16626,54.55207
+16627,61.86711
+16628,60.686348
+16629,70.2883
+16630,78.49089
+16631,78.790054
+16632,81.996796
+16633,81.5601
+16634,77.629776
+16635,82.93973
+16636,85.44516
+16637,82.521904
+16638,38.073967
+16639,40.654
+16640,45.432686
+16641,53.621845
+16642,57.08123
+16643,59.71268
+16644,26.79074
+16645,33.456768
+16646,38.465393
+16647,40.526463
+16648,42.57916
+16649,56.00094
+16650,13.4289875
+16651,20.477112
+16652,27.285652
+16653,35.603394
+16654,42.452843
+16655,36.833366
+16656,38.71409
+16657,43.281853
+16658,45.35084
+16659,48.01139
+16660,51.276817
+16661,56.86294
+16662,59.068104
+16663,58.271774
+16664,61.115555
+16665,62.245167
+16666,67.792
+16667,7.856657
+16668,11.221097
+16669,13.570565
+16670,17.98014
+16671,28.516855
+16672,44.72089
+16673,46.983124
+16674,49.81309
+16675,23.397503
+16676,29.084293
+16677,34.97121
+16678,35.98486
+16679,32.98438
+16680,35.309837
+16681,35.21756
+16682,37.40696
+16683,39.30597
+16684,44.478485
+16685,26.834301
+16686,30.52011
+16687,33.496216
+16688,35.196568
+16689,39.59156
+16690,42.507412
+16691,43.988052
+16692,44.702465
+16693,15.847311
+16694,20.198217
+16695,21.732307
+16696,19.614828
+16697,18.332184
+16698,26.820095
+16699,28.493042
+16700,31.683311
+16701,45.783085
+16702,52.015724
+16703,55.311474
+16704,62.55061
+16705,30.74533
+16706,32.912613
+16707,36.450554
+16708,37.607765
+16709,40.704887
+16710,43.659374
+16711,44.78068
+16712,48.87153
+16713,50.49373
+16714,49.945633
+16715,52.216938
+16716,52.12397
+16717,24.784218
+16718,26.46629
+16719,30.139595
+16720,39.76163
+16721,42.705357
+16722,50.101234
+16723,20.196903
+16724,22.64015
+16725,23.943668
+16726,25.789782
+16727,29.073801
+16728,29.922096
+16729,34.683037
+16730,35.493217
+16731,37.27803
+16732,39.263687
+16733,13.027699
+16734,13.801984
+16735,14.812025
+16736,15.57729
+16737,18.625782
+16738,21.489645
+16739,25.8214
+16740,24.135557
+16741,28.221668
+16742,17.170689
+16743,22.607916
+16744,25.267618
+16745,27.707512
+16746,29.240429
+16747,6.610457
+16748,8.905359
+16749,10.396066
+16750,17.829416
+16751,19.607094
+16752,20.400778
+16753,24.843523
+16754,26.930773
+16755,28.645905
+16756,29.789843
+16757,32.211044
+16758,34.03918
+16759,5.800488
+16760,6.5001597
+16761,10.644418
+16762,13.710267
+16763,18.018877
+16764,19.763855
+16765,21.82009
+16766,23.355852
+16767,26.816803
+16768,26.951887
+16769,27.895693
+16770,31.076605
+16771,20.33739
+16772,24.116507
+16773,27.06408
+16774,29.490623
+16775,27.789707
+16776,38.02573
+16777,40.569725
+16778,40.486267
+16779,30.082012
+16780,30.56792
+16781,31.738007
+16782,32.29605
+16783,32.60991
+16784,34.792393
+16785,21.308338
+16786,21.732958
+16787,25.50656
+16788,30.655136
+16789,32.625618
+16790,38.811806
+16791,42.456703
+16792,44.877304
+16793,43.076687
+16794,49.41928
+16795,52.335327
+16796,54.78001
+16797,36.48948
+16798,38.635452
+16799,38.080105
+16800,40.656994
+16801,51.502026
+16802,10.656025
+16803,14.692658
+16804,15.761832
+16805,22.51529
+16806,24.238401
+16807,26.648516
+16808,28.275524
+16809,29.596706
+16810,35.33959
+16811,43.26767
+16812,40.738525
+16813,41.321815
+16814,43.028667
+16815,43.15695
+16816,44.111664
+16817,47.19305
+16818,51.814304
+16819,53.13543
+16820,58.80452
+16821,18.983763
+16822,19.421167
+16823,27.420946
+16824,29.658169
+16825,31.977316
+16826,32.437897
+16827,35.230156
+16828,32.811264
+16829,35.00614
+16830,36.457012
+16831,39.392445
+16832,43.384823
+16833,4.7940536
+16834,6.596765
+16835,12.724096
+16836,17.659912
+16837,38.172092
+16838,45.40304
+16839,45.906235
+16840,50.46917
+16841,52.33656
+16842,51.497353
+16843,55.35956
+16844,55.798393
+16845,54.800705
+16846,56.022293
+16847,56.739735
+16848,57.004547
+16849,48.54474
+16850,52.50378
+16851,56.827984
+16852,56.339386
+16853,59.166046
+16854,60.958054
+16855,61.59227
+16856,64.434235
+16857,67.81164
+16858,70.9232
+16859,85.11887
+16860,86.33614
+16861,29.391869
+16862,32.052135
+16863,34.866528
+16864,40.91469
+16865,42.751396
+16866,46.218525
+16867,46.176315
+16868,49.011757
+16869,50.878437
+16870,51.181385
+16871,52.21315
+16872,54.322346
+16873,48.07786
+16874,50.086815
+16875,53.61969
+16876,55.794456
+16877,60.09085
+16878,22.475443
+16879,25.77325
+16880,26.661781
+16881,30.072884
+16882,33.782703
+16883,33.87172
+16884,35.858654
+16885,41.843437
+16886,42.51058
+16887,44.54386
+16888,47.206505
+16889,49.455063
+16890,49.54444
+16891,53.59838
+16892,53.715622
+16893,55.87484
+16894,57.375015
+16895,58.227577
+16896,25.522799
+16897,28.64545
+16898,30.45202
+16899,31.291159
+16900,34.848072
+16901,40.947697
+16902,42.085457
+16903,47.162403
+16904,48.344604
+16905,50.539207
+16906,51.43821
+16907,55.659405
+16908,10.687309
+16909,12.88666
+16910,15.26425
+16911,13.069946
+16912,18.696981
+16913,21.60382
+16914,23.279573
+16915,28.811201
+16916,25.547482
+16917,27.361038
+16918,33.63852
+16919,33.07668
+16920,26.558483
+16921,26.284266
+16922,24.433416
+16923,26.783558
+16924,26.813183
+16925,28.714146
+16926,31.493605
+16927,32.88211
+16928,35.47709
+16929,33.233456
+16930,35.95784
+16931,37.968876
+16932,25.065659
+16933,26.304966
+16934,26.62521
+16935,28.920038
+16936,28.889692
+16937,29.262909
+16938,35.848923
+16939,34.497673
+16940,24.254808
+16941,23.318798
+16942,27.866238
+16943,32.140205
+16944,34.988144
+16945,40.484695
+16946,42.738438
+16947,46.23974
+16948,49.091473
+16949,49.87446
+16950,54.210785
+16951,54.5596
+16952,6.958663
+16953,11.3234415
+16954,13.570308
+16955,12.857825
+16956,15.150247
+16957,16.306826
+16958,18.356335
+16959,20.860611
+16960,21.722446
+16961,21.763329
+16962,23.448936
+16963,22.723705
+16964,0.003664867
+16965,0.71938443
+16966,1.7414198
+16967,4.5988936
+16968,5.9245043
+16969,7.705365
+16970,8.350761
+16971,9.326334
+16972,38.31336
+16973,41.572807
+16974,41.08018
+16975,43.86009
+16976,47.608402
+16977,48.623047
+16978,54.384846
+16979,56.453686
+16980,57.82499
+16981,56.468895
+16982,58.63171
+16983,61.34543
+16984,40.055286
+16985,44.518715
+16986,46.894417
+16987,50.23489
+16988,35.691895
+16989,40.75455
+16990,46.985165
+16991,52.466568
+16992,18.413437
+16993,19.07947
+16994,20.039959
+16995,21.61722
+16996,21.90852
+16997,24.261784
+16998,26.158464
+16999,27.810883
+17000,30.066345
+17001,36.732136
+17002,46.323692
+17003,44.198006
+17004,39.349323
+17005,39.933872
+17006,40.373795
+17007,41.322426
+17008,43.076828
+17009,43.573807
+17010,46.33837
+17011,56.196255
+17012,53.920246
+17013,53.516468
+17014,64.77635
+17015,47.1445
+17016,51.47325
+17017,55.166916
+17018,57.808018
+17019,9.503628
+17020,11.73641
+17021,15.371853
+17022,19.426004
+17023,37.188717
+17024,41.052433
+17025,41.544296
+17026,43.136726
+17027,44.424984
+17028,48.819847
+17029,49.48214
+17030,49.238937
+17031,49.421482
+17032,28.859007
+17033,32.0689
+17034,33.903625
+17035,33.921936
+17036,38.231045
+17037,40.55897
+17038,42.759842
+17039,49.020103
+17040,48.833572
+17041,52.178555
+17042,55.24236
+17043,56.988968
+17044,9.636357
+17045,11.538946
+17046,18.917479
+17047,23.642096
+17048,48.380985
+17049,52.695786
+17050,53.111862
+17051,57.074085
+17052,58.25829
+17053,59.379704
+17054,64.98982
+17055,65.04687
+17056,67.39745
+17057,67.94464
+17058,71.87124
+17059,73.235504
+17060,30.652426
+17061,31.846071
+17062,32.79265
+17063,34.813232
+17064,39.07576
+17065,38.845776
+17066,43.26889
+17067,44.77311
+17068,46.611774
+17069,53.322258
+17070,12.548323
+17071,19.040844
+17072,20.818071
+17073,20.972748
+17074,23.218113
+17075,23.618206
+17076,0.90259844
+17077,2.9007611
+17078,3.8258574
+17079,5.1761103
+17080,38.63478
+17081,45.14197
+17082,53.02503
+17083,55.680035
+17084,26.657356
+17085,28.702988
+17086,36.662067
+17087,42.345028
+17088,41.410484
+17089,26.6881
+17090,33.470737
+17091,35.92183
+17092,34.63651
+17093,37.235672
+17094,38.503254
+17095,41.297417
+17096,20.745499
+17097,21.30761
+17098,22.54049
+17099,24.277786
+17100,31.074917
+17101,31.37172
+17102,39.35638
+17103,42.896572
+17104,44.891666
+17105,46.488285
+17106,47.10949
+17107,49.212738
+17108,12.687351
+17109,14.414202
+17110,16.089989
+17111,22.95641
+17112,27.318277
+17113,26.957863
+17114,32.787025
+17115,38.572357
+17116,38.77777
+17117,40.453842
+17118,43.17255
+17119,49.08429
+17120,5.4439883
+17121,5.865328
+17122,11.2126045
+17123,16.560595
+17124,17.095882
+17125,19.148022
+17126,24.276491
+17127,34.934246
+17128,33.898872
+17129,33.652813
+17130,35.015705
+17131,40.26893
+17132,36.102703
+17133,39.29547
+17134,38.937885
+17135,46.596027
+17136,44.655193
+17137,43.683117
+17138,44.35527
+17139,46.436523
+17140,48.731415
+17141,48.782852
+17142,48.25382
+17143,50.147503
+17144,31.404081
+17145,42.644554
+17146,42.40435
+17147,38.81374
+17148,40.85941
+17149,41.7462
+17150,44.143322
+17151,46.903725
+17152,48.89617
+17153,50.07263
+17154,50.553986
+17155,52.151306
+17156,42.274418
+17157,46.18457
+17158,48.643387
+17159,51.233215
+17160,23.80799
+17161,27.266062
+17162,31.219097
+17163,35.05165
+17164,37.1319
+17165,42.291626
+17166,46.242325
+17167,46.29796
+17168,50.211338
+17169,52.850563
+17170,53.297096
+17171,54.174538
+17172,16.542332
+17173,16.357813
+17174,15.475657
+17175,17.467564
+17176,21.454943
+17177,23.820152
+17178,25.102825
+17179,26.586115
+17180,25.279045
+17181,33.824715
+17182,36.045048
+17183,38.48735
+17184,46.658215
+17185,53.058155
+17186,61.285717
+17187,65.47856
+17188,31.798454
+17189,34.854233
+17190,40.14748
+17191,44.25927
+17192,46.041786
+17193,51.040894
+17194,52.07933
+17195,52.10501
+17196,57.106434
+17197,57.80698
+17198,29.59379
+17199,29.969547
+17200,30.548721
+17201,31.560629
+17202,10.869982
+17203,18.03054
+17204,27.101404
+17205,30.481949
+17206,22.55845
+17207,25.971445
+17208,27.631887
+17209,29.027378
+17210,31.624348
+17211,30.771206
+17212,33.784683
+17213,36.631836
+17214,27.613966
+17215,29.229565
+17216,35.967392
+17217,35.374866
+17218,42.12274
+17219,40.811584
+17220,44.480232
+17221,45.311584
+17222,46.818684
+17223,48.062695
+17224,50.101524
+17225,50.515472
+17226,40.304855
+17227,41.739494
+17228,46.34079
+17229,54.709656
+17230,50.36099
+17231,54.632893
+17232,62.622498
+17233,56.124157
+17234,59.202423
+17235,58.699078
+17236,60.28469
+17237,61.745888
+17238,36.2809
+17239,40.485226
+17240,40.894
+17241,43.186497
+17242,48.27718
+17243,52.66986
+17244,51.53746
+17245,52.38684
+17246,54.751114
+17247,58.73329
+17248,60.300945
+17249,59.13461
+17250,18.653423
+17251,24.501179
+17252,26.331587
+17253,30.054949
+17254,31.705414
+17255,32.734756
+17256,35.796818
+17257,40.2697
+17258,43.71509
+17259,45.594303
+17260,49.332695
+17261,50.340828
+17262,20.062477
+17263,22.089142
+17264,22.226625
+17265,24.784666
+17266,27.76968
+17267,30.332802
+17268,35.499275
+17269,36.927773
+17270,42.092693
+17271,45.855114
+17272,48.54727
+17273,40.366108
+17274,44.189102
+17275,47.897293
+17276,47.050648
+17277,51.00073
+17278,52.66754
+17279,53.68242
+17280,56.37931
+17281,57.763157
+17282,60.18786
+17283,60.95849
+17284,61.665447
+17285,23.41637
+17286,28.745102
+17287,32.310543
+17288,31.567448
+17289,28.803902
+17290,30.048803
+17291,33.531033
+17292,41.398373
+17293,44.506294
+17294,35.545235
+17295,36.048298
+17296,38.641575
+17297,41.32675
+17298,45.649963
+17299,51.544983
+17300,48.693047
+17301,52.067375
+17302,52.81408
+17303,55.3167
+17304,59.195484
+17305,62.100452
+17306,22.758114
+17307,19.922943
+17308,27.51205
+17309,25.141922
+17310,27.591564
+17311,32.345055
+17312,33.059364
+17313,38.622215
+17314,41.161346
+17315,40.886925
+17316,41.948532
+17317,34.65902
+17318,34.680172
+17319,38.34809
+17320,40.865093
+17321,38.118725
+17322,39.82036
+17323,42.439167
+17324,48.90577
+17325,43.52582
+17326,48.827515
+17327,52.992046
+17328,55.398884
+17329,13.518114
+17330,16.836979
+17331,27.523075
+17332,33.351383
+17333,33.208645
+17334,23.641144
+17335,31.421825
+17336,30.344334
+17337,34.929504
+17338,38.71443
+17339,39.32334
+17340,39.434864
+17341,36.07052
+17342,37.831936
+17343,39.22652
+17344,40.14396
+17345,41.95646
+17346,42.42575
+17347,44.56549
+17348,44.433678
+17349,44.426773
+17350,47.063705
+17351,47.961704
+17352,50.747818
+17353,25.763561
+17354,31.209223
+17355,39.41689
+17356,43.250923
+17357,27.680424
+17358,28.477392
+17359,33.80268
+17360,36.275658
+17361,40.901173
+17362,46.354347
+17363,45.9482
+17364,46.36092
+17365,50.089733
+17366,53.619762
+17367,55.724907
+17368,23.219267
+17369,28.148914
+17370,29.376722
+17371,28.925749
+17372,35.768246
+17373,39.440388
+17374,38.95513
+17375,49.72439
+17376,54.93861
+17377,57.11197
+17378,62.095215
+17379,64.45172
+17380,26.60106
+17381,29.409822
+17382,34.681564
+17383,37.69059
+17384,11.0434265
+17385,12.474919
+17386,12.910807
+17387,17.807
+17388,19.880913
+17389,21.21852
+17390,24.802662
+17391,34.44406
+17392,41.07763
+17393,47.820835
+17394,48.96764
+17395,29.615967
+17396,31.213007
+17397,31.95539
+17398,38.049362
+17399,40.411705
+17400,41.452766
+17401,45.280445
+17402,45.273792
+17403,48.562515
+17404,49.826023
+17405,51.535778
+17406,52.847122
+17407,30.591385
+17408,34.064682
+17409,36.91256
+17410,42.441338
+17411,45.51204
+17412,48.24102
+17413,52.715622
+17414,63.942844
+17415,30.204119
+17416,34.803074
+17417,40.230595
+17418,40.32527
+17419,46.302326
+17420,45.4469
+17421,45.50816
+17422,52.239075
+17423,51.38878
+17424,53.607376
+17425,58.11487
+17426,62.21004
+17427,56.387905
+17428,58.506653
+17429,58.706852
+17430,58.30661
+17431,24.779716
+17432,40.875305
+17433,42.49008
+17434,46.883354
+17435,41.36045
+17436,42.842598
+17437,45.76307
+17438,48.610058
+17439,2.8714364
+17440,3.1045473
+17441,6.986743
+17442,11.562768
+17443,14.340521
+17444,12.956892
+17445,19.954288
+17446,21.780771
+17447,17.183098
+17448,23.735624
+17449,21.726887
+17450,25.485847
+17451,7.728296
+17452,8.369657
+17453,10.646066
+17454,12.314779
+17455,14.926359
+17456,14.907682
+17457,18.48046
+17458,20.765696
+17459,25.888079
+17460,27.282171
+17461,27.490599
+17462,29.586292
+17463,28.443316
+17464,32.79622
+17465,41.062263
+17466,52.353004
+17467,10.666168
+17468,12.463499
+17469,16.561043
+17470,19.147892
+17471,22.84552
+17472,23.749273
+17473,28.48219
+17474,29.815825
+17475,35.08355
+17476,43.32271
+17477,43.276623
+17478,47.513508
+17479,11.955604
+17480,15.512849
+17481,18.483347
+17482,22.540524
+17483,25.455318
+17484,7.7264442
+17485,10.625807
+17486,13.128461
+17487,13.99297
+17488,16.247551
+17489,15.921986
+17490,20.649076
+17491,26.430147
+17492,20.47432
+17493,23.931562
+17494,28.935776
+17495,31.877878
+17496,11.500138
+17497,13.194622
+17498,13.896391
+17499,16.241533
+17500,17.051378
+17501,17.68161
+17502,24.330484
+17503,27.505827
+17504,27.674038
+17505,32.98093
+17506,35.104317
+17507,34.737038
+17508,5.5909486
+17509,7.6000814
+17510,8.119436
+17511,9.670668
+17512,42.621788
+17513,51.750603
+17514,54.571445
+17515,56.23
+17516,60.38254
+17517,14.056017
+17518,16.926945
+17519,17.734549
+17520,24.752155
+17521,29.901495
+17522,23.238098
+17523,29.311554
+17524,34.578373
+17525,38.459724
+17526,22.360355
+17527,26.002964
+17528,29.557117
+17529,32.495663
+17530,37.77363
+17531,40.284904
+17532,40.684956
+17533,42.233284
+17534,42.315422
+17535,46.03949
+17536,46.756557
+17537,49.96602
+17538,21.127335
+17539,23.462824
+17540,25.231007
+17541,27.133268
+17542,31.129002
+17543,34.763878
+17544,35.750042
+17545,38.226624
+17546,39.65239
+17547,39.85451
+17548,38.349564
+17549,39.65308
+17550,57.380077
+17551,62.858894
+17552,63.04004
+17553,65.252365
+17554,69.28834
+17555,67.61442
+17556,25.60197
+17557,30.685783
+17558,36.498947
+17559,44.21388
+17560,26.42099
+17561,28.893064
+17562,33.857315
+17563,37.477608
+17564,42.423233
+17565,23.072334
+17566,32.031883
+17567,33.222397
+17568,35.465942
+17569,41.20765
+17570,41.273
+17571,42.91082
+17572,42.735107
+17573,43.746353
+17574,44.526855
+17575,47.517937
+17576,50.79607
+17577,34.87347
+17578,39.50337
+17579,43.36785
+17580,40.77984
+17581,44.642227
+17582,46.961132
+17583,48.405216
+17584,56.459282
+17585,53.44024
+17586,56.862465
+17587,55.971252
+17588,61.094864
+17589,62.85994
+17590,63.35839
+17591,66.63727
+17592,69.44582
+17593,71.56855
+17594,72.95491
+17595,74.548584
+17596,74.66873
+17597,79.10092
+17598,79.45355
+17599,83.441376
+17600,84.32282
+17601,21.323381
+17602,29.23512
+17603,33.144363
+17604,37.397083
+17605,42.67004
+17606,31.74241
+17607,30.505209
+17608,41.197567
+17609,48.29673
+17610,45.854782
+17611,54.51365
+17612,23.82204
+17613,25.909899
+17614,26.070965
+17615,25.89558
+17616,27.266434
+17617,28.168352
+17618,31.120638
+17619,28.20241
+17620,31.31771
+17621,33.71262
+17622,37.339146
+17623,40.115738
+17624,44.305496
+17625,47.540565
+17626,48.090958
+17627,51.900276
+17628,57.92671
+17629,62.59005
+17630,61.97381
+17631,47.377697
+17632,47.898823
+17633,46.61982
+17634,49.739616
+17635,47.46092
+17636,49.542496
+17637,51.946407
+17638,54.24449
+17639,55.475235
+17640,60.09401
+17641,63.52366
+17642,29.971386
+17643,33.123528
+17644,38.877987
+17645,41.098896
+17646,44.838158
+17647,48.774734
+17648,55.081184
+17649,56.327812
+17650,55.70071
+17651,59.239197
+17652,61.189392
+17653,63.136364
+17654,7.6339407
+17655,7.8622355
+17656,10.838415
+17657,12.966188
+17658,17.010092
+17659,17.329214
+17660,17.70703
+17661,18.49101
+17662,25.316706
+17663,26.357328
+17664,27.352552
+17665,34.89493
+17666,37.12757
+17667,44.586945
+17668,43.263798
+17669,51.514435
+17670,39.173225
+17671,39.330425
+17672,42.41341
+17673,44.26651
+17674,18.86316
+17675,18.187693
+17676,22.841734
+17677,26.24167
+17678,30.671478
+17679,38.039646
+17680,39.94017
+17681,46.663624
+17682,44.86489
+17683,48.581623
+17684,53.615036
+17685,56.4715
+17686,42.187042
+17687,44.62407
+17688,45.6261
+17689,48.01627
+17690,50.056763
+17691,52.642113
+17692,56.078365
+17693,57.42363
+17694,60.88369
+17695,58.040684
+17696,62.072243
+17697,63.851692
+17698,24.384752
+17699,29.799963
+17700,36.26539
+17701,43.072937
+17702,39.277325
+17703,47.780193
+17704,56.815475
+17705,58.176895
+17706,58.976204
+17707,20.789753
+17708,22.883219
+17709,27.779045
+17710,35.664047
+17711,40.6466
+17712,38.005016
+17713,41.224133
+17714,45.83554
+17715,52.344383
+17716,52.21504
+17717,55.98744
+17718,57.049583
+17719,58.986504
+17720,61.272408
+17721,61.65839
+17722,64.01259
+17723,65.05737
+17724,31.121756
+17725,31.940613
+17726,37.08129
+17727,39.958492
+17728,42.418465
+17729,46.27137
+17730,50.400673
+17731,25.748232
+17732,32.6585
+17733,35.00537
+17734,36.84908
+17735,38.396477
+17736,41.871876
+17737,1.2516475
+17738,6.3612885
+17739,7.535282
+17740,9.504422
+17741,20.518744
+17742,23.050617
+17743,23.743069
+17744,25.39195
+17745,28.151855
+17746,30.53378
+17747,34.31822
+17748,35.839264
+17749,39.450943
+17750,40.102226
+17751,42.96758
+17752,45.13928
+17753,9.206343
+17754,12.04571
+17755,13.576221
+17756,14.263048
+17757,15.258651
+17758,22.871859
+17759,29.801165
+17760,29.85386
+17761,32.534313
+17762,32.008896
+17763,37.95172
+17764,38.185642
+17765,13.019573
+17766,15.118553
+17767,14.556572
+17768,22.365784
+17769,51.17781
+17770,53.792587
+17771,54.96676
+17772,53.970173
+17773,56.685284
+17774,58.228516
+17775,25.855959
+17776,34.28546
+17777,38.305
+17778,37.091164
+17779,21.397758
+17780,22.1767
+17781,23.912691
+17782,30.713789
+17783,32.695778
+17784,49.991085
+17785,53.535538
+17786,57.08592
+17787,56.719135
+17788,58.53204
+17789,61.787983
+17790,61.632782
+17791,65.13904
+17792,65.80382
+17793,69.16348
+17794,69.49075
+17795,69.141136
+17796,22.689985
+17797,27.295353
+17798,32.751038
+17799,38.006104
+17800,40.793682
+17801,44.36749
+17802,45.36222
+17803,47.15028
+17804,53.549004
+17805,49.873856
+17806,51.84584
+17807,13.04105
+17808,13.789553
+17809,15.242567
+17810,19.318762
+17811,23.411089
+17812,25.08524
+17813,27.996508
+17814,29.319925
+17815,31.729519
+17816,31.475468
+17817,33.608974
+17818,34.154606
+17819,23.437464
+17820,30.088364
+17821,29.721622
+17822,31.72899
+17823,38.514263
+17824,44.352978
+17825,43.478783
+17826,45.17083
+17827,51.03817
+17828,49.26021
+17829,53.04851
+17830,52.942596
+17831,18.634676
+17832,21.618382
+17833,23.523586
+17834,24.8553
+17835,27.389135
+17836,29.770367
+17837,31.838238
+17838,35.822247
+17839,42.132812
+17840,44.43848
+17841,24.953985
+17842,30.416937
+17843,29.488705
+17844,29.771255
+17845,28.995388
+17846,32.37026
+17847,33.435017
+17848,19.747885
+17849,27.718344
+17850,33.108772
+17851,35.927345
+17852,21.083408
+17853,25.703764
+17854,28.634174
+17855,29.343906
+17856,32.794
+17857,36.772118
+17858,42.951366
+17859,45.634155
+17860,52.685577
+17861,15.87644
+17862,18.826797
+17863,22.244167
+17864,23.736448
+17865,24.570282
+17866,28.262794
+17867,30.608126
+17868,32.793873
+17869,33.733467
+17870,38.9693
+17871,38.944294
+17872,39.27453
+17873,31.064793
+17874,34.903786
+17875,42.778427
+17876,47.54837
+17877,48.09062
+17878,25.354809
+17879,32.922184
+17880,34.01509
+17881,34.30326
+17882,15.752573
+17883,18.277773
+17884,21.010174
+17885,24.181229
+17886,24.304197
+17887,30.359892
+17888,33.86949
+17889,37.295822
+17890,38.91896
+17891,40.652203
+17892,43.957977
+17893,44.08425
+17894,50.628086
+17895,52.599274
+17896,53.394768
+17897,57.584846
+17898,57.02504
+17899,58.14771
+17900,62.27455
+17901,62.571926
+17902,65.299355
+17903,65.41366
+17904,68.12872
+17905,69.18082
+17906,11.75445
+17907,14.053089
+17908,17.689255
+17909,19.960604
+17910,25.230038
+17911,24.800142
+17912,27.226675
+17913,30.513699
+17914,32.305187
+17915,32.43308
+17916,39.100506
+17917,43.40944
+17918,40.03875
+17919,45.755466
+17920,47.62754
+17921,50.287533
+17922,52.64537
+17923,27.047089
+17924,32.79506
+17925,37.188763
+17926,37.05464
+17927,42.875584
+17928,44.378536
+17929,48.862457
+17930,48.854053
+17931,53.106213
+17932,56.087692
+17933,57.109123
+17934,60.110443
+17935,33.392143
+17936,36.739674
+17937,46.059284
+17938,52.344704
+17939,34.338806
+17940,36.25051
+17941,40.879475
+17942,45.027637
+17943,44.71367
+17944,48.054848
+17945,48.923016
+17946,52.276634
+17947,55.06982
+17948,55.06819
+17949,57.700897
+17950,57.78625
+17951,14.2216625
+17952,16.312778
+17953,17.703823
+17954,21.416443
+17955,27.017605
+17956,28.37694
+17957,27.981684
+17958,31.998457
+17959,32.58103
+17960,36.690678
+17961,-0.52115417
+17962,0.07057038
+17963,1.0658301
+17964,2.0106559
+17965,4.9463553
+17966,5.4759603
+17967,9.165598
+17968,10.221682
+17969,11.975308
+17970,16.78798
+17971,20.273932
+17972,22.582497
+17973,36.08753
+17974,36.003296
+17975,40.854782
+17976,43.83038
+17977,43.45343
+17978,46.813663
+17979,50.65988
+17980,51.827477
+17981,51.16202
+17982,51.303246
+17983,54.677273
+17984,55.335632
+17985,24.825033
+17986,27.184235
+17987,27.205484
+17988,29.867033
+17989,31.697144
+17990,35.37663
+17991,38.116905
+17992,42.082916
+17993,30.706417
+17994,31.197521
+17995,35.47502
+17996,41.405594
+17997,50.24778
+17998,47.816494
+17999,53.318512
+18000,53.660652
+18001,22.660414
+18002,25.549171
+18003,31.749376
+18004,37.602882
+18005,12.4861
+18006,16.388119
+18007,18.328775
+18008,33.981083
+18009,18.194197
+18010,27.110163
+18011,32.845398
+18012,26.363306
+18013,33.407158
+18014,34.097614
+18015,41.56248
+18016,21.92865
+18017,22.872147
+18018,23.51965
+18019,26.127548
+18020,26.38615
+18021,25.937202
+18022,30.987156
+18023,32.047607
+18024,34.405525
+18025,35.65439
+18026,37.351257
+18027,37.708603
+18028,1.000262
+18029,2.0162523
+18030,3.4488835
+18031,4.6091604
+18032,9.157955
+18033,10.810833
+18034,37.36099
+18035,43.28177
+18036,45.632587
+18037,44.096687
+18038,48.806236
+18039,53.268654
+18040,57.651424
+18041,57.8992
+18042,57.517056
+18043,57.796947
+18044,60.642
+18045,61.44257
+18046,20.561749
+18047,20.01098
+18048,23.009302
+18049,24.997646
+18050,24.11242
+18051,27.125954
+18052,30.0312
+18053,20.92626
+18054,21.903015
+18055,30.978024
+18056,33.422234
+18057,28.166965
+18058,32.50048
+18059,35.73987
+18060,39.461742
+18061,38.19676
+18062,40.52257
+18063,40.7026
+18064,43.60371
+18065,42.660328
+18066,51.969757
+18067,53.712513
+18068,48.44774
+18069,51.537895
+18070,54.2273
+18071,56.87353
+18072,57.176888
+18073,58.91046
+18074,61.484314
+18075,61.156715
+18076,67.92163
+18077,12.425497
+18078,13.620289
+18079,17.986906
+18080,21.727419
+18081,21.710358
+18082,27.21622
+18083,28.74689
+18084,30.057497
+18085,35.533905
+18086,37.480442
+18087,38.05167
+18088,41.408066
+18089,48.07584
+18090,49.88312
+18091,47.111134
+18092,51.705173
+18093,31.24998
+18094,35.11851
+18095,37.9687
+18096,39.038567
+18097,45.148212
+18098,46.61541
+18099,48.979973
+18100,53.59474
+18101,42.543182
+18102,51.23592
+18103,55.536175
+18104,59.943516
+18105,25.479553
+18106,34.277077
+18107,36.244553
+18108,38.18114
+18109,40.443523
+18110,23.71766
+18111,25.186066
+18112,24.677147
+18113,28.419983
+18114,8.850828
+18115,10.9503355
+18116,16.038275
+18117,18.544502
+18118,18.467262
+18119,20.659407
+18120,26.465103
+18121,26.98922
+18122,29.107098
+18123,27.400917
+18124,31.315239
+18125,32.397736
+18126,41.85806
+18127,42.328453
+18128,43.938786
+18129,47.995895
+18130,50.009666
+18131,51.574078
+18132,51.756058
+18133,55.234512
+18134,55.363533
+18135,55.215744
+18136,57.664795
+18137,60.40353
+18138,18.21549
+18139,21.871283
+18140,24.809206
+18141,31.427677
+18142,34.178925
+18143,33.296875
+18144,28.157969
+18145,30.165535
+18146,36.76843
+18147,40.11908
+18148,2.9984245
+18149,5.363933
+18150,8.579199
+18151,13.455358
+18152,21.22463
+18153,22.317627
+18154,22.233486
+18155,25.403996
+18156,27.094397
+18157,13.0903225
+18158,12.777653
+18159,15.283262
+18160,20.184027
+18161,23.574612
+18162,28.100908
+18163,31.795341
+18164,31.19077
+18165,36.011745
+18166,40.584496
+18167,44.920288
+18168,42.74628
+18169,19.99621
+18170,24.612753
+18171,28.692417
+18172,30.924376
+18173,34.030605
+18174,39.170006
+18175,41.67086
+18176,46.126686
+18177,17.769331
+18178,22.750683
+18179,27.762396
+18180,31.451796
+18181,31.903881
+18182,34.243385
+18183,36.294155
+18184,36.64366
+18185,36.261597
+18186,40.01809
+18187,37.564777
+18188,40.491333
+18189,37.64911
+18190,44.956207
+18191,47.64351
+18192,46.89351
+18193,48.77633
+18194,50.25817
+18195,53.40717
+18196,56.338135
+18197,58.985455
+18198,48.080704
+18199,48.790554
+18200,54.477306
+18201,57.19935
+18202,57.808533
+18203,62.1092
+18204,61.911427
+18205,65.14045
+18206,65.317474
+18207,64.74245
+18208,66.36828
+18209,67.345604
+18210,29.804806
+18211,31.432158
+18212,34.76464
+18213,38.80119
+18214,45.134026
+18215,48.234436
+18216,35.272053
+18217,42.634266
+18218,48.613102
+18219,53.55372
+18220,25.998276
+18221,34.566063
+18222,37.13114
+18223,42.507027
+18224,45.70452
+18225,28.049204
+18226,31.120155
+18227,33.242012
+18228,33.922783
+18229,40.10115
+18230,41.118145
+18231,35.09214
+18232,40.484673
+18233,46.841858
+18234,48.51052
+18235,48.772957
+18236,51.75125
+18237,56.277817
+18238,56.668564
+18239,57.425785
+18240,59.736256
+18241,61.16775
+18242,59.060688
+18243,29.176918
+18244,31.361414
+18245,32.283165
+18246,39.022324
+18247,43.93074
+18248,45.163013
+18249,50.362232
+18250,51.46347
+18251,52.97724
+18252,32.636417
+18253,33.179367
+18254,33.18593
+18255,35.208324
+18256,38.80252
+18257,44.775818
+18258,21.286215
+18259,26.804203
+18260,33.63964
+18261,34.35443
+18262,44.14048
+18263,43.8005
+18264,40.871403
+18265,47.027237
+18266,48.43125
+18267,50.67929
+18268,52.468285
+18269,56.701916
+18270,22.412472
+18271,28.233818
+18272,31.81128
+18273,30.25655
+18274,28.278017
+18275,38.23228
+18276,39.10881
+18277,42.74207
+18278,45.08225
+18279,47.649197
+18280,48.637016
+18281,53.81105
+18282,28.042286
+18283,30.589674
+18284,31.062521
+18285,34.06465
+18286,34.97673
+18287,12.022676
+18288,14.690791
+18289,15.597686
+18290,17.59931
+18291,27.680117
+18292,28.511362
+18293,29.431181
+18294,30.2406
+18295,33.08166
+18296,36.55078
+18297,40.07418
+18298,40.938198
+18299,41.318657
+18300,46.373283
+18301,48.066566
+18302,51.755375
+18303,16.6467
+18304,19.666372
+18305,31.954496
+18306,34.60147
+18307,13.5386915
+18308,14.494991
+18309,22.254578
+18310,24.907448
+18311,25.335327
+18312,29.812346
+18313,33.12588
+18314,35.880177
+18315,38.530704
+18316,22.66185
+18317,25.43928
+18318,26.33599
+18319,32.52484
+18320,36.563297
+18321,37.381176
+18322,40.19001
+18323,44.14871
+18324,47.501644
+18325,49.590122
+18326,51.68628
+18327,51.922268
+18328,0.6965614
+18329,1.4493245
+18330,2.887737
+18331,4.563804
+18332,22.72489
+18333,30.13485
+18334,39.162407
+18335,41.89563
+18336,33.87023
+18337,36.093067
+18338,43.55674
+18339,46.847656
+18340,18.833942
+18341,24.287893
+18342,25.036455
+18343,30.070612
+18344,34.49737
+18345,36.339523
+18346,37.406082
+18347,45.436214
+18348,48.52226
+18349,52.995552
+18350,31.838228
+18351,34.17041
+18352,37.130722
+18353,40.09625
+18354,21.952549
+18355,26.053085
+18356,28.249836
+18357,36.097313
+18358,15.051406
+18359,17.075487
+18360,20.91068
+18361,22.571442
+18362,14.699672
+18363,24.272686
+18364,28.443542
+18365,28.408802
+18366,32.307457
+18367,34.023205
+18368,35.919037
+18369,39.76149
+18370,40.259933
+18371,41.70925
+18372,36.411953
+18373,37.356068
+18374,37.935833
+18375,40.64192
+18376,42.36465
+18377,19.251717
+18378,20.8054
+18379,22.46364
+18380,24.644854
+18381,29.397646
+18382,32.662262
+18383,32.073036
+18384,35.827385
+18385,36.468132
+18386,41.05419
+18387,46.460022
+18388,49.484116
+18389,8.400343
+18390,7.899214
+18391,7.503912
+18392,10.575213
+18393,38.83422
+18394,39.81293
+18395,42.23918
+18396,47.322212
+18397,47.933273
+18398,50.87552
+18399,52.54521
+18400,54.37107
+18401,57.216175
+18402,54.86445
+18403,56.063522
+18404,59.59962
+18405,63.176254
+18406,64.52446
+18407,66.63912
+18408,67.5604
+18409,68.26211
+18410,68.50771
+18411,68.7314
+18412,70.602554
+18413,71.74864
+18414,32.478188
+18415,39.818764
+18416,41.693268
+18417,40.485046
+18418,41.082363
+18419,48.729248
+18420,49.914764
+18421,47.072155
+18422,52.893246
+18423,55.319748
+18424,55.76602
+18425,57.031807
+18426,36.78074
+18427,39.758686
+18428,45.22383
+18429,46.221542
+18430,51.19806
+18431,59.649242
+18432,61.005905
+18433,62.175087
+18434,62.15868
+18435,65.26539
+18436,64.92497
+18437,65.93106
+18438,38.394035
+18439,48.288143
+18440,49.147686
+18441,47.114414
+18442,52.791203
+18443,55.245552
+18444,59.808853
+18445,26.97805
+18446,30.12829
+18447,36.03045
+18448,38.42154
+18449,22.914387
+18450,35.149765
+18451,37.4469
+18452,38.086502
+18453,42.178417
+18454,17.830467
+18455,25.360622
+18456,27.997524
+18457,32.63247
+18458,45.62159
+18459,46.415512
+18460,47.965958
+18461,54.876564
+18462,58.692944
+18463,60.76139
+18464,61.450874
+18465,64.115875
+18466,64.258286
+18467,66.229614
+18468,67.53198
+18469,68.678894
+18470,30.519413
+18471,34.678116
+18472,34.984875
+18473,39.63363
+18474,38.820976
+18475,40.18234
+18476,51.490078
+18477,56.471233
+18478,51.729263
+18479,57.15267
+18480,57.777775
+18481,59.756493
+18482,60.924828
+18483,64.39015
+18484,66.18588
+18485,68.98672
+18486,13.648577
+18487,13.7995205
+18488,17.570522
+18489,17.847958
+18490,21.466677
+18491,30.255127
+18492,33.6175
+18493,41.508167
+18494,44.66108
+18495,47.17272
+18496,50.528744
+18497,57.0625
+18498,23.86126
+18499,23.694878
+18500,27.495955
+18501,28.523579
+18502,28.727211
+18503,34.439964
+18504,37.12479
+18505,37.63982
+18506,39.916252
+18507,37.190815
+18508,44.436375
+18509,45.27524
+18510,3.1233149
+18511,4.145213
+18512,6.584921
+18513,10.143985
+18514,19.057707
+18515,25.857317
+18516,28.703976
+18517,26.460033
+18518,27.879436
+18519,38.344913
+18520,44.651997
+18521,44.374397
+18522,38.32107
+18523,39.326767
+18524,44.86885
+18525,50.213745
+18526,36.43949
+18527,46.468494
+18528,46.994965
+18529,48.048264
+18530,51.22286
+18531,54.865112
+18532,52.59272
+18533,57.14473
+18534,57.03279
+18535,60.594555
+18536,61.650993
+18537,31.25078
+18538,31.730978
+18539,31.51301
+18540,33.014908
+18541,34.89776
+18542,38.957573
+18543,40.17994
+18544,40.952847
+18545,40.945717
+18546,42.33613
+18547,42.513195
+18548,47.636986
+18549,38.928886
+18550,43.518036
+18551,47.407837
+18552,47.903152
+18553,51.94343
+18554,56.817127
+18555,49.883514
+18556,53.57315
+18557,56.296227
+18558,56.88124
+18559,57.975918
+18560,62.92304
+18561,64.17821
+18562,61.56879
+18563,65.73713
+18564,66.3277
+18565,69.147415
+18566,65.91732
+18567,18.524302
+18568,19.014757
+18569,19.210978
+18570,21.560776
+18571,28.47552
+18572,29.45612
+18573,29.678732
+18574,32.74753
+18575,36.79344
+18576,41.293926
+18577,45.111088
+18578,47.55882
+18579,47.68547
+18580,52.024307
+18581,28.973942
+18582,31.672209
+18583,31.97668
+18584,40.055984
+18585,43.861202
+18586,44.311005
+18587,22.69493
+18588,24.347033
+18589,25.966751
+18590,31.437504
+18591,34.98536
+18592,39.222137
+18593,45.116222
+18594,49.288445
+18595,53.009205
+18596,57.01597
+18597,57.77736
+18598,60.345684
+18599,0.116615556
+18600,1.6334896
+18601,3.248814
+18602,3.6358497
+18603,7.7610497
+18604,8.563029
+18605,10.601142
+18606,11.972124
+18607,15.645013
+18608,19.065311
+18609,21.835064
+18610,23.408016
+18611,9.0733
+18612,10.865312
+18613,13.5347805
+18614,17.287136
+18615,22.931713
+18616,26.815836
+18617,29.696032
+18618,30.514812
+18619,37.03416
+18620,37.69536
+18621,43.23975
+18622,37.588684
+18623,41.412502
+18624,42.830814
+18625,44.533188
+18626,46.33872
+18627,48.52283
+18628,48.346474
+18629,29.364433
+18630,34.458946
+18631,39.346687
+18632,46.0656
+18633,22.19157
+18634,24.307995
+18635,26.26518
+18636,28.74154
+18637,28.681423
+18638,35.12968
+18639,37.17854
+18640,38.368
+18641,42.414528
+18642,42.956192
+18643,47.37313
+18644,47.64235
+18645,30.844917
+18646,37.187275
+18647,38.509197
+18648,40.902657
+18649,44.644806
+18650,15.462114
+18651,21.817661
+18652,23.605536
+18653,23.069563
+18654,22.39553
+18655,25.260162
+18656,29.227879
+18657,30.706066
+18658,36.61978
+18659,38.257088
+18660,41.984657
+18661,44.35069
+18662,27.472937
+18663,33.76436
+18664,33.87579
+18665,35.7499
+18666,51.015465
+18667,65.18731
+18668,66.36207
+18669,64.902115
+18670,21.321617
+18671,23.977997
+18672,28.707336
+18673,33.39254
+18674,16.984173
+18675,25.654642
+18676,29.063936
+18677,29.906406
+18678,27.078735
+18679,31.029087
+18680,32.545715
+18681,39.30439
+18682,37.554955
+18683,42.77342
+18684,45.609715
+18685,47.172504
+18686,21.828726
+18687,27.02358
+18688,36.88298
+18689,41.806095
+18690,36.548748
+18691,40.7665
+18692,41.73477
+18693,45.89403
+18694,50.161182
+18695,52.299812
+18696,55.01308
+18697,51.650414
+18698,32.14432
+18699,33.061222
+18700,40.56024
+18701,45.273075
+18702,50.23699
+18703,54.118042
+18704,53.257526
+18705,58.329613
+18706,60.88696
+18707,63.004677
+18708,68.4632
+18709,67.64899
+18710,31.152336
+18711,36.389297
+18712,38.094517
+18713,41.153057
+18714,46.922577
+18715,47.871655
+18716,50.57111
+18717,53.5981
+18718,54.733467
+18719,57.89924
+18720,57.255333
+18721,61.736877
+18722,33.197662
+18723,45.81179
+18724,47.88695
+18725,50.4939
+18726,28.283493
+18727,28.118942
+18728,31.491549
+18729,34.609123
+18730,9.092557
+18731,11.711039
+18732,14.546377
+18733,23.879023
+18734,44.69805
+18735,51.838615
+18736,56.269657
+18737,60.948486
+18738,32.049973
+18739,34.588844
+18740,37.902916
+18741,38.193573
+18742,32.72963
+18743,35.004807
+18744,39.734512
+18745,41.850975
+18746,44.474842
+18747,48.160103
+18748,50.821243
+18749,52.07602
+18750,60.47579
+18751,59.58007
+18752,38.92701
+18753,46.73719
+18754,50.24843
+18755,50.855885
+18756,17.646559
+18757,18.910988
+18758,22.167355
+18759,26.465967
+18760,26.515089
+18761,30.015804
+18762,35.86486
+18763,39.002663
+18764,45.202923
+18765,43.052933
+18766,44.634937
+18767,48.164734
+18768,47.836952
+18769,51.74166
+18770,52.255398
+18771,54.321724
+18772,7.11579
+18773,7.116635
+18774,10.70654
+18775,13.333087
+18776,17.557003
+18777,34.257435
+18778,35.098106
+18779,35.84958
+18780,38.085793
+18781,40.143974
+18782,40.82151
+18783,45.297417
+18784,17.19095
+18785,23.624956
+18786,24.368156
+18787,27.877548
+18788,26.022114
+18789,28.714193
+18790,31.851091
+18791,35.599907
+18792,42.89916
+18793,40.10222
+18794,42.440765
+18795,-0.53644574
+18796,-0.24073118
+18797,-1.1190829
+18798,1.0563356
+18799,2.5204992
+18800,6.4403386
+18801,7.157474
+18802,8.641512
+18803,9.182193
+18804,12.62714
+18805,11.550649
+18806,14.060733
+18807,13.51771
+18808,18.972218
+18809,23.219227
+18810,29.15168
+18811,33.649452
+18812,39.36934
+18813,44.005775
+18814,44.937195
+18815,51.210693
+18816,56.21252
+18817,54.794994
+18818,18.44898
+18819,21.907265
+18820,23.473988
+18821,27.348967
+18822,28.594639
+18823,29.702778
+18824,35.32818
+18825,35.442505
+18826,38.790916
+18827,41.12588
+18828,40.26044
+18829,43.890663
+18830,21.119705
+18831,24.074642
+18832,32.990112
+18833,33.89359
+18834,31.141665
+18835,33.65435
+18836,35.947357
+18837,38.408913
+18838,40.73546
+18839,10.234394
+18840,14.018916
+18841,15.745662
+18842,24.132462
+18843,28.247799
+18844,30.118181
+18845,25.118923
+18846,27.929817
+18847,30.957802
+18848,36.14029
+18849,35.34327
+18850,46.21998
+18851,45.270172
+18852,43.978413
+18853,48.86579
+18854,51.19485
+18855,50.112442
+18856,57.634483
+18857,28.261267
+18858,29.57597
+18859,28.340855
+18860,31.134163
+18861,14.282264
+18862,18.601753
+18863,21.530441
+18864,22.139143
+18865,32.844997
+18866,37.42836
+18867,43.316887
+18868,44.98319
+18869,48.42133
+18870,34.826385
+18871,35.392174
+18872,38.02601
+18873,38.673134
+18874,39.890846
+18875,38.74158
+18876,42.705444
+18877,29.530941
+18878,34.258633
+18879,36.82201
+18880,36.74875
+18881,37.632736
+18882,43.094162
+18883,44.52137
+18884,47.639248
+18885,50.88432
+18886,29.601425
+18887,33.102253
+18888,33.498356
+18889,41.353527
+18890,8.547717
+18891,12.102989
+18892,15.126894
+18893,12.070148
+18894,15.731583
+18895,16.71375
+18896,21.013002
+18897,24.669367
+18898,25.791834
+18899,25.608093
+18900,49.697906
+18901,56.972977
+18902,55.031384
+18903,55.084557
+18904,60.000336
+18905,61.150177
+18906,63.778633
+18907,64.86755
+18908,65.97296
+18909,67.43801
+18910,68.00266
+18911,69.71076
+18912,31.024208
+18913,34.09674
+18914,38.495903
+18915,40.712643
+18916,44.926235
+18917,17.58088
+18918,21.643356
+18919,23.311813
+18920,30.022278
+18921,21.76021
+18922,30.316708
+18923,29.289793
+18924,26.01044
+18925,28.879616
+18926,30.501717
+18927,34.66208
+18928,33.54374
+18929,30.876766
+18930,31.178493
+18931,31.329863
+18932,34.149136
+18933,17.99268
+18934,17.321602
+18935,24.562963
+18936,28.958996
+18937,33.77038
+18938,39.922047
+18939,41.72422
+18940,51.54771
+18941,20.380157
+18942,19.923069
+18943,19.596334
+18944,25.787073
+18945,23.975452
+18946,34.372746
+18947,36.978497
+18948,35.773376
+18949,11.419848
+18950,15.711814
+18951,20.444855
+18952,24.604622
+18953,35.954536
+18954,23.055794
+18955,26.584612
+18956,32.978783
+18957,34.48825
+18958,32.220722
+18959,38.431824
+18960,39.5155
+18961,47.942986
+18962,46.506165
+18963,48.696075
+18964,52.063553
+18965,53.995716
+18966,24.049458
+18967,29.387775
+18968,34.763237
+18969,34.669518
+18970,40.48273
+18971,44.320644
+18972,43.701176
+18973,47.66213
+18974,46.66595
+18975,49.885155
+18976,49.923904
+18977,51.47788
+18978,19.010372
+18979,23.396906
+18980,26.983103
+18981,29.018707
+18982,27.302925
+18983,34.668488
+18984,34.511795
+18985,34.766335
+18986,35.34198
+18987,34.43926
+18988,38.415657
+18989,40.332756
+18990,29.460567
+18991,41.06992
+18992,41.446526
+18993,41.24189
+18994,44.243397
+18995,11.192678
+18996,15.637299
+18997,19.552448
+18998,19.37679
+18999,24.327166
+19000,28.34245
+19001,25.162613
+19002,32.16238
+19003,32.26002
+19004,32.295334
+19005,35.701355
+19006,36.17691
+19007,21.757252
+19008,26.60496
+19009,31.54636
+19010,34.18891
+19011,29.567497
+19012,33.757828
+19013,36.17366
+19014,39.228382
+19015,40.61982
+19016,23.970192
+19017,24.739782
+19018,26.473358
+19019,25.416174
+19020,27.91598
+19021,28.964827
+19022,32.347706
+19023,34.48485
+19024,35.688927
+19025,36.666542
+19026,40.48073
+19027,43.368843
+19028,30.908352
+19029,33.80115
+19030,36.135418
+19031,37.95832
+19032,40.8613
+19033,38.88939
+19034,43.796017
+19035,48.36067
+19036,56.556892
+19037,54.076065
+19038,55.746162
+19039,57.642315
+19040,22.802418
+19041,25.720205
+19042,30.80748
+19043,39.62721
+19044,0.39812273
+19045,0.7300501
+19046,1.7076714
+19047,6.1674414
+19048,7.3166385
+19049,9.136759
+19050,12.512331
+19051,14.131219
+19052,15.184353
+19053,17.48941
+19054,28.42916
+19055,29.05703
+19056,27.649023
+19057,31.270126
+19058,22.670315
+19059,24.318182
+19060,26.967102
+19061,29.615406
+19062,17.173054
+19063,22.66184
+19064,21.704222
+19065,26.622196
+19066,32.216473
+19067,44.14019
+19068,49.978085
+19069,22.017735
+19070,26.962223
+19071,29.221148
+19072,29.247847
+19073,32.25488
+19074,28.951227
+19075,34.21438
+19076,37.067707
+19077,44.98859
+19078,18.313124
+19079,20.637627
+19080,22.791334
+19081,26.97488
+19082,30.186285
+19083,34.927963
+19084,38.101677
+19085,37.331505
+19086,42.464443
+19087,42.29051
+19088,6.731801
+19089,9.685209
+19090,11.860424
+19091,11.459939
+19092,23.025124
+19093,31.161312
+19094,37.71233
+19095,45.910313
+19096,62.300446
+19097,63.940163
+19098,64.18534
+19099,66.237114
+19100,68.64176
+19101,70.33008
+19102,69.20924
+19103,70.44911
+19104,70.5252
+19105,71.47671
+19106,72.370766
+19107,75.178444
+19108,33.11963
+19109,37.220703
+19110,38.725895
+19111,36.77555
+19112,38.05237
+19113,39.931614
+19114,43.184746
+19115,45.31552
+19116,45.727673
+19117,47.46265
+19118,47.63177
+19119,49.57591
+19120,27.347275
+19121,29.348808
+19122,32.595062
+19123,38.45665
+19124,37.892384
+19125,41.47529
+19126,36.778362
+19127,49.530823
+19128,52.136856
+19129,54.090492
+19130,54.484848
+19131,54.69809
+19132,9.982287
+19133,11.389293
+19134,13.2795315
+19135,16.487778
+19136,18.57683
+19137,22.289988
+19138,26.55021
+19139,28.982565
+19140,31.160282
+19141,30.540138
+19142,35.745567
+19143,41.897507
+19144,15.884794
+19145,16.07708
+19146,19.023808
+19147,25.64383
+19148,28.732498
+19149,27.336742
+19150,32.951145
+19151,34.2013
+19152,39.19673
+19153,36.927185
+19154,38.493492
+19155,15.697519
+19156,26.58216
+19157,28.547932
+19158,28.067392
+19159,2.9289618
+19160,5.9602246
+19161,7.438358
+19162,8.6891365
+19163,10.297871
+19164,13.274222
+19165,13.186838
+19166,17.663685
+19167,19.566082
+19168,27.565096
+19169,32.205616
+19170,30.865292
+19171,33.940674
+19172,39.891693
+19173,44.74413
+19174,45.8533
+19175,50.8726
+19176,50.9635
+19177,54.359413
+19178,57.81037
+19179,57.261253
+19180,24.525967
+19181,25.381168
+19182,31.014639
+19183,33.24067
+19184,37.40562
+19185,26.432991
+19186,27.124796
+19187,32.0927
+19188,39.10712
+19189,43.27529
+19190,39.597874
+19191,44.09829
+19192,44.637066
+19193,46.97042
+19194,51.2502
+19195,54.29182
+19196,57.93534
+19197,26.876303
+19198,28.969652
+19199,29.377329
+19200,30.695488
+19201,32.01059
+19202,33.216045
+19203,38.572815
+19204,40.39855
+19205,44.14888
+19206,47.095562
+19207,51.03087
+19208,49.80646
+19209,0.45955116
+19210,0.4308159
+19211,0.67297876
+19212,2.088325
+19213,5.4367275
+19214,6.5811276
+19215,7.5381975
+19216,33.528294
+19217,38.826878
+19218,46.11268
+19219,47.54155
+19220,45.21003
+19221,48.25107
+19222,50.1901
+19223,50.166115
+19224,52.905357
+19225,56.34562
+19226,54.452244
+19227,57.338238
+19228,29.049227
+19229,31.89437
+19230,34.31893
+19231,34.706448
+19232,43.168457
+19233,45.061058
+19234,51.907726
+19235,54.239616
+19236,56.67395
+19237,57.29653
+19238,57.784492
+19239,58.399265
+19240,34.290672
+19241,39.140125
+19242,39.971874
+19243,42.990772
+19244,37.962337
+19245,35.72708
+19246,40.31927
+19247,41.841606
+19248,45.0381
+19249,44.026215
+19250,48.13556
+19251,56.570377
+19252,56.929203
+19253,57.77063
+19254,58.653908
+19255,66.721794
+19256,27.480293
+19257,33.978374
+19258,37.71463
+19259,37.38468
+19260,12.487965
+19261,16.736702
+19262,23.16926
+19263,25.168968
+19264,33.63279
+19265,36.870544
+19266,41.037537
+19267,38.95784
+19268,44.792923
+19269,50.69827
+19270,50.193695
+19271,54.804237
+19272,55.902702
+19273,54.11316
+19274,57.033234
+19275,60.551323
+19276,26.672274
+19277,29.90179
+19278,31.59188
+19279,32.906723
+19280,34.15659
+19281,36.379826
+19282,43.10736
+19283,47.58735
+19284,45.810097
+19285,47.31374
+19286,50.592106
+19287,51.397846
+19288,20.096737
+19289,22.288607
+19290,24.591618
+19291,29.7072
+19292,38.64851
+19293,38.736004
+19294,42.244896
+19295,46.626934
+19296,47.363144
+19297,47.446526
+19298,53.180527
+19299,54.74754
+19300,53.3768
+19301,55.162968
+19302,56.157444
+19303,57.27574
+19304,25.268518
+19305,26.844902
+19306,30.120012
+19307,31.295477
+19308,31.979301
+19309,30.5462
+19310,32.16884
+19311,35.08779
+19312,36.006226
+19313,37.474373
+19314,39.673214
+19315,39.799267
+19316,32.434834
+19317,40.820038
+19318,43.251846
+19319,43.049423
+19320,47.944584
+19321,49.34506
+19322,54.13628
+19323,56.251274
+19324,55.34092
+19325,58.53692
+19326,59.602383
+19327,59.586967
+19328,27.410772
+19329,30.604128
+19330,34.76324
+19331,37.62288
+19332,12.497438
+19333,17.396978
+19334,19.555027
+19335,21.816479
+19336,22.71825
+19337,27.50838
+19338,31.398535
+19339,32.598618
+19340,35.887154
+19341,41.667248
+19342,42.193764
+19343,21.88996
+19344,27.381311
+19345,30.465832
+19346,33.501366
+19347,36.01545
+19348,41.460583
+19349,47.598164
+19350,45.29497
+19351,49.31636
+19352,48.30004
+19353,55.74189
+19354,58.559925
+19355,64.4297
+19356,64.51283
+19357,69.244446
+19358,66.50143
+19359,22.9654
+19360,25.520954
+19361,28.270432
+19362,37.31513
+19363,39.907715
+19364,37.61099
+19365,41.165276
+19366,44.255905
+19367,21.11554
+19368,22.7485
+19369,29.45372
+19370,34.945145
+19371,34.132896
+19372,39.83752
+19373,37.85439
+19374,39.941788
+19375,30.855362
+19376,33.478546
+19377,35.900272
+19378,40.545773
+19379,4.8051534
+19380,8.551815
+19381,12.273492
+19382,16.662506
+19383,21.49119
+19384,29.666328
+19385,36.46261
+19386,42.49623
+19387,43.32011
+19388,20.44189
+19389,30.518602
+19390,32.616386
+19391,31.743044
+19392,12.932147
+19393,14.69231
+19394,15.987889
+19395,20.37135
+19396,22.62597
+19397,19.942173
+19398,23.75504
+19399,27.74476
+19400,29.305216
+19401,29.726215
+19402,28.659706
+19403,30.983604
+19404,23.855122
+19405,31.813143
+19406,34.20415
+19407,35.236473
+19408,38.212376
+19409,30.787544
+19410,35.453415
+19411,46.417805
+19412,43.854645
+19413,44.43364
+19414,45.645226
+19415,43.52751
+19416,49.547596
+19417,50.913284
+19418,50.006874
+19419,52.645756
+19420,23.135479
+19421,36.48876
+19422,43.870514
+19423,40.538216
+19424,31.872639
+19425,31.360184
+19426,33.49897
+19427,36.39943
+19428,34.49634
+19429,36.80372
+19430,41.640114
+19431,43.94164
+19432,46.963623
+19433,46.64399
+19434,52.908924
+19435,56.289566
+19436,52.194614
+19437,55.902233
+19438,55.637005
+19439,60.448875
+19440,62.13087
+19441,26.572538
+19442,30.842499
+19443,32.03537
+19444,34.79941
+19445,35.809
+19446,37.22634
+19447,24.533863
+19448,28.064716
+19449,31.223787
+19450,36.78606
+19451,40.07531
+19452,45.56713
+19453,46.290234
+19454,48.32284
+19455,52.33143
+19456,54.828335
+19457,56.488693
+19458,58.56966
+19459,31.11213
+19460,32.979366
+19461,39.876842
+19462,44.57407
+19463,46.968567
+19464,50.282146
+19465,49.07112
+19466,51.862823
+19467,54.864754
+19468,59.185204
+19469,60.941067
+19470,64.193825
+19471,64.67651
+19472,68.363846
+19473,53.08663
+19474,53.84541
+19475,56.85788
+19476,55.028015
+19477,58.52884
+19478,60.48474
+19479,61.68105
+19480,63.60833
+19481,63.523663
+19482,63.349968
+19483,67.63864
+19484,63.58476
+19485,24.989805
+19486,35.79799
+19487,41.210255
+19488,37.47168
+19489,41.67292
+19490,41.11067
+19491,45.07012
+19492,49.560127
+19493,52.2848
+19494,52.967697
+19495,52.93656
+19496,54.160187
+19497,11.89922
+19498,22.78114
+19499,23.367062
+19500,26.929066
+19501,35.35616
+19502,37.415535
+19503,43.173584
+19504,47.06349
+19505,45.312344
+19506,47.39068
+19507,50.033333
+19508,52.57533
+19509,27.440323
+19510,31.381468
+19511,41.445408
+19512,47.390156
+19513,42.283714
+19514,45.653145
+19515,46.23725
+19516,49.831627
+19517,57.43329
+19518,58.243176
+19519,58.489105
+19520,59.85006
+19521,24.126572
+19522,25.421219
+19523,27.456837
+19524,29.065502
+19525,29.769308
+19526,31.356213
+19527,38.642082
+19528,38.972706
+19529,41.612106
+19530,44.190357
+19531,47.334427
+19532,50.192905
+19533,34.98451
+19534,34.42212
+19535,33.632145
+19536,37.807274
+19537,42.85549
+19538,46.447495
+19539,47.808174
+19540,47.392735
+19541,49.148666
+19542,11.60598
+19543,13.782195
+19544,17.74255
+19545,17.0252
+19546,22.466356
+19547,25.277945
+19548,27.274836
+19549,29.38016
+19550,30.21283
+19551,1.5161008
+19552,2.4803338
+19553,3.3851674
+19554,5.078942
+19555,39.61194
+19556,40.266495
+19557,43.76821
+19558,46.467625
+19559,46.92466
+19560,51.568317
+19561,53.885544
+19562,54.996113
+19563,59.396156
+19564,58.69574
+19565,58.604355
+19566,59.855675
+19567,43.993755
+19568,45.15219
+19569,48.68444
+19570,47.729122
+19571,32.38698
+19572,33.041695
+19573,37.806095
+19574,40.17052
+19575,46.654194
+19576,22.040432
+19577,28.414509
+19578,31.19557
+19579,36.12258
+19580,37.798553
+19581,37.360046
+19582,11.955378
+19583,13.891297
+19584,15.130081
+19585,16.63676
+19586,20.045912
+19587,22.773975
+19588,22.805927
+19589,25.827242
+19590,29.577555
+19591,32.653244
+19592,33.65069
+19593,33.685875
+19594,25.115213
+19595,29.095451
+19596,30.159727
+19597,32.35108
+19598,38.25999
+19599,42.09394
+19600,40.90754
+19601,44.23342
+19602,45.983562
+19603,46.88991
+19604,47.516605
+19605,49.650616
+19606,49.564846
+19607,55.986904
+19608,57.622982
+19609,59.609097
+19610,23.409815
+19611,24.702358
+19612,27.251217
+19613,33.90634
+19614,37.638542
+19615,41.101738
+19616,43.127678
+19617,42.28531
+19618,44.911865
+19619,47.838173
+19620,46.944817
+19621,51.887787
+19622,23.045952
+19623,26.827108
+19624,29.329847
+19625,29.464664
+19626,34.92318
+19627,38.038303
+19628,39.376953
+19629,43.446007
+19630,48.083252
+19631,47.13474
+19632,49.571693
+19633,54.091595
+19634,37.00516
+19635,32.56785
+19636,33.650597
+19637,39.225273
+19638,41.264885
+19639,42.614758
+19640,52.794334
+19641,52.32251
+19642,57.828857
+19643,24.79124
+19644,25.632795
+19645,26.420454
+19646,30.414635
+19647,32.293697
+19648,32.900536
+19649,35.226147
+19650,34.64704
+19651,41.787865
+19652,43.612167
+19653,45.43647
+19654,16.503788
+19655,23.93736
+19656,29.165674
+19657,34.35208
+19658,26.461452
+19659,26.899426
+19660,28.943407
+19661,29.338043
+19662,34.143555
+19663,-0.41480085
+19664,-0.36129528
+19665,0.48597807
+19666,2.635916
+19667,4.1465664
+19668,6.9235682
+19669,9.075391
+19670,10.322718
+19671,14.18128
+19672,15.68651
+19673,16.141645
+19674,21.208227
+19675,42.25194
+19676,48.375427
+19677,49.558235
+19678,58.966125
+19679,4.1001806
+19680,6.8924713
+19681,7.201129
+19682,7.576389
+19683,2.8051794
+19684,5.285451
+19685,7.041116
+19686,10.976162
+19687,11.77417
+19688,14.089181
+19689,17.307753
+19690,17.066765
+19691,39.51585
+19692,41.19973
+19693,44.681824
+19694,46.95469
+19695,51.57388
+19696,50.94629
+19697,54.653656
+19698,57.800663
+19699,58.653545
+19700,63.27807
+19701,60.873383
+19702,66.7109
+19703,9.088778
+19704,10.777794
+19705,12.172564
+19706,15.520075
+19707,17.862465
+19708,22.520802
+19709,25.323933
+19710,26.67406
+19711,28.434378
+19712,34.416862
+19713,34.366695
+19714,36.927223
+19715,37.641106
+19716,53.809036
+19717,56.332577
+19718,64.12461
+19719,34.308784
+19720,35.61641
+19721,38.184982
+19722,37.69607
+19723,39.455105
+19724,41.33902
+19725,44.288353
+19726,43.487736
+19727,46.52912
+19728,50.305847
+19729,56.58641
+19730,56.33086
+19731,17.832275
+19732,18.56081
+19733,21.794424
+19734,29.154127
+19735,37.415913
+19736,43.357716
+19737,57.13522
+19738,56.31639
+19739,42.321453
+19740,47.126503
+19741,55.439312
+19742,58.57498
+19743,5.4132347
+19744,8.687032
+19745,10.959725
+19746,12.464483
+19747,13.193801
+19748,15.745639
+19749,18.275917
+19750,21.289833
+19751,22.313457
+19752,32.26298
+19753,34.082462
+19754,42.359848
+19755,43.589066
+19756,47.257523
+19757,28.801489
+19758,33.95897
+19759,36.22661
+19760,38.01529
+19761,39.2875
+19762,39.435013
+19763,39.796406
+19764,43.787323
+19765,42.582138
+19766,26.886557
+19767,28.285114
+19768,31.174133
+19769,36.889748
+19770,38.672913
+19771,39.81971
+19772,42.769913
+19773,45.183544
+19774,49.71729
+19775,49.387524
+19776,50.524357
+19777,54.367672
+19778,25.820305
+19779,34.495117
+19780,35.534718
+19781,34.93641
+19782,38.24906
+19783,40.97773
+19784,49.03446
+19785,58.077713
+19786,65.71223
+19787,67.889915
+19788,30.198004
+19789,35.293083
+19790,43.44359
+19791,49.208755
+19792,20.227856
+19793,21.168987
+19794,24.086311
+19795,24.679398
+19796,14.979064
+19797,16.028975
+19798,18.544325
+19799,25.223505
+19800,28.386576
+19801,25.481972
+19802,29.531038
+19803,31.783524
+19804,33.75427
+19805,34.004177
+19806,35.84293
+19807,36.25063
+19808,19.69441
+19809,22.619226
+19810,25.239233
+19811,29.075336
+19812,31.893047
+19813,33.716717
+19814,39.355186
+19815,38.74454
+19816,38.95599
+19817,40.339127
+19818,43.736137
+19819,50.74269
+19820,9.49588
+19821,10.842093
+19822,14.754843
+19823,17.294533
+19824,19.246252
+19825,22.327011
+19826,23.904707
+19827,27.57301
+19828,28.429756
+19829,30.467922
+19830,30.725353
+19831,31.02311
+19832,25.795715
+19833,29.313004
+19834,31.750408
+19835,34.980865
+19836,38.17943
+19837,39.925404
+19838,43.76424
+19839,48.21279
+19840,47.30869
+19841,49.421303
+19842,53.448685
+19843,54.219894
+19844,10.599024
+19845,11.727927
+19846,14.458279
+19847,16.9822
+19848,18.000463
+19849,21.55374
+19850,21.674297
+19851,24.906199
+19852,28.47834
+19853,35.710896
+19854,35.62826
+19855,18.82499
+19856,22.61753
+19857,29.087568
+19858,34.3003
+19859,11.340092
+19860,14.515542
+19861,18.504824
+19862,22.04631
+19863,22.524292
+19864,24.986532
+19865,15.63539
+19866,17.639334
+19867,21.501324
+19868,31.121899
+19869,19.716448
+19870,28.362446
+19871,30.274044
+19872,32.338303
+19873,37.46865
+19874,41.297333
+19875,46.4169
+19876,47.687714
+19877,47.771793
+19878,49.594982
+19879,56.247658
+19880,54.56101
+19881,53.62569
+19882,57.469723
+19883,37.061314
+19884,40.30299
+19885,41.327
+19886,42.39241
+19887,46.329826
+19888,49.432198
+19889,52.42703
+19890,55.542286
+19891,57.16994
+19892,59.33841
+19893,65.7957
+19894,67.032005
+19895,19.3386
+19896,26.415565
+19897,25.43869
+19898,27.883293
+19899,31.966446
+19900,34.47373
+19901,36.617958
+19902,39.6044
+19903,42.64205
+19904,44.71847
+19905,46.11171
+19906,49.098618
+19907,16.664661
+19908,20.420124
+19909,25.155993
+19910,24.204876
+19911,30.186996
+19912,31.204266
+19913,32.936386
+19914,36.43151
+19915,37.49547
+19916,41.19943
+19917,44.991566
+19918,44.126938
+19919,48.019695
+19920,48.588036
+19921,50.716698
+19922,51.8564
+19923,0.66149056
+19924,0.97834206
+19925,1.174826
+19926,3.5144713
+19927,4.7852197
+19928,8.558789
+19929,9.983971
+19930,39.247032
+19931,41.67039
+19932,44.088337
+19933,46.36913
+19934,52.736782
+19935,54.666058
+19936,58.127064
+19937,59.24356
+19938,60.163143
+19939,62.017582
+19940,63.66864
+19941,47.140873
+19942,50.48263
+19943,48.788376
+19944,56.261375
+19945,60.215187
+19946,37.794544
+19947,44.56276
+19948,46.12498
+19949,47.95665
+19950,52.241196
+19951,17.438457
+19952,18.6661
+19953,25.277138
+19954,28.50271
+19955,44.259274
+19956,52.273766
+19957,56.51652
+19958,58.955788
+19959,62.341537
+19960,28.109163
+19961,33.748184
+19962,34.295025
+19963,41.356834
+19964,14.305542
+19965,18.867525
+19966,23.062521
+19967,24.411503
+19968,23.825703
+19969,27.285028
+19970,24.914576
+19971,32.92715
+19972,37.405712
+19973,39.235435
+19974,42.87352
+19975,44.63539
+19976,36.08444
+19977,39.44358
+19978,42.6303
+19979,48.404385
+19980,48.63276
+19981,2.1105955
+19982,3.8989701
+19983,8.241063
+19984,8.292007
+19985,2.0664113
+19986,3.149184
+19987,6.154417
+19988,7.790012
+19989,9.41032
+19990,13.4702215
+19991,16.961424
+19992,18.292776
+19993,21.296646
+19994,17.447498
+19995,22.229626
+19996,31.696138
+19997,35.943325
+19998,35.99227
+19999,41.7628
+20000,6.28829
+20001,7.461113
+20002,9.75045
+20003,11.681267
+20004,14.781847
+20005,17.820429
+20006,22.94914
+20007,23.757267
+20008,28.61904
+20009,31.309353
+20010,33.517517
+20011,39.268906
+20012,8.201185
+20013,7.8936577
+20014,10.65711
+20015,13.001606
+20016,18.664099
+20017,21.073418
+20018,23.62082
+20019,24.151823
+20020,33.468807
+20021,37.314682
+20022,34.56564
+20023,32.15749
+20024,37.876686
+20025,45.21826
+20026,48.75784
+20027,44.41255
+20028,49.914677
+20029,53.262573
+20030,57.482914
+20031,19.238853
+20032,19.160309
+20033,24.122244
+20034,26.137272
+20035,27.103964
+20036,19.554703
+20037,21.686348
+20038,22.632486
+20039,29.208187
+20040,16.627663
+20041,17.605282
+20042,19.550594
+20043,21.069014
+20044,16.979244
+20045,15.907207
+20046,19.037218
+20047,25.126122
+20048,26.971838
+20049,27.815117
+20050,29.848276
+20051,30.892353
+20052,33.833893
+20053,32.891624
+20054,33.614464
+20055,35.536755
+20056,17.794687
+20057,19.521513
+20058,25.000593
+20059,26.542332
+20060,33.03422
+20061,32.14371
+20062,33.37249
+20063,35.822044
+20064,27.988653
+20065,30.869835
+20066,32.606243
+20067,33.38799
+20068,14.050014
+20069,16.429462
+20070,20.674536
+20071,19.714493
+20072,24.94024
+20073,27.399641
+20074,26.445236
+20075,35.83308
+20076,35.871685
+20077,33.128
+20078,41.116386
+20079,41.26422
+20080,28.927145
+20081,28.606396
+20082,28.763748
+20083,29.501198
+20084,29.422878
+20085,31.576773
+20086,33.521027
+20087,32.550964
+20088,34.321846
+20089,33.638092
+20090,37.755413
+20091,38.131794
+20092,28.494223
+20093,29.237133
+20094,28.467205
+20095,31.699627
+20096,32.206917
+20097,32.697655
+20098,35.14804
+20099,37.454845
+20100,38.316765
+20101,40.37572
+20102,45.11123
+20103,45.080082
+20104,17.67237
+20105,19.719788
+20106,23.140116
+20107,30.78295
+20108,35.511208
+20109,61.544334
+20110,62.577396
+20111,61.168495
+20112,67.05077
+20113,40.10317
+20114,42.975853
+20115,40.762157
+20116,43.05609
+20117,47.13376
+20118,50.798267
+20119,45.482975
+20120,46.73406
+20121,50.07938
+20122,52.15065
+20123,51.50545
+20124,44.217037
+20125,50.20357
+20126,54.619682
+20127,54.65272
+20128,39.74744
+20129,40.964714
+20130,42.048454
+20131,57.08387
+20132,57.160576
+20133,53.212368
+20134,63.45712
+20135,62.98915
+20136,64.37075
+20137,66.46775
+20138,69.910355
+20139,71.86134
+20140,20.160715
+20141,23.399757
+20142,24.217875
+20143,29.577866
+20144,31.59479
+20145,34.920464
+20146,40.46165
+20147,41.80931
+20148,43.183052
+20149,46.187996
+20150,45.845463
+20151,50.369377
+20152,28.892218
+20153,29.830776
+20154,33.757027
+20155,35.13053
+20156,41.749043
+20157,43.68835
+20158,45.970768
+20159,19.411785
+20160,19.729137
+20161,20.475027
+20162,25.979563
+20163,33.497116
+20164,39.20574
+20165,38.598534
+20166,42.73802
+20167,50.13427
+20168,23.217804
+20169,28.34959
+20170,30.277624
+20171,32.745632
+20172,33.998947
+20173,37.8065
+20174,39.21333
+20175,46.770645
+20176,47.705097
+20177,47.204536
+20178,48.901394
+20179,49.810833
+20180,55.23682
+20181,55.428116
+20182,59.633568
+20183,63.329964
+20184,62.73289
+20185,63.238155
+20186,65.650894
+20187,64.70722
+20188,65.5783
+20189,1.9763596
+20190,3.4603376
+20191,4.832989
+20192,7.038546
+20193,10.336485
+20194,15.8180485
+20195,19.492037
+20196,0.46885574
+20197,1.4036344
+20198,2.3187203
+20199,3.1229224
+20200,29.828108
+20201,36.257824
+20202,35.75887
+20203,35.274033
+20204,16.042555
+20205,16.92435
+20206,17.908512
+20207,22.239155
+20208,22.16466
+20209,25.258743
+20210,25.871656
+20211,30.471817
+20212,33.176575
+20213,36.83348
+20214,41.96018
+20215,41.168186
+20216,48.190235
+20217,46.33715
+20218,49.83321
+20219,51.85604
+20220,54.75859
+20221,54.22076
+20222,53.699677
+20223,53.526897
+20224,60.44107
+20225,62.236633
+20226,62.353424
+20227,66.573166
+20228,19.398968
+20229,28.328716
+20230,35.341904
+20231,42.78557
+20232,25.84831
+20233,29.736553
+20234,33.30586
+20235,44.73211
+20236,48.678547
+20237,9.780227
+20238,10.777971
+20239,10.855225
+20240,13.431429
+20241,20.143974
+20242,22.30973
+20243,25.279297
+20244,27.589716
+20245,31.409523
+20246,35.146942
+20247,36.523743
+20248,41.401512
+20249,45.41344
+20250,45.705906
+20251,45.317604
+20252,48.27544
+20253,52.134724
+20254,51.287098
+20255,10.7581415
+20256,11.267965
+20257,14.711336
+20258,21.060528
+20259,21.675312
+20260,22.499542
+20261,68.25696
+20262,70.14449
+20263,71.60442
+20264,73.03675
+20265,71.13456
+20266,74.22069
+20267,76.333984
+20268,74.86059
+20269,78.51678
+20270,80.609955
+20271,78.193634
+20272,79.53046
+20273,16.668121
+20274,22.265322
+20275,25.147501
+20276,48.078625
+20277,13.814137
+20278,18.209572
+20279,18.267605
+20280,19.222454
+20281,21.662151
+20282,23.131172
+20283,28.204082
+20284,33.94198
+20285,39.362335
+20286,39.49702
+20287,41.033813
+20288,51.10515
+20289,12.800208
+20290,14.28413
+20291,18.513016
+20292,20.178522
+20293,23.810173
+20294,27.70845
+20295,47.30513
+20296,49.63774
+20297,52.001213
+20298,56.98433
+20299,55.143806
+20300,62.17454
+20301,65.355064
+20302,68.68557
+20303,68.44965
+20304,66.30621
+20305,70.68344
+20306,74.6951
+20307,32.001972
+20308,40.436386
+20309,46.55925
+20310,52.22855
+20311,54.369865
+20312,15.932969
+20313,18.312534
+20314,22.234257
+20315,24.443283
+20316,3.8469255
+20317,4.9705462
+20318,11.3075695
+20319,12.492324
+20320,16.396952
+20321,29.221563
+20322,31.926723
+20323,35.64035
+20324,39.08648
+20325,42.846302
+20326,41.45009
+20327,44.40117
+20328,46.011868
+20329,48.52175
+20330,49.17433
+20331,50.52632
+20332,49.162987
+20333,27.202908
+20334,32.308716
+20335,35.12242
+20336,39.486748
+20337,40.53849
+20338,43.79999
+20339,46.197697
+20340,47.786755
+20341,50.07983
+20342,32.13311
+20343,35.866386
+20344,35.198387
+20345,43.045662
+20346,45.939407
+20347,47.32157
+20348,51.866066
+20349,53.314156
+20350,56.363934
+20351,56.773724
+20352,61.379963
+20353,61.172203
+20354,17.391472
+20355,17.700253
+20356,20.57335
+20357,23.658884
+20358,28.39569
+20359,34.790634
+20360,37.13961
+20361,36.840584
+20362,37.86428
+20363,40.777943
+20364,43.64081
+20365,46.8216
+20366,28.887741
+20367,40.345272
+20368,43.024338
+20369,42.36802
+20370,45.70587
+20371,34.775692
+20372,35.87222
+20373,38.258217
+20374,42.79925
+20375,46.712025
+20376,47.90645
+20377,50.599957
+20378,52.780075
+20379,54.957733
+20380,55.77987
+20381,59.83539
+20382,61.22962
+20383,29.24357
+20384,29.105
+20385,32.470417
+20386,43.158348
+20387,51.51632
+20388,45.071255
+20389,45.21142
+20390,47.97972
+20391,53.33926
+20392,53.31144
+20393,57.55273
+20394,55.032497
+20395,57.138012
+20396,56.834385
+20397,60.091606
+20398,61.352013
+20399,63.932083
+20400,64.2223
+20401,67.44712
+20402,65.714714
+20403,68.78001
+20404,70.20126
+20405,2.4821227
+20406,5.041417
+20407,6.6203656
+20408,9.502779
+20409,56.950314
+20410,54.611645
+20411,55.243454
+20412,58.97503
+20413,60.25946
+20414,58.806732
+20415,59.93682
+20416,34.230488
+20417,36.175392
+20418,39.09813
+20419,42.047623
+20420,45.66896
+20421,46.518906
+20422,47.612778
+20423,49.337933
+20424,51.444965
+20425,52.028145
+20426,55.57274
+20427,56.248734
+20428,11.422475
+20429,13.856905
+20430,18.969479
+20431,21.921627
+20432,26.61605
+20433,28.919361
+20434,32.19206
+20435,37.028435
+20436,40.022728
+20437,43.873528
+20438,44.23629
+20439,46.590965
+20440,50.8938
+20441,48.830048
+20442,52.32888
+20443,52.199947
+20444,58.799133
+20445,44.048286
+20446,51.254215
+20447,51.889343
+20448,47.709946
+20449,57.283577
+20450,56.33573
+20451,61.703613
+20452,62.180977
+20453,66.94167
+20454,68.878815
+20455,75.43953
+20456,75.012
+20457,24.746199
+20458,24.045883
+20459,29.179237
+20460,33.591015
+20461,38.703537
+20462,16.338942
+20463,17.335493
+20464,18.943893
+20465,20.414066
+20466,24.390331
+20467,26.137758
+20468,17.442043
+20469,18.995518
+20470,23.1718
+20471,28.520348
+20472,31.270908
+20473,31.4735
+20474,35.528175
+20475,38.713913
+20476,42.24534
+20477,43.141624
+20478,49.189068
+20479,49.890354
+20480,31.031326
+20481,34.46757
+20482,44.155724
+20483,48.213047
+20484,50.967155
+20485,16.313112
+20486,22.255775
+20487,24.424757
+20488,27.209679
+20489,27.99105
+20490,10.185904
+20491,14.125737
+20492,19.546658
+20493,20.590677
+20494,46.900146
+20495,50.61555
+20496,54.295097
+20497,60.124733
+20498,42.054955
+20499,45.92111
+20500,49.79906
+20501,49.69414
+20502,56.108437
+20503,57.68197
+20504,33.98764
+20505,30.487038
+20506,34.743504
+20507,36.2152
+20508,37.709007
+20509,35.863758
+20510,42.51088
+20511,43.303207
+20512,39.61561
+20513,39.679
+20514,43.000088
+20515,45.266384
+20516,18.601784
+20517,33.228718
+20518,32.016697
+20519,30.302816
+20520,35.511192
+20521,28.096912
+20522,33.30698
+20523,38.32799
+20524,44.65382
+20525,59.55812
+20526,60.24665
+20527,62.301247
+20528,58.50358
+20529,62.821495
+20530,64.40328
+20531,66.11131
+20532,67.17375
+20533,64.87412
+20534,71.42371
+20535,71.41217
+20536,73.41599
+20537,38.900677
+20538,43.311172
+20539,45.10272
+20540,45.572826
+20541,51.109474
+20542,55.39166
+20543,54.87121
+20544,35.35994
+20545,36.541286
+20546,37.97254
+20547,43.02724
+20548,21.370344
+20549,23.040924
+20550,25.951313
+20551,31.301235
+20552,34.671085
+20553,35.257248
+20554,37.05974
+20555,36.230816
+20556,37.9866
+20557,36.413483
+20558,32.67057
+20559,37.961304
+20560,38.25975
+20561,42.608837
+20562,18.036787
+20563,19.78761
+20564,19.38264
+20565,21.697502
+20566,22.89732
+20567,25.645748
+20568,30.997225
+20569,29.240074
+20570,33.020393
+20571,35.668613
+20572,35.820957
+20573,37.433693
+20574,44.658337
+20575,42.776077
+20576,41.724987
+20577,40.82828
+20578,40.014442
+20579,44.502922
+20580,48.198853
+20581,35.801884
+20582,34.832283
+20583,36.022644
+20584,36.841015
+20585,37.65744
+20586,42.81621
+20587,46.074417
+20588,53.712994
+20589,57.89208
+20590,29.088173
+20591,30.834988
+20592,35.774063
+20593,35.789337
+20594,38.825607
+20595,42.109863
+20596,45.058605
+20597,51.761555
+20598,49.551826
+20599,53.446785
+20600,60.040287
+20601,62.685745
+20602,35.143616
+20603,36.619926
+20604,36.922974
+20605,38.54066
+20606,39.339817
+20607,38.74997
+20608,39.659527
+20609,40.776886
+20610,4.2076726
+20611,5.7294345
+20612,6.6693454
+20613,9.191
+20614,35.133286
+20615,38.353127
+20616,40.605595
+20617,46.915203
+20618,49.340385
+20619,52.162247
+20620,53.807755
+20621,56.49116
+20622,59.6265
+20623,61.525093
+20624,62.84815
+20625,44.12479
+20626,47.35685
+20627,48.654312
+20628,53.902443
+20629,50.86257
+20630,54.16667
+20631,55.80827
+20632,56.75763
+20633,21.24279
+20634,26.422262
+20635,30.238646
+20636,30.942997
+20637,36.941666
+20638,39.42572
+20639,40.03109
+20640,40.733406
+20641,0.389601
+20642,-0.14938796
+20643,2.6463213
+20644,2.8464303
+20645,5.662871
+20646,10.403547
+20647,13.213379
+20648,15.783479
+20649,15.400329
+20650,16.659634
+20651,18.688042
+20652,20.232203
+20653,17.09682
+20654,17.757435
+20655,20.592598
+20656,24.62276
+20657,26.774775
+20658,30.382761
+20659,30.909346
+20660,31.25486
+20661,37.064667
+20662,39.15526
+20663,44.355507
+20664,45.280964
+20665,46.926987
+20666,52.88506
+20667,54.236233
+20668,57.29086
+20669,62.217327
+20670,61.329582
+20671,57.98081
+20672,61.87563
+20673,64.01915
+20674,67.93278
+20675,25.953182
+20676,27.028492
+20677,31.660603
+20678,37.790375
+20679,9.200826
+20680,13.366719
+20681,15.844641
+20682,17.980942
+20683,17.183674
+20684,18.985878
+20685,19.664051
+20686,24.719
+20687,25.388046
+20688,26.522917
+20689,29.015224
+20690,22.445484
+20691,24.408306
+20692,29.011707
+20693,31.015358
+20694,34.032467
+20695,37.97193
+20696,38.931393
+20697,40.9167
+20698,44.599205
+20699,49.629482
+20700,50.806484
+20701,47.84627
+20702,28.47492
+20703,30.715046
+20704,34.993813
+20705,37.550053
+20706,42.986824
+20707,42.277992
+20708,42.977848
+20709,18.858974
+20710,20.102852
+20711,26.192347
+20712,28.319313
+20713,30.889917
+20714,34.901634
+20715,37.84128
+20716,38.879654
+20717,42.395626
+20718,43.17546
+20719,42.75139
+20720,48.231033
+20721,0.23543769
+20722,0.45537147
+20723,1.1598524
+20724,3.2899346
+20725,4.3044043
+20726,9.471497
+20727,10.485247
+20728,36.736347
+20729,33.42355
+20730,39.450012
+20731,41.697395
+20732,46.861786
+20733,50.56914
+20734,49.568916
+20735,48.84356
+20736,54.405315
+20737,57.27596
+20738,58.32658
+20739,58.605865
+20740,16.21399
+20741,15.866892
+20742,18.527752
+20743,21.148142
+20744,7.653059
+20745,8.5306015
+20746,12.784376
+20747,16.51062
+20748,27.575386
+20749,41.115635
+20750,41.17652
+20751,43.89357
+20752,42.345455
+20753,43.82656
+20754,45.257233
+20755,44.075798
+20756,45.089256
+20757,46.67104
+20758,49.526802
+20759,50.347523
+20760,50.076653
+20761,25.34634
+20762,36.400433
+20763,42.895885
+20764,45.115025
+20765,31.086817
+20766,34.902534
+20767,38.452145
+20768,42.58305
+20769,45.923042
+20770,52.894352
+20771,50.294296
+20772,56.53532
+20773,55.59862
+20774,54.54554
+20775,54.481983
+20776,61.450798
+20777,57.126205
+20778,55.92814
+20779,56.799557
+20780,58.381676
+20781,59.730164
+20782,35.296333
+20783,38.38911
+20784,42.559803
+20785,43.7393
+20786,30.227982
+20787,33.138893
+20788,33.59249
+20789,36.84468
+20790,41.088543
+20791,45.937195
+20792,47.87287
+20793,50.449028
+20794,52.626274
+20795,21.354122
+20796,25.056305
+20797,27.144108
+20798,35.74655
+20799,38.358345
+20800,38.688084
+20801,39.111874
+20802,42.662262
+20803,42.950275
+20804,50.85515
+20805,49.094658
+20806,51.440147
+20807,24.594116
+20808,31.452827
+20809,33.647682
+20810,33.76332
+20811,37.314503
+20812,43.49549
+20813,40.87198
+20814,44.57852
+20815,4.3691607
+20816,5.886368
+20817,7.3249907
+20818,10.506738
+20819,14.744506
+20820,15.985393
+20821,25.620583
+20822,33.063427
+20823,38.509754
+20824,43.017193
+20825,3.3289738
+20826,4.69606
+20827,5.407557
+20828,8.856252
+20829,13.350512
+20830,16.632246
+20831,52.96889
+20832,53.756035
+20833,54.426205
+20834,57.089706
+20835,58.988754
+20836,61.147655
+20837,61.036522
+20838,59.747894
+20839,65.69721
+20840,65.58657
+20841,65.70898
+20842,69.060165
+20843,45.649998
+20844,51.62053
+20845,55.375282
+20846,61.23634
+20847,0.36678785
+20848,0.4943225
+20849,0.78309816
+20850,2.4617913
+20851,28.351717
+20852,30.915916
+20853,32.162983
+20854,37.22531
+20855,40.181366
+20856,39.5218
+20857,46.498524
+20858,45.481415
+20859,49.756763
+20860,56.29412
+20861,63.543633
+20862,57.10013
+20863,30.530651
+20864,34.60088
+20865,34.686665
+20866,41.885242
+20867,46.214504
+20868,48.279
+20869,14.158714
+20870,16.085526
+20871,26.073204
+20872,27.54781
+20873,25.255451
+20874,29.400196
+20875,31.265242
+20876,30.13799
+20877,31.074242
+20878,34.828503
+20879,36.838047
+20880,38.490074
+20881,26.057034
+20882,34.141594
+20883,38.297928
+20884,42.681618
+20885,43.881676
+20886,45.991776
+20887,49.677395
+20888,49.76976
+20889,51.74221
+20890,54.01992
+20891,18.037598
+20892,23.135792
+20893,24.586342
+20894,25.866816
+20895,25.720894
+20896,29.212439
+20897,33.29494
+20898,38.92472
+20899,41.139404
+20900,42.0473
+20901,48.222427
+20902,46.69148
+20903,21.079031
+20904,22.85389
+20905,26.490677
+20906,27.599659
+20907,42.08285
+20908,48.97446
+20909,54.673412
+20910,59.98218
+20911,25.982279
+20912,32.00111
+20913,35.9943
+20914,38.622288
+20915,40.33595
+20916,41.0383
+20917,47.041348
+20918,47.78338
+20919,51.747208
+20920,53.414177
+20921,55.8162
+20922,58.84229
+20923,16.16969
+20924,15.856285
+20925,21.895157
+20926,22.263721
+20927,26.139677
+20928,25.945286
+20929,32.335938
+20930,36.957283
+20931,35.767105
+20932,38.597004
+20933,46.0262
+20934,49.179897
+20935,43.787476
+20936,44.07406
+20937,44.17749
+20938,44.932083
+20939,45.923386
+20940,47.116093
+20941,50.119865
+20942,50.88627
+20943,53.977646
+20944,53.597595
+20945,55.651978
+20946,57.55814
+20947,8.595098
+20948,9.962252
+20949,11.666449
+20950,15.058653
+20951,35.292774
+20952,40.28854
+20953,46.28749
+20954,44.576
+20955,48.65344
+20956,51.8543
+20957,55.82093
+20958,56.948425
+20959,57.67404
+20960,59.926025
+20961,60.64103
+20962,61.404263
+20963,20.775305
+20964,26.910341
+20965,31.952526
+20966,38.63275
+20967,38.876965
+20968,42.97921
+20969,47.38685
+20970,45.365814
+20971,44.619946
+20972,50.918453
+20973,51.210636
+20974,52.223175
+20975,8.625965
+20976,9.769968
+20977,10.801603
+20978,13.859187
+20979,14.499883
+20980,22.82125
+20981,28.763077
+20982,31.591503
+20983,31.556679
+20984,34.25344
+20985,38.16778
+20986,22.564732
+20987,24.536213
+20988,26.399
+20989,28.208294
+20990,33.84376
+20991,38.67984
+20992,40.360588
+20993,43.18728
+20994,46.45157
+20995,30.741966
+20996,43.471382
+20997,46.116974
+20998,47.206486
+20999,27.364689
+21000,39.25484
+21001,40.494186
+21002,38.937504
+21003,40.58127
+21004,46.83553
+21005,49.44654
+21006,49.361454
+21007,3.5051396
+21008,4.3747625
+21009,7.238986
+21010,7.323219
+21011,11.1647835
+21012,12.893124
+21013,14.316723
+21014,14.886492
+21015,17.677242
+21016,18.557138
+21017,17.93932
+21018,23.498121
+21019,26.664572
+21020,26.164692
+21021,25.126581
+21022,25.54447
+21023,28.214
+21024,30.009142
+21025,30.272038
+21026,29.541546
+21027,41.90421
+21028,45.81826
+21029,52.469227
+21030,52.963142
+21031,24.740694
+21032,28.025938
+21033,32.74672
+21034,33.418934
+21035,39.60148
+21036,41.265957
+21037,45.297363
+21038,47.075554
+21039,47.877686
+21040,48.22226
+21041,50.477356
+21042,53.698204
+21043,29.424782
+21044,28.312798
+21045,30.093466
+21046,35.27653
+21047,38.590847
+21048,40.976746
+21049,44.28999
+21050,49.864906
+21051,49.17199
+21052,49.405437
+21053,55.341896
+21054,55.6843
+21055,33.115234
+21056,34.74813
+21057,44.012844
+21058,48.424316
+21059,49.223576
+21060,55.03174
+21061,59.57756
+21062,59.26843
+21063,61.037643
+21064,60.706264
+21065,66.057655
+21066,63.8256
+21067,33.33052
+21068,34.98604
+21069,41.342896
+21070,44.798473
+21071,48.70944
+21072,52.888912
+21073,56.776703
+21074,54.689022
+21075,59.33199
+21076,62.36239
+21077,63.014847
+21078,62.465473
+21079,21.745459
+21080,22.867254
+21081,24.344513
+21082,25.040218
+21083,29.385471
+21084,29.959988
+21085,32.913418
+21086,34.231125
+21087,34.53518
+21088,38.042076
+21089,37.530533
+21090,39.72561
+21091,24.117373
+21092,29.174015
+21093,33.839676
+21094,36.547302
+21095,30.211575
+21096,36.12081
+21097,40.311783
+21098,40.17471
+21099,14.86219
+21100,17.240376
+21101,19.728683
+21102,27.795267
+21103,30.085564
+21104,27.443953
+21105,30.684036
+21106,32.6013
+21107,37.60591
+21108,38.248608
+21109,23.910149
+21110,26.661486
+21111,28.118958
+21112,33.633415
+21113,35.732998
+21114,37.736916
+21115,51.567085
+21116,46.859276
+21117,51.118477
+21118,25.550135
+21119,27.285316
+21120,30.19247
+21121,31.909353
+21122,30.485422
+21123,31.832275
+21124,34.517986
+21125,38.12015
+21126,37.172127
+21127,41.043587
+21128,42.45207
+21129,45.20738
+21130,46.513237
+21131,48.50405
+21132,47.791344
+21133,50.70334
+21134,39.69648
+21135,49.31261
+21136,53.627968
+21137,55.420975
+21138,59.339314
+21139,32.65286
+21140,34.29654
+21141,35.614697
+21142,43.02349
+21143,49.63549
+21144,52.473473
+21145,58.054874
+21146,55.80229
+21147,58.584663
+21148,59.146378
+21149,61.391285
+21150,63.799
+21151,0.84975696
+21152,1.3678168
+21153,1.198718
+21154,6.7479486
+21155,2.5659838
+21156,8.642823
+21157,9.915248
+21158,13.280035
+21159,7.853027
+21160,9.416399
+21161,10.428509
+21162,13.3560705
+21163,15.032114
+21164,18.021313
+21165,20.188465
+21166,22.617521
+21167,26.173132
+21168,28.670246
+21169,31.010313
+21170,35.635796
+21171,22.818932
+21172,25.708221
+21173,26.21774
+21174,31.769623
+21175,32.027775
+21176,36.35429
+21177,43.59064
+21178,49.923935
+21179,47.972267
+21180,53.27373
+21181,48.566696
+21182,62.77372
+21183,60.611206
+21184,62.36084
+21185,67.75243
+21186,67.355835
+21187,19.593695
+21188,24.125223
+21189,32.435074
+21190,35.982407
+21191,32.678284
+21192,34.34042
+21193,37.641525
+21194,41.003983
+21195,45.795692
+21196,48.714493
+21197,47.470776
+21198,47.37862
+21199,39.51845
+21200,43.598087
+21201,46.52893
+21202,49.975292
+21203,55.307518
+21204,16.962158
+21205,15.876225
+21206,25.239716
+21207,28.478945
+21208,62.735615
+21209,65.180466
+21210,67.71802
+21211,68.225586
+21212,69.4895
+21213,68.09419
+21214,70.17561
+21215,65.85862
+21216,70.98003
+21217,72.55585
+21218,76.51755
+21219,76.90408
+21220,28.610867
+21221,30.166197
+21222,31.661814
+21223,32.560646
+21224,36.667164
+21225,40.442917
+21226,41.783134
+21227,44.725044
+21228,45.563194
+21229,44.174168
+21230,47.088535
+21231,48.07487
+21232,10.08687
+21233,11.427006
+21234,16.541584
+21235,18.371738
+21236,22.70987
+21237,24.874447
+21238,31.62103
+21239,34.23816
+21240,36.932568
+21241,33.052963
+21242,35.842888
+21243,42.155403
+21244,40.30548
+21245,44.80218
+21246,49.597656
+21247,64.78329
+21248,63.442875
+21249,61.76487
+21250,63.028835
+21251,63.46151
+21252,63.47438
+21253,70.718155
+21254,78.189476
+21255,10.905901
+21256,19.69431
+21257,22.10807
+21258,22.056782
+21259,49.97553
+21260,59.254818
+21261,59.277992
+21262,60.02118
+21263,58.278645
+21264,58.0561
+21265,61.30052
+21266,62.959633
+21267,66.97385
+21268,69.02315
+21269,69.024124
+21270,68.690575
+21271,18.741865
+21272,23.090242
+21273,26.883184
+21274,25.455904
+21275,29.537388
+21276,31.108751
+21277,32.90831
+21278,35.49632
+21279,37.217876
+21280,37.201668
+21281,29.337414
+21282,29.661121
+21283,33.66333
+21284,39.42984
+21285,41.597946
+21286,42.11988
+21287,44.389645
+21288,48.81179
+21289,48.46891
+21290,49.20038
+21291,50.714912
+21292,49.049446
+21293,9.5641985
+21294,9.522803
+21295,10.59608
+21296,13.688252
+21297,16.676147
+21298,20.587132
+21299,22.516518
+21300,24.496284
+21301,25.40487
+21302,25.906488
+21303,30.251488
+21304,32.477425
+21305,32.770195
+21306,36.781857
+21307,38.429367
+21308,48.89779
+21309,76.39624
+21310,79.499435
+21311,80.7573
+21312,85.15698
+21313,84.286896
+21314,85.84951
+21315,84.67159
+21316,89.83437
+21317,90.29648
+21318,89.17335
+21319,90.30838
+21320,94.072495
+21321,4.3796234
+21322,5.2645516
+21323,13.774611
+21324,14.165053
+21325,52.77859
+21326,55.056515
+21327,56.42176
+21328,53.35837
+21329,55.504944
+21330,55.179813
+21331,55.881996
+21332,60.803867
+21333,58.301315
+21334,60.989143
+21335,10.119749
+21336,12.572385
+21337,15.839394
+21338,23.772665
+21339,43.469643
+21340,47.008587
+21341,51.009216
+21342,53.926846
+21343,61.575287
+21344,60.666645
+21345,62.79913
+21346,67.05141
+21347,67.304344
+21348,65.10807
+21349,71.29533
+21350,71.29658
+21351,49.815613
+21352,51.46114
+21353,51.092438
+21354,50.9721
+21355,54.132004
+21356,55.784554
+21357,27.5983
+21358,28.214478
+21359,31.386984
+21360,36.809895
+21361,37.67491
+21362,37.311768
+21363,37.501167
+21364,37.425144
+21365,42.77426
+21366,42.622288
+21367,44.26538
+21368,49.352016
+21369,31.661163
+21370,36.877155
+21371,38.986122
+21372,43.134007
+21373,42.63725
+21374,46.435192
+21375,46.606773
+21376,46.094906
+21377,50.354744
+21378,51.267773
+21379,53.009514
+21380,51.2272
+21381,31.657255
+21382,37.114998
+21383,38.780148
+21384,41.198544
+21385,12.59383
+21386,12.600124
+21387,15.057381
+21388,21.222334
+21389,23.1874
+21390,22.470177
+21391,26.92445
+21392,31.439796
+21393,33.899696
+21394,35.521084
+21395,36.90586
+21396,39.384514
+21397,12.796029
+21398,15.20502
+21399,22.770084
+21400,23.302896
+21401,22.418411
+21402,32.09024
+21403,35.406876
+21404,39.60018
+21405,45.127056
+21406,45.03988
+21407,51.589672
+21408,47.804523
+21409,47.489426
+21410,49.222786
+21411,57.319275
+21412,57.042923
+21413,19.904064
+21414,24.77536
+21415,31.954407
+21416,37.59871
+21417,32.7457
+21418,36.77988
+21419,40.209404
+21420,44.728943
+21421,36.151978
+21422,38.929253
+21423,39.707146
+21424,41.056763
+21425,46.30755
+21426,47.577805
+21427,49.671455
+21428,51.36223
+21429,52.128345
+21430,53.677525
+21431,59.284508
+21432,61.174816
+21433,12.953423
+21434,14.386256
+21435,15.363997
+21436,25.642248
+21437,26.915567
+21438,26.214008
+21439,28.7644
+21440,31.70806
+21441,43.17142
+21442,43.33566
+21443,42.90775
+21444,46.53843
+21445,44.6168
+21446,47.93801
+21447,51.72239
+21448,58.229797
+21449,57.62769
+21450,61.04368
+21451,18.19899
+21452,27.545599
+21453,28.869722
+21454,31.229382
+21455,23.549393
+21456,25.30374
+21457,32.609993
+21458,29.988636
+21459,33.11509
+21460,37.47847
+21461,39.208412
+21462,43.193577
+21463,44.97635
+21464,49.361168
+21465,54.629753
+21466,29.532177
+21467,30.916227
+21468,36.532978
+21469,39.13936
+21470,45.450645
+21471,47.921597
+21472,51.327347
+21473,51.55512
+21474,54.029694
+21475,56.867683
+21476,58.67682
+21477,62.751053
+21478,20.42712
+21479,24.47133
+21480,35.011982
+21481,36.122433
+21482,42.862526
+21483,29.510063
+21484,33.6951
+21485,43.272854
+21486,47.432693
+21487,21.572626
+21488,23.590025
+21489,27.661259
+21490,33.80854
+21491,34.719635
+21492,39.43493
+21493,38.883614
+21494,42.152554
+21495,44.752182
+21496,46.887222
+21497,47.812973
+21498,45.179955
+21499,22.156023
+21500,30.17404
+21501,32.33891
+21502,28.127941
+21503,23.279617
+21504,32.696964
+21505,31.556072
+21506,36.65635
+21507,40.166397
+21508,42.687477
+21509,48.35175
+21510,51.753338
+21511,53.490505
+21512,55.060413
+21513,57.09775
+21514,58.93522
+21515,18.441439
+21516,25.972202
+21517,28.42553
+21518,24.21379
+21519,27.267788
+21520,31.463017
+21521,34.960617
+21522,35.71664
+21523,40.287197
+21524,45.715183
+21525,46.12822
+21526,26.323124
+21527,27.129902
+21528,26.861462
+21529,30.383976
+21530,30.481245
+21531,28.758474
+21532,31.536114
+21533,33.966763
+21534,35.599625
+21535,35.936523
+21536,38.670498
+21537,39.753273
+21538,10.701322
+21539,10.695312
+21540,13.695644
+21541,15.01465
+21542,21.415298
+21543,23.173641
+21544,24.290005
+21545,29.14296
+21546,30.72918
+21547,32.408638
+21548,35.736454
+21549,34.63545
+21550,47.04061
+21551,43.774693
+21552,49.70691
+21553,54.212383
+21554,5.3646975
+21555,8.036404
+21556,10.701027
+21557,12.215928
+21558,17.202732
+21559,19.54908
+21560,20.462126
+21561,27.576681
+21562,22.83244
+21563,27.080214
+21564,28.768078
+21565,28.53997
+21566,29.807728
+21567,32.071392
+21568,36.33206
+21569,40.633503
+21570,46.503628
+21571,46.71626
+21572,47.31208
+21573,51.491993
+21574,51.805996
+21575,53.01639
+21576,52.229645
+21577,54.380314
+21578,9.8001
+21579,12.789281
+21580,17.94183
+21581,20.962917
+21582,22.68143
+21583,16.504435
+21584,20.046507
+21585,22.066559
+21586,22.918964
+21587,5.844425
+21588,8.69417
+21589,10.7621765
+21590,10.589272
+21591,15.076822
+21592,13.420962
+21593,18.139887
+21594,23.261654
+21595,26.891138
+21596,28.729307
+21597,32.385933
+21598,35.669643
+21599,18.03807
+21600,20.960485
+21601,20.918976
+21602,28.536383
+21603,30.133532
+21604,31.945482
+21605,34.08324
+21606,33.029972
+21607,33.586185
+21608,36.96836
+21609,41.61808
+21610,42.405975
+21611,51.883682
+21612,52.060802
+21613,54.203884
+21614,54.55155
+21615,58.11541
+21616,58.41585
+21617,60.30162
+21618,59.28888
+21619,63.090893
+21620,64.32481
+21621,63.67515
+21622,65.574326
+21623,16.005627
+21624,18.373259
+21625,21.705683
+21626,24.741568
+21627,25.258816
+21628,26.776001
+21629,30.3167
+21630,33.30671
+21631,42.04249
+21632,33.674473
+21633,36.186928
+21634,39.197598
+21635,49.41646
+21636,49.31787
+21637,47.951756
+21638,56.382652
+21639,56.234383
+21640,55.247025
+21641,56.72112
+21642,57.27153
+21643,61.223404
+21644,58.35189
+21645,60.54678
+21646,66.29385
+21647,41.34584
+21648,41.417088
+21649,47.47478
+21650,47.647453
+21651,51.547253
+21652,66.35125
+21653,60.828445
+21654,64.648895
+21655,27.227062
+21656,28.184734
+21657,31.289696
+21658,34.311317
+21659,38.21811
+21660,41.537704
+21661,9.051063
+21662,9.830933
+21663,12.090243
+21664,15.161768
+21665,14.273254
+21666,19.322414
+21667,21.353233
+21668,26.491133
+21669,2.3279526
+21670,3.5436354
+21671,5.390846
+21672,6.163806
+21673,8.181431
+21674,24.02804
+21675,27.710232
+21676,29.675709
+21677,29.524607
+21678,36.50847
+21679,43.057228
+21680,40.402317
+21681,44.632732
+21682,48.465286
+21683,48.594345
+21684,52.39159
+21685,56.25196
+21686,59.08995
+21687,29.664555
+21688,34.915764
+21689,39.791557
+21690,40.555325
+21691,20.485836
+21692,22.049307
+21693,24.789038
+21694,29.227774
+21695,31.490953
+21696,36.83939
+21697,37.30785
+21698,41.80225
+21699,42.4104
+21700,44.761047
+21701,45.898155
+21702,48.979736
+21703,0.9396812
+21704,3.0689163
+21705,3.363149
+21706,5.9783664
+21707,42.55143
+21708,42.664093
+21709,45.888134
+21710,47.471424
+21711,46.273895
+21712,49.993004
+21713,52.003864
+21714,54.227577
+21715,53.860573
+21716,57.650383
+21717,59.121635
+21718,60.11891
+21719,9.885757
+21720,14.10635
+21721,14.4062195
+21722,15.507986
+21723,26.53718
+21724,30.23877
+21725,37.139175
+21726,40.719013
+21727,24.698683
+21728,27.380878
+21729,29.788136
+21730,32.288322
+21731,30.276226
+21732,34.134377
+21733,37.210026
+21734,42.663826
+21735,43.71936
+21736,46.252354
+21737,47.98986
+21738,49.142414
+21739,35.169777
+21740,39.931477
+21741,42.218838
+21742,45.101784
+21743,48.074074
+21744,52.198174
+21745,53.995956
+21746,56.918854
+21747,58.54636
+21748,61.971645
+21749,62.59607
+21750,66.2333
+21751,27.021729
+21752,30.818743
+21753,33.755836
+21754,37.750366
+21755,41.609787
+21756,30.049332
+21757,32.560493
+21758,35.807983
+21759,37.59898
+21760,41.75084
+21761,41.831768
+21762,45.496666
+21763,12.8335705
+21764,14.467453
+21765,13.377798
+21766,16.778522
+21767,21.901205
+21768,25.461014
+21769,26.553968
+21770,33.41251
+21771,36.408752
+21772,37.499256
+21773,39.096317
+21774,46.088184
+21775,8.122288
+21776,16.15859
+21777,16.790436
+21778,14.823414
+21779,16.823774
+21780,20.19299
+21781,21.023312
+21782,22.562666
+21783,24.588953
+21784,25.407251
+21785,25.890623
+21786,27.20093
+21787,24.131363
+21788,26.026623
+21789,26.071049
+21790,32.54371
+21791,36.21673
+21792,39.073597
+21793,24.71445
+21794,29.788982
+21795,33.06438
+21796,35.579258
+21797,41.712902
+21798,50.37967
+21799,50.96821
+21800,51.092186
+21801,31.174688
+21802,34.167694
+21803,36.309185
+21804,42.631588
+21805,44.729584
+21806,46.74882
+21807,53.91726
+21808,54.17665
+21809,55.329865
+21810,56.53313
+21811,63.78125
+21812,60.18124
+21813,4.458866
+21814,5.45383
+21815,7.9407597
+21816,9.742904
+21817,39.005028
+21818,42.797836
+21819,47.02698
+21820,52.69092
+21821,0.016114844
+21822,2.1690464
+21823,3.9890337
+21824,4.9107437
+21825,6.2599397
+21826,10.148726
+21827,12.838372
+21828,14.692859
+21829,12.278112
+21830,17.808374
+21831,16.862535
+21832,17.628866
+21833,49.145874
+21834,53.54355
+21835,57.544403
+21836,63.564983
+21837,26.574944
+21838,34.12555
+21839,36.218864
+21840,33.865257
+21841,37.685936
+21842,43.875683
+21843,50.84083
+21844,49.2248
+21845,49.983353
+21846,52.247307
+21847,54.71543
+21848,55.87789
+21849,22.320065
+21850,23.999872
+21851,25.310177
+21852,29.199598
+21853,34.306038
+21854,35.481865
+21855,38.309998
+21856,38.640354
+21857,26.824493
+21858,34.49876
+21859,37.50106
+21860,35.528336
+21861,43.734352
+21862,49.433914
+21863,27.72131
+21864,28.708447
+21865,26.91119
+21866,32.204388
+21867,44.267937
+21868,47.841995
+21869,51.87422
+21870,54.11739
+21871,58.831993
+21872,16.702763
+21873,21.096493
+21874,20.818089
+21875,31.88695
+21876,52.71387
+21877,56.025024
+21878,61.552853
+21879,60.133904
+21880,62.05634
+21881,66.7498
+21882,70.04237
+21883,69.445175
+21884,21.31679
+21885,22.422161
+21886,25.42197
+21887,35.622475
+21888,37.50587
+21889,40.218246
+21890,43.051792
+21891,45.52805
+21892,47.364212
+21893,47.291805
+21894,48.66386
+21895,47.793793
+21896,6.3757544
+21897,9.173171
+21898,8.33408
+21899,8.916767
+21900,12.272215
+21901,16.335157
+21902,27.158358
+21903,29.521315
+21904,29.89912
+21905,21.779488
+21906,27.663828
+21907,35.91278
+21908,40.11678
+21909,43.160393
+21910,24.631636
+21911,29.601448
+21912,30.284336
+21913,33.06139
+21914,41.700325
+21915,50.05107
+21916,61.2108
+21917,66.5318
+21918,70.991104
+21919,6.7754683
+21920,14.671836
+21921,18.506464
+21922,20.58936
+21923,24.293785
+21924,22.740797
+21925,24.881378
+21926,26.017103
+21927,30.67171
+21928,36.203938
+21929,35.98225
+21930,39.019753
+21931,39.78766
+21932,40.494843
+21933,15.164261
+21934,17.550669
+21935,24.253958
+21936,29.045528
+21937,39.272087
+21938,39.576263
+21939,39.309723
+21940,41.18878
+21941,41.113735
+21942,43.528442
+21943,46.253693
+21944,47.495895
+21945,48.39466
+21946,50.610886
+21947,52.406887
+21948,54.92389
+21949,32.523758
+21950,32.91194
+21951,34.14343
+21952,35.279358
+21953,38.61811
+21954,20.395355
+21955,26.83596
+21956,32.59082
+21957,30.530735
+21958,43.991516
+21959,50.09587
+21960,48.91588
+21961,56.344074
+21962,59.384346
+21963,43.590744
+21964,51.221893
+21965,54.063393
+21966,57.046406
+21967,59.642548
+21968,62.462875
+21969,62.79823
+21970,64.57681
+21971,66.64085
+21972,64.60399
+21973,67.26549
+21974,67.589714
+21975,35.450054
+21976,40.447647
+21977,43.30015
+21978,51.234535
+21979,55.19638
+21980,14.500739
+21981,17.024715
+21982,16.17913
+21983,17.311954
+21984,13.275865
+21985,18.051498
+21986,20.703457
+21987,18.707954
+21988,46.958607
+21989,51.301464
+21990,51.870808
+21991,54.544613
+21992,56.54713
+21993,45.1816
+21994,46.591644
+21995,52.14791
+21996,53.728386
+21997,55.091805
+21998,56.67144
+21999,59.27955
+22000,62.038036
+22001,64.6598
+22002,65.7699
+22003,66.88449
+22004,66.506966
+22005,32.567043
+22006,32.61079
+22007,34.02318
+22008,38.078503
+22009,37.481903
+22010,38.062122
+22011,41.67846
+22012,44.04603
+22013,45.376595
+22014,48.706997
+22015,51.540325
+22016,49.753963
+22017,39.72775
+22018,41.238453
+22019,42.905678
+22020,44.68586
+22021,43.770775
+22022,44.87995
+22023,42.069626
+22024,45.169964
+22025,49.84536
+22026,49.218613
+22027,53.79951
+22028,59.60019
+22029,0.54043293
+22030,1.3604084
+22031,2.4419966
+22032,3.3136685
+22033,6.2390747
+22034,13.206307
+22035,13.375624
+22036,16.466614
+22037,19.869656
+22038,19.7413
+22039,-0.40292343
+22040,-0.36745515
+22041,0.030247098
+22042,1.3508922
+22043,3.4374118
+22044,4.335069
+22045,8.200927
+22046,9.332943
+22047,14.150399
+22048,14.005875
+22049,14.376352
+22050,15.636352
+22051,62.98386
+22052,63.98699
+22053,71.81201
+22054,63.05695
+22055,74.06653
+22056,71.98806
+22057,68.91432
+22058,77.22636
+22059,75.891945
+22060,80.81851
+22061,79.193565
+22062,79.425766
+22063,12.595002
+22064,14.382517
+22065,13.762333
+22066,21.68601
+22067,20.681808
+22068,20.429783
+22069,23.599045
+22070,24.969486
+22071,14.925139
+22072,17.17244
+22073,21.354454
+22074,26.019043
+22075,25.227953
+22076,28.133493
+22077,32.27039
+22078,34.261135
+22079,32.87583
+22080,36.17107
+22081,38.080135
+22082,42.267914
+22083,34.764465
+22084,38.490486
+22085,49.700146
+22086,61.569324
+22087,42.35915
+22088,45.966743
+22089,50.420403
+22090,52.68649
+22091,54.775635
+22092,56.874825
+22093,59.25636
+22094,59.323933
+22095,62.020668
+22096,63.910973
+22097,65.161736
+22098,68.51241
+22099,21.633812
+22100,33.60096
+22101,37.1994
+22102,40.93724
+22103,3.5886164
+22104,3.0259893
+22105,6.0192475
+22106,10.757218
+22107,14.635052
+22108,15.03925
+22109,17.523643
+22110,22.088907
+22111,25.938158
+22112,29.07186
+22113,29.401917
+22114,31.160784
+22115,13.2816305
+22116,19.166677
+22117,20.107046
+22118,19.003893
+22119,16.722107
+22120,20.367018
+22121,24.25984
+22122,23.560482
+22123,24.967854
+22124,33.482235
+22125,29.601562
+22126,35.15471
+22127,43.64737
+22128,53.234726
+22129,55.1317
+22130,49.951836
+22131,54.977364
+22132,56.240566
+22133,58.05307
+22134,60.396233
+22135,63.145138
+22136,63.540966
+22137,64.56284
+22138,70.37819
+22139,12.186396
+22140,14.081011
+22141,15.802451
+22142,16.546581
+22143,19.503859
+22144,20.655476
+22145,23.255005
+22146,14.0759735
+22147,21.288141
+22148,23.000864
+22149,23.386005
+22150,25.437119
+22151,26.700481
+22152,27.150139
+22153,31.618755
+22154,31.234045
+22155,32.30947
+22156,36.07341
+22157,36.168133
+22158,16.69805
+22159,15.991491
+22160,17.354143
+22161,21.613363
+22162,21.373192
+22163,25.059175
+22164,29.845924
+22165,34.644707
+22166,36.443333
+22167,41.484707
+22168,41.233955
+22169,47.23929
+22170,40.933712
+22171,43.85366
+22172,45.31237
+22173,49.54449
+22174,55.272858
+22175,59.33089
+22176,62.25596
+22177,63.80937
+22178,62.424866
+22179,66.17218
+22180,70.01372
+22181,67.12764
+22182,13.69989
+22183,18.15866
+22184,21.997187
+22185,22.246798
+22186,14.501271
+22187,15.237332
+22188,14.640931
+22189,19.269365
+22190,44.67754
+22191,48.979877
+22192,46.162754
+22193,55.06038
+22194,51.171154
+22195,48.875393
+22196,51.12902
+22197,53.12797
+22198,53.50507
+22199,59.279655
+22200,57.654015
+22201,59.10991
+22202,33.660343
+22203,39.187996
+22204,40.67358
+22205,40.827377
+22206,42.1477
+22207,43.53755
+22208,43.74648
+22209,44.75139
+22210,46.309025
+22211,45.883457
+22212,31.32244
+22213,37.234028
+22214,41.17385
+22215,41.949432
+22216,32.22252
+22217,36.030586
+22218,38.16695
+22219,46.195435
+22220,50.89516
+22221,51.859856
+22222,56.73239
+22223,22.849483
+22224,24.389791
+22225,28.553972
+22226,31.28955
+22227,35.71681
+22228,38.270454
+22229,42.929855
+22230,43.355568
+22231,49.117695
+22232,50.18091
+22233,53.33607
+22234,55.353745
+22235,21.11577
+22236,30.311016
+22237,35.543377
+22238,36.894363
+22239,43.445034
+22240,49.047596
+22241,47.246277
+22242,47.54476
+22243,50.33883
+22244,51.84936
+22245,53.9668
+22246,55.608658
+22247,1.0439632
+22248,3.349116
+22249,4.474239
+22250,8.457041
+22251,11.115204
+22252,13.035255
+22253,15.442201
+22254,19.262028
+22255,17.468601
+22256,22.559046
+22257,24.3529
+22258,27.499557
+22259,28.48875
+22260,23.529408
+22261,32.939613
+22262,37.38102
+22263,38.94388
+22264,44.205116
+22265,46.041367
+22266,46.852234
+22267,50.30162
+22268,49.47335
+22269,51.091873
+22270,52.609386
+22271,22.209188
+22272,25.680002
+22273,26.958937
+22274,26.810482
+22275,28.840221
+22276,31.299555
+22277,34.08554
+22278,35.166042
+22279,38.52838
+22280,40.91417
+22281,45.485367
+22282,51.991722
+22283,16.054771
+22284,20.565722
+22285,22.729958
+22286,30.668703
+22287,7.452913
+22288,15.478755
+22289,17.525864
+22290,18.805508
+22291,22.442549
+22292,22.47153
+22293,24.026466
+22294,27.909569
+22295,24.170753
+22296,31.611105
+22297,40.701496
+22298,37.822563
+22299,16.708633
+22300,18.496931
+22301,22.598034
+22302,29.528694
+22303,21.99229
+22304,24.705921
+22305,24.08461
+22306,30.881142
+22307,32.53534
+22308,34.15656
+22309,37.512096
+22310,41.156734
+22311,43.459805
+22312,49.16014
+22313,48.58096
+22314,50.035465
+22315,18.119223
+22316,21.339891
+22317,24.10686
+22318,25.590014
+22319,29.916077
+22320,31.899326
+22321,35.959618
+22322,49.273975
+22323,44.4535
+22324,43.60389
+22325,48.1382
+22326,49.561268
+22327,28.472925
+22328,27.884989
+22329,29.50908
+22330,32.71978
+22331,35.26515
+22332,33.291626
+22333,37.28059
+22334,40.460285
+22335,42.789303
+22336,48.210697
+22337,44.746975
+22338,48.24608
+22339,49.374626
+22340,52.80495
+22341,6.9255023
+22342,9.101163
+22343,9.987484
+22344,16.255005
+22345,21.20353
+22346,22.919006
+22347,30.87353
+22348,68.55151
+22349,66.56892
+22350,71.585526
+22351,71.80227
+22352,72.97113
+22353,74.02164
+22354,75.26466
+22355,74.0251
+22356,73.32771
+22357,74.505226
+22358,76.07766
+22359,79.29824
+22360,35.963863
+22361,39.755684
+22362,40.65328
+22363,43.867237
+22364,22.144424
+22365,22.592197
+22366,23.981625
+22367,23.36677
+22368,26.262617
+22369,27.373219
+22370,29.86705
+22371,30.699005
+22372,35.621162
+22373,36.759903
+22374,40.567757
+22375,41.94713
+22376,39.2194
+22377,39.811386
+22378,47.93985
+22379,50.868416
+22380,53.653572
+22381,55.527695
+22382,59.15242
+22383,58.032173
+22384,58.629974
+22385,61.09777
+22386,59.83692
+22387,62.888245
+22388,8.351906
+22389,10.821341
+22390,19.048431
+22391,26.110128
+22392,30.0303
+22393,30.765293
+22394,41.841022
+22395,44.888855
+22396,41.877457
+22397,44.843864
+22398,47.72586
+22399,48.553555
+22400,50.377174
+22401,53.426243
+22402,37.427757
+22403,36.095886
+22404,38.447403
+22405,42.028767
+22406,38.223476
+22407,41.72901
+22408,48.748947
+22409,49.24414
+22410,51.95231
+22411,-0.4246172
+22412,-0.67491126
+22413,0.69462365
+22414,1.7426572
+22415,3.9131234
+22416,5.294757
+22417,7.0152516
+22418,9.919217
+22419,13.704002
+22420,16.294594
+22421,14.538479
+22422,19.630583
+22423,25.718449
+22424,26.28664
+22425,36.964428
+22426,41.012573
+22427,4.145385
+22428,7.5289507
+22429,7.501377
+22430,10.166217
+22431,12.153904
+22432,16.130596
+22433,19.285242
+22434,27.78667
+22435,28.654697
+22436,26.42578
+22437,30.578547
+22438,32.67459
+22439,26.25599
+22440,26.60612
+22441,28.6486
+22442,31.871946
+22443,34.375553
+22444,34.94135
+22445,35.98986
+22446,36.90375
+22447,37.51611
+22448,39.836227
+22449,41.555653
+22450,45.36013
+22451,48.837128
+22452,50.563103
+22453,51.251377
+22454,53.88846
+22455,57.74741
+22456,58.911453
+22457,62.130993
+22458,62.138824
+22459,17.759827
+22460,23.35387
+22461,25.35489
+22462,22.626041
+22463,28.149681
+22464,31.234753
+22465,33.9579
+22466,38.788433
+22467,41.047596
+22468,40.663395
+22469,44.02734
+22470,46.796154
+22471,21.977034
+22472,24.119503
+22473,33.938694
+22474,37.523994
+22475,37.481606
+22476,39.49403
+22477,31.659363
+22478,40.570694
+22479,45.44453
+22480,43.202736
+22481,58.819633
+22482,55.137238
+22483,61.59066
+22484,65.18422
+22485,6.135864
+22486,6.0972157
+22487,8.545899
+22488,11.520515
+22489,15.477516
+22490,18.504936
+22491,19.690731
+22492,21.383533
+22493,27.12627
+22494,30.271053
+22495,33.378754
+22496,36.99139
+22497,21.826971
+22498,23.614822
+22499,25.187967
+22500,30.39298
+22501,32.507797
+22502,28.032711
+22503,34.039513
+22504,38.532005
+22505,42.30317
+22506,47.594425
+22507,47.94278
+22508,45.49547
+22509,49.449142
+22510,52.380165
+22511,46.483936
+22512,47.90776
+22513,50.262512
+22514,51.7228
+22515,55.32628
+22516,7.7408
+22517,8.780786
+22518,10.612841
+22519,11.221348
+22520,12.080036
+22521,14.376235
+22522,15.644613
+22523,19.301376
+22524,21.802576
+22525,20.701809
+22526,22.131685
+22527,22.904371
+22528,48.07151
+22529,47.22593
+22530,47.310406
+22531,47.15941
+22532,52.054237
+22533,52.74046
+22534,54.670853
+22535,54.820423
+22536,56.22924
+22537,57.693512
+22538,59.56598
+22539,60.065624
+22540,24.527073
+22541,31.389544
+22542,33.294636
+22543,33.733177
+22544,39.269302
+22545,37.96435
+22546,37.05996
+22547,41.09457
+22548,50.675373
+22549,52.535564
+22550,54.546314
+22551,60.404896
+22552,10.769473
+22553,15.275319
+22554,17.464712
+22555,18.85553
+22556,22.661386
+22557,28.196266
+22558,29.620182
+22559,29.045204
+22560,32.342182
+22561,29.883152
+22562,31.92715
+22563,31.367884
+22564,35.983574
+22565,37.065327
+22566,41.405434
+22567,51.36824
+22568,57.193035
+22569,50.097862
+22570,54.604366
+22571,63.612843
+22572,63.13948
+22573,63.702713
+22574,63.77435
+22575,65.73908
+22576,19.946144
+22577,28.971224
+22578,31.190493
+22579,27.709974
+22580,32.583805
+22581,33.27862
+22582,37.40349
+22583,39.00373
+22584,40.085377
+22585,41.615337
+22586,42.70578
+22587,43.02164
+22588,6.342416
+22589,9.349297
+22590,11.924007
+22591,17.577372
+22592,22.15239
+22593,22.67876
+22594,23.244534
+22595,32.124172
+22596,31.118057
+22597,34.801193
+22598,32.877747
+22599,35.319866
+22600,18.037981
+22601,20.986376
+22602,24.385645
+22603,35.042606
+22604,34.604458
+22605,34.973606
+22606,39.527588
+22607,43.20986
+22608,45.73385
+22609,48.694424
+22610,53.663094
+22611,55.51979
+22612,17.715515
+22613,27.85993
+22614,30.810535
+22615,28.160992
+22616,30.934584
+22617,35.01101
+22618,35.915024
+22619,40.1178
+22620,39.954086
+22621,45.86124
+22622,49.89976
+22623,47.3255
+22624,26.51566
+22625,28.790728
+22626,30.015713
+22627,33.11391
+22628,34.675385
+22629,37.43684
+22630,36.660915
+22631,41.158062
+22632,46.0533
+22633,53.02528
+22634,57.11538
+22635,19.802233
+22636,25.393423
+22637,26.50314
+22638,30.28756
+22639,34.847492
+22640,35.166035
+22641,38.369606
+22642,41.400898
+22643,32.27517
+22644,32.82073
+22645,34.87421
+22646,36.077522
+22647,27.562578
+22648,32.029064
+22649,37.90751
+22650,40.708458
+22651,31.913101
+22652,32.91526
+22653,36.84306
+22654,38.494476
+22655,41.37226
+22656,42.14103
+22657,45.0212
+22658,49.975365
+22659,23.032358
+22660,23.899818
+22661,26.922043
+22662,28.531786
+22663,34.562088
+22664,31.962448
+22665,34.673386
+22666,9.421991
+22667,9.539953
+22668,17.457565
+22669,21.403187
+22670,8.34832
+22671,11.29718
+22672,12.265615
+22673,15.706264
+22674,35.02488
+22675,39.854504
+22676,42.068546
+22677,41.910107
+22678,7.1855774
+22679,8.822018
+22680,9.642589
+22681,10.257179
+22682,17.930315
+22683,34.17042
+22684,37.14423
+22685,37.20616
+22686,38.261154
+22687,37.10417
+22688,41.434464
+22689,41.45089
+22690,42.868057
+22691,47.663254
+22692,46.587124
+22693,25.932957
+22694,31.651165
+22695,33.698936
+22696,36.857906
+22697,46.73127
+22698,52.712257
+22699,53.357895
+22700,55.19094
+22701,55.185318
+22702,30.25422
+22703,35.143944
+22704,39.44758
+22705,37.567146
+22706,40.13333
+22707,49.26033
+22708,55.943985
+22709,48.41383
+22710,51.763554
+22711,53.471645
+22712,55.506546
+22713,6.5404005
+22714,9.9284525
+22715,13.048087
+22716,16.936554
+22717,30.243063
+22718,31.41848
+22719,34.029747
+22720,33.881966
+22721,38.183796
+22722,39.664562
+22723,39.205566
+22724,41.559444
+22725,42.363434
+22726,41.90854
+22727,44.745255
+22728,46.202995
+22729,1.9924405
+22730,2.9714193
+22731,6.224148
+22732,8.891286
+22733,10.608482
+22734,12.693
+22735,14.841728
+22736,18.780094
+22737,20.112795
+22738,23.12003
+22739,27.906776
+22740,26.49886
+22741,26.003387
+22742,30.517525
+22743,31.55432
+22744,32.348927
+22745,46.04532
+22746,48.59869
+22747,45.787086
+22748,49.217415
+22749,50.872166
+22750,55.795906
+22751,56.633865
+22752,57.232613
+22753,19.595457
+22754,20.984451
+22755,24.042526
+22756,30.12571
+22757,32.411312
+22758,42.841293
+22759,41.65668
+22760,38.116535
+22761,44.892105
+22762,46.40618
+22763,45.00106
+22764,46.471756
+22765,50.246155
+22766,57.374126
+22767,58.52917
+22768,64.276764
+22769,10.771854
+22770,17.405434
+22771,21.093102
+22772,19.80104
+22773,35.356964
+22774,40.531223
+22775,42.54778
+22776,44.414967
+22777,47.42549
+22778,48.727066
+22779,51.0441
+22780,53.894367
+22781,54.032734
+22782,53.563534
+22783,55.62595
+22784,55.58752
+22785,56.071785
+22786,57.436607
+22787,60.319057
+22788,62.104015
+22789,60.54161
+22790,24.499432
+22791,27.642107
+22792,33.292366
+22793,34.142788
+22794,32.42962
+22795,35.667908
+22796,36.695908
+22797,41.310158
+22798,41.37345
+22799,45.83403
+22800,47.86785
+22801,49.004803
+22802,30.469826
+22803,39.43586
+22804,42.086185
+22805,41.411556
+22806,43.926167
+22807,45.673855
+22808,48.351955
+22809,53.408314
+22810,52.681385
+22811,53.367695
+22812,23.516832
+22813,31.123886
+22814,34.242115
+22815,33.08865
+22816,37.45438
+22817,37.768524
+22818,42.921383
+22819,44.49865
+22820,46.921135
+22821,47.400497
+22822,9.680067
+22823,8.497247
+22824,11.763899
+22825,18.283512
+22826,16.615444
+22827,17.995718
+22828,22.67009
+22829,24.660896
+22830,25.431396
+22831,31.471565
+22832,29.55652
+22833,28.896732
+22834,31.76472
+22835,33.99581
+22836,33.335827
+22837,37.942497
+22838,20.33254
+22839,20.490288
+22840,22.675995
+22841,39.875828
+22842,43.64033
+22843,46.657074
+22844,31.20606
+22845,33.40835
+22846,34.402157
+22847,40.30445
+22848,40.23068
+22849,41.41076
+22850,48.555756
+22851,51.683437
+22852,51.330116
+22853,52.710598
+22854,55.689617
+22855,22.88898
+22856,26.776731
+22857,28.568037
+22858,28.276577
+22859,34.0257
+22860,35.819077
+22861,36.0184
+22862,36.538662
+22863,35.91646
+22864,36.617836
+22865,40.37465
+22866,42.128754
+22867,46.606247
+22868,48.448143
+22869,51.071953
+22870,52.81298
+22871,55.207565
+22872,55.610962
+22873,59.64067
+22874,59.72329
+22875,61.700325
+22876,63.198753
+22877,63.16106
+22878,41.769352
+22879,42.602753
+22880,44.80549
+22881,49.428684
+22882,50.211098
+22883,52.39023
+22884,57.67864
+22885,57.84813
+22886,21.126574
+22887,27.06744
+22888,25.13102
+22889,26.580748
+22890,33.67005
+22891,37.06372
+22892,36.363102
+22893,46.086975
+22894,49.037437
+22895,44.701366
+22896,52.69613
+22897,57.34076
+22898,9.010044
+22899,13.048851
+22900,14.03181
+22901,13.086507
+22902,16.514664
+22903,18.377083
+22904,18.591461
+22905,24.19239
+22906,27.139448
+22907,32.496593
+22908,31.565676
+22909,34.477436
+22910,35.655014
+22911,35.224632
+22912,40.0709
+22913,42.950577
+22914,29.919786
+22915,43.430866
+22916,46.03853
+22917,49.068222
+22918,11.416091
+22919,12.82375
+22920,12.561552
+22921,14.486821
+22922,16.454288
+22923,29.128403
+22924,31.273096
+22925,32.00853
+22926,33.317543
+22927,27.536615
+22928,27.962708
+22929,26.781984
+22930,29.657583
+22931,30.05526
+22932,31.469234
+22933,21.775677
+22934,33.73775
+22935,36.529327
+22936,36.044445
+22937,56.162537
+22938,56.883312
+22939,60.951202
+22940,63.809933
+22941,64.09287
+22942,66.539825
+22943,67.91111
+22944,67.27843
+22945,70.90329
+22946,70.63653
+22947,39.206173
+22948,40.938995
+22949,47.344048
+22950,48.050762
+22951,50.939747
+22952,51.56071
+22953,52.879623
+22954,52.851597
+22955,55.014347
+22956,58.094803
+22957,37.534748
+22958,39.94021
+22959,42.14029
+22960,44.327835
+22961,45.06374
+22962,46.956448
+22963,46.922386
+22964,19.182144
+22965,25.117355
+22966,27.513676
+22967,25.514053
+22968,28.97941
+22969,31.42484
+22970,33.97479
+22971,33.460556
+22972,36.93022
+22973,39.24978
+22974,36.203613
+22975,38.35222
+22976,15.605673
+22977,17.648872
+22978,19.485601
+22979,20.955786
+22980,9.219795
+22981,10.079903
+22982,10.567284
+22983,11.924031
+22984,11.926227
+22985,12.968571
+22986,18.521008
+22987,18.721252
+22988,19.43415
+22989,20.04884
+22990,23.58396
+22991,25.574001
+22992,56.406845
+22993,57.989624
+22994,59.16159
+22995,63.5362
+22996,66.35379
+22997,65.04335
+22998,65.0284
+22999,67.95229
+23000,67.650185
+23001,68.766014
+23002,70.677574
+23003,71.41637
+23004,8.702215
+23005,10.413718
+23006,12.547375
+23007,16.672897
+23008,15.527813
+23009,18.573511
+23010,22.161737
+23011,27.885202
+23012,32.50615
+23013,32.65516
+23014,35.892086
+23015,41.771896
+23016,42.005386
+23017,46.07444
+23018,48.57875
+23019,52.889355
+23020,18.754162
+23021,23.39532
+23022,25.669704
+23023,29.20863
+23024,30.929457
+23025,32.098526
+23026,37.780987
+23027,40.621666
+23028,23.801054
+23029,25.539099
+23030,26.881939
+23031,31.20174
+23032,33.7358
+23033,37.64886
+23034,42.3461
+23035,43.013317
+23036,47.80224
+23037,48.62814
+23038,13.729783
+23039,14.937672
+23040,14.7276325
+23041,17.845652
+23042,18.86495
+23043,25.492496
+23044,24.41862
+23045,27.886045
+23046,31.764244
+23047,31.516323
+23048,43.297478
+23049,43.19733
+23050,41.918083
+23051,45.451508
+23052,55.022182
+23053,57.90051
+23054,68.41392
+23055,69.01547
+23056,70.50517
+23057,71.89023
+23058,73.59184
+23059,74.07003
+23060,73.82338
+23061,75.29428
+23062,76.81338
+23063,75.98872
+23064,79.16051
+23065,77.62451
+23066,16.691784
+23067,21.265846
+23068,23.507385
+23069,25.859348
+23070,29.058107
+23071,30.87991
+23072,35.58672
+23073,35.495907
+23074,39.146935
+23075,44.9878
+23076,50.324657
+23077,52.32304
+23078,49.538155
+23079,52.17575
+23080,52.293148
+23081,53.853333
+23082,57.585228
+23083,56.57688
+23084,57.44644
+23085,59.708492
+23086,60.49775
+23087,65.10681
+23088,14.518103
+23089,18.80228
+23090,23.0508
+23091,23.757446
+23092,26.354712
+23093,27.618738
+23094,31.753254
+23095,32.14276
+23096,37.7986
+23097,38.56757
+23098,5.2437468
+23099,8.41457
+23100,11.336803
+23101,11.376348
+23102,13.364085
+23103,17.12025
+23104,21.803308
+23105,26.454554
+23106,25.92489
+23107,30.998878
+23108,32.342445
+23109,0.27336025
+23110,0.5902689
+23111,0.6460951
+23112,2.0152643
+23113,19.619045
+23114,21.315079
+23115,21.365309
+23116,22.56307
+23117,24.084127
+23118,27.738268
+23119,31.602406
+23120,34.164116
+23121,37.204185
+23122,39.92036
+23123,39.22792
+23124,1.0096204
+23125,2.6195483
+23126,4.246999
+23127,8.594557
+23128,11.272104
+23129,9.35363
+23130,16.164124
+23131,18.112267
+23132,19.424671
+23133,23.007294
+23134,31.756683
+23135,35.40666
+23136,41.98598
+23137,44.18621
+23138,49.2623
+23139,51.86638
+23140,54.79832
+23141,57.782166
+23142,62.176243
+23143,62.39826
+23144,61.594265
+23145,64.58714
+23146,66.909515
+23147,68.10267
+23148,34.439865
+23149,34.30708
+23150,36.786224
+23151,37.584988
+23152,37.116196
+23153,38.261124
+23154,39.638283
+23155,17.312202
+23156,20.166227
+23157,23.251207
+23158,24.10412
+23159,28.696823
+23160,35.881588
+23161,38.465645
+23162,41.774128
+23163,31.170435
+23164,32.804783
+23165,33.190987
+23166,32.2455
+23167,34.90738
+23168,34.779198
+23169,37.210842
+23170,41.35353
+23171,38.65369
+23172,21.621586
+23173,25.919464
+23174,23.548424
+23175,28.773891
+23176,30.264719
+23177,33.612972
+23178,38.660614
+23179,45.303673
+23180,48.670307
+23181,47.961903
+23182,48.803783
+23183,55.142654
+23184,37.589577
+23185,42.614727
+23186,39.0719
+23187,39.359295
+23188,41.727196
+23189,42.874653
+23190,45.208702
+23191,47.557064
+23192,50.515892
+23193,53.02974
+23194,56.325233
+23195,56.871044
+23196,6.3196855
+23197,7.8465147
+23198,12.717046
+23199,15.006981
+23200,14.543119
+23201,18.442295
+23202,22.617577
+23203,27.19712
+23204,32.06287
+23205,33.550255
+23206,35.479515
+23207,38.407207
+23208,5.6750593
+23209,6.441516
+23210,7.762143
+23211,6.648986
+23212,12.018488
+23213,6.03842
+23214,5.6102095
+23215,8.788977
+23216,12.496656
+23217,18.731806
+23218,21.356377
+23219,24.143194
+23220,25.657986
+23221,28.633724
+23222,36.50528
+23223,34.632805
+23224,37.165565
+23225,28.427992
+23226,38.730324
+23227,43.395393
+23228,36.012997
+23229,39.790733
+23230,40.819008
+23231,43.390995
+23232,47.382072
+23233,50.851074
+23234,49.28435
+23235,52.990833
+23236,53.90242
+23237,30.542133
+23238,33.971367
+23239,35.37455
+23240,35.32242
+23241,39.240288
+23242,41.322285
+23243,36.306095
+23244,37.636044
+23245,39.032097
+23246,45.52015
+23247,47.77458
+23248,51.191925
+23249,55.105003
+23250,54.421047
+23251,53.986645
+23252,57.54353
+23253,59.293404
+23254,59.012444
+23255,51.43389
+23256,52.110523
+23257,53.913914
+23258,53.95809
+23259,57.80925
+23260,59.996147
+23261,61.84297
+23262,62.079758
+23263,67.163704
+23264,66.72288
+23265,67.844986
+23266,72.973434
+23267,9.166259
+23268,11.981395
+23269,13.247599
+23270,11.011394
+23271,43.139038
+23272,51.671173
+23273,55.59316
+23274,56.986355
+23275,22.955334
+23276,24.813644
+23277,29.505302
+23278,31.630253
+23279,35.97567
+23280,41.431072
+23281,35.86451
+23282,42.704094
+23283,46.63758
+23284,29.505112
+23285,36.473385
+23286,42.10228
+23287,35.71841
+23288,40.073345
+23289,42.751465
+23290,47.89785
+23291,52.264374
+23292,51.78914
+23293,53.105267
+23294,56.04014
+23295,61.802612
+23296,45.606876
+23297,46.237137
+23298,44.704678
+23299,47.3086
+23300,49.013382
+23301,46.730553
+23302,50.01228
+23303,48.624226
+23304,51.58678
+23305,51.19931
+23306,53.145454
+23307,55.7028
+23308,0.18399693
+23309,0.60805446
+23310,1.3530473
+23311,2.1558628
+23312,6.281998
+23313,10.761654
+23314,14.69653
+23315,9.8934145
+23316,18.610144
+23317,24.098413
+23318,25.945362
+23319,30.573181
+23320,17.37827
+23321,19.168463
+23322,23.015593
+23323,25.213947
+23324,27.930935
+23325,29.210564
+23326,30.266367
+23327,34.273666
+23328,38.69163
+23329,35.899715
+23330,37.582214
+23331,51.337215
+23332,58.973743
+23333,60.773746
+23334,58.520058
+23335,60.80496
+23336,62.513657
+23337,54.114273
+23338,56.521683
+23339,60.912457
+23340,60.8276
+23341,61.25524
+23342,63.450058
+23343,65.03989
+23344,68.53886
+23345,64.92907
+23346,66.083786
+23347,68.38199
+23348,67.17076
+23349,32.09617
+23350,40.91219
+23351,43.195755
+23352,39.551163
+23353,45.37065
+23354,47.49575
+23355,50.59948
+23356,53.62674
+23357,56.26361
+23358,55.506638
+23359,60.24888
+23360,18.733881
+23361,20.876762
+23362,20.72228
+23363,24.359299
+23364,29.64022
+23365,33.257812
+23366,35.10393
+23367,41.329308
+23368,45.78396
+23369,43.94921
+23370,46.19861
+23371,51.2889
+23372,5.4781713
+23373,5.283165
+23374,8.218311
+23375,11.898584
+23376,17.454044
+23377,19.832169
+23378,20.565037
+23379,24.470406
+23380,24.33326
+23381,30.052364
+23382,29.177895
+23383,29.481293
+23384,44.595222
+23385,44.927628
+23386,48.18333
+23387,53.328865
+23388,13.605705
+23389,15.600277
+23390,21.31951
+23391,23.467102
+23392,27.423962
+23393,22.76231
+23394,23.811487
+23395,27.118553
+23396,33.58713
+23397,34.418575
+23398,36.68448
+23399,42.181717
+23400,39.50702
+23401,43.448284
+23402,44.8348
+23403,47.574665
+23404,52.6075
+23405,50.021645
+23406,56.526886
+23407,62.65624
+23408,67.3917
+23409,65.577614
+23410,71.197426
+23411,72.375916
+23412,71.91102
+23413,73.30241
+23414,77.84064
+23415,19.30989
+23416,21.724014
+23417,27.098488
+23418,29.081654
+23419,30.825888
+23420,35.257805
+23421,38.256584
+23422,9.72407
+23423,15.973135
+23424,15.154088
+23425,19.829445
+23426,22.715775
+23427,24.624441
+23428,27.624943
+23429,28.135593
+23430,27.955
+23431,39.090107
+23432,43.920498
+23433,41.073936
+23434,43.223785
+23435,52.395462
+23436,51.768482
+23437,52.03955
+23438,51.118755
+23439,55.203594
+23440,52.483406
+23441,54.599693
+23442,53.18834
+23443,26.59613
+23444,30.870039
+23445,32.898605
+23446,33.732994
+23447,53.901054
+23448,55.805054
+23449,58.817547
+23450,61.006145
+23451,12.683897
+23452,16.48177
+23453,21.409086
+23454,23.489712
+23455,26.98574
+23456,30.566666
+23457,33.13634
+23458,38.067543
+23459,41.579865
+23460,21.723286
+23461,23.625284
+23462,26.084051
+23463,31.712173
+23464,16.893568
+23465,19.677845
+23466,22.012882
+23467,29.790993
+23468,33.026703
+23469,29.9244
+23470,31.31579
+23471,38.485268
+23472,37.868
+23473,41.05387
+23474,43.09433
+23475,45.743587
+23476,37.964695
+23477,43.290356
+23478,47.922802
+23479,48.186
+23480,49.700394
+23481,51.208096
+23482,53.332478
+23483,53.92465
+23484,56.92136
+23485,58.97718
+23486,58.47126
+23487,60.485744
+23488,28.62063
+23489,30.897915
+23490,33.706917
+23491,34.77789
+23492,5.994474
+23493,7.8995285
+23494,11.7496805
+23495,14.678323
+23496,15.409571
+23497,19.955032
+23498,23.739197
+23499,20.023235
+23500,23.702984
+23501,28.418762
+23502,31.802399
+23503,34.672577
+23504,25.773663
+23505,27.063787
+23506,32.69481
+23507,36.357513
+23508,40.88069
+23509,43.01349
+23510,46.30172
+23511,48.674446
+23512,52.234165
+23513,52.92333
+23514,55.672626
+23515,55.450287
+23516,12.323152
+23517,13.594976
+23518,14.923395
+23519,21.704172
+23520,24.470139
+23521,20.554499
+23522,25.337088
+23523,27.32248
+23524,29.93193
+23525,32.614395
+23526,35.712048
+23527,36.407684
+23528,30.366644
+23529,34.240307
+23530,36.15804
+23531,43.35669
+23532,55.824112
+23533,36.98952
+23534,40.76899
+23535,43.164513
+23536,45.91763
+23537,49.90672
+23538,14.099784
+23539,15.59152
+23540,17.387672
+23541,18.85867
+23542,19.40292
+23543,4.4475594
+23544,7.00999
+23545,6.0786424
+23546,11.831301
+23547,14.444228
+23548,19.452532
+23549,21.74175
+23550,15.678477
+23551,16.015018
+23552,26.533667
+23553,27.855564
+23554,27.482285
+23555,30.297739
+23556,32.224953
+23557,34.748474
+23558,35.279854
+23559,37.766304
+23560,41.986877
+23561,40.73227
+23562,18.669106
+23563,30.436352
+23564,33.30729
+23565,26.951723
+23566,30.521326
+23567,33.36123
+23568,37.377888
+23569,40.109447
+23570,42.66593
+23571,47.208008
+23572,47.14833
+23573,51.467117
+23574,56.612484
+23575,60.057556
+23576,57.969704
+23577,62.581844
+23578,2.4683871
+23579,8.165182
+23580,10.3246155
+23581,17.791496
+23582,22.875557
+23583,18.839327
+23584,20.878654
+23585,21.079334
+23586,22.888449
+23587,25.117472
+23588,28.309782
+23589,32.124657
+23590,34.927505
+23591,34.18043
+23592,35.623333
+23593,39.84875
+23594,37.407463
+23595,45.62177
+23596,48.932693
+23597,53.84504
+23598,57.11058
+23599,59.344883
+23600,61.63046
+23601,63.745094
+23602,64.92293
+23603,65.33722
+23604,67.32652
+23605,68.09024
+23606,69.05441
+23607,48.05754
+23608,51.91523
+23609,57.161346
+23610,57.756226
+23611,62.25232
+23612,62.920166
+23613,63.031265
+23614,66.19158
+23615,67.0301
+23616,10.940273
+23617,13.646778
+23618,18.99658
+23619,23.16666
+23620,24.98312
+23621,24.073238
+23622,26.733212
+23623,27.940723
+23624,29.134985
+23625,32.358345
+23626,34.851166
+23627,37.610077
+23628,20.636715
+23629,25.106117
+23630,27.030106
+23631,26.87897
+23632,29.805029
+23633,50.055252
+23634,53.38249
+23635,53.766953
+23636,60.929688
+23637,36.64741
+23638,38.102135
+23639,38.403988
+23640,40.583412
+23641,42.285686
+23642,45.778687
+23643,47.380512
+23644,48.39034
+23645,51.873837
+23646,78.051506
+23647,77.882774
+23648,79.79856
+23649,79.683235
+23650,79.68977
+23651,78.75747
+23652,79.78296
+23653,84.34964
+23654,84.66555
+23655,84.888054
+23656,40.89284
+23657,44.92049
+23658,51.79177
+23659,58.655163
+23660,40.12536
+23661,40.061676
+23662,41.507675
+23663,44.98709
+23664,44.588337
+23665,48.99284
+23666,48.399895
+23667,52.430443
+23668,53.41746
+23669,56.548656
+23670,57.17611
+23671,59.84589
diff --git a/preprocess/prediction_on.ipynb b/preprocess/prediction_on.ipynb
index 028cda3f3e6d78dd462bb22303b66108b091f7de..79b18b3f07f3e84d447ed80441a6ab2cc831a8d9 100644
--- a/preprocess/prediction_on.ipynb
+++ b/preprocess/prediction_on.ipynb
@@ -4,26 +4,5801 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Performance du modèle d'imputation linéaire - MAE: 1.33, R²: 0.97\n",
+ "Pourcentage de valeurs manquantes après imputation: 0.00%\n",
+ "Variable 'time_since_diagnosis' ajoutée avec succès.\n",
+ "\n",
+ "===== IMPUTATION GLOBALE DE 'on' =====\n",
+ "\n",
+ "===== IMPUTATION GLOBALE DE 'off' =====\n",
+ "\n",
+ "✅ Imputation globale terminée.\n",
+ "patient_id 0\n",
+ "cohort 0\n",
+ "sexM 0\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "time_since_intake_on 25940\n",
+ "time_since_intake_off 43828\n",
+ "on 0\n",
+ "off 0\n",
+ "est_LRRK2+ 0\n",
+ "est_GBA+ 0\n",
+ "est_OTHER+ 0\n",
+ "time_since_diagnosis 0\n",
+ "dtype: int64\n",
+ "0\n",
+ "patient_id 0\n",
+ "cohort 0\n",
+ "sexM 0\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "on 0\n",
+ "off 0\n",
+ "est_LRRK2+ 0\n",
+ "est_GBA+ 0\n",
+ "est_OTHER+ 0\n",
+ "time_since_diagnosis 0\n",
+ "num_visite 0\n",
+ "nb_visites 0\n",
+ "diff_on 0\n",
+ "diff_off 0\n",
+ "diff_on_first 0\n",
+ "diff_off_first 0\n",
+ "mean_on 0\n",
+ "mean_off 0\n",
+ "std_on 0\n",
+ "std_off 0\n",
+ "time_since_last_visit 0\n",
+ "ratio_on_off 0\n",
+ "max_off 0\n",
+ "moyenne_geometriques_off 0\n",
+ "moyenne_geometriques_on 0\n",
+ "relative_diff_off 0\n",
+ "relative_diff_on 0\n",
+ "diff_off_mean 0\n",
+ "diff_off_max 0\n",
+ "ratio_visite 0\n",
+ "mean_off_prog_interaction 0\n",
+ "mean_off_based_on_age 0\n",
+ "mean_off_based_on_disease_duration 0\n",
+ "dtype: int64\n"
+ ]
+ }
+ ],
"source": [
"import pandas as pd\n",
"import numpy as np \n",
- "from preprocess4 import PreprocessData"
+ "from preprocess_data import PreprocessData"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Performance du modèle d'imputation linéaire - MAE: 1.33, R²: 0.97\n",
+ "Pourcentage de valeurs manquantes après imputation: 0.00%\n",
+ "Variable 'time_since_diagnosis' ajoutée avec succès.\n",
+ "\n",
+ "===== IMPUTATION GLOBALE DE 'on' =====\n",
+ "\n",
+ "===== IMPUTATION GLOBALE DE 'off' =====\n",
+ "\n",
+ "✅ Imputation globale terminée.\n",
+ "patient_id 0\n",
+ "cohort 0\n",
+ "sexM 0\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "time_since_intake_on 25940\n",
+ "time_since_intake_off 43828\n",
+ "on 0\n",
+ "off 0\n",
+ "est_LRRK2+ 0\n",
+ "est_GBA+ 0\n",
+ "est_OTHER+ 0\n",
+ "time_since_diagnosis 0\n",
+ "dtype: int64\n"
+ ]
+ }
+ ],
"source": [
- "data = pd.read_csv('data/X_train_6ZIKlTY.csv')\n"
+ "\n",
+ "\n",
+ "X_train_full = pd.read_csv('data/X_train_6ZIKlTY.csv')\n",
+ "y_train_full = pd.read_csv('data/y_train_lXj6X5y.csv')['target']\n",
+ "X_test = pd.read_csv('data/X_test_oiZ2ukx.csv')\n",
+ "preprocessor=PreprocessData(X_train_full,y_train_full,X_test)\n",
+ "preprocessor.process_transformation()\n",
+ "X_train,y_train,X_test=preprocessor.get_data()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "patient_id 0\n",
+ "cohort 0\n",
+ "sexM 0\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "on 0\n",
+ "off 0\n",
+ "est_LRRK2+ 0\n",
+ "est_GBA+ 0\n",
+ "est_OTHER+ 0\n",
+ "time_since_diagnosis 0\n",
+ "num_visite 0\n",
+ "nb_visites 0\n",
+ "diff_on 0\n",
+ "diff_off 0\n",
+ "diff_on_first 0\n",
+ "diff_off_first 0\n",
+ "mean_on 0\n",
+ "mean_off 0\n",
+ "std_on 0\n",
+ "std_off 0\n",
+ "time_since_last_visit 0\n",
+ "ratio_on_off 0\n",
+ "max_off 0\n",
+ "moyenne_geometriques_off 0\n",
+ "moyenne_geometriques_on 0\n",
+ "relative_diff_off 0\n",
+ "relative_diff_on 0\n",
+ "diff_off_mean 0\n",
+ "diff_off_max 0\n",
+ "ratio_visite 0\n",
+ "mean_off_prog_interaction 0\n",
+ "mean_off_based_on_age 0\n",
+ "mean_off_based_on_disease_duration 0\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_test.isna().sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[<Axes: title={'center': 'cohort'}>,\n",
+ " <Axes: title={'center': 'sexM'}>,\n",
+ " <Axes: title={'center': 'age_at_diagnosis'}>,\n",
+ " <Axes: title={'center': 'age'}>, <Axes: title={'center': 'on'}>,\n",
+ " <Axes: title={'center': 'off'}>,\n",
+ " <Axes: title={'center': 'est_LRRK2+'}>],\n",
+ " [<Axes: title={'center': 'est_GBA+'}>,\n",
+ " <Axes: title={'center': 'est_OTHER+'}>,\n",
+ " <Axes: title={'center': 'time_since_diagnosis'}>,\n",
+ " <Axes: title={'center': 'num_visite'}>,\n",
+ " <Axes: title={'center': 'nb_visites'}>,\n",
+ " <Axes: title={'center': 'diff_on'}>,\n",
+ " <Axes: title={'center': 'diff_off'}>],\n",
+ " [<Axes: title={'center': 'diff_on_first'}>,\n",
+ " <Axes: title={'center': 'diff_off_first'}>,\n",
+ " <Axes: title={'center': 'mean_on'}>,\n",
+ " <Axes: title={'center': 'mean_off'}>,\n",
+ " <Axes: title={'center': 'std_on'}>,\n",
+ " <Axes: title={'center': 'std_off'}>,\n",
+ " <Axes: title={'center': 'time_since_last_visit'}>],\n",
+ " [<Axes: title={'center': 'slope_off_time'}>,\n",
+ " <Axes: title={'center': 'delta_off_total'}>,\n",
+ " <Axes: title={'center': 'delta_off_per_day'}>,\n",
+ " <Axes: title={'center': 'nb_increase_off'}>,\n",
+ " <Axes: title={'center': 'nb_decrease_off'}>,\n",
+ " <Axes: title={'center': 'off_time_interaction'}>,\n",
+ " <Axes: title={'center': 'mean_off_time_interaction'}>],\n",
+ " [<Axes: title={'center': 'progression_ratio'}>,\n",
+ " <Axes: title={'center': 'off_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'mean_off_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'diff_off_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'diff_off_first_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'slope_off_time_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'std_off_prog_interaction'}>],\n",
+ " [<Axes: title={'center': 'on_off_ratio'}>,\n",
+ " <Axes: title={'center': 'off_on_ratio'}>,\n",
+ " <Axes: title={'center': 'mean_on_mean_off_ratio'}>,\n",
+ " <Axes: title={'center': 'mean_off_mean_on_ratio'}>,\n",
+ " <Axes: title={'center': 'std_on_std_off_ratio'}>,\n",
+ " <Axes: title={'center': 'std_off_std_on_ratio'}>,\n",
+ " <Axes: title={'center': 'diff_on_diff_off_ratio'}>],\n",
+ " [<Axes: title={'center': 'progression_time_ratio'}>,\n",
+ " <Axes: title={'center': 'off_geometric_mean'}>,\n",
+ " <Axes: title={'center': 'off_geom_ratio'}>,\n",
+ " <Axes: title={'center': 'geom_mean_prog_interaction'}>,\n",
+ " <Axes: title={'center': 'off_prev_1'}>,\n",
+ " <Axes: title={'center': 'off_prev_2'}>,\n",
+ " <Axes: title={'center': 'off_last_2_mean'}>],\n",
+ " [<Axes: title={'center': 'off_diff_from_prev_1'}>,\n",
+ " <Axes: title={'center': 'off_diff_from_prev_2'}>,\n",
+ " <Axes: title={'center': 'off_diff_from_last_2_mean'}>,\n",
+ " <Axes: title={'center': 'off_trend'}>,\n",
+ " <Axes: title={'center': 'trend_prog_interaction'}>, <Axes: >,\n",
+ " <Axes: >]], dtype=object)"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 2000x1500 with 56 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: >"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 640x480 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "y_train.hist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "X_test.drop('patient_id', axis=1, inplace=True)\n",
+ "X_train.drop('patient_id', axis=1, inplace=True)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "# Exemple avec XGBoost\n",
+ "from xgboost import XGBRegressor\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.metrics import mean_squared_error\n",
+ "# import de randomforest\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "from sklearn.model_selection import GridSearchCV\n",
+ "\n",
+ "X_tr, X_val, y_tr, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[0]\tvalidation_0-rmse:15.41412\n",
+ "[1]\tvalidation_0-rmse:14.44605\n",
+ "[2]\tvalidation_0-rmse:13.54916\n",
+ "[3]\tvalidation_0-rmse:12.72203\n",
+ "[4]\tvalidation_0-rmse:11.95729\n",
+ "[5]\tvalidation_0-rmse:11.24975\n",
+ "[6]\tvalidation_0-rmse:10.59421\n",
+ "[7]\tvalidation_0-rmse:9.99216\n",
+ "[8]\tvalidation_0-rmse:9.43953\n",
+ "[9]\tvalidation_0-rmse:8.92905\n",
+ "[10]\tvalidation_0-rmse:8.45906\n",
+ "[11]\tvalidation_0-rmse:8.02779\n",
+ "[12]\tvalidation_0-rmse:7.63398\n",
+ "[13]\tvalidation_0-rmse:7.27073\n",
+ "[14]\tvalidation_0-rmse:6.93992\n",
+ "[15]\tvalidation_0-rmse:6.63813\n",
+ "[16]\tvalidation_0-rmse:6.36346\n",
+ "[17]\tvalidation_0-rmse:6.11081\n",
+ "[18]\tvalidation_0-rmse:5.87857\n",
+ "[19]\tvalidation_0-rmse:5.66885\n",
+ "[20]\tvalidation_0-rmse:5.47990\n",
+ "[21]\tvalidation_0-rmse:5.30954\n",
+ "[22]\tvalidation_0-rmse:5.15349\n",
+ "[23]\tvalidation_0-rmse:5.01351\n",
+ "[24]\tvalidation_0-rmse:4.88841\n",
+ "[25]\tvalidation_0-rmse:4.77393\n",
+ "[26]\tvalidation_0-rmse:4.67273\n",
+ "[27]\tvalidation_0-rmse:4.57744\n",
+ "[28]\tvalidation_0-rmse:4.49493\n",
+ "[29]\tvalidation_0-rmse:4.41882\n",
+ "[30]\tvalidation_0-rmse:4.34998\n",
+ "[31]\tvalidation_0-rmse:4.29005\n",
+ "[32]\tvalidation_0-rmse:4.23765\n",
+ "[33]\tvalidation_0-rmse:4.18912\n",
+ "[34]\tvalidation_0-rmse:4.14409\n",
+ "[35]\tvalidation_0-rmse:4.10431\n",
+ "[36]\tvalidation_0-rmse:4.06724\n",
+ "[37]\tvalidation_0-rmse:4.03592\n",
+ "[38]\tvalidation_0-rmse:4.00640\n",
+ "[39]\tvalidation_0-rmse:3.97973\n",
+ "[40]\tvalidation_0-rmse:3.95627\n",
+ "[41]\tvalidation_0-rmse:3.93445\n",
+ "[42]\tvalidation_0-rmse:3.91572\n",
+ "[43]\tvalidation_0-rmse:3.89681\n",
+ "[44]\tvalidation_0-rmse:3.87975\n",
+ "[45]\tvalidation_0-rmse:3.86325\n",
+ "[46]\tvalidation_0-rmse:3.84979\n",
+ "[47]\tvalidation_0-rmse:3.83667\n",
+ "[48]\tvalidation_0-rmse:3.82407\n",
+ "[49]\tvalidation_0-rmse:3.81217\n",
+ "[50]\tvalidation_0-rmse:3.80147\n",
+ "[51]\tvalidation_0-rmse:3.79268\n",
+ "[52]\tvalidation_0-rmse:3.78490\n",
+ "[53]\tvalidation_0-rmse:3.77565\n",
+ "[54]\tvalidation_0-rmse:3.76677\n",
+ "[55]\tvalidation_0-rmse:3.76086\n",
+ "[56]\tvalidation_0-rmse:3.75557\n",
+ "[57]\tvalidation_0-rmse:3.75060\n",
+ "[58]\tvalidation_0-rmse:3.74454\n",
+ "[59]\tvalidation_0-rmse:3.73919\n",
+ "[60]\tvalidation_0-rmse:3.73407\n",
+ "[61]\tvalidation_0-rmse:3.72950\n",
+ "[62]\tvalidation_0-rmse:3.72224\n",
+ "[63]\tvalidation_0-rmse:3.71912\n",
+ "[64]\tvalidation_0-rmse:3.71370\n",
+ "[65]\tvalidation_0-rmse:3.70825\n",
+ "[66]\tvalidation_0-rmse:3.70407\n",
+ "[67]\tvalidation_0-rmse:3.69867\n",
+ "[68]\tvalidation_0-rmse:3.69403\n",
+ "[69]\tvalidation_0-rmse:3.69169\n",
+ "[70]\tvalidation_0-rmse:3.68810\n",
+ "[71]\tvalidation_0-rmse:3.68383\n",
+ "[72]\tvalidation_0-rmse:3.67925\n",
+ "[73]\tvalidation_0-rmse:3.67683\n",
+ "[74]\tvalidation_0-rmse:3.67487\n",
+ "[75]\tvalidation_0-rmse:3.66915\n",
+ "[76]\tvalidation_0-rmse:3.66767\n",
+ "[77]\tvalidation_0-rmse:3.66208\n",
+ "[78]\tvalidation_0-rmse:3.65773\n",
+ "[79]\tvalidation_0-rmse:3.65435\n",
+ "[80]\tvalidation_0-rmse:3.65294\n",
+ "[81]\tvalidation_0-rmse:3.64770\n",
+ "[82]\tvalidation_0-rmse:3.64488\n",
+ "[83]\tvalidation_0-rmse:3.64159\n",
+ "[84]\tvalidation_0-rmse:3.64006\n",
+ "[85]\tvalidation_0-rmse:3.63787\n",
+ "[86]\tvalidation_0-rmse:3.63573\n",
+ "[87]\tvalidation_0-rmse:3.63414\n",
+ "[88]\tvalidation_0-rmse:3.63203\n",
+ "[89]\tvalidation_0-rmse:3.63043\n",
+ "[90]\tvalidation_0-rmse:3.62879\n",
+ "[91]\tvalidation_0-rmse:3.62572\n",
+ "[92]\tvalidation_0-rmse:3.62225\n",
+ "[93]\tvalidation_0-rmse:3.61940\n",
+ "[94]\tvalidation_0-rmse:3.61827\n",
+ "[95]\tvalidation_0-rmse:3.61702\n",
+ "[96]\tvalidation_0-rmse:3.61448\n",
+ "[97]\tvalidation_0-rmse:3.61223\n",
+ "[98]\tvalidation_0-rmse:3.61019\n",
+ "[99]\tvalidation_0-rmse:3.60876\n",
+ "[100]\tvalidation_0-rmse:3.60666\n",
+ "[101]\tvalidation_0-rmse:3.60498\n",
+ "[102]\tvalidation_0-rmse:3.60383\n",
+ "[103]\tvalidation_0-rmse:3.60058\n",
+ "[104]\tvalidation_0-rmse:3.59767\n",
+ "[105]\tvalidation_0-rmse:3.59682\n",
+ "[106]\tvalidation_0-rmse:3.59595\n",
+ "[107]\tvalidation_0-rmse:3.59289\n",
+ "[108]\tvalidation_0-rmse:3.59210\n",
+ "[109]\tvalidation_0-rmse:3.58837\n",
+ "[110]\tvalidation_0-rmse:3.58379\n",
+ "[111]\tvalidation_0-rmse:3.58272\n",
+ "[112]\tvalidation_0-rmse:3.58172\n",
+ "[113]\tvalidation_0-rmse:3.57833\n",
+ "[114]\tvalidation_0-rmse:3.57639\n",
+ "[115]\tvalidation_0-rmse:3.57517\n",
+ "[116]\tvalidation_0-rmse:3.57165\n",
+ "[117]\tvalidation_0-rmse:3.56944\n",
+ "[118]\tvalidation_0-rmse:3.56600\n",
+ "[119]\tvalidation_0-rmse:3.56530\n",
+ "[120]\tvalidation_0-rmse:3.56404\n",
+ "[121]\tvalidation_0-rmse:3.56360\n",
+ "[122]\tvalidation_0-rmse:3.56111\n",
+ "[123]\tvalidation_0-rmse:3.55995\n",
+ "[124]\tvalidation_0-rmse:3.55834\n",
+ "[125]\tvalidation_0-rmse:3.55676\n",
+ "[126]\tvalidation_0-rmse:3.55212\n",
+ "[127]\tvalidation_0-rmse:3.55158\n",
+ "[128]\tvalidation_0-rmse:3.55013\n",
+ "[129]\tvalidation_0-rmse:3.54922\n",
+ "[130]\tvalidation_0-rmse:3.54883\n",
+ "[131]\tvalidation_0-rmse:3.54572\n",
+ "[132]\tvalidation_0-rmse:3.54210\n",
+ "[133]\tvalidation_0-rmse:3.54091\n",
+ "[134]\tvalidation_0-rmse:3.53986\n",
+ "[135]\tvalidation_0-rmse:3.53833\n",
+ "[136]\tvalidation_0-rmse:3.53666\n",
+ "[137]\tvalidation_0-rmse:3.53531\n",
+ "[138]\tvalidation_0-rmse:3.53423\n",
+ "[139]\tvalidation_0-rmse:3.53391\n",
+ "[140]\tvalidation_0-rmse:3.53192\n",
+ "[141]\tvalidation_0-rmse:3.52830\n",
+ "[142]\tvalidation_0-rmse:3.52735\n",
+ "[143]\tvalidation_0-rmse:3.52503\n",
+ "[144]\tvalidation_0-rmse:3.52321\n",
+ "[145]\tvalidation_0-rmse:3.52095\n",
+ "[146]\tvalidation_0-rmse:3.52019\n",
+ "[147]\tvalidation_0-rmse:3.51953\n",
+ "[148]\tvalidation_0-rmse:3.51600\n",
+ "[149]\tvalidation_0-rmse:3.51145\n",
+ "[150]\tvalidation_0-rmse:3.50987\n",
+ "[151]\tvalidation_0-rmse:3.50916\n",
+ "[152]\tvalidation_0-rmse:3.50876\n",
+ "[153]\tvalidation_0-rmse:3.50373\n",
+ "[154]\tvalidation_0-rmse:3.50322\n",
+ "[155]\tvalidation_0-rmse:3.50211\n",
+ "[156]\tvalidation_0-rmse:3.50155\n",
+ "[157]\tvalidation_0-rmse:3.50052\n",
+ "[158]\tvalidation_0-rmse:3.49963\n",
+ "[159]\tvalidation_0-rmse:3.49911\n",
+ "[160]\tvalidation_0-rmse:3.49745\n",
+ "[161]\tvalidation_0-rmse:3.49668\n",
+ "[162]\tvalidation_0-rmse:3.49240\n",
+ "[163]\tvalidation_0-rmse:3.49127\n",
+ "[164]\tvalidation_0-rmse:3.48843\n",
+ "[165]\tvalidation_0-rmse:3.48379\n",
+ "[166]\tvalidation_0-rmse:3.48291\n",
+ "[167]\tvalidation_0-rmse:3.48101\n",
+ "[168]\tvalidation_0-rmse:3.47984\n",
+ "[169]\tvalidation_0-rmse:3.47964\n",
+ "[170]\tvalidation_0-rmse:3.47597\n",
+ "[171]\tvalidation_0-rmse:3.47451\n",
+ "[172]\tvalidation_0-rmse:3.47340\n",
+ "[173]\tvalidation_0-rmse:3.47179\n",
+ "[174]\tvalidation_0-rmse:3.46942\n",
+ "[175]\tvalidation_0-rmse:3.46541\n",
+ "[176]\tvalidation_0-rmse:3.46296\n",
+ "[177]\tvalidation_0-rmse:3.45907\n",
+ "[178]\tvalidation_0-rmse:3.45582\n",
+ "[179]\tvalidation_0-rmse:3.45464\n",
+ "[180]\tvalidation_0-rmse:3.45066\n",
+ "[181]\tvalidation_0-rmse:3.44828\n",
+ "[182]\tvalidation_0-rmse:3.44695\n",
+ "[183]\tvalidation_0-rmse:3.44631\n",
+ "[184]\tvalidation_0-rmse:3.44517\n",
+ "[185]\tvalidation_0-rmse:3.44511\n",
+ "[186]\tvalidation_0-rmse:3.44282\n",
+ "[187]\tvalidation_0-rmse:3.44066\n",
+ "[188]\tvalidation_0-rmse:3.43843\n",
+ "[189]\tvalidation_0-rmse:3.43633\n",
+ "[190]\tvalidation_0-rmse:3.43462\n",
+ "[191]\tvalidation_0-rmse:3.43337\n",
+ "[192]\tvalidation_0-rmse:3.43202\n",
+ "[193]\tvalidation_0-rmse:3.43050\n",
+ "[194]\tvalidation_0-rmse:3.42976\n",
+ "[195]\tvalidation_0-rmse:3.42682\n",
+ "[196]\tvalidation_0-rmse:3.42440\n",
+ "[197]\tvalidation_0-rmse:3.42212\n",
+ "[198]\tvalidation_0-rmse:3.42017\n",
+ "[199]\tvalidation_0-rmse:3.41722\n",
+ "[200]\tvalidation_0-rmse:3.41432\n",
+ "[201]\tvalidation_0-rmse:3.41259\n",
+ "[202]\tvalidation_0-rmse:3.41203\n",
+ "[203]\tvalidation_0-rmse:3.41079\n",
+ "[204]\tvalidation_0-rmse:3.40989\n",
+ "[205]\tvalidation_0-rmse:3.40871\n",
+ "[206]\tvalidation_0-rmse:3.40740\n",
+ "[207]\tvalidation_0-rmse:3.40718\n",
+ "[208]\tvalidation_0-rmse:3.40712\n",
+ "[209]\tvalidation_0-rmse:3.40683\n",
+ "[210]\tvalidation_0-rmse:3.40517\n",
+ "[211]\tvalidation_0-rmse:3.40416\n",
+ "[212]\tvalidation_0-rmse:3.40296\n",
+ "[213]\tvalidation_0-rmse:3.40219\n",
+ "[214]\tvalidation_0-rmse:3.40047\n",
+ "[215]\tvalidation_0-rmse:3.40003\n",
+ "[216]\tvalidation_0-rmse:3.39823\n",
+ "[217]\tvalidation_0-rmse:3.39784\n",
+ "[218]\tvalidation_0-rmse:3.39731\n",
+ "[219]\tvalidation_0-rmse:3.39580\n",
+ "[220]\tvalidation_0-rmse:3.39492\n",
+ "[221]\tvalidation_0-rmse:3.39473\n",
+ "[222]\tvalidation_0-rmse:3.39403\n",
+ "[223]\tvalidation_0-rmse:3.39316\n",
+ "[224]\tvalidation_0-rmse:3.39308\n",
+ "[225]\tvalidation_0-rmse:3.39192\n",
+ "[226]\tvalidation_0-rmse:3.39029\n",
+ "[227]\tvalidation_0-rmse:3.38764\n",
+ "[228]\tvalidation_0-rmse:3.38704\n",
+ "[229]\tvalidation_0-rmse:3.38380\n",
+ "[230]\tvalidation_0-rmse:3.38235\n",
+ "[231]\tvalidation_0-rmse:3.38167\n",
+ "[232]\tvalidation_0-rmse:3.38098\n",
+ "[233]\tvalidation_0-rmse:3.38011\n",
+ "[234]\tvalidation_0-rmse:3.37941\n",
+ "[235]\tvalidation_0-rmse:3.37839\n",
+ "[236]\tvalidation_0-rmse:3.37772\n",
+ "[237]\tvalidation_0-rmse:3.37730\n",
+ "[238]\tvalidation_0-rmse:3.37408\n",
+ "[239]\tvalidation_0-rmse:3.37312\n",
+ "[240]\tvalidation_0-rmse:3.37140\n",
+ "[241]\tvalidation_0-rmse:3.37004\n",
+ "[242]\tvalidation_0-rmse:3.36902\n",
+ "[243]\tvalidation_0-rmse:3.36775\n",
+ "[244]\tvalidation_0-rmse:3.36743\n",
+ "[245]\tvalidation_0-rmse:3.36549\n",
+ "[246]\tvalidation_0-rmse:3.36546\n",
+ "[247]\tvalidation_0-rmse:3.36431\n",
+ "[248]\tvalidation_0-rmse:3.36342\n",
+ "[249]\tvalidation_0-rmse:3.35982\n",
+ "[250]\tvalidation_0-rmse:3.35908\n",
+ "[251]\tvalidation_0-rmse:3.35577\n",
+ "[252]\tvalidation_0-rmse:3.35518\n",
+ "[253]\tvalidation_0-rmse:3.35467\n",
+ "[254]\tvalidation_0-rmse:3.35198\n",
+ "[255]\tvalidation_0-rmse:3.35144\n",
+ "[256]\tvalidation_0-rmse:3.35100\n",
+ "[257]\tvalidation_0-rmse:3.35062\n",
+ "[258]\tvalidation_0-rmse:3.34989\n",
+ "[259]\tvalidation_0-rmse:3.34846\n",
+ "[260]\tvalidation_0-rmse:3.34521\n",
+ "[261]\tvalidation_0-rmse:3.34468\n",
+ "[262]\tvalidation_0-rmse:3.34424\n",
+ "[263]\tvalidation_0-rmse:3.34389\n",
+ "[264]\tvalidation_0-rmse:3.34159\n",
+ "[265]\tvalidation_0-rmse:3.34092\n",
+ "[266]\tvalidation_0-rmse:3.34023\n",
+ "[267]\tvalidation_0-rmse:3.34062\n",
+ "[268]\tvalidation_0-rmse:3.33878\n",
+ "[269]\tvalidation_0-rmse:3.33565\n",
+ "[270]\tvalidation_0-rmse:3.33438\n",
+ "[271]\tvalidation_0-rmse:3.33235\n",
+ "[272]\tvalidation_0-rmse:3.33248\n",
+ "[273]\tvalidation_0-rmse:3.33151\n",
+ "[274]\tvalidation_0-rmse:3.33024\n",
+ "[275]\tvalidation_0-rmse:3.32929\n",
+ "[276]\tvalidation_0-rmse:3.32843\n",
+ "[277]\tvalidation_0-rmse:3.32804\n",
+ "[278]\tvalidation_0-rmse:3.32566\n",
+ "[279]\tvalidation_0-rmse:3.32489\n",
+ "[280]\tvalidation_0-rmse:3.32435\n",
+ "[281]\tvalidation_0-rmse:3.32385\n",
+ "[282]\tvalidation_0-rmse:3.32280\n",
+ "[283]\tvalidation_0-rmse:3.32181\n",
+ "[284]\tvalidation_0-rmse:3.32161\n",
+ "[285]\tvalidation_0-rmse:3.31897\n",
+ "[286]\tvalidation_0-rmse:3.31908\n",
+ "[287]\tvalidation_0-rmse:3.31804\n",
+ "[288]\tvalidation_0-rmse:3.31766\n",
+ "[289]\tvalidation_0-rmse:3.31726\n",
+ "[290]\tvalidation_0-rmse:3.31489\n",
+ "[291]\tvalidation_0-rmse:3.31458\n",
+ "[292]\tvalidation_0-rmse:3.31304\n",
+ "[293]\tvalidation_0-rmse:3.31256\n",
+ "[294]\tvalidation_0-rmse:3.31232\n",
+ "[295]\tvalidation_0-rmse:3.30834\n",
+ "[296]\tvalidation_0-rmse:3.30822\n",
+ "[297]\tvalidation_0-rmse:3.30773\n",
+ "[298]\tvalidation_0-rmse:3.30554\n",
+ "[299]\tvalidation_0-rmse:3.30542\n",
+ "[300]\tvalidation_0-rmse:3.30464\n",
+ "[301]\tvalidation_0-rmse:3.30274\n",
+ "[302]\tvalidation_0-rmse:3.30046\n",
+ "[303]\tvalidation_0-rmse:3.29853\n",
+ "[304]\tvalidation_0-rmse:3.29569\n",
+ "[305]\tvalidation_0-rmse:3.29449\n",
+ "[306]\tvalidation_0-rmse:3.29180\n",
+ "[307]\tvalidation_0-rmse:3.29020\n",
+ "[308]\tvalidation_0-rmse:3.28687\n",
+ "[309]\tvalidation_0-rmse:3.28617\n",
+ "[310]\tvalidation_0-rmse:3.28511\n",
+ "[311]\tvalidation_0-rmse:3.28355\n",
+ "[312]\tvalidation_0-rmse:3.28216\n",
+ "[313]\tvalidation_0-rmse:3.28049\n",
+ "[314]\tvalidation_0-rmse:3.28025\n",
+ "[315]\tvalidation_0-rmse:3.27780\n",
+ "[316]\tvalidation_0-rmse:3.27575\n",
+ "[317]\tvalidation_0-rmse:3.27504\n",
+ "[318]\tvalidation_0-rmse:3.27465\n",
+ "[319]\tvalidation_0-rmse:3.27407\n",
+ "[320]\tvalidation_0-rmse:3.27388\n",
+ "[321]\tvalidation_0-rmse:3.27335\n",
+ "[322]\tvalidation_0-rmse:3.27102\n",
+ "[323]\tvalidation_0-rmse:3.26988\n",
+ "[324]\tvalidation_0-rmse:3.26732\n",
+ "[325]\tvalidation_0-rmse:3.26540\n",
+ "[326]\tvalidation_0-rmse:3.26535\n",
+ "[327]\tvalidation_0-rmse:3.26467\n",
+ "[328]\tvalidation_0-rmse:3.26319\n",
+ "[329]\tvalidation_0-rmse:3.26208\n",
+ "[330]\tvalidation_0-rmse:3.26142\n",
+ "[331]\tvalidation_0-rmse:3.26103\n",
+ "[332]\tvalidation_0-rmse:3.26077\n",
+ "[333]\tvalidation_0-rmse:3.26036\n",
+ "[334]\tvalidation_0-rmse:3.25987\n",
+ "[335]\tvalidation_0-rmse:3.25882\n",
+ "[336]\tvalidation_0-rmse:3.25813\n",
+ "[337]\tvalidation_0-rmse:3.25625\n",
+ "[338]\tvalidation_0-rmse:3.25482\n",
+ "[339]\tvalidation_0-rmse:3.25393\n",
+ "[340]\tvalidation_0-rmse:3.25341\n",
+ "[341]\tvalidation_0-rmse:3.25181\n",
+ "[342]\tvalidation_0-rmse:3.25170\n",
+ "[343]\tvalidation_0-rmse:3.24854\n",
+ "[344]\tvalidation_0-rmse:3.24780\n",
+ "[345]\tvalidation_0-rmse:3.24743\n",
+ "[346]\tvalidation_0-rmse:3.24596\n",
+ "[347]\tvalidation_0-rmse:3.24443\n",
+ "[348]\tvalidation_0-rmse:3.24442\n",
+ "[349]\tvalidation_0-rmse:3.24380\n",
+ "[350]\tvalidation_0-rmse:3.24193\n",
+ "[351]\tvalidation_0-rmse:3.23980\n",
+ "[352]\tvalidation_0-rmse:3.23933\n",
+ "[353]\tvalidation_0-rmse:3.23731\n",
+ "[354]\tvalidation_0-rmse:3.23572\n",
+ "[355]\tvalidation_0-rmse:3.23521\n",
+ "[356]\tvalidation_0-rmse:3.23398\n",
+ "[357]\tvalidation_0-rmse:3.23357\n",
+ "[358]\tvalidation_0-rmse:3.23329\n",
+ "[359]\tvalidation_0-rmse:3.23337\n",
+ "[360]\tvalidation_0-rmse:3.23159\n",
+ "[361]\tvalidation_0-rmse:3.22935\n",
+ "[362]\tvalidation_0-rmse:3.22907\n",
+ "[363]\tvalidation_0-rmse:3.22839\n",
+ "[364]\tvalidation_0-rmse:3.22590\n",
+ "[365]\tvalidation_0-rmse:3.22582\n",
+ "[366]\tvalidation_0-rmse:3.22597\n",
+ "[367]\tvalidation_0-rmse:3.22396\n",
+ "[368]\tvalidation_0-rmse:3.22347\n",
+ "[369]\tvalidation_0-rmse:3.22070\n",
+ "[370]\tvalidation_0-rmse:3.21976\n",
+ "[371]\tvalidation_0-rmse:3.21954\n",
+ "[372]\tvalidation_0-rmse:3.21881\n",
+ "[373]\tvalidation_0-rmse:3.21793\n",
+ "[374]\tvalidation_0-rmse:3.21684\n",
+ "[375]\tvalidation_0-rmse:3.21654\n",
+ "[376]\tvalidation_0-rmse:3.21439\n",
+ "[377]\tvalidation_0-rmse:3.21411\n",
+ "[378]\tvalidation_0-rmse:3.21260\n",
+ "[379]\tvalidation_0-rmse:3.21151\n",
+ "[380]\tvalidation_0-rmse:3.21006\n",
+ "[381]\tvalidation_0-rmse:3.20786\n",
+ "[382]\tvalidation_0-rmse:3.20728\n",
+ "[383]\tvalidation_0-rmse:3.20678\n",
+ "[384]\tvalidation_0-rmse:3.20505\n",
+ "[385]\tvalidation_0-rmse:3.20227\n",
+ "[386]\tvalidation_0-rmse:3.20153\n",
+ "[387]\tvalidation_0-rmse:3.20045\n",
+ "[388]\tvalidation_0-rmse:3.20005\n",
+ "[389]\tvalidation_0-rmse:3.19927\n",
+ "[390]\tvalidation_0-rmse:3.19912\n",
+ "[391]\tvalidation_0-rmse:3.19734\n",
+ "[392]\tvalidation_0-rmse:3.19652\n",
+ "[393]\tvalidation_0-rmse:3.19474\n",
+ "[394]\tvalidation_0-rmse:3.19431\n",
+ "[395]\tvalidation_0-rmse:3.19258\n",
+ "[396]\tvalidation_0-rmse:3.19177\n",
+ "[397]\tvalidation_0-rmse:3.19153\n",
+ "[398]\tvalidation_0-rmse:3.19050\n",
+ "[399]\tvalidation_0-rmse:3.19046\n",
+ "[400]\tvalidation_0-rmse:3.18982\n",
+ "[401]\tvalidation_0-rmse:3.18939\n",
+ "[402]\tvalidation_0-rmse:3.18916\n",
+ "[403]\tvalidation_0-rmse:3.18884\n",
+ "[404]\tvalidation_0-rmse:3.18788\n",
+ "[405]\tvalidation_0-rmse:3.18785\n",
+ "[406]\tvalidation_0-rmse:3.18743\n",
+ "[407]\tvalidation_0-rmse:3.18732\n",
+ "[408]\tvalidation_0-rmse:3.18674\n",
+ "[409]\tvalidation_0-rmse:3.18621\n",
+ "[410]\tvalidation_0-rmse:3.18453\n",
+ "[411]\tvalidation_0-rmse:3.18379\n",
+ "[412]\tvalidation_0-rmse:3.18260\n",
+ "[413]\tvalidation_0-rmse:3.18164\n",
+ "[414]\tvalidation_0-rmse:3.18068\n",
+ "[415]\tvalidation_0-rmse:3.18037\n",
+ "[416]\tvalidation_0-rmse:3.17910\n",
+ "[417]\tvalidation_0-rmse:3.17872\n",
+ "[418]\tvalidation_0-rmse:3.17843\n",
+ "[419]\tvalidation_0-rmse:3.17774\n",
+ "[420]\tvalidation_0-rmse:3.17743\n",
+ "[421]\tvalidation_0-rmse:3.17721\n",
+ "[422]\tvalidation_0-rmse:3.17691\n",
+ "[423]\tvalidation_0-rmse:3.17680\n",
+ "[424]\tvalidation_0-rmse:3.17543\n",
+ "[425]\tvalidation_0-rmse:3.17453\n",
+ "[426]\tvalidation_0-rmse:3.17417\n",
+ "[427]\tvalidation_0-rmse:3.17299\n",
+ "[428]\tvalidation_0-rmse:3.17320\n",
+ "[429]\tvalidation_0-rmse:3.17276\n",
+ "[430]\tvalidation_0-rmse:3.17238\n",
+ "[431]\tvalidation_0-rmse:3.16997\n",
+ "[432]\tvalidation_0-rmse:3.16945\n",
+ "[433]\tvalidation_0-rmse:3.16858\n",
+ "[434]\tvalidation_0-rmse:3.16802\n",
+ "[435]\tvalidation_0-rmse:3.16602\n",
+ "[436]\tvalidation_0-rmse:3.16469\n",
+ "[437]\tvalidation_0-rmse:3.16431\n",
+ "[438]\tvalidation_0-rmse:3.16414\n",
+ "[439]\tvalidation_0-rmse:3.16205\n",
+ "[440]\tvalidation_0-rmse:3.16069\n",
+ "[441]\tvalidation_0-rmse:3.16038\n",
+ "[442]\tvalidation_0-rmse:3.15944\n",
+ "[443]\tvalidation_0-rmse:3.15933\n",
+ "[444]\tvalidation_0-rmse:3.15873\n",
+ "[445]\tvalidation_0-rmse:3.15761\n",
+ "[446]\tvalidation_0-rmse:3.15656\n",
+ "[447]\tvalidation_0-rmse:3.15665\n",
+ "[448]\tvalidation_0-rmse:3.15633\n",
+ "[449]\tvalidation_0-rmse:3.15599\n",
+ "[450]\tvalidation_0-rmse:3.15543\n",
+ "[451]\tvalidation_0-rmse:3.15513\n",
+ "[452]\tvalidation_0-rmse:3.15484\n",
+ "[453]\tvalidation_0-rmse:3.15449\n",
+ "[454]\tvalidation_0-rmse:3.15444\n",
+ "[455]\tvalidation_0-rmse:3.15414\n",
+ "[456]\tvalidation_0-rmse:3.15376\n",
+ "[457]\tvalidation_0-rmse:3.15265\n",
+ "[458]\tvalidation_0-rmse:3.15266\n",
+ "[459]\tvalidation_0-rmse:3.15214\n",
+ "[460]\tvalidation_0-rmse:3.15195\n",
+ "[461]\tvalidation_0-rmse:3.15175\n",
+ "[462]\tvalidation_0-rmse:3.15141\n",
+ "[463]\tvalidation_0-rmse:3.15054\n",
+ "[464]\tvalidation_0-rmse:3.14965\n",
+ "[465]\tvalidation_0-rmse:3.14832\n",
+ "[466]\tvalidation_0-rmse:3.14832\n",
+ "[467]\tvalidation_0-rmse:3.14734\n",
+ "[468]\tvalidation_0-rmse:3.14704\n",
+ "[469]\tvalidation_0-rmse:3.14628\n",
+ "[470]\tvalidation_0-rmse:3.14527\n",
+ "[471]\tvalidation_0-rmse:3.14514\n",
+ "[472]\tvalidation_0-rmse:3.14372\n",
+ "[473]\tvalidation_0-rmse:3.14337\n",
+ "[474]\tvalidation_0-rmse:3.14371\n",
+ "[475]\tvalidation_0-rmse:3.14377\n",
+ "[476]\tvalidation_0-rmse:3.14377\n",
+ "[477]\tvalidation_0-rmse:3.14241\n",
+ "[478]\tvalidation_0-rmse:3.14190\n",
+ "[479]\tvalidation_0-rmse:3.14072\n",
+ "[480]\tvalidation_0-rmse:3.13944\n",
+ "[481]\tvalidation_0-rmse:3.13894\n",
+ "[482]\tvalidation_0-rmse:3.13792\n",
+ "[483]\tvalidation_0-rmse:3.13667\n",
+ "[484]\tvalidation_0-rmse:3.13292\n",
+ "[485]\tvalidation_0-rmse:3.13171\n",
+ "[486]\tvalidation_0-rmse:3.13150\n",
+ "[487]\tvalidation_0-rmse:3.13044\n",
+ "[488]\tvalidation_0-rmse:3.12980\n",
+ "[489]\tvalidation_0-rmse:3.12959\n",
+ "[490]\tvalidation_0-rmse:3.12715\n",
+ "[491]\tvalidation_0-rmse:3.12587\n",
+ "[492]\tvalidation_0-rmse:3.12475\n",
+ "[493]\tvalidation_0-rmse:3.12236\n",
+ "[494]\tvalidation_0-rmse:3.12123\n",
+ "[495]\tvalidation_0-rmse:3.11963\n",
+ "[496]\tvalidation_0-rmse:3.11628\n",
+ "[497]\tvalidation_0-rmse:3.11387\n",
+ "[498]\tvalidation_0-rmse:3.11342\n",
+ "[499]\tvalidation_0-rmse:3.11339\n",
+ "[500]\tvalidation_0-rmse:3.11268\n",
+ "[501]\tvalidation_0-rmse:3.11239\n",
+ "[502]\tvalidation_0-rmse:3.11162\n",
+ "[503]\tvalidation_0-rmse:3.11064\n",
+ "[504]\tvalidation_0-rmse:3.11031\n",
+ "[505]\tvalidation_0-rmse:3.11013\n",
+ "[506]\tvalidation_0-rmse:3.10994\n",
+ "[507]\tvalidation_0-rmse:3.10948\n",
+ "[508]\tvalidation_0-rmse:3.10867\n",
+ "[509]\tvalidation_0-rmse:3.10857\n",
+ "[510]\tvalidation_0-rmse:3.10850\n",
+ "[511]\tvalidation_0-rmse:3.10767\n",
+ "[512]\tvalidation_0-rmse:3.10722\n",
+ "[513]\tvalidation_0-rmse:3.10642\n",
+ "[514]\tvalidation_0-rmse:3.10607\n",
+ "[515]\tvalidation_0-rmse:3.10559\n",
+ "[516]\tvalidation_0-rmse:3.10540\n",
+ "[517]\tvalidation_0-rmse:3.10499\n",
+ "[518]\tvalidation_0-rmse:3.10513\n",
+ "[519]\tvalidation_0-rmse:3.10498\n",
+ "[520]\tvalidation_0-rmse:3.10421\n",
+ "[521]\tvalidation_0-rmse:3.10270\n",
+ "[522]\tvalidation_0-rmse:3.10247\n",
+ "[523]\tvalidation_0-rmse:3.10222\n",
+ "[524]\tvalidation_0-rmse:3.10157\n",
+ "[525]\tvalidation_0-rmse:3.10166\n",
+ "[526]\tvalidation_0-rmse:3.09928\n",
+ "[527]\tvalidation_0-rmse:3.09912\n",
+ "[528]\tvalidation_0-rmse:3.09791\n",
+ "[529]\tvalidation_0-rmse:3.09686\n",
+ "[530]\tvalidation_0-rmse:3.09612\n",
+ "[531]\tvalidation_0-rmse:3.09498\n",
+ "[532]\tvalidation_0-rmse:3.09341\n",
+ "[533]\tvalidation_0-rmse:3.09341\n",
+ "[534]\tvalidation_0-rmse:3.09338\n",
+ "[535]\tvalidation_0-rmse:3.09217\n",
+ "[536]\tvalidation_0-rmse:3.09209\n",
+ "[537]\tvalidation_0-rmse:3.09216\n",
+ "[538]\tvalidation_0-rmse:3.09171\n",
+ "[539]\tvalidation_0-rmse:3.09124\n",
+ "[540]\tvalidation_0-rmse:3.09095\n",
+ "[541]\tvalidation_0-rmse:3.08925\n",
+ "[542]\tvalidation_0-rmse:3.08823\n",
+ "[543]\tvalidation_0-rmse:3.08852\n",
+ "[544]\tvalidation_0-rmse:3.08848\n",
+ "[545]\tvalidation_0-rmse:3.08824\n",
+ "[546]\tvalidation_0-rmse:3.08751\n",
+ "[547]\tvalidation_0-rmse:3.08607\n",
+ "[548]\tvalidation_0-rmse:3.08578\n",
+ "[549]\tvalidation_0-rmse:3.08575\n",
+ "[550]\tvalidation_0-rmse:3.08488\n",
+ "[551]\tvalidation_0-rmse:3.08435\n",
+ "[552]\tvalidation_0-rmse:3.08336\n",
+ "[553]\tvalidation_0-rmse:3.08198\n",
+ "[554]\tvalidation_0-rmse:3.08085\n",
+ "[555]\tvalidation_0-rmse:3.07893\n",
+ "[556]\tvalidation_0-rmse:3.07753\n",
+ "[557]\tvalidation_0-rmse:3.07621\n",
+ "[558]\tvalidation_0-rmse:3.07531\n",
+ "[559]\tvalidation_0-rmse:3.07510\n",
+ "[560]\tvalidation_0-rmse:3.07417\n",
+ "[561]\tvalidation_0-rmse:3.07215\n",
+ "[562]\tvalidation_0-rmse:3.07134\n",
+ "[563]\tvalidation_0-rmse:3.07084\n",
+ "[564]\tvalidation_0-rmse:3.07061\n",
+ "[565]\tvalidation_0-rmse:3.07030\n",
+ "[566]\tvalidation_0-rmse:3.06968\n",
+ "[567]\tvalidation_0-rmse:3.06800\n",
+ "[568]\tvalidation_0-rmse:3.06641\n",
+ "[569]\tvalidation_0-rmse:3.06610\n",
+ "[570]\tvalidation_0-rmse:3.06514\n",
+ "[571]\tvalidation_0-rmse:3.06473\n",
+ "[572]\tvalidation_0-rmse:3.06443\n",
+ "[573]\tvalidation_0-rmse:3.06345\n",
+ "[574]\tvalidation_0-rmse:3.06216\n",
+ "[575]\tvalidation_0-rmse:3.06213\n",
+ "[576]\tvalidation_0-rmse:3.06184\n",
+ "[577]\tvalidation_0-rmse:3.06067\n",
+ "[578]\tvalidation_0-rmse:3.05961\n",
+ "[579]\tvalidation_0-rmse:3.05924\n",
+ "[580]\tvalidation_0-rmse:3.05917\n",
+ "[581]\tvalidation_0-rmse:3.05814\n",
+ "[582]\tvalidation_0-rmse:3.05728\n",
+ "[583]\tvalidation_0-rmse:3.05709\n",
+ "[584]\tvalidation_0-rmse:3.05685\n",
+ "[585]\tvalidation_0-rmse:3.05637\n",
+ "[586]\tvalidation_0-rmse:3.05606\n",
+ "[587]\tvalidation_0-rmse:3.05555\n",
+ "[588]\tvalidation_0-rmse:3.05570\n",
+ "[589]\tvalidation_0-rmse:3.05514\n",
+ "[590]\tvalidation_0-rmse:3.05514\n",
+ "[591]\tvalidation_0-rmse:3.05485\n",
+ "[592]\tvalidation_0-rmse:3.05434\n",
+ "[593]\tvalidation_0-rmse:3.05167\n",
+ "[594]\tvalidation_0-rmse:3.05061\n",
+ "[595]\tvalidation_0-rmse:3.04959\n",
+ "[596]\tvalidation_0-rmse:3.04757\n",
+ "[597]\tvalidation_0-rmse:3.04754\n",
+ "[598]\tvalidation_0-rmse:3.04722\n",
+ "[599]\tvalidation_0-rmse:3.04698\n",
+ "[600]\tvalidation_0-rmse:3.04647\n",
+ "[601]\tvalidation_0-rmse:3.04655\n",
+ "[602]\tvalidation_0-rmse:3.04513\n",
+ "[603]\tvalidation_0-rmse:3.04404\n",
+ "[604]\tvalidation_0-rmse:3.04372\n",
+ "[605]\tvalidation_0-rmse:3.04303\n",
+ "[606]\tvalidation_0-rmse:3.04270\n",
+ "[607]\tvalidation_0-rmse:3.04230\n",
+ "[608]\tvalidation_0-rmse:3.04188\n",
+ "[609]\tvalidation_0-rmse:3.04145\n",
+ "[610]\tvalidation_0-rmse:3.04118\n",
+ "[611]\tvalidation_0-rmse:3.04081\n",
+ "[612]\tvalidation_0-rmse:3.04078\n",
+ "[613]\tvalidation_0-rmse:3.04061\n",
+ "[614]\tvalidation_0-rmse:3.03963\n",
+ "[615]\tvalidation_0-rmse:3.03963\n",
+ "[616]\tvalidation_0-rmse:3.03849\n",
+ "[617]\tvalidation_0-rmse:3.03780\n",
+ "[618]\tvalidation_0-rmse:3.03730\n",
+ "[619]\tvalidation_0-rmse:3.03712\n",
+ "[620]\tvalidation_0-rmse:3.03669\n",
+ "[621]\tvalidation_0-rmse:3.03506\n",
+ "[622]\tvalidation_0-rmse:3.03443\n",
+ "[623]\tvalidation_0-rmse:3.03441\n",
+ "[624]\tvalidation_0-rmse:3.03298\n",
+ "[625]\tvalidation_0-rmse:3.03224\n",
+ "[626]\tvalidation_0-rmse:3.03179\n",
+ "[627]\tvalidation_0-rmse:3.03108\n",
+ "[628]\tvalidation_0-rmse:3.03018\n",
+ "[629]\tvalidation_0-rmse:3.02986\n",
+ "[630]\tvalidation_0-rmse:3.02839\n",
+ "[631]\tvalidation_0-rmse:3.02809\n",
+ "[632]\tvalidation_0-rmse:3.02792\n",
+ "[633]\tvalidation_0-rmse:3.02614\n",
+ "[634]\tvalidation_0-rmse:3.02593\n",
+ "[635]\tvalidation_0-rmse:3.02572\n",
+ "[636]\tvalidation_0-rmse:3.02449\n",
+ "[637]\tvalidation_0-rmse:3.02378\n",
+ "[638]\tvalidation_0-rmse:3.02386\n",
+ "[639]\tvalidation_0-rmse:3.02283\n",
+ "[640]\tvalidation_0-rmse:3.02147\n",
+ "[641]\tvalidation_0-rmse:3.02137\n",
+ "[642]\tvalidation_0-rmse:3.02070\n",
+ "[643]\tvalidation_0-rmse:3.02017\n",
+ "[644]\tvalidation_0-rmse:3.02043\n",
+ "[645]\tvalidation_0-rmse:3.02054\n",
+ "[646]\tvalidation_0-rmse:3.01948\n",
+ "[647]\tvalidation_0-rmse:3.01882\n",
+ "[648]\tvalidation_0-rmse:3.01875\n",
+ "[649]\tvalidation_0-rmse:3.01828\n",
+ "[650]\tvalidation_0-rmse:3.01829\n",
+ "[651]\tvalidation_0-rmse:3.01756\n",
+ "[652]\tvalidation_0-rmse:3.01690\n",
+ "[653]\tvalidation_0-rmse:3.01624\n",
+ "[654]\tvalidation_0-rmse:3.01578\n",
+ "[655]\tvalidation_0-rmse:3.01587\n",
+ "[656]\tvalidation_0-rmse:3.01566\n",
+ "[657]\tvalidation_0-rmse:3.01488\n",
+ "[658]\tvalidation_0-rmse:3.01501\n",
+ "[659]\tvalidation_0-rmse:3.01466\n",
+ "[660]\tvalidation_0-rmse:3.01450\n",
+ "[661]\tvalidation_0-rmse:3.01407\n",
+ "[662]\tvalidation_0-rmse:3.01278\n",
+ "[663]\tvalidation_0-rmse:3.01248\n",
+ "[664]\tvalidation_0-rmse:3.01245\n",
+ "[665]\tvalidation_0-rmse:3.01155\n",
+ "[666]\tvalidation_0-rmse:3.01137\n",
+ "[667]\tvalidation_0-rmse:3.01107\n",
+ "[668]\tvalidation_0-rmse:3.01018\n",
+ "[669]\tvalidation_0-rmse:3.00928\n",
+ "[670]\tvalidation_0-rmse:3.00869\n",
+ "[671]\tvalidation_0-rmse:3.00751\n",
+ "[672]\tvalidation_0-rmse:3.00687\n",
+ "[673]\tvalidation_0-rmse:3.00565\n",
+ "[674]\tvalidation_0-rmse:3.00547\n",
+ "[675]\tvalidation_0-rmse:3.00534\n",
+ "[676]\tvalidation_0-rmse:3.00426\n",
+ "[677]\tvalidation_0-rmse:3.00388\n",
+ "[678]\tvalidation_0-rmse:3.00393\n",
+ "[679]\tvalidation_0-rmse:3.00282\n",
+ "[680]\tvalidation_0-rmse:3.00254\n",
+ "[681]\tvalidation_0-rmse:3.00162\n",
+ "[682]\tvalidation_0-rmse:3.00136\n",
+ "[683]\tvalidation_0-rmse:3.00120\n",
+ "[684]\tvalidation_0-rmse:3.00117\n",
+ "[685]\tvalidation_0-rmse:3.00044\n",
+ "[686]\tvalidation_0-rmse:2.99989\n",
+ "[687]\tvalidation_0-rmse:2.99972\n",
+ "[688]\tvalidation_0-rmse:2.99938\n",
+ "[689]\tvalidation_0-rmse:2.99895\n",
+ "[690]\tvalidation_0-rmse:2.99873\n",
+ "[691]\tvalidation_0-rmse:2.99862\n",
+ "[692]\tvalidation_0-rmse:2.99834\n",
+ "[693]\tvalidation_0-rmse:2.99830\n",
+ "[694]\tvalidation_0-rmse:2.99812\n",
+ "[695]\tvalidation_0-rmse:2.99758\n",
+ "[696]\tvalidation_0-rmse:2.99590\n",
+ "[697]\tvalidation_0-rmse:2.99479\n",
+ "[698]\tvalidation_0-rmse:2.99461\n",
+ "[699]\tvalidation_0-rmse:2.99382\n",
+ "[700]\tvalidation_0-rmse:2.99348\n",
+ "[701]\tvalidation_0-rmse:2.99317\n",
+ "[702]\tvalidation_0-rmse:2.99336\n",
+ "[703]\tvalidation_0-rmse:2.99314\n",
+ "[704]\tvalidation_0-rmse:2.99319\n",
+ "[705]\tvalidation_0-rmse:2.99273\n",
+ "[706]\tvalidation_0-rmse:2.99222\n",
+ "[707]\tvalidation_0-rmse:2.99134\n",
+ "[708]\tvalidation_0-rmse:2.99128\n",
+ "[709]\tvalidation_0-rmse:2.99121\n",
+ "[710]\tvalidation_0-rmse:2.99121\n",
+ "[711]\tvalidation_0-rmse:2.99096\n",
+ "[712]\tvalidation_0-rmse:2.99072\n",
+ "[713]\tvalidation_0-rmse:2.98985\n",
+ "[714]\tvalidation_0-rmse:2.98880\n",
+ "[715]\tvalidation_0-rmse:2.98857\n",
+ "[716]\tvalidation_0-rmse:2.98820\n",
+ "[717]\tvalidation_0-rmse:2.98671\n",
+ "[718]\tvalidation_0-rmse:2.98615\n",
+ "[719]\tvalidation_0-rmse:2.98593\n",
+ "[720]\tvalidation_0-rmse:2.98562\n",
+ "[721]\tvalidation_0-rmse:2.98513\n",
+ "[722]\tvalidation_0-rmse:2.98411\n",
+ "[723]\tvalidation_0-rmse:2.98358\n",
+ "[724]\tvalidation_0-rmse:2.98356\n",
+ "[725]\tvalidation_0-rmse:2.98335\n",
+ "[726]\tvalidation_0-rmse:2.98297\n",
+ "[727]\tvalidation_0-rmse:2.98279\n",
+ "[728]\tvalidation_0-rmse:2.98293\n",
+ "[729]\tvalidation_0-rmse:2.98278\n",
+ "[730]\tvalidation_0-rmse:2.98157\n",
+ "[731]\tvalidation_0-rmse:2.98176\n",
+ "[732]\tvalidation_0-rmse:2.98045\n",
+ "[733]\tvalidation_0-rmse:2.97876\n",
+ "[734]\tvalidation_0-rmse:2.97827\n",
+ "[735]\tvalidation_0-rmse:2.97752\n",
+ "[736]\tvalidation_0-rmse:2.97660\n",
+ "[737]\tvalidation_0-rmse:2.97658\n",
+ "[738]\tvalidation_0-rmse:2.97653\n",
+ "[739]\tvalidation_0-rmse:2.97642\n",
+ "[740]\tvalidation_0-rmse:2.97634\n",
+ "[741]\tvalidation_0-rmse:2.97531\n",
+ "[742]\tvalidation_0-rmse:2.97484\n",
+ "[743]\tvalidation_0-rmse:2.97427\n",
+ "[744]\tvalidation_0-rmse:2.97420\n",
+ "[745]\tvalidation_0-rmse:2.97371\n",
+ "[746]\tvalidation_0-rmse:2.97233\n",
+ "[747]\tvalidation_0-rmse:2.97207\n",
+ "[748]\tvalidation_0-rmse:2.97048\n",
+ "[749]\tvalidation_0-rmse:2.97007\n",
+ "[750]\tvalidation_0-rmse:2.96993\n",
+ "[751]\tvalidation_0-rmse:2.96995\n",
+ "[752]\tvalidation_0-rmse:2.96990\n",
+ "[753]\tvalidation_0-rmse:2.96959\n",
+ "[754]\tvalidation_0-rmse:2.96962\n",
+ "[755]\tvalidation_0-rmse:2.96933\n",
+ "[756]\tvalidation_0-rmse:2.96912\n",
+ "[757]\tvalidation_0-rmse:2.96893\n",
+ "[758]\tvalidation_0-rmse:2.96862\n",
+ "[759]\tvalidation_0-rmse:2.96833\n",
+ "[760]\tvalidation_0-rmse:2.96856\n",
+ "[761]\tvalidation_0-rmse:2.96846\n",
+ "[762]\tvalidation_0-rmse:2.96781\n",
+ "[763]\tvalidation_0-rmse:2.96768\n",
+ "[764]\tvalidation_0-rmse:2.96760\n",
+ "[765]\tvalidation_0-rmse:2.96751\n",
+ "[766]\tvalidation_0-rmse:2.96686\n",
+ "[767]\tvalidation_0-rmse:2.96679\n",
+ "[768]\tvalidation_0-rmse:2.96692\n",
+ "[769]\tvalidation_0-rmse:2.96591\n",
+ "[770]\tvalidation_0-rmse:2.96536\n",
+ "[771]\tvalidation_0-rmse:2.96525\n",
+ "[772]\tvalidation_0-rmse:2.96514\n",
+ "[773]\tvalidation_0-rmse:2.96517\n",
+ "[774]\tvalidation_0-rmse:2.96470\n",
+ "[775]\tvalidation_0-rmse:2.96472\n",
+ "[776]\tvalidation_0-rmse:2.96422\n",
+ "[777]\tvalidation_0-rmse:2.96396\n",
+ "[778]\tvalidation_0-rmse:2.96364\n",
+ "[779]\tvalidation_0-rmse:2.96319\n",
+ "[780]\tvalidation_0-rmse:2.96268\n",
+ "[781]\tvalidation_0-rmse:2.96254\n",
+ "[782]\tvalidation_0-rmse:2.96181\n",
+ "[783]\tvalidation_0-rmse:2.96169\n",
+ "[784]\tvalidation_0-rmse:2.96095\n",
+ "[785]\tvalidation_0-rmse:2.96121\n",
+ "[786]\tvalidation_0-rmse:2.96091\n",
+ "[787]\tvalidation_0-rmse:2.96021\n",
+ "[788]\tvalidation_0-rmse:2.95983\n",
+ "[789]\tvalidation_0-rmse:2.95983\n",
+ "[790]\tvalidation_0-rmse:2.95974\n",
+ "[791]\tvalidation_0-rmse:2.95942\n",
+ "[792]\tvalidation_0-rmse:2.95925\n",
+ "[793]\tvalidation_0-rmse:2.95908\n",
+ "[794]\tvalidation_0-rmse:2.95893\n",
+ "[795]\tvalidation_0-rmse:2.95869\n",
+ "[796]\tvalidation_0-rmse:2.95831\n",
+ "[797]\tvalidation_0-rmse:2.95761\n",
+ "[798]\tvalidation_0-rmse:2.95767\n",
+ "[799]\tvalidation_0-rmse:2.95619\n",
+ "[800]\tvalidation_0-rmse:2.95523\n",
+ "[801]\tvalidation_0-rmse:2.95511\n",
+ "[802]\tvalidation_0-rmse:2.95499\n",
+ "[803]\tvalidation_0-rmse:2.95495\n",
+ "[804]\tvalidation_0-rmse:2.95463\n",
+ "[805]\tvalidation_0-rmse:2.95384\n",
+ "[806]\tvalidation_0-rmse:2.95328\n",
+ "[807]\tvalidation_0-rmse:2.95275\n",
+ "[808]\tvalidation_0-rmse:2.95279\n",
+ "[809]\tvalidation_0-rmse:2.95268\n",
+ "[810]\tvalidation_0-rmse:2.95270\n",
+ "[811]\tvalidation_0-rmse:2.95284\n",
+ "[812]\tvalidation_0-rmse:2.95243\n",
+ "[813]\tvalidation_0-rmse:2.95233\n",
+ "[814]\tvalidation_0-rmse:2.95210\n",
+ "[815]\tvalidation_0-rmse:2.95139\n",
+ "[816]\tvalidation_0-rmse:2.95142\n",
+ "[817]\tvalidation_0-rmse:2.95147\n",
+ "[818]\tvalidation_0-rmse:2.95096\n",
+ "[819]\tvalidation_0-rmse:2.95101\n",
+ "[820]\tvalidation_0-rmse:2.95091\n",
+ "[821]\tvalidation_0-rmse:2.95074\n",
+ "[822]\tvalidation_0-rmse:2.95068\n",
+ "[823]\tvalidation_0-rmse:2.95080\n",
+ "[824]\tvalidation_0-rmse:2.95068\n",
+ "[825]\tvalidation_0-rmse:2.95064\n",
+ "[826]\tvalidation_0-rmse:2.95073\n",
+ "[827]\tvalidation_0-rmse:2.95095\n",
+ "[828]\tvalidation_0-rmse:2.95071\n",
+ "[829]\tvalidation_0-rmse:2.94976\n",
+ "[830]\tvalidation_0-rmse:2.94892\n",
+ "[831]\tvalidation_0-rmse:2.94854\n",
+ "[832]\tvalidation_0-rmse:2.94834\n",
+ "[833]\tvalidation_0-rmse:2.94811\n",
+ "[834]\tvalidation_0-rmse:2.94737\n",
+ "[835]\tvalidation_0-rmse:2.94727\n",
+ "[836]\tvalidation_0-rmse:2.94733\n",
+ "[837]\tvalidation_0-rmse:2.94731\n",
+ "[838]\tvalidation_0-rmse:2.94686\n",
+ "[839]\tvalidation_0-rmse:2.94546\n",
+ "[840]\tvalidation_0-rmse:2.94529\n",
+ "[841]\tvalidation_0-rmse:2.94402\n",
+ "[842]\tvalidation_0-rmse:2.94251\n",
+ "[843]\tvalidation_0-rmse:2.94242\n",
+ "[844]\tvalidation_0-rmse:2.94141\n",
+ "[845]\tvalidation_0-rmse:2.94144\n",
+ "[846]\tvalidation_0-rmse:2.94071\n",
+ "[847]\tvalidation_0-rmse:2.94007\n",
+ "[848]\tvalidation_0-rmse:2.93940\n",
+ "[849]\tvalidation_0-rmse:2.93932\n",
+ "[850]\tvalidation_0-rmse:2.93925\n",
+ "[851]\tvalidation_0-rmse:2.93931\n",
+ "[852]\tvalidation_0-rmse:2.93940\n",
+ "[853]\tvalidation_0-rmse:2.93921\n",
+ "[854]\tvalidation_0-rmse:2.93864\n",
+ "[855]\tvalidation_0-rmse:2.93871\n",
+ "[856]\tvalidation_0-rmse:2.93852\n",
+ "[857]\tvalidation_0-rmse:2.93790\n",
+ "[858]\tvalidation_0-rmse:2.93786\n",
+ "[859]\tvalidation_0-rmse:2.93747\n",
+ "[860]\tvalidation_0-rmse:2.93714\n",
+ "[861]\tvalidation_0-rmse:2.93711\n",
+ "[862]\tvalidation_0-rmse:2.93654\n",
+ "[863]\tvalidation_0-rmse:2.93622\n",
+ "[864]\tvalidation_0-rmse:2.93477\n",
+ "[865]\tvalidation_0-rmse:2.93463\n",
+ "[866]\tvalidation_0-rmse:2.93452\n",
+ "[867]\tvalidation_0-rmse:2.93457\n",
+ "[868]\tvalidation_0-rmse:2.93447\n",
+ "[869]\tvalidation_0-rmse:2.93439\n",
+ "[870]\tvalidation_0-rmse:2.93424\n",
+ "[871]\tvalidation_0-rmse:2.93356\n",
+ "[872]\tvalidation_0-rmse:2.93314\n",
+ "[873]\tvalidation_0-rmse:2.93318\n",
+ "[874]\tvalidation_0-rmse:2.93313\n",
+ "[875]\tvalidation_0-rmse:2.93269\n",
+ "[876]\tvalidation_0-rmse:2.93275\n",
+ "[877]\tvalidation_0-rmse:2.93288\n",
+ "[878]\tvalidation_0-rmse:2.93281\n",
+ "[879]\tvalidation_0-rmse:2.93270\n",
+ "[880]\tvalidation_0-rmse:2.93267\n",
+ "[881]\tvalidation_0-rmse:2.93142\n",
+ "[882]\tvalidation_0-rmse:2.93114\n",
+ "[883]\tvalidation_0-rmse:2.93039\n",
+ "[884]\tvalidation_0-rmse:2.93024\n",
+ "[885]\tvalidation_0-rmse:2.92951\n",
+ "[886]\tvalidation_0-rmse:2.92942\n",
+ "[887]\tvalidation_0-rmse:2.92937\n",
+ "[888]\tvalidation_0-rmse:2.92866\n",
+ "[889]\tvalidation_0-rmse:2.92821\n",
+ "[890]\tvalidation_0-rmse:2.92800\n",
+ "[891]\tvalidation_0-rmse:2.92788\n",
+ "[892]\tvalidation_0-rmse:2.92757\n",
+ "[893]\tvalidation_0-rmse:2.92620\n",
+ "[894]\tvalidation_0-rmse:2.92509\n",
+ "[895]\tvalidation_0-rmse:2.92478\n",
+ "[896]\tvalidation_0-rmse:2.92479\n",
+ "[897]\tvalidation_0-rmse:2.92478\n",
+ "[898]\tvalidation_0-rmse:2.92406\n",
+ "[899]\tvalidation_0-rmse:2.92324\n",
+ "[900]\tvalidation_0-rmse:2.92284\n",
+ "[901]\tvalidation_0-rmse:2.92288\n",
+ "[902]\tvalidation_0-rmse:2.92233\n",
+ "[903]\tvalidation_0-rmse:2.92218\n",
+ "[904]\tvalidation_0-rmse:2.92236\n",
+ "[905]\tvalidation_0-rmse:2.92227\n",
+ "[906]\tvalidation_0-rmse:2.92210\n",
+ "[907]\tvalidation_0-rmse:2.92210\n",
+ "[908]\tvalidation_0-rmse:2.92187\n",
+ "[909]\tvalidation_0-rmse:2.92163\n",
+ "[910]\tvalidation_0-rmse:2.92138\n",
+ "[911]\tvalidation_0-rmse:2.92114\n",
+ "[912]\tvalidation_0-rmse:2.92102\n",
+ "[913]\tvalidation_0-rmse:2.91991\n",
+ "[914]\tvalidation_0-rmse:2.91868\n",
+ "[915]\tvalidation_0-rmse:2.91766\n",
+ "[916]\tvalidation_0-rmse:2.91772\n",
+ "[917]\tvalidation_0-rmse:2.91760\n",
+ "[918]\tvalidation_0-rmse:2.91769\n",
+ "[919]\tvalidation_0-rmse:2.91768\n",
+ "[920]\tvalidation_0-rmse:2.91726\n",
+ "[921]\tvalidation_0-rmse:2.91613\n",
+ "[922]\tvalidation_0-rmse:2.91618\n",
+ "[923]\tvalidation_0-rmse:2.91619\n",
+ "[924]\tvalidation_0-rmse:2.91530\n",
+ "[925]\tvalidation_0-rmse:2.91516\n",
+ "[926]\tvalidation_0-rmse:2.91474\n",
+ "[927]\tvalidation_0-rmse:2.91392\n",
+ "[928]\tvalidation_0-rmse:2.91334\n",
+ "[929]\tvalidation_0-rmse:2.91336\n",
+ "[930]\tvalidation_0-rmse:2.91236\n",
+ "[931]\tvalidation_0-rmse:2.91241\n",
+ "[932]\tvalidation_0-rmse:2.91204\n",
+ "[933]\tvalidation_0-rmse:2.91199\n",
+ "[934]\tvalidation_0-rmse:2.91198\n",
+ "[935]\tvalidation_0-rmse:2.91199\n",
+ "[936]\tvalidation_0-rmse:2.91194\n",
+ "[937]\tvalidation_0-rmse:2.91175\n",
+ "[938]\tvalidation_0-rmse:2.91168\n",
+ "[939]\tvalidation_0-rmse:2.91143\n",
+ "[940]\tvalidation_0-rmse:2.91099\n",
+ "[941]\tvalidation_0-rmse:2.91020\n",
+ "[942]\tvalidation_0-rmse:2.90991\n",
+ "[943]\tvalidation_0-rmse:2.90965\n",
+ "[944]\tvalidation_0-rmse:2.90898\n",
+ "[945]\tvalidation_0-rmse:2.90880\n",
+ "[946]\tvalidation_0-rmse:2.90895\n",
+ "[947]\tvalidation_0-rmse:2.90814\n",
+ "[948]\tvalidation_0-rmse:2.90803\n",
+ "[949]\tvalidation_0-rmse:2.90777\n",
+ "[950]\tvalidation_0-rmse:2.90760\n",
+ "[951]\tvalidation_0-rmse:2.90731\n",
+ "[952]\tvalidation_0-rmse:2.90730\n",
+ "[953]\tvalidation_0-rmse:2.90717\n",
+ "[954]\tvalidation_0-rmse:2.90688\n",
+ "[955]\tvalidation_0-rmse:2.90599\n",
+ "[956]\tvalidation_0-rmse:2.90562\n",
+ "[957]\tvalidation_0-rmse:2.90514\n",
+ "[958]\tvalidation_0-rmse:2.90507\n",
+ "[959]\tvalidation_0-rmse:2.90501\n",
+ "[960]\tvalidation_0-rmse:2.90496\n",
+ "[961]\tvalidation_0-rmse:2.90481\n",
+ "[962]\tvalidation_0-rmse:2.90472\n",
+ "[963]\tvalidation_0-rmse:2.90486\n",
+ "[964]\tvalidation_0-rmse:2.90492\n",
+ "[965]\tvalidation_0-rmse:2.90447\n",
+ "[966]\tvalidation_0-rmse:2.90418\n",
+ "[967]\tvalidation_0-rmse:2.90427\n",
+ "[968]\tvalidation_0-rmse:2.90429\n",
+ "[969]\tvalidation_0-rmse:2.90428\n",
+ "[970]\tvalidation_0-rmse:2.90403\n",
+ "[971]\tvalidation_0-rmse:2.90311\n",
+ "[972]\tvalidation_0-rmse:2.90251\n",
+ "[973]\tvalidation_0-rmse:2.90231\n",
+ "[974]\tvalidation_0-rmse:2.90223\n",
+ "[975]\tvalidation_0-rmse:2.90197\n",
+ "[976]\tvalidation_0-rmse:2.90178\n",
+ "[977]\tvalidation_0-rmse:2.90167\n",
+ "[978]\tvalidation_0-rmse:2.90073\n",
+ "[979]\tvalidation_0-rmse:2.90094\n",
+ "[980]\tvalidation_0-rmse:2.90050\n",
+ "[981]\tvalidation_0-rmse:2.89976\n",
+ "[982]\tvalidation_0-rmse:2.89911\n",
+ "[983]\tvalidation_0-rmse:2.89814\n",
+ "[984]\tvalidation_0-rmse:2.89800\n",
+ "[985]\tvalidation_0-rmse:2.89711\n",
+ "[986]\tvalidation_0-rmse:2.89656\n",
+ "[987]\tvalidation_0-rmse:2.89586\n",
+ "[988]\tvalidation_0-rmse:2.89584\n",
+ "[989]\tvalidation_0-rmse:2.89600\n",
+ "[990]\tvalidation_0-rmse:2.89577\n",
+ "[991]\tvalidation_0-rmse:2.89543\n",
+ "[992]\tvalidation_0-rmse:2.89480\n",
+ "[993]\tvalidation_0-rmse:2.89411\n",
+ "[994]\tvalidation_0-rmse:2.89359\n",
+ "[995]\tvalidation_0-rmse:2.89359\n",
+ "[996]\tvalidation_0-rmse:2.89368\n",
+ "[997]\tvalidation_0-rmse:2.89305\n",
+ "[998]\tvalidation_0-rmse:2.89304\n",
+ "[999]\tvalidation_0-rmse:2.89306\n",
+ "[1000]\tvalidation_0-rmse:2.89256\n",
+ "[1001]\tvalidation_0-rmse:2.89191\n",
+ "[1002]\tvalidation_0-rmse:2.89187\n",
+ "[1003]\tvalidation_0-rmse:2.89186\n",
+ "[1004]\tvalidation_0-rmse:2.89203\n",
+ "[1005]\tvalidation_0-rmse:2.89144\n",
+ "[1006]\tvalidation_0-rmse:2.89147\n",
+ "[1007]\tvalidation_0-rmse:2.89093\n",
+ "[1008]\tvalidation_0-rmse:2.89086\n",
+ "[1009]\tvalidation_0-rmse:2.89033\n",
+ "[1010]\tvalidation_0-rmse:2.89008\n",
+ "[1011]\tvalidation_0-rmse:2.88977\n",
+ "[1012]\tvalidation_0-rmse:2.88974\n",
+ "[1013]\tvalidation_0-rmse:2.88955\n",
+ "[1014]\tvalidation_0-rmse:2.88947\n",
+ "[1015]\tvalidation_0-rmse:2.88938\n",
+ "[1016]\tvalidation_0-rmse:2.88899\n",
+ "[1017]\tvalidation_0-rmse:2.88896\n",
+ "[1018]\tvalidation_0-rmse:2.88907\n",
+ "[1019]\tvalidation_0-rmse:2.88890\n",
+ "[1020]\tvalidation_0-rmse:2.88867\n",
+ "[1021]\tvalidation_0-rmse:2.88873\n",
+ "[1022]\tvalidation_0-rmse:2.88877\n",
+ "[1023]\tvalidation_0-rmse:2.88855\n",
+ "[1024]\tvalidation_0-rmse:2.88863\n",
+ "[1025]\tvalidation_0-rmse:2.88819\n",
+ "[1026]\tvalidation_0-rmse:2.88756\n",
+ "[1027]\tvalidation_0-rmse:2.88742\n",
+ "[1028]\tvalidation_0-rmse:2.88730\n",
+ "[1029]\tvalidation_0-rmse:2.88707\n",
+ "[1030]\tvalidation_0-rmse:2.88668\n",
+ "[1031]\tvalidation_0-rmse:2.88645\n",
+ "[1032]\tvalidation_0-rmse:2.88607\n",
+ "[1033]\tvalidation_0-rmse:2.88593\n",
+ "[1034]\tvalidation_0-rmse:2.88590\n",
+ "[1035]\tvalidation_0-rmse:2.88586\n",
+ "[1036]\tvalidation_0-rmse:2.88555\n",
+ "[1037]\tvalidation_0-rmse:2.88522\n",
+ "[1038]\tvalidation_0-rmse:2.88504\n",
+ "[1039]\tvalidation_0-rmse:2.88487\n",
+ "[1040]\tvalidation_0-rmse:2.88478\n",
+ "[1041]\tvalidation_0-rmse:2.88465\n",
+ "[1042]\tvalidation_0-rmse:2.88457\n",
+ "[1043]\tvalidation_0-rmse:2.88360\n",
+ "[1044]\tvalidation_0-rmse:2.88355\n",
+ "[1045]\tvalidation_0-rmse:2.88356\n",
+ "[1046]\tvalidation_0-rmse:2.88351\n",
+ "[1047]\tvalidation_0-rmse:2.88319\n",
+ "[1048]\tvalidation_0-rmse:2.88303\n",
+ "[1049]\tvalidation_0-rmse:2.88295\n",
+ "[1050]\tvalidation_0-rmse:2.88304\n",
+ "[1051]\tvalidation_0-rmse:2.88308\n",
+ "[1052]\tvalidation_0-rmse:2.88299\n",
+ "[1053]\tvalidation_0-rmse:2.88287\n",
+ "[1054]\tvalidation_0-rmse:2.88283\n",
+ "[1055]\tvalidation_0-rmse:2.88290\n",
+ "[1056]\tvalidation_0-rmse:2.88303\n",
+ "[1057]\tvalidation_0-rmse:2.88320\n",
+ "[1058]\tvalidation_0-rmse:2.88252\n",
+ "[1059]\tvalidation_0-rmse:2.88195\n",
+ "[1060]\tvalidation_0-rmse:2.88188\n",
+ "[1061]\tvalidation_0-rmse:2.88187\n",
+ "[1062]\tvalidation_0-rmse:2.88122\n",
+ "[1063]\tvalidation_0-rmse:2.88129\n",
+ "[1064]\tvalidation_0-rmse:2.88128\n",
+ "[1065]\tvalidation_0-rmse:2.88126\n",
+ "[1066]\tvalidation_0-rmse:2.88053\n",
+ "[1067]\tvalidation_0-rmse:2.88021\n",
+ "[1068]\tvalidation_0-rmse:2.87998\n",
+ "[1069]\tvalidation_0-rmse:2.87931\n",
+ "[1070]\tvalidation_0-rmse:2.87897\n",
+ "[1071]\tvalidation_0-rmse:2.87851\n",
+ "[1072]\tvalidation_0-rmse:2.87835\n",
+ "[1073]\tvalidation_0-rmse:2.87797\n",
+ "[1074]\tvalidation_0-rmse:2.87793\n",
+ "[1075]\tvalidation_0-rmse:2.87727\n",
+ "[1076]\tvalidation_0-rmse:2.87718\n",
+ "[1077]\tvalidation_0-rmse:2.87709\n",
+ "[1078]\tvalidation_0-rmse:2.87622\n",
+ "[1079]\tvalidation_0-rmse:2.87589\n",
+ "[1080]\tvalidation_0-rmse:2.87555\n",
+ "[1081]\tvalidation_0-rmse:2.87481\n",
+ "[1082]\tvalidation_0-rmse:2.87409\n",
+ "[1083]\tvalidation_0-rmse:2.87365\n",
+ "[1084]\tvalidation_0-rmse:2.87375\n",
+ "[1085]\tvalidation_0-rmse:2.87320\n",
+ "[1086]\tvalidation_0-rmse:2.87175\n",
+ "[1087]\tvalidation_0-rmse:2.87128\n",
+ "[1088]\tvalidation_0-rmse:2.87093\n",
+ "[1089]\tvalidation_0-rmse:2.87006\n",
+ "[1090]\tvalidation_0-rmse:2.86917\n",
+ "[1091]\tvalidation_0-rmse:2.86908\n",
+ "[1092]\tvalidation_0-rmse:2.86843\n",
+ "[1093]\tvalidation_0-rmse:2.86801\n",
+ "[1094]\tvalidation_0-rmse:2.86761\n",
+ "[1095]\tvalidation_0-rmse:2.86709\n",
+ "[1096]\tvalidation_0-rmse:2.86685\n",
+ "[1097]\tvalidation_0-rmse:2.86611\n",
+ "[1098]\tvalidation_0-rmse:2.86607\n",
+ "[1099]\tvalidation_0-rmse:2.86581\n",
+ "[1100]\tvalidation_0-rmse:2.86578\n",
+ "[1101]\tvalidation_0-rmse:2.86582\n",
+ "[1102]\tvalidation_0-rmse:2.86566\n",
+ "[1103]\tvalidation_0-rmse:2.86584\n",
+ "[1104]\tvalidation_0-rmse:2.86528\n",
+ "[1105]\tvalidation_0-rmse:2.86475\n",
+ "[1106]\tvalidation_0-rmse:2.86458\n",
+ "[1107]\tvalidation_0-rmse:2.86453\n",
+ "[1108]\tvalidation_0-rmse:2.86389\n",
+ "[1109]\tvalidation_0-rmse:2.86336\n",
+ "[1110]\tvalidation_0-rmse:2.86285\n",
+ "[1111]\tvalidation_0-rmse:2.86278\n",
+ "[1112]\tvalidation_0-rmse:2.86264\n",
+ "[1113]\tvalidation_0-rmse:2.86239\n",
+ "[1114]\tvalidation_0-rmse:2.86202\n",
+ "[1115]\tvalidation_0-rmse:2.86179\n",
+ "[1116]\tvalidation_0-rmse:2.86093\n",
+ "[1117]\tvalidation_0-rmse:2.86069\n",
+ "[1118]\tvalidation_0-rmse:2.85985\n",
+ "[1119]\tvalidation_0-rmse:2.85991\n",
+ "[1120]\tvalidation_0-rmse:2.85838\n",
+ "[1121]\tvalidation_0-rmse:2.85841\n",
+ "[1122]\tvalidation_0-rmse:2.85820\n",
+ "[1123]\tvalidation_0-rmse:2.85830\n",
+ "[1124]\tvalidation_0-rmse:2.85797\n",
+ "[1125]\tvalidation_0-rmse:2.85767\n",
+ "[1126]\tvalidation_0-rmse:2.85742\n",
+ "[1127]\tvalidation_0-rmse:2.85719\n",
+ "[1128]\tvalidation_0-rmse:2.85682\n",
+ "[1129]\tvalidation_0-rmse:2.85706\n",
+ "[1130]\tvalidation_0-rmse:2.85708\n",
+ "[1131]\tvalidation_0-rmse:2.85615\n",
+ "[1132]\tvalidation_0-rmse:2.85612\n",
+ "[1133]\tvalidation_0-rmse:2.85616\n",
+ "[1134]\tvalidation_0-rmse:2.85575\n",
+ "[1135]\tvalidation_0-rmse:2.85547\n",
+ "[1136]\tvalidation_0-rmse:2.85441\n",
+ "[1137]\tvalidation_0-rmse:2.85415\n",
+ "[1138]\tvalidation_0-rmse:2.85411\n",
+ "[1139]\tvalidation_0-rmse:2.85414\n",
+ "[1140]\tvalidation_0-rmse:2.85415\n",
+ "[1141]\tvalidation_0-rmse:2.85421\n",
+ "[1142]\tvalidation_0-rmse:2.85412\n",
+ "[1143]\tvalidation_0-rmse:2.85428\n",
+ "[1144]\tvalidation_0-rmse:2.85431\n",
+ "[1145]\tvalidation_0-rmse:2.85422\n",
+ "[1146]\tvalidation_0-rmse:2.85419\n",
+ "[1147]\tvalidation_0-rmse:2.85398\n",
+ "[1148]\tvalidation_0-rmse:2.85389\n",
+ "[1149]\tvalidation_0-rmse:2.85385\n",
+ "[1150]\tvalidation_0-rmse:2.85339\n",
+ "[1151]\tvalidation_0-rmse:2.85349\n",
+ "[1152]\tvalidation_0-rmse:2.85334\n",
+ "[1153]\tvalidation_0-rmse:2.85278\n",
+ "[1154]\tvalidation_0-rmse:2.85299\n",
+ "[1155]\tvalidation_0-rmse:2.85229\n",
+ "[1156]\tvalidation_0-rmse:2.85183\n",
+ "[1157]\tvalidation_0-rmse:2.85178\n",
+ "[1158]\tvalidation_0-rmse:2.85116\n",
+ "[1159]\tvalidation_0-rmse:2.85064\n",
+ "[1160]\tvalidation_0-rmse:2.85073\n",
+ "[1161]\tvalidation_0-rmse:2.85079\n",
+ "[1162]\tvalidation_0-rmse:2.85002\n",
+ "[1163]\tvalidation_0-rmse:2.84915\n",
+ "[1164]\tvalidation_0-rmse:2.84908\n",
+ "[1165]\tvalidation_0-rmse:2.84895\n",
+ "[1166]\tvalidation_0-rmse:2.84827\n",
+ "[1167]\tvalidation_0-rmse:2.84775\n",
+ "[1168]\tvalidation_0-rmse:2.84771\n",
+ "[1169]\tvalidation_0-rmse:2.84779\n",
+ "[1170]\tvalidation_0-rmse:2.84729\n",
+ "[1171]\tvalidation_0-rmse:2.84709\n",
+ "[1172]\tvalidation_0-rmse:2.84678\n",
+ "[1173]\tvalidation_0-rmse:2.84645\n",
+ "[1174]\tvalidation_0-rmse:2.84502\n",
+ "[1175]\tvalidation_0-rmse:2.84506\n",
+ "[1176]\tvalidation_0-rmse:2.84507\n",
+ "[1177]\tvalidation_0-rmse:2.84488\n",
+ "[1178]\tvalidation_0-rmse:2.84458\n",
+ "[1179]\tvalidation_0-rmse:2.84477\n",
+ "[1180]\tvalidation_0-rmse:2.84424\n",
+ "[1181]\tvalidation_0-rmse:2.84427\n",
+ "[1182]\tvalidation_0-rmse:2.84369\n",
+ "[1183]\tvalidation_0-rmse:2.84322\n",
+ "[1184]\tvalidation_0-rmse:2.84297\n",
+ "[1185]\tvalidation_0-rmse:2.84235\n",
+ "[1186]\tvalidation_0-rmse:2.84235\n",
+ "[1187]\tvalidation_0-rmse:2.84256\n",
+ "[1188]\tvalidation_0-rmse:2.84191\n",
+ "[1189]\tvalidation_0-rmse:2.84156\n",
+ "[1190]\tvalidation_0-rmse:2.84158\n",
+ "[1191]\tvalidation_0-rmse:2.84127\n",
+ "[1192]\tvalidation_0-rmse:2.84129\n",
+ "[1193]\tvalidation_0-rmse:2.84082\n",
+ "[1194]\tvalidation_0-rmse:2.84063\n",
+ "[1195]\tvalidation_0-rmse:2.84051\n",
+ "[1196]\tvalidation_0-rmse:2.83996\n",
+ "[1197]\tvalidation_0-rmse:2.83992\n",
+ "[1198]\tvalidation_0-rmse:2.83961\n",
+ "[1199]\tvalidation_0-rmse:2.83921\n",
+ "[1200]\tvalidation_0-rmse:2.83932\n",
+ "[1201]\tvalidation_0-rmse:2.83933\n",
+ "[1202]\tvalidation_0-rmse:2.83934\n",
+ "[1203]\tvalidation_0-rmse:2.83938\n",
+ "[1204]\tvalidation_0-rmse:2.83924\n",
+ "[1205]\tvalidation_0-rmse:2.83884\n",
+ "[1206]\tvalidation_0-rmse:2.83837\n",
+ "[1207]\tvalidation_0-rmse:2.83845\n",
+ "[1208]\tvalidation_0-rmse:2.83859\n",
+ "[1209]\tvalidation_0-rmse:2.83862\n",
+ "[1210]\tvalidation_0-rmse:2.83867\n",
+ "[1211]\tvalidation_0-rmse:2.83873\n",
+ "[1212]\tvalidation_0-rmse:2.83797\n",
+ "[1213]\tvalidation_0-rmse:2.83747\n",
+ "[1214]\tvalidation_0-rmse:2.83673\n",
+ "[1215]\tvalidation_0-rmse:2.83676\n",
+ "[1216]\tvalidation_0-rmse:2.83643\n",
+ "[1217]\tvalidation_0-rmse:2.83603\n",
+ "[1218]\tvalidation_0-rmse:2.83576\n",
+ "[1219]\tvalidation_0-rmse:2.83587\n",
+ "[1220]\tvalidation_0-rmse:2.83553\n",
+ "[1221]\tvalidation_0-rmse:2.83569\n",
+ "[1222]\tvalidation_0-rmse:2.83565\n",
+ "[1223]\tvalidation_0-rmse:2.83577\n",
+ "[1224]\tvalidation_0-rmse:2.83570\n",
+ "[1225]\tvalidation_0-rmse:2.83578\n",
+ "[1226]\tvalidation_0-rmse:2.83565\n",
+ "[1227]\tvalidation_0-rmse:2.83541\n",
+ "[1228]\tvalidation_0-rmse:2.83537\n",
+ "[1229]\tvalidation_0-rmse:2.83522\n",
+ "[1230]\tvalidation_0-rmse:2.83523\n",
+ "[1231]\tvalidation_0-rmse:2.83528\n",
+ "[1232]\tvalidation_0-rmse:2.83515\n",
+ "[1233]\tvalidation_0-rmse:2.83462\n",
+ "[1234]\tvalidation_0-rmse:2.83426\n",
+ "[1235]\tvalidation_0-rmse:2.83399\n",
+ "[1236]\tvalidation_0-rmse:2.83340\n",
+ "[1237]\tvalidation_0-rmse:2.83304\n",
+ "[1238]\tvalidation_0-rmse:2.83306\n",
+ "[1239]\tvalidation_0-rmse:2.83229\n",
+ "[1240]\tvalidation_0-rmse:2.83195\n",
+ "[1241]\tvalidation_0-rmse:2.83173\n",
+ "[1242]\tvalidation_0-rmse:2.83184\n",
+ "[1243]\tvalidation_0-rmse:2.83131\n",
+ "[1244]\tvalidation_0-rmse:2.83115\n",
+ "[1245]\tvalidation_0-rmse:2.83119\n",
+ "[1246]\tvalidation_0-rmse:2.83114\n",
+ "[1247]\tvalidation_0-rmse:2.83097\n",
+ "[1248]\tvalidation_0-rmse:2.83070\n",
+ "[1249]\tvalidation_0-rmse:2.83091\n",
+ "[1250]\tvalidation_0-rmse:2.83063\n",
+ "[1251]\tvalidation_0-rmse:2.83038\n",
+ "[1252]\tvalidation_0-rmse:2.83032\n",
+ "[1253]\tvalidation_0-rmse:2.82983\n",
+ "[1254]\tvalidation_0-rmse:2.82970\n",
+ "[1255]\tvalidation_0-rmse:2.82930\n",
+ "[1256]\tvalidation_0-rmse:2.82905\n",
+ "[1257]\tvalidation_0-rmse:2.82879\n",
+ "[1258]\tvalidation_0-rmse:2.82880\n",
+ "[1259]\tvalidation_0-rmse:2.82877\n",
+ "[1260]\tvalidation_0-rmse:2.82845\n",
+ "[1261]\tvalidation_0-rmse:2.82810\n",
+ "[1262]\tvalidation_0-rmse:2.82759\n",
+ "[1263]\tvalidation_0-rmse:2.82685\n",
+ "[1264]\tvalidation_0-rmse:2.82616\n",
+ "[1265]\tvalidation_0-rmse:2.82552\n",
+ "[1266]\tvalidation_0-rmse:2.82560\n",
+ "[1267]\tvalidation_0-rmse:2.82551\n",
+ "[1268]\tvalidation_0-rmse:2.82551\n",
+ "[1269]\tvalidation_0-rmse:2.82524\n",
+ "[1270]\tvalidation_0-rmse:2.82516\n",
+ "[1271]\tvalidation_0-rmse:2.82522\n",
+ "[1272]\tvalidation_0-rmse:2.82524\n",
+ "[1273]\tvalidation_0-rmse:2.82507\n",
+ "[1274]\tvalidation_0-rmse:2.82497\n",
+ "[1275]\tvalidation_0-rmse:2.82510\n",
+ "[1276]\tvalidation_0-rmse:2.82518\n",
+ "[1277]\tvalidation_0-rmse:2.82502\n",
+ "[1278]\tvalidation_0-rmse:2.82495\n",
+ "[1279]\tvalidation_0-rmse:2.82446\n",
+ "[1280]\tvalidation_0-rmse:2.82440\n",
+ "[1281]\tvalidation_0-rmse:2.82459\n",
+ "[1282]\tvalidation_0-rmse:2.82442\n",
+ "[1283]\tvalidation_0-rmse:2.82387\n",
+ "[1284]\tvalidation_0-rmse:2.82382\n",
+ "[1285]\tvalidation_0-rmse:2.82376\n",
+ "[1286]\tvalidation_0-rmse:2.82363\n",
+ "[1287]\tvalidation_0-rmse:2.82347\n",
+ "[1288]\tvalidation_0-rmse:2.82296\n",
+ "[1289]\tvalidation_0-rmse:2.82287\n",
+ "[1290]\tvalidation_0-rmse:2.82243\n",
+ "[1291]\tvalidation_0-rmse:2.82249\n",
+ "[1292]\tvalidation_0-rmse:2.82216\n",
+ "[1293]\tvalidation_0-rmse:2.82173\n",
+ "[1294]\tvalidation_0-rmse:2.82173\n",
+ "[1295]\tvalidation_0-rmse:2.82145\n",
+ "[1296]\tvalidation_0-rmse:2.82137\n",
+ "[1297]\tvalidation_0-rmse:2.82118\n",
+ "[1298]\tvalidation_0-rmse:2.82086\n",
+ "[1299]\tvalidation_0-rmse:2.82097\n",
+ "[1300]\tvalidation_0-rmse:2.82076\n",
+ "[1301]\tvalidation_0-rmse:2.82081\n",
+ "[1302]\tvalidation_0-rmse:2.82077\n",
+ "[1303]\tvalidation_0-rmse:2.82070\n",
+ "[1304]\tvalidation_0-rmse:2.82004\n",
+ "[1305]\tvalidation_0-rmse:2.81949\n",
+ "[1306]\tvalidation_0-rmse:2.81912\n",
+ "[1307]\tvalidation_0-rmse:2.81899\n",
+ "[1308]\tvalidation_0-rmse:2.81889\n",
+ "[1309]\tvalidation_0-rmse:2.81869\n",
+ "[1310]\tvalidation_0-rmse:2.81853\n",
+ "[1311]\tvalidation_0-rmse:2.81840\n",
+ "[1312]\tvalidation_0-rmse:2.81803\n",
+ "[1313]\tvalidation_0-rmse:2.81788\n",
+ "[1314]\tvalidation_0-rmse:2.81771\n",
+ "[1315]\tvalidation_0-rmse:2.81762\n",
+ "[1316]\tvalidation_0-rmse:2.81766\n",
+ "[1317]\tvalidation_0-rmse:2.81716\n",
+ "[1318]\tvalidation_0-rmse:2.81702\n",
+ "[1319]\tvalidation_0-rmse:2.81699\n",
+ "[1320]\tvalidation_0-rmse:2.81673\n",
+ "[1321]\tvalidation_0-rmse:2.81643\n",
+ "[1322]\tvalidation_0-rmse:2.81636\n",
+ "[1323]\tvalidation_0-rmse:2.81589\n",
+ "[1324]\tvalidation_0-rmse:2.81580\n",
+ "[1325]\tvalidation_0-rmse:2.81559\n",
+ "[1326]\tvalidation_0-rmse:2.81557\n",
+ "[1327]\tvalidation_0-rmse:2.81558\n",
+ "[1328]\tvalidation_0-rmse:2.81546\n",
+ "[1329]\tvalidation_0-rmse:2.81575\n",
+ "[1330]\tvalidation_0-rmse:2.81565\n",
+ "[1331]\tvalidation_0-rmse:2.81541\n",
+ "[1332]\tvalidation_0-rmse:2.81544\n",
+ "[1333]\tvalidation_0-rmse:2.81533\n",
+ "[1334]\tvalidation_0-rmse:2.81484\n",
+ "[1335]\tvalidation_0-rmse:2.81487\n",
+ "[1336]\tvalidation_0-rmse:2.81479\n",
+ "[1337]\tvalidation_0-rmse:2.81453\n",
+ "[1338]\tvalidation_0-rmse:2.81468\n",
+ "[1339]\tvalidation_0-rmse:2.81461\n",
+ "[1340]\tvalidation_0-rmse:2.81453\n",
+ "[1341]\tvalidation_0-rmse:2.81435\n",
+ "[1342]\tvalidation_0-rmse:2.81383\n",
+ "[1343]\tvalidation_0-rmse:2.81362\n",
+ "[1344]\tvalidation_0-rmse:2.81370\n",
+ "[1345]\tvalidation_0-rmse:2.81352\n",
+ "[1346]\tvalidation_0-rmse:2.81330\n",
+ "[1347]\tvalidation_0-rmse:2.81282\n",
+ "[1348]\tvalidation_0-rmse:2.81278\n",
+ "[1349]\tvalidation_0-rmse:2.81275\n",
+ "[1350]\tvalidation_0-rmse:2.81198\n",
+ "[1351]\tvalidation_0-rmse:2.81148\n",
+ "[1352]\tvalidation_0-rmse:2.81174\n",
+ "[1353]\tvalidation_0-rmse:2.81190\n",
+ "[1354]\tvalidation_0-rmse:2.81200\n",
+ "[1355]\tvalidation_0-rmse:2.81138\n",
+ "[1356]\tvalidation_0-rmse:2.81116\n",
+ "[1357]\tvalidation_0-rmse:2.81117\n",
+ "[1358]\tvalidation_0-rmse:2.81102\n",
+ "[1359]\tvalidation_0-rmse:2.81080\n",
+ "[1360]\tvalidation_0-rmse:2.81069\n",
+ "[1361]\tvalidation_0-rmse:2.81066\n",
+ "[1362]\tvalidation_0-rmse:2.81052\n",
+ "[1363]\tvalidation_0-rmse:2.81038\n",
+ "[1364]\tvalidation_0-rmse:2.81013\n",
+ "[1365]\tvalidation_0-rmse:2.80955\n",
+ "[1366]\tvalidation_0-rmse:2.80929\n",
+ "[1367]\tvalidation_0-rmse:2.80915\n",
+ "[1368]\tvalidation_0-rmse:2.80890\n",
+ "[1369]\tvalidation_0-rmse:2.80862\n",
+ "[1370]\tvalidation_0-rmse:2.80867\n",
+ "[1371]\tvalidation_0-rmse:2.80874\n",
+ "[1372]\tvalidation_0-rmse:2.80902\n",
+ "[1373]\tvalidation_0-rmse:2.80905\n",
+ "[1374]\tvalidation_0-rmse:2.80867\n",
+ "[1375]\tvalidation_0-rmse:2.80884\n",
+ "[1376]\tvalidation_0-rmse:2.80865\n",
+ "[1377]\tvalidation_0-rmse:2.80855\n",
+ "[1378]\tvalidation_0-rmse:2.80864\n",
+ "[1379]\tvalidation_0-rmse:2.80866\n",
+ "[1380]\tvalidation_0-rmse:2.80832\n",
+ "[1381]\tvalidation_0-rmse:2.80831\n",
+ "[1382]\tvalidation_0-rmse:2.80773\n",
+ "[1383]\tvalidation_0-rmse:2.80773\n",
+ "[1384]\tvalidation_0-rmse:2.80745\n",
+ "[1385]\tvalidation_0-rmse:2.80743\n",
+ "[1386]\tvalidation_0-rmse:2.80742\n",
+ "[1387]\tvalidation_0-rmse:2.80726\n",
+ "[1388]\tvalidation_0-rmse:2.80698\n",
+ "[1389]\tvalidation_0-rmse:2.80712\n",
+ "[1390]\tvalidation_0-rmse:2.80680\n",
+ "[1391]\tvalidation_0-rmse:2.80693\n",
+ "[1392]\tvalidation_0-rmse:2.80683\n",
+ "[1393]\tvalidation_0-rmse:2.80664\n",
+ "[1394]\tvalidation_0-rmse:2.80661\n",
+ "[1395]\tvalidation_0-rmse:2.80654\n",
+ "[1396]\tvalidation_0-rmse:2.80627\n",
+ "[1397]\tvalidation_0-rmse:2.80605\n",
+ "[1398]\tvalidation_0-rmse:2.80554\n",
+ "[1399]\tvalidation_0-rmse:2.80521\n",
+ "[1400]\tvalidation_0-rmse:2.80490\n",
+ "[1401]\tvalidation_0-rmse:2.80491\n",
+ "[1402]\tvalidation_0-rmse:2.80453\n",
+ "[1403]\tvalidation_0-rmse:2.80439\n",
+ "[1404]\tvalidation_0-rmse:2.80437\n",
+ "[1405]\tvalidation_0-rmse:2.80431\n",
+ "[1406]\tvalidation_0-rmse:2.80385\n",
+ "[1407]\tvalidation_0-rmse:2.80388\n",
+ "[1408]\tvalidation_0-rmse:2.80386\n",
+ "[1409]\tvalidation_0-rmse:2.80371\n",
+ "[1410]\tvalidation_0-rmse:2.80370\n",
+ "[1411]\tvalidation_0-rmse:2.80368\n",
+ "[1412]\tvalidation_0-rmse:2.80347\n",
+ "[1413]\tvalidation_0-rmse:2.80289\n",
+ "[1414]\tvalidation_0-rmse:2.80279\n",
+ "[1415]\tvalidation_0-rmse:2.80280\n",
+ "[1416]\tvalidation_0-rmse:2.80239\n",
+ "[1417]\tvalidation_0-rmse:2.80245\n",
+ "[1418]\tvalidation_0-rmse:2.80224\n",
+ "[1419]\tvalidation_0-rmse:2.80206\n",
+ "[1420]\tvalidation_0-rmse:2.80187\n",
+ "[1421]\tvalidation_0-rmse:2.80165\n",
+ "[1422]\tvalidation_0-rmse:2.80115\n",
+ "[1423]\tvalidation_0-rmse:2.80120\n",
+ "[1424]\tvalidation_0-rmse:2.80115\n",
+ "[1425]\tvalidation_0-rmse:2.80116\n",
+ "[1426]\tvalidation_0-rmse:2.80113\n",
+ "[1427]\tvalidation_0-rmse:2.80114\n",
+ "[1428]\tvalidation_0-rmse:2.80039\n",
+ "[1429]\tvalidation_0-rmse:2.80038\n",
+ "[1430]\tvalidation_0-rmse:2.80035\n",
+ "[1431]\tvalidation_0-rmse:2.80052\n",
+ "[1432]\tvalidation_0-rmse:2.80034\n",
+ "[1433]\tvalidation_0-rmse:2.80025\n",
+ "[1434]\tvalidation_0-rmse:2.80002\n",
+ "[1435]\tvalidation_0-rmse:2.79998\n",
+ "[1436]\tvalidation_0-rmse:2.79996\n",
+ "[1437]\tvalidation_0-rmse:2.79997\n",
+ "[1438]\tvalidation_0-rmse:2.80003\n",
+ "[1439]\tvalidation_0-rmse:2.80003\n",
+ "[1440]\tvalidation_0-rmse:2.80009\n",
+ "[1441]\tvalidation_0-rmse:2.79962\n",
+ "[1442]\tvalidation_0-rmse:2.79954\n",
+ "[1443]\tvalidation_0-rmse:2.79963\n",
+ "[1444]\tvalidation_0-rmse:2.79923\n",
+ "[1445]\tvalidation_0-rmse:2.79832\n",
+ "[1446]\tvalidation_0-rmse:2.79820\n",
+ "[1447]\tvalidation_0-rmse:2.79815\n",
+ "[1448]\tvalidation_0-rmse:2.79804\n",
+ "[1449]\tvalidation_0-rmse:2.79758\n",
+ "[1450]\tvalidation_0-rmse:2.79756\n",
+ "[1451]\tvalidation_0-rmse:2.79732\n",
+ "[1452]\tvalidation_0-rmse:2.79715\n",
+ "[1453]\tvalidation_0-rmse:2.79719\n",
+ "[1454]\tvalidation_0-rmse:2.79698\n",
+ "[1455]\tvalidation_0-rmse:2.79701\n",
+ "[1456]\tvalidation_0-rmse:2.79667\n",
+ "[1457]\tvalidation_0-rmse:2.79656\n",
+ "[1458]\tvalidation_0-rmse:2.79663\n",
+ "[1459]\tvalidation_0-rmse:2.79669\n",
+ "[1460]\tvalidation_0-rmse:2.79681\n",
+ "[1461]\tvalidation_0-rmse:2.79683\n",
+ "[1462]\tvalidation_0-rmse:2.79661\n",
+ "[1463]\tvalidation_0-rmse:2.79574\n",
+ "[1464]\tvalidation_0-rmse:2.79571\n",
+ "[1465]\tvalidation_0-rmse:2.79573\n",
+ "[1466]\tvalidation_0-rmse:2.79567\n",
+ "[1467]\tvalidation_0-rmse:2.79572\n",
+ "[1468]\tvalidation_0-rmse:2.79577\n",
+ "[1469]\tvalidation_0-rmse:2.79575\n",
+ "[1470]\tvalidation_0-rmse:2.79566\n",
+ "[1471]\tvalidation_0-rmse:2.79506\n",
+ "[1472]\tvalidation_0-rmse:2.79511\n",
+ "[1473]\tvalidation_0-rmse:2.79504\n",
+ "[1474]\tvalidation_0-rmse:2.79505\n",
+ "[1475]\tvalidation_0-rmse:2.79502\n",
+ "[1476]\tvalidation_0-rmse:2.79489\n",
+ "[1477]\tvalidation_0-rmse:2.79510\n",
+ "[1478]\tvalidation_0-rmse:2.79467\n",
+ "[1479]\tvalidation_0-rmse:2.79474\n",
+ "[1480]\tvalidation_0-rmse:2.79461\n",
+ "[1481]\tvalidation_0-rmse:2.79457\n",
+ "[1482]\tvalidation_0-rmse:2.79395\n",
+ "[1483]\tvalidation_0-rmse:2.79335\n",
+ "[1484]\tvalidation_0-rmse:2.79332\n",
+ "[1485]\tvalidation_0-rmse:2.79331\n",
+ "[1486]\tvalidation_0-rmse:2.79283\n",
+ "[1487]\tvalidation_0-rmse:2.79265\n",
+ "[1488]\tvalidation_0-rmse:2.79254\n",
+ "[1489]\tvalidation_0-rmse:2.79235\n",
+ "[1490]\tvalidation_0-rmse:2.79179\n",
+ "[1491]\tvalidation_0-rmse:2.79174\n",
+ "[1492]\tvalidation_0-rmse:2.79184\n",
+ "[1493]\tvalidation_0-rmse:2.79185\n",
+ "[1494]\tvalidation_0-rmse:2.79193\n",
+ "[1495]\tvalidation_0-rmse:2.79162\n",
+ "[1496]\tvalidation_0-rmse:2.79115\n",
+ "[1497]\tvalidation_0-rmse:2.79064\n",
+ "[1498]\tvalidation_0-rmse:2.79056\n",
+ "[1499]\tvalidation_0-rmse:2.79001\n",
+ "[1500]\tvalidation_0-rmse:2.78994\n",
+ "[1501]\tvalidation_0-rmse:2.78981\n",
+ "[1502]\tvalidation_0-rmse:2.78962\n",
+ "[1503]\tvalidation_0-rmse:2.78910\n",
+ "[1504]\tvalidation_0-rmse:2.78902\n",
+ "[1505]\tvalidation_0-rmse:2.78902\n",
+ "[1506]\tvalidation_0-rmse:2.78881\n",
+ "[1507]\tvalidation_0-rmse:2.78859\n",
+ "[1508]\tvalidation_0-rmse:2.78836\n",
+ "[1509]\tvalidation_0-rmse:2.78819\n",
+ "[1510]\tvalidation_0-rmse:2.78813\n",
+ "[1511]\tvalidation_0-rmse:2.78808\n",
+ "[1512]\tvalidation_0-rmse:2.78809\n",
+ "[1513]\tvalidation_0-rmse:2.78808\n",
+ "[1514]\tvalidation_0-rmse:2.78804\n",
+ "[1515]\tvalidation_0-rmse:2.78808\n",
+ "[1516]\tvalidation_0-rmse:2.78808\n",
+ "[1517]\tvalidation_0-rmse:2.78789\n",
+ "[1518]\tvalidation_0-rmse:2.78771\n",
+ "[1519]\tvalidation_0-rmse:2.78782\n",
+ "[1520]\tvalidation_0-rmse:2.78737\n",
+ "[1521]\tvalidation_0-rmse:2.78741\n",
+ "[1522]\tvalidation_0-rmse:2.78745\n",
+ "[1523]\tvalidation_0-rmse:2.78738\n",
+ "[1524]\tvalidation_0-rmse:2.78727\n",
+ "[1525]\tvalidation_0-rmse:2.78716\n",
+ "[1526]\tvalidation_0-rmse:2.78686\n",
+ "[1527]\tvalidation_0-rmse:2.78693\n",
+ "[1528]\tvalidation_0-rmse:2.78704\n",
+ "[1529]\tvalidation_0-rmse:2.78703\n",
+ "[1530]\tvalidation_0-rmse:2.78674\n",
+ "[1531]\tvalidation_0-rmse:2.78612\n",
+ "[1532]\tvalidation_0-rmse:2.78611\n",
+ "[1533]\tvalidation_0-rmse:2.78611\n",
+ "[1534]\tvalidation_0-rmse:2.78610\n",
+ "[1535]\tvalidation_0-rmse:2.78620\n",
+ "[1536]\tvalidation_0-rmse:2.78582\n",
+ "[1537]\tvalidation_0-rmse:2.78545\n",
+ "[1538]\tvalidation_0-rmse:2.78543\n",
+ "[1539]\tvalidation_0-rmse:2.78565\n",
+ "[1540]\tvalidation_0-rmse:2.78531\n",
+ "[1541]\tvalidation_0-rmse:2.78536\n",
+ "[1542]\tvalidation_0-rmse:2.78528\n",
+ "[1543]\tvalidation_0-rmse:2.78486\n",
+ "[1544]\tvalidation_0-rmse:2.78459\n",
+ "[1545]\tvalidation_0-rmse:2.78430\n",
+ "[1546]\tvalidation_0-rmse:2.78399\n",
+ "[1547]\tvalidation_0-rmse:2.78403\n",
+ "[1548]\tvalidation_0-rmse:2.78402\n",
+ "[1549]\tvalidation_0-rmse:2.78380\n",
+ "[1550]\tvalidation_0-rmse:2.78384\n",
+ "[1551]\tvalidation_0-rmse:2.78373\n",
+ "[1552]\tvalidation_0-rmse:2.78386\n",
+ "[1553]\tvalidation_0-rmse:2.78385\n",
+ "[1554]\tvalidation_0-rmse:2.78373\n",
+ "[1555]\tvalidation_0-rmse:2.78383\n",
+ "[1556]\tvalidation_0-rmse:2.78397\n",
+ "[1557]\tvalidation_0-rmse:2.78392\n",
+ "[1558]\tvalidation_0-rmse:2.78362\n",
+ "[1559]\tvalidation_0-rmse:2.78343\n",
+ "[1560]\tvalidation_0-rmse:2.78338\n",
+ "[1561]\tvalidation_0-rmse:2.78316\n",
+ "[1562]\tvalidation_0-rmse:2.78286\n",
+ "[1563]\tvalidation_0-rmse:2.78268\n",
+ "[1564]\tvalidation_0-rmse:2.78262\n",
+ "[1565]\tvalidation_0-rmse:2.78246\n",
+ "[1566]\tvalidation_0-rmse:2.78205\n",
+ "[1567]\tvalidation_0-rmse:2.78166\n",
+ "[1568]\tvalidation_0-rmse:2.78171\n",
+ "[1569]\tvalidation_0-rmse:2.78132\n",
+ "[1570]\tvalidation_0-rmse:2.78128\n",
+ "[1571]\tvalidation_0-rmse:2.78122\n",
+ "[1572]\tvalidation_0-rmse:2.78075\n",
+ "[1573]\tvalidation_0-rmse:2.78066\n",
+ "[1574]\tvalidation_0-rmse:2.78060\n",
+ "[1575]\tvalidation_0-rmse:2.78056\n",
+ "[1576]\tvalidation_0-rmse:2.78042\n",
+ "[1577]\tvalidation_0-rmse:2.78019\n",
+ "[1578]\tvalidation_0-rmse:2.78021\n",
+ "[1579]\tvalidation_0-rmse:2.78019\n",
+ "[1580]\tvalidation_0-rmse:2.78031\n",
+ "[1581]\tvalidation_0-rmse:2.78017\n",
+ "[1582]\tvalidation_0-rmse:2.78015\n",
+ "[1583]\tvalidation_0-rmse:2.77995\n",
+ "[1584]\tvalidation_0-rmse:2.77963\n",
+ "[1585]\tvalidation_0-rmse:2.77953\n",
+ "[1586]\tvalidation_0-rmse:2.77957\n",
+ "[1587]\tvalidation_0-rmse:2.77929\n",
+ "[1588]\tvalidation_0-rmse:2.77925\n",
+ "[1589]\tvalidation_0-rmse:2.77928\n",
+ "[1590]\tvalidation_0-rmse:2.77883\n",
+ "[1591]\tvalidation_0-rmse:2.77891\n",
+ "[1592]\tvalidation_0-rmse:2.77852\n",
+ "[1593]\tvalidation_0-rmse:2.77848\n",
+ "[1594]\tvalidation_0-rmse:2.77846\n",
+ "[1595]\tvalidation_0-rmse:2.77818\n",
+ "[1596]\tvalidation_0-rmse:2.77806\n",
+ "[1597]\tvalidation_0-rmse:2.77766\n",
+ "[1598]\tvalidation_0-rmse:2.77766\n",
+ "[1599]\tvalidation_0-rmse:2.77758\n",
+ "[1600]\tvalidation_0-rmse:2.77749\n",
+ "[1601]\tvalidation_0-rmse:2.77752\n",
+ "[1602]\tvalidation_0-rmse:2.77739\n",
+ "[1603]\tvalidation_0-rmse:2.77731\n",
+ "[1604]\tvalidation_0-rmse:2.77727\n",
+ "[1605]\tvalidation_0-rmse:2.77706\n",
+ "[1606]\tvalidation_0-rmse:2.77700\n",
+ "[1607]\tvalidation_0-rmse:2.77692\n",
+ "[1608]\tvalidation_0-rmse:2.77682\n",
+ "[1609]\tvalidation_0-rmse:2.77677\n",
+ "[1610]\tvalidation_0-rmse:2.77679\n",
+ "[1611]\tvalidation_0-rmse:2.77661\n",
+ "[1612]\tvalidation_0-rmse:2.77656\n",
+ "[1613]\tvalidation_0-rmse:2.77657\n",
+ "[1614]\tvalidation_0-rmse:2.77637\n",
+ "[1615]\tvalidation_0-rmse:2.77618\n",
+ "[1616]\tvalidation_0-rmse:2.77625\n",
+ "[1617]\tvalidation_0-rmse:2.77630\n",
+ "[1618]\tvalidation_0-rmse:2.77641\n",
+ "[1619]\tvalidation_0-rmse:2.77640\n",
+ "[1620]\tvalidation_0-rmse:2.77635\n",
+ "[1621]\tvalidation_0-rmse:2.77601\n",
+ "[1622]\tvalidation_0-rmse:2.77561\n",
+ "[1623]\tvalidation_0-rmse:2.77540\n",
+ "[1624]\tvalidation_0-rmse:2.77529\n",
+ "[1625]\tvalidation_0-rmse:2.77521\n",
+ "[1626]\tvalidation_0-rmse:2.77505\n",
+ "[1627]\tvalidation_0-rmse:2.77506\n",
+ "[1628]\tvalidation_0-rmse:2.77508\n",
+ "[1629]\tvalidation_0-rmse:2.77486\n",
+ "[1630]\tvalidation_0-rmse:2.77490\n",
+ "[1631]\tvalidation_0-rmse:2.77489\n",
+ "[1632]\tvalidation_0-rmse:2.77473\n",
+ "[1633]\tvalidation_0-rmse:2.77441\n",
+ "[1634]\tvalidation_0-rmse:2.77406\n",
+ "[1635]\tvalidation_0-rmse:2.77395\n",
+ "[1636]\tvalidation_0-rmse:2.77403\n",
+ "[1637]\tvalidation_0-rmse:2.77407\n",
+ "[1638]\tvalidation_0-rmse:2.77392\n",
+ "[1639]\tvalidation_0-rmse:2.77352\n",
+ "[1640]\tvalidation_0-rmse:2.77336\n",
+ "[1641]\tvalidation_0-rmse:2.77300\n",
+ "[1642]\tvalidation_0-rmse:2.77300\n",
+ "[1643]\tvalidation_0-rmse:2.77286\n",
+ "[1644]\tvalidation_0-rmse:2.77285\n",
+ "[1645]\tvalidation_0-rmse:2.77260\n",
+ "[1646]\tvalidation_0-rmse:2.77255\n",
+ "[1647]\tvalidation_0-rmse:2.77241\n",
+ "[1648]\tvalidation_0-rmse:2.77220\n",
+ "[1649]\tvalidation_0-rmse:2.77204\n",
+ "[1650]\tvalidation_0-rmse:2.77200\n",
+ "[1651]\tvalidation_0-rmse:2.77182\n",
+ "[1652]\tvalidation_0-rmse:2.77179\n",
+ "[1653]\tvalidation_0-rmse:2.77175\n",
+ "[1654]\tvalidation_0-rmse:2.77178\n",
+ "[1655]\tvalidation_0-rmse:2.77181\n",
+ "[1656]\tvalidation_0-rmse:2.77156\n",
+ "[1657]\tvalidation_0-rmse:2.77132\n",
+ "[1658]\tvalidation_0-rmse:2.77119\n",
+ "[1659]\tvalidation_0-rmse:2.77121\n",
+ "[1660]\tvalidation_0-rmse:2.77097\n",
+ "[1661]\tvalidation_0-rmse:2.77087\n",
+ "[1662]\tvalidation_0-rmse:2.77078\n",
+ "[1663]\tvalidation_0-rmse:2.77081\n",
+ "[1664]\tvalidation_0-rmse:2.77083\n",
+ "[1665]\tvalidation_0-rmse:2.77082\n",
+ "[1666]\tvalidation_0-rmse:2.77071\n",
+ "[1667]\tvalidation_0-rmse:2.77067\n",
+ "[1668]\tvalidation_0-rmse:2.77064\n",
+ "[1669]\tvalidation_0-rmse:2.77069\n",
+ "[1670]\tvalidation_0-rmse:2.77078\n",
+ "[1671]\tvalidation_0-rmse:2.77023\n",
+ "[1672]\tvalidation_0-rmse:2.76982\n",
+ "[1673]\tvalidation_0-rmse:2.76984\n",
+ "[1674]\tvalidation_0-rmse:2.76975\n",
+ "[1675]\tvalidation_0-rmse:2.76970\n",
+ "[1676]\tvalidation_0-rmse:2.76967\n",
+ "[1677]\tvalidation_0-rmse:2.76960\n",
+ "[1678]\tvalidation_0-rmse:2.76967\n",
+ "[1679]\tvalidation_0-rmse:2.76966\n",
+ "[1680]\tvalidation_0-rmse:2.76957\n",
+ "[1681]\tvalidation_0-rmse:2.76931\n",
+ "[1682]\tvalidation_0-rmse:2.76920\n",
+ "[1683]\tvalidation_0-rmse:2.76923\n",
+ "[1684]\tvalidation_0-rmse:2.76922\n",
+ "[1685]\tvalidation_0-rmse:2.76938\n",
+ "[1686]\tvalidation_0-rmse:2.76930\n",
+ "[1687]\tvalidation_0-rmse:2.76912\n",
+ "[1688]\tvalidation_0-rmse:2.76900\n",
+ "[1689]\tvalidation_0-rmse:2.76889\n",
+ "[1690]\tvalidation_0-rmse:2.76896\n",
+ "[1691]\tvalidation_0-rmse:2.76898\n",
+ "[1692]\tvalidation_0-rmse:2.76901\n",
+ "[1693]\tvalidation_0-rmse:2.76904\n",
+ "[1694]\tvalidation_0-rmse:2.76874\n",
+ "[1695]\tvalidation_0-rmse:2.76876\n",
+ "[1696]\tvalidation_0-rmse:2.76855\n",
+ "[1697]\tvalidation_0-rmse:2.76809\n",
+ "[1698]\tvalidation_0-rmse:2.76790\n",
+ "[1699]\tvalidation_0-rmse:2.76791\n",
+ "[1700]\tvalidation_0-rmse:2.76792\n",
+ "[1701]\tvalidation_0-rmse:2.76787\n",
+ "[1702]\tvalidation_0-rmse:2.76769\n",
+ "[1703]\tvalidation_0-rmse:2.76764\n",
+ "[1704]\tvalidation_0-rmse:2.76760\n",
+ "[1705]\tvalidation_0-rmse:2.76748\n",
+ "[1706]\tvalidation_0-rmse:2.76750\n",
+ "[1707]\tvalidation_0-rmse:2.76752\n",
+ "[1708]\tvalidation_0-rmse:2.76755\n",
+ "[1709]\tvalidation_0-rmse:2.76715\n",
+ "[1710]\tvalidation_0-rmse:2.76692\n",
+ "[1711]\tvalidation_0-rmse:2.76684\n",
+ "[1712]\tvalidation_0-rmse:2.76679\n",
+ "[1713]\tvalidation_0-rmse:2.76642\n",
+ "[1714]\tvalidation_0-rmse:2.76634\n",
+ "[1715]\tvalidation_0-rmse:2.76598\n",
+ "[1716]\tvalidation_0-rmse:2.76583\n",
+ "[1717]\tvalidation_0-rmse:2.76574\n",
+ "[1718]\tvalidation_0-rmse:2.76578\n",
+ "[1719]\tvalidation_0-rmse:2.76539\n",
+ "[1720]\tvalidation_0-rmse:2.76506\n",
+ "[1721]\tvalidation_0-rmse:2.76480\n",
+ "[1722]\tvalidation_0-rmse:2.76466\n",
+ "[1723]\tvalidation_0-rmse:2.76474\n",
+ "[1724]\tvalidation_0-rmse:2.76474\n",
+ "[1725]\tvalidation_0-rmse:2.76463\n",
+ "[1726]\tvalidation_0-rmse:2.76422\n",
+ "[1727]\tvalidation_0-rmse:2.76412\n",
+ "[1728]\tvalidation_0-rmse:2.76380\n",
+ "[1729]\tvalidation_0-rmse:2.76365\n",
+ "[1730]\tvalidation_0-rmse:2.76343\n",
+ "[1731]\tvalidation_0-rmse:2.76330\n",
+ "[1732]\tvalidation_0-rmse:2.76318\n",
+ "[1733]\tvalidation_0-rmse:2.76312\n",
+ "[1734]\tvalidation_0-rmse:2.76313\n",
+ "[1735]\tvalidation_0-rmse:2.76313\n",
+ "[1736]\tvalidation_0-rmse:2.76310\n",
+ "[1737]\tvalidation_0-rmse:2.76303\n",
+ "[1738]\tvalidation_0-rmse:2.76266\n",
+ "[1739]\tvalidation_0-rmse:2.76279\n",
+ "[1740]\tvalidation_0-rmse:2.76282\n",
+ "[1741]\tvalidation_0-rmse:2.76275\n",
+ "[1742]\tvalidation_0-rmse:2.76280\n",
+ "[1743]\tvalidation_0-rmse:2.76270\n",
+ "[1744]\tvalidation_0-rmse:2.76253\n",
+ "[1745]\tvalidation_0-rmse:2.76245\n",
+ "[1746]\tvalidation_0-rmse:2.76241\n",
+ "[1747]\tvalidation_0-rmse:2.76228\n",
+ "[1748]\tvalidation_0-rmse:2.76221\n",
+ "[1749]\tvalidation_0-rmse:2.76209\n",
+ "[1750]\tvalidation_0-rmse:2.76197\n",
+ "[1751]\tvalidation_0-rmse:2.76208\n",
+ "[1752]\tvalidation_0-rmse:2.76207\n",
+ "[1753]\tvalidation_0-rmse:2.76187\n",
+ "[1754]\tvalidation_0-rmse:2.76196\n",
+ "[1755]\tvalidation_0-rmse:2.76200\n",
+ "[1756]\tvalidation_0-rmse:2.76168\n",
+ "[1757]\tvalidation_0-rmse:2.76127\n",
+ "[1758]\tvalidation_0-rmse:2.76100\n",
+ "[1759]\tvalidation_0-rmse:2.76099\n",
+ "[1760]\tvalidation_0-rmse:2.76103\n",
+ "[1761]\tvalidation_0-rmse:2.76080\n",
+ "[1762]\tvalidation_0-rmse:2.76075\n",
+ "[1763]\tvalidation_0-rmse:2.76061\n",
+ "[1764]\tvalidation_0-rmse:2.76065\n",
+ "[1765]\tvalidation_0-rmse:2.76056\n",
+ "[1766]\tvalidation_0-rmse:2.76045\n",
+ "[1767]\tvalidation_0-rmse:2.76031\n",
+ "[1768]\tvalidation_0-rmse:2.76023\n",
+ "[1769]\tvalidation_0-rmse:2.76018\n",
+ "[1770]\tvalidation_0-rmse:2.76012\n",
+ "[1771]\tvalidation_0-rmse:2.76001\n",
+ "[1772]\tvalidation_0-rmse:2.75990\n",
+ "[1773]\tvalidation_0-rmse:2.75977\n",
+ "[1774]\tvalidation_0-rmse:2.75972\n",
+ "[1775]\tvalidation_0-rmse:2.75962\n",
+ "[1776]\tvalidation_0-rmse:2.75956\n",
+ "[1777]\tvalidation_0-rmse:2.75945\n",
+ "[1778]\tvalidation_0-rmse:2.75951\n",
+ "[1779]\tvalidation_0-rmse:2.75923\n",
+ "[1780]\tvalidation_0-rmse:2.75921\n",
+ "[1781]\tvalidation_0-rmse:2.75923\n",
+ "[1782]\tvalidation_0-rmse:2.75924\n",
+ "[1783]\tvalidation_0-rmse:2.75927\n",
+ "[1784]\tvalidation_0-rmse:2.75909\n",
+ "[1785]\tvalidation_0-rmse:2.75905\n",
+ "[1786]\tvalidation_0-rmse:2.75899\n",
+ "[1787]\tvalidation_0-rmse:2.75863\n",
+ "[1788]\tvalidation_0-rmse:2.75864\n",
+ "[1789]\tvalidation_0-rmse:2.75847\n",
+ "[1790]\tvalidation_0-rmse:2.75844\n",
+ "[1791]\tvalidation_0-rmse:2.75835\n",
+ "[1792]\tvalidation_0-rmse:2.75826\n",
+ "[1793]\tvalidation_0-rmse:2.75824\n",
+ "[1794]\tvalidation_0-rmse:2.75813\n",
+ "[1795]\tvalidation_0-rmse:2.75812\n",
+ "[1796]\tvalidation_0-rmse:2.75825\n",
+ "[1797]\tvalidation_0-rmse:2.75826\n",
+ "[1798]\tvalidation_0-rmse:2.75787\n",
+ "[1799]\tvalidation_0-rmse:2.75793\n",
+ "[1800]\tvalidation_0-rmse:2.75785\n",
+ "[1801]\tvalidation_0-rmse:2.75751\n",
+ "[1802]\tvalidation_0-rmse:2.75733\n",
+ "[1803]\tvalidation_0-rmse:2.75736\n",
+ "[1804]\tvalidation_0-rmse:2.75746\n",
+ "[1805]\tvalidation_0-rmse:2.75755\n",
+ "[1806]\tvalidation_0-rmse:2.75727\n",
+ "[1807]\tvalidation_0-rmse:2.75718\n",
+ "[1808]\tvalidation_0-rmse:2.75730\n",
+ "[1809]\tvalidation_0-rmse:2.75694\n",
+ "[1810]\tvalidation_0-rmse:2.75682\n",
+ "[1811]\tvalidation_0-rmse:2.75646\n",
+ "[1812]\tvalidation_0-rmse:2.75621\n",
+ "[1813]\tvalidation_0-rmse:2.75613\n",
+ "[1814]\tvalidation_0-rmse:2.75599\n",
+ "[1815]\tvalidation_0-rmse:2.75554\n",
+ "[1816]\tvalidation_0-rmse:2.75552\n",
+ "[1817]\tvalidation_0-rmse:2.75559\n",
+ "[1818]\tvalidation_0-rmse:2.75560\n",
+ "[1819]\tvalidation_0-rmse:2.75480\n",
+ "[1820]\tvalidation_0-rmse:2.75441\n",
+ "[1821]\tvalidation_0-rmse:2.75427\n",
+ "[1822]\tvalidation_0-rmse:2.75412\n",
+ "[1823]\tvalidation_0-rmse:2.75387\n",
+ "[1824]\tvalidation_0-rmse:2.75366\n",
+ "[1825]\tvalidation_0-rmse:2.75319\n",
+ "[1826]\tvalidation_0-rmse:2.75328\n",
+ "[1827]\tvalidation_0-rmse:2.75264\n",
+ "[1828]\tvalidation_0-rmse:2.75254\n",
+ "[1829]\tvalidation_0-rmse:2.75245\n",
+ "[1830]\tvalidation_0-rmse:2.75228\n",
+ "[1831]\tvalidation_0-rmse:2.75232\n",
+ "[1832]\tvalidation_0-rmse:2.75185\n",
+ "[1833]\tvalidation_0-rmse:2.75177\n",
+ "[1834]\tvalidation_0-rmse:2.75167\n",
+ "[1835]\tvalidation_0-rmse:2.75168\n",
+ "[1836]\tvalidation_0-rmse:2.75171\n",
+ "[1837]\tvalidation_0-rmse:2.75172\n",
+ "[1838]\tvalidation_0-rmse:2.75129\n",
+ "[1839]\tvalidation_0-rmse:2.75126\n",
+ "[1840]\tvalidation_0-rmse:2.75127\n",
+ "[1841]\tvalidation_0-rmse:2.75104\n",
+ "[1842]\tvalidation_0-rmse:2.75109\n",
+ "[1843]\tvalidation_0-rmse:2.75086\n",
+ "[1844]\tvalidation_0-rmse:2.75014\n",
+ "[1845]\tvalidation_0-rmse:2.75010\n",
+ "[1846]\tvalidation_0-rmse:2.75022\n",
+ "[1847]\tvalidation_0-rmse:2.75018\n",
+ "[1848]\tvalidation_0-rmse:2.75000\n",
+ "[1849]\tvalidation_0-rmse:2.74954\n",
+ "[1850]\tvalidation_0-rmse:2.74938\n",
+ "[1851]\tvalidation_0-rmse:2.74935\n",
+ "[1852]\tvalidation_0-rmse:2.74923\n",
+ "[1853]\tvalidation_0-rmse:2.74911\n",
+ "[1854]\tvalidation_0-rmse:2.74892\n",
+ "[1855]\tvalidation_0-rmse:2.74845\n",
+ "[1856]\tvalidation_0-rmse:2.74848\n",
+ "[1857]\tvalidation_0-rmse:2.74831\n",
+ "[1858]\tvalidation_0-rmse:2.74827\n",
+ "[1859]\tvalidation_0-rmse:2.74821\n",
+ "[1860]\tvalidation_0-rmse:2.74823\n",
+ "[1861]\tvalidation_0-rmse:2.74819\n",
+ "[1862]\tvalidation_0-rmse:2.74788\n",
+ "[1863]\tvalidation_0-rmse:2.74760\n",
+ "[1864]\tvalidation_0-rmse:2.74731\n",
+ "[1865]\tvalidation_0-rmse:2.74732\n",
+ "[1866]\tvalidation_0-rmse:2.74727\n",
+ "[1867]\tvalidation_0-rmse:2.74660\n",
+ "[1868]\tvalidation_0-rmse:2.74611\n",
+ "[1869]\tvalidation_0-rmse:2.74613\n",
+ "[1870]\tvalidation_0-rmse:2.74611\n",
+ "[1871]\tvalidation_0-rmse:2.74612\n",
+ "[1872]\tvalidation_0-rmse:2.74611\n",
+ "[1873]\tvalidation_0-rmse:2.74596\n",
+ "[1874]\tvalidation_0-rmse:2.74561\n",
+ "[1875]\tvalidation_0-rmse:2.74560\n",
+ "[1876]\tvalidation_0-rmse:2.74555\n",
+ "[1877]\tvalidation_0-rmse:2.74547\n",
+ "[1878]\tvalidation_0-rmse:2.74542\n",
+ "[1879]\tvalidation_0-rmse:2.74528\n",
+ "[1880]\tvalidation_0-rmse:2.74512\n",
+ "[1881]\tvalidation_0-rmse:2.74509\n",
+ "[1882]\tvalidation_0-rmse:2.74482\n",
+ "[1883]\tvalidation_0-rmse:2.74477\n",
+ "[1884]\tvalidation_0-rmse:2.74477\n",
+ "[1885]\tvalidation_0-rmse:2.74481\n",
+ "[1886]\tvalidation_0-rmse:2.74469\n",
+ "[1887]\tvalidation_0-rmse:2.74468\n",
+ "[1888]\tvalidation_0-rmse:2.74467\n",
+ "[1889]\tvalidation_0-rmse:2.74458\n",
+ "[1890]\tvalidation_0-rmse:2.74428\n",
+ "[1891]\tvalidation_0-rmse:2.74425\n",
+ "[1892]\tvalidation_0-rmse:2.74418\n",
+ "[1893]\tvalidation_0-rmse:2.74404\n",
+ "[1894]\tvalidation_0-rmse:2.74401\n",
+ "[1895]\tvalidation_0-rmse:2.74398\n",
+ "[1896]\tvalidation_0-rmse:2.74387\n",
+ "[1897]\tvalidation_0-rmse:2.74383\n",
+ "[1898]\tvalidation_0-rmse:2.74387\n",
+ "[1899]\tvalidation_0-rmse:2.74330\n",
+ "[1900]\tvalidation_0-rmse:2.74327\n",
+ "[1901]\tvalidation_0-rmse:2.74301\n",
+ "[1902]\tvalidation_0-rmse:2.74299\n",
+ "[1903]\tvalidation_0-rmse:2.74294\n",
+ "[1904]\tvalidation_0-rmse:2.74287\n",
+ "[1905]\tvalidation_0-rmse:2.74289\n",
+ "[1906]\tvalidation_0-rmse:2.74277\n",
+ "[1907]\tvalidation_0-rmse:2.74250\n",
+ "[1908]\tvalidation_0-rmse:2.74236\n",
+ "[1909]\tvalidation_0-rmse:2.74234\n",
+ "[1910]\tvalidation_0-rmse:2.74205\n",
+ "[1911]\tvalidation_0-rmse:2.74196\n",
+ "[1912]\tvalidation_0-rmse:2.74181\n",
+ "[1913]\tvalidation_0-rmse:2.74178\n",
+ "[1914]\tvalidation_0-rmse:2.74184\n",
+ "[1915]\tvalidation_0-rmse:2.74188\n",
+ "[1916]\tvalidation_0-rmse:2.74172\n",
+ "[1917]\tvalidation_0-rmse:2.74158\n",
+ "[1918]\tvalidation_0-rmse:2.74152\n",
+ "[1919]\tvalidation_0-rmse:2.74121\n",
+ "[1920]\tvalidation_0-rmse:2.74081\n",
+ "[1921]\tvalidation_0-rmse:2.74073\n",
+ "[1922]\tvalidation_0-rmse:2.74058\n",
+ "[1923]\tvalidation_0-rmse:2.74049\n",
+ "[1924]\tvalidation_0-rmse:2.74048\n",
+ "[1925]\tvalidation_0-rmse:2.74044\n",
+ "[1926]\tvalidation_0-rmse:2.74030\n",
+ "[1927]\tvalidation_0-rmse:2.74021\n",
+ "[1928]\tvalidation_0-rmse:2.74030\n",
+ "[1929]\tvalidation_0-rmse:2.74012\n",
+ "[1930]\tvalidation_0-rmse:2.74003\n",
+ "[1931]\tvalidation_0-rmse:2.74001\n",
+ "[1932]\tvalidation_0-rmse:2.73995\n",
+ "[1933]\tvalidation_0-rmse:2.74004\n",
+ "[1934]\tvalidation_0-rmse:2.74005\n",
+ "[1935]\tvalidation_0-rmse:2.74002\n",
+ "[1936]\tvalidation_0-rmse:2.74000\n",
+ "[1937]\tvalidation_0-rmse:2.73982\n",
+ "[1938]\tvalidation_0-rmse:2.73988\n",
+ "[1939]\tvalidation_0-rmse:2.73987\n",
+ "[1940]\tvalidation_0-rmse:2.73988\n",
+ "[1941]\tvalidation_0-rmse:2.73978\n",
+ "[1942]\tvalidation_0-rmse:2.73968\n",
+ "[1943]\tvalidation_0-rmse:2.73953\n",
+ "[1944]\tvalidation_0-rmse:2.73933\n",
+ "[1945]\tvalidation_0-rmse:2.73930\n",
+ "[1946]\tvalidation_0-rmse:2.73923\n",
+ "[1947]\tvalidation_0-rmse:2.73893\n",
+ "[1948]\tvalidation_0-rmse:2.73849\n",
+ "[1949]\tvalidation_0-rmse:2.73848\n",
+ "[1950]\tvalidation_0-rmse:2.73837\n",
+ "[1951]\tvalidation_0-rmse:2.73832\n",
+ "[1952]\tvalidation_0-rmse:2.73820\n",
+ "[1953]\tvalidation_0-rmse:2.73799\n",
+ "[1954]\tvalidation_0-rmse:2.73787\n",
+ "[1955]\tvalidation_0-rmse:2.73778\n",
+ "[1956]\tvalidation_0-rmse:2.73779\n",
+ "[1957]\tvalidation_0-rmse:2.73765\n",
+ "[1958]\tvalidation_0-rmse:2.73737\n",
+ "[1959]\tvalidation_0-rmse:2.73698\n",
+ "[1960]\tvalidation_0-rmse:2.73697\n",
+ "[1961]\tvalidation_0-rmse:2.73690\n",
+ "[1962]\tvalidation_0-rmse:2.73682\n",
+ "[1963]\tvalidation_0-rmse:2.73654\n",
+ "[1964]\tvalidation_0-rmse:2.73630\n",
+ "[1965]\tvalidation_0-rmse:2.73619\n",
+ "[1966]\tvalidation_0-rmse:2.73615\n",
+ "[1967]\tvalidation_0-rmse:2.73582\n",
+ "[1968]\tvalidation_0-rmse:2.73575\n",
+ "[1969]\tvalidation_0-rmse:2.73572\n",
+ "[1970]\tvalidation_0-rmse:2.73573\n",
+ "[1971]\tvalidation_0-rmse:2.73575\n",
+ "[1972]\tvalidation_0-rmse:2.73583\n",
+ "[1973]\tvalidation_0-rmse:2.73593\n",
+ "[1974]\tvalidation_0-rmse:2.73587\n",
+ "[1975]\tvalidation_0-rmse:2.73562\n",
+ "[1976]\tvalidation_0-rmse:2.73548\n",
+ "[1977]\tvalidation_0-rmse:2.73518\n",
+ "[1978]\tvalidation_0-rmse:2.73517\n",
+ "[1979]\tvalidation_0-rmse:2.73488\n",
+ "[1980]\tvalidation_0-rmse:2.73492\n",
+ "[1981]\tvalidation_0-rmse:2.73489\n",
+ "[1982]\tvalidation_0-rmse:2.73469\n",
+ "[1983]\tvalidation_0-rmse:2.73473\n",
+ "[1984]\tvalidation_0-rmse:2.73475\n",
+ "[1985]\tvalidation_0-rmse:2.73457\n",
+ "[1986]\tvalidation_0-rmse:2.73464\n",
+ "[1987]\tvalidation_0-rmse:2.73466\n",
+ "[1988]\tvalidation_0-rmse:2.73461\n",
+ "[1989]\tvalidation_0-rmse:2.73448\n",
+ "[1990]\tvalidation_0-rmse:2.73451\n",
+ "[1991]\tvalidation_0-rmse:2.73443\n",
+ "[1992]\tvalidation_0-rmse:2.73421\n",
+ "[1993]\tvalidation_0-rmse:2.73433\n",
+ "[1994]\tvalidation_0-rmse:2.73433\n",
+ "[1995]\tvalidation_0-rmse:2.73427\n",
+ "[1996]\tvalidation_0-rmse:2.73412\n",
+ "[1997]\tvalidation_0-rmse:2.73400\n",
+ "[1998]\tvalidation_0-rmse:2.73399\n",
+ "[1999]\tvalidation_0-rmse:2.73393\n",
+ "[2000]\tvalidation_0-rmse:2.73393\n",
+ "[2001]\tvalidation_0-rmse:2.73390\n",
+ "[2002]\tvalidation_0-rmse:2.73381\n",
+ "[2003]\tvalidation_0-rmse:2.73365\n",
+ "[2004]\tvalidation_0-rmse:2.73356\n",
+ "[2005]\tvalidation_0-rmse:2.73346\n",
+ "[2006]\tvalidation_0-rmse:2.73332\n",
+ "[2007]\tvalidation_0-rmse:2.73294\n",
+ "[2008]\tvalidation_0-rmse:2.73289\n",
+ "[2009]\tvalidation_0-rmse:2.73286\n",
+ "[2010]\tvalidation_0-rmse:2.73288\n",
+ "[2011]\tvalidation_0-rmse:2.73283\n",
+ "[2012]\tvalidation_0-rmse:2.73279\n",
+ "[2013]\tvalidation_0-rmse:2.73275\n",
+ "[2014]\tvalidation_0-rmse:2.73266\n",
+ "[2015]\tvalidation_0-rmse:2.73267\n",
+ "[2016]\tvalidation_0-rmse:2.73262\n",
+ "[2017]\tvalidation_0-rmse:2.73255\n",
+ "[2018]\tvalidation_0-rmse:2.73259\n",
+ "[2019]\tvalidation_0-rmse:2.73225\n",
+ "[2020]\tvalidation_0-rmse:2.73196\n",
+ "[2021]\tvalidation_0-rmse:2.73201\n",
+ "[2022]\tvalidation_0-rmse:2.73190\n",
+ "[2023]\tvalidation_0-rmse:2.73165\n",
+ "[2024]\tvalidation_0-rmse:2.73161\n",
+ "[2025]\tvalidation_0-rmse:2.73142\n",
+ "[2026]\tvalidation_0-rmse:2.73130\n",
+ "[2027]\tvalidation_0-rmse:2.73134\n",
+ "[2028]\tvalidation_0-rmse:2.73147\n",
+ "[2029]\tvalidation_0-rmse:2.73143\n",
+ "[2030]\tvalidation_0-rmse:2.73142\n",
+ "[2031]\tvalidation_0-rmse:2.73135\n",
+ "[2032]\tvalidation_0-rmse:2.73111\n",
+ "[2033]\tvalidation_0-rmse:2.73115\n",
+ "[2034]\tvalidation_0-rmse:2.73110\n",
+ "[2035]\tvalidation_0-rmse:2.73091\n",
+ "[2036]\tvalidation_0-rmse:2.73089\n",
+ "[2037]\tvalidation_0-rmse:2.73089\n",
+ "[2038]\tvalidation_0-rmse:2.73082\n",
+ "[2039]\tvalidation_0-rmse:2.73073\n",
+ "[2040]\tvalidation_0-rmse:2.73070\n",
+ "[2041]\tvalidation_0-rmse:2.73061\n",
+ "[2042]\tvalidation_0-rmse:2.73049\n",
+ "[2043]\tvalidation_0-rmse:2.73043\n",
+ "[2044]\tvalidation_0-rmse:2.73023\n",
+ "[2045]\tvalidation_0-rmse:2.73032\n",
+ "[2046]\tvalidation_0-rmse:2.73023\n",
+ "[2047]\tvalidation_0-rmse:2.73007\n",
+ "[2048]\tvalidation_0-rmse:2.72975\n",
+ "[2049]\tvalidation_0-rmse:2.72958\n",
+ "[2050]\tvalidation_0-rmse:2.72953\n",
+ "[2051]\tvalidation_0-rmse:2.72944\n",
+ "[2052]\tvalidation_0-rmse:2.72921\n",
+ "[2053]\tvalidation_0-rmse:2.72920\n",
+ "[2054]\tvalidation_0-rmse:2.72910\n",
+ "[2055]\tvalidation_0-rmse:2.72895\n",
+ "[2056]\tvalidation_0-rmse:2.72885\n",
+ "[2057]\tvalidation_0-rmse:2.72853\n",
+ "[2058]\tvalidation_0-rmse:2.72840\n",
+ "[2059]\tvalidation_0-rmse:2.72858\n",
+ "[2060]\tvalidation_0-rmse:2.72857\n",
+ "[2061]\tvalidation_0-rmse:2.72852\n",
+ "[2062]\tvalidation_0-rmse:2.72822\n",
+ "[2063]\tvalidation_0-rmse:2.72822\n",
+ "[2064]\tvalidation_0-rmse:2.72812\n",
+ "[2065]\tvalidation_0-rmse:2.72808\n",
+ "[2066]\tvalidation_0-rmse:2.72817\n",
+ "[2067]\tvalidation_0-rmse:2.72819\n",
+ "[2068]\tvalidation_0-rmse:2.72826\n",
+ "[2069]\tvalidation_0-rmse:2.72817\n",
+ "[2070]\tvalidation_0-rmse:2.72805\n",
+ "[2071]\tvalidation_0-rmse:2.72805\n",
+ "[2072]\tvalidation_0-rmse:2.72800\n",
+ "[2073]\tvalidation_0-rmse:2.72790\n",
+ "[2074]\tvalidation_0-rmse:2.72783\n",
+ "[2075]\tvalidation_0-rmse:2.72762\n",
+ "[2076]\tvalidation_0-rmse:2.72758\n",
+ "[2077]\tvalidation_0-rmse:2.72750\n",
+ "[2078]\tvalidation_0-rmse:2.72736\n",
+ "[2079]\tvalidation_0-rmse:2.72746\n",
+ "[2080]\tvalidation_0-rmse:2.72748\n",
+ "[2081]\tvalidation_0-rmse:2.72718\n",
+ "[2082]\tvalidation_0-rmse:2.72725\n",
+ "[2083]\tvalidation_0-rmse:2.72720\n",
+ "[2084]\tvalidation_0-rmse:2.72724\n",
+ "[2085]\tvalidation_0-rmse:2.72728\n",
+ "[2086]\tvalidation_0-rmse:2.72722\n",
+ "[2087]\tvalidation_0-rmse:2.72720\n",
+ "[2088]\tvalidation_0-rmse:2.72697\n",
+ "[2089]\tvalidation_0-rmse:2.72709\n",
+ "[2090]\tvalidation_0-rmse:2.72706\n",
+ "[2091]\tvalidation_0-rmse:2.72710\n",
+ "[2092]\tvalidation_0-rmse:2.72693\n",
+ "[2093]\tvalidation_0-rmse:2.72693\n",
+ "[2094]\tvalidation_0-rmse:2.72684\n",
+ "[2095]\tvalidation_0-rmse:2.72682\n",
+ "[2096]\tvalidation_0-rmse:2.72672\n",
+ "[2097]\tvalidation_0-rmse:2.72653\n",
+ "[2098]\tvalidation_0-rmse:2.72653\n",
+ "[2099]\tvalidation_0-rmse:2.72656\n",
+ "[2100]\tvalidation_0-rmse:2.72654\n",
+ "[2101]\tvalidation_0-rmse:2.72639\n",
+ "[2102]\tvalidation_0-rmse:2.72636\n",
+ "[2103]\tvalidation_0-rmse:2.72634\n",
+ "[2104]\tvalidation_0-rmse:2.72633\n",
+ "[2105]\tvalidation_0-rmse:2.72631\n",
+ "[2106]\tvalidation_0-rmse:2.72630\n",
+ "[2107]\tvalidation_0-rmse:2.72627\n",
+ "[2108]\tvalidation_0-rmse:2.72610\n",
+ "[2109]\tvalidation_0-rmse:2.72607\n",
+ "[2110]\tvalidation_0-rmse:2.72610\n",
+ "[2111]\tvalidation_0-rmse:2.72609\n",
+ "[2112]\tvalidation_0-rmse:2.72619\n",
+ "[2113]\tvalidation_0-rmse:2.72623\n",
+ "[2114]\tvalidation_0-rmse:2.72622\n",
+ "[2115]\tvalidation_0-rmse:2.72619\n",
+ "[2116]\tvalidation_0-rmse:2.72584\n",
+ "[2117]\tvalidation_0-rmse:2.72587\n",
+ "[2118]\tvalidation_0-rmse:2.72574\n",
+ "[2119]\tvalidation_0-rmse:2.72560\n",
+ "[2120]\tvalidation_0-rmse:2.72560\n",
+ "[2121]\tvalidation_0-rmse:2.72561\n",
+ "[2122]\tvalidation_0-rmse:2.72552\n",
+ "[2123]\tvalidation_0-rmse:2.72542\n",
+ "[2124]\tvalidation_0-rmse:2.72508\n",
+ "[2125]\tvalidation_0-rmse:2.72513\n",
+ "[2126]\tvalidation_0-rmse:2.72488\n",
+ "[2127]\tvalidation_0-rmse:2.72497\n",
+ "[2128]\tvalidation_0-rmse:2.72501\n",
+ "[2129]\tvalidation_0-rmse:2.72505\n",
+ "[2130]\tvalidation_0-rmse:2.72508\n",
+ "[2131]\tvalidation_0-rmse:2.72506\n",
+ "[2132]\tvalidation_0-rmse:2.72485\n",
+ "[2133]\tvalidation_0-rmse:2.72472\n",
+ "[2134]\tvalidation_0-rmse:2.72476\n",
+ "[2135]\tvalidation_0-rmse:2.72454\n",
+ "[2136]\tvalidation_0-rmse:2.72435\n",
+ "[2137]\tvalidation_0-rmse:2.72428\n",
+ "[2138]\tvalidation_0-rmse:2.72422\n",
+ "[2139]\tvalidation_0-rmse:2.72410\n",
+ "[2140]\tvalidation_0-rmse:2.72407\n",
+ "[2141]\tvalidation_0-rmse:2.72386\n",
+ "[2142]\tvalidation_0-rmse:2.72372\n",
+ "[2143]\tvalidation_0-rmse:2.72343\n",
+ "[2144]\tvalidation_0-rmse:2.72318\n",
+ "[2145]\tvalidation_0-rmse:2.72308\n",
+ "[2146]\tvalidation_0-rmse:2.72275\n",
+ "[2147]\tvalidation_0-rmse:2.72245\n",
+ "[2148]\tvalidation_0-rmse:2.72210\n",
+ "[2149]\tvalidation_0-rmse:2.72220\n",
+ "[2150]\tvalidation_0-rmse:2.72198\n",
+ "[2151]\tvalidation_0-rmse:2.72174\n",
+ "[2152]\tvalidation_0-rmse:2.72168\n",
+ "[2153]\tvalidation_0-rmse:2.72160\n",
+ "[2154]\tvalidation_0-rmse:2.72143\n",
+ "[2155]\tvalidation_0-rmse:2.72142\n",
+ "[2156]\tvalidation_0-rmse:2.72140\n",
+ "[2157]\tvalidation_0-rmse:2.72129\n",
+ "[2158]\tvalidation_0-rmse:2.72132\n",
+ "[2159]\tvalidation_0-rmse:2.72120\n",
+ "[2160]\tvalidation_0-rmse:2.72109\n",
+ "[2161]\tvalidation_0-rmse:2.72109\n",
+ "[2162]\tvalidation_0-rmse:2.72099\n",
+ "[2163]\tvalidation_0-rmse:2.72090\n",
+ "[2164]\tvalidation_0-rmse:2.72090\n",
+ "[2165]\tvalidation_0-rmse:2.72068\n",
+ "[2166]\tvalidation_0-rmse:2.72038\n",
+ "[2167]\tvalidation_0-rmse:2.72032\n",
+ "[2168]\tvalidation_0-rmse:2.72020\n",
+ "[2169]\tvalidation_0-rmse:2.72001\n",
+ "[2170]\tvalidation_0-rmse:2.72002\n",
+ "[2171]\tvalidation_0-rmse:2.72006\n",
+ "[2172]\tvalidation_0-rmse:2.72005\n",
+ "[2173]\tvalidation_0-rmse:2.71991\n",
+ "[2174]\tvalidation_0-rmse:2.71995\n",
+ "[2175]\tvalidation_0-rmse:2.71987\n",
+ "[2176]\tvalidation_0-rmse:2.71984\n",
+ "[2177]\tvalidation_0-rmse:2.71980\n",
+ "[2178]\tvalidation_0-rmse:2.71949\n",
+ "[2179]\tvalidation_0-rmse:2.71919\n",
+ "[2180]\tvalidation_0-rmse:2.71900\n",
+ "[2181]\tvalidation_0-rmse:2.71901\n",
+ "[2182]\tvalidation_0-rmse:2.71880\n",
+ "[2183]\tvalidation_0-rmse:2.71869\n",
+ "[2184]\tvalidation_0-rmse:2.71856\n",
+ "[2185]\tvalidation_0-rmse:2.71853\n",
+ "[2186]\tvalidation_0-rmse:2.71833\n",
+ "[2187]\tvalidation_0-rmse:2.71817\n",
+ "[2188]\tvalidation_0-rmse:2.71813\n",
+ "[2189]\tvalidation_0-rmse:2.71809\n",
+ "[2190]\tvalidation_0-rmse:2.71816\n",
+ "[2191]\tvalidation_0-rmse:2.71823\n",
+ "[2192]\tvalidation_0-rmse:2.71825\n",
+ "[2193]\tvalidation_0-rmse:2.71818\n",
+ "[2194]\tvalidation_0-rmse:2.71812\n",
+ "[2195]\tvalidation_0-rmse:2.71811\n",
+ "[2196]\tvalidation_0-rmse:2.71803\n",
+ "[2197]\tvalidation_0-rmse:2.71800\n",
+ "[2198]\tvalidation_0-rmse:2.71785\n",
+ "[2199]\tvalidation_0-rmse:2.71777\n",
+ "[2200]\tvalidation_0-rmse:2.71786\n",
+ "[2201]\tvalidation_0-rmse:2.71771\n",
+ "[2202]\tvalidation_0-rmse:2.71768\n",
+ "[2203]\tvalidation_0-rmse:2.71762\n",
+ "[2204]\tvalidation_0-rmse:2.71755\n",
+ "[2205]\tvalidation_0-rmse:2.71736\n",
+ "[2206]\tvalidation_0-rmse:2.71738\n",
+ "[2207]\tvalidation_0-rmse:2.71738\n",
+ "[2208]\tvalidation_0-rmse:2.71721\n",
+ "[2209]\tvalidation_0-rmse:2.71697\n",
+ "[2210]\tvalidation_0-rmse:2.71701\n",
+ "[2211]\tvalidation_0-rmse:2.71696\n",
+ "[2212]\tvalidation_0-rmse:2.71685\n",
+ "[2213]\tvalidation_0-rmse:2.71684\n",
+ "[2214]\tvalidation_0-rmse:2.71679\n",
+ "[2215]\tvalidation_0-rmse:2.71667\n",
+ "[2216]\tvalidation_0-rmse:2.71647\n",
+ "[2217]\tvalidation_0-rmse:2.71653\n",
+ "[2218]\tvalidation_0-rmse:2.71656\n",
+ "[2219]\tvalidation_0-rmse:2.71604\n",
+ "[2220]\tvalidation_0-rmse:2.71589\n",
+ "[2221]\tvalidation_0-rmse:2.71576\n",
+ "[2222]\tvalidation_0-rmse:2.71575\n",
+ "[2223]\tvalidation_0-rmse:2.71579\n",
+ "[2224]\tvalidation_0-rmse:2.71579\n",
+ "[2225]\tvalidation_0-rmse:2.71585\n",
+ "[2226]\tvalidation_0-rmse:2.71587\n",
+ "[2227]\tvalidation_0-rmse:2.71567\n",
+ "[2228]\tvalidation_0-rmse:2.71560\n",
+ "[2229]\tvalidation_0-rmse:2.71565\n",
+ "[2230]\tvalidation_0-rmse:2.71534\n",
+ "[2231]\tvalidation_0-rmse:2.71521\n",
+ "[2232]\tvalidation_0-rmse:2.71520\n",
+ "[2233]\tvalidation_0-rmse:2.71503\n",
+ "[2234]\tvalidation_0-rmse:2.71487\n",
+ "[2235]\tvalidation_0-rmse:2.71478\n",
+ "[2236]\tvalidation_0-rmse:2.71474\n",
+ "[2237]\tvalidation_0-rmse:2.71455\n",
+ "[2238]\tvalidation_0-rmse:2.71457\n",
+ "[2239]\tvalidation_0-rmse:2.71454\n",
+ "[2240]\tvalidation_0-rmse:2.71451\n",
+ "[2241]\tvalidation_0-rmse:2.71412\n",
+ "[2242]\tvalidation_0-rmse:2.71378\n",
+ "[2243]\tvalidation_0-rmse:2.71368\n",
+ "[2244]\tvalidation_0-rmse:2.71374\n",
+ "[2245]\tvalidation_0-rmse:2.71359\n",
+ "[2246]\tvalidation_0-rmse:2.71364\n",
+ "[2247]\tvalidation_0-rmse:2.71351\n",
+ "[2248]\tvalidation_0-rmse:2.71350\n",
+ "[2249]\tvalidation_0-rmse:2.71347\n",
+ "[2250]\tvalidation_0-rmse:2.71350\n",
+ "[2251]\tvalidation_0-rmse:2.71346\n",
+ "[2252]\tvalidation_0-rmse:2.71346\n",
+ "[2253]\tvalidation_0-rmse:2.71332\n",
+ "[2254]\tvalidation_0-rmse:2.71329\n",
+ "[2255]\tvalidation_0-rmse:2.71333\n",
+ "[2256]\tvalidation_0-rmse:2.71296\n",
+ "[2257]\tvalidation_0-rmse:2.71267\n",
+ "[2258]\tvalidation_0-rmse:2.71254\n",
+ "[2259]\tvalidation_0-rmse:2.71253\n",
+ "[2260]\tvalidation_0-rmse:2.71255\n",
+ "[2261]\tvalidation_0-rmse:2.71244\n",
+ "[2262]\tvalidation_0-rmse:2.71213\n",
+ "[2263]\tvalidation_0-rmse:2.71223\n",
+ "[2264]\tvalidation_0-rmse:2.71207\n",
+ "[2265]\tvalidation_0-rmse:2.71193\n",
+ "[2266]\tvalidation_0-rmse:2.71171\n",
+ "[2267]\tvalidation_0-rmse:2.71160\n",
+ "[2268]\tvalidation_0-rmse:2.71157\n",
+ "[2269]\tvalidation_0-rmse:2.71170\n",
+ "[2270]\tvalidation_0-rmse:2.71144\n",
+ "[2271]\tvalidation_0-rmse:2.71139\n",
+ "[2272]\tvalidation_0-rmse:2.71124\n",
+ "[2273]\tvalidation_0-rmse:2.71112\n",
+ "[2274]\tvalidation_0-rmse:2.71089\n",
+ "[2275]\tvalidation_0-rmse:2.71072\n",
+ "[2276]\tvalidation_0-rmse:2.71071\n",
+ "[2277]\tvalidation_0-rmse:2.71069\n",
+ "[2278]\tvalidation_0-rmse:2.71058\n",
+ "[2279]\tvalidation_0-rmse:2.71053\n",
+ "[2280]\tvalidation_0-rmse:2.71030\n",
+ "[2281]\tvalidation_0-rmse:2.71031\n",
+ "[2282]\tvalidation_0-rmse:2.71032\n",
+ "[2283]\tvalidation_0-rmse:2.71040\n",
+ "[2284]\tvalidation_0-rmse:2.71026\n",
+ "[2285]\tvalidation_0-rmse:2.71032\n",
+ "[2286]\tvalidation_0-rmse:2.71030\n",
+ "[2287]\tvalidation_0-rmse:2.71021\n",
+ "[2288]\tvalidation_0-rmse:2.71023\n",
+ "[2289]\tvalidation_0-rmse:2.71030\n",
+ "[2290]\tvalidation_0-rmse:2.71033\n",
+ "[2291]\tvalidation_0-rmse:2.71036\n",
+ "[2292]\tvalidation_0-rmse:2.71025\n",
+ "[2293]\tvalidation_0-rmse:2.71014\n",
+ "[2294]\tvalidation_0-rmse:2.71003\n",
+ "[2295]\tvalidation_0-rmse:2.71005\n",
+ "[2296]\tvalidation_0-rmse:2.70990\n",
+ "[2297]\tvalidation_0-rmse:2.70975\n",
+ "[2298]\tvalidation_0-rmse:2.70953\n",
+ "[2299]\tvalidation_0-rmse:2.70946\n",
+ "[2300]\tvalidation_0-rmse:2.70948\n",
+ "[2301]\tvalidation_0-rmse:2.70945\n",
+ "[2302]\tvalidation_0-rmse:2.70931\n",
+ "[2303]\tvalidation_0-rmse:2.70939\n",
+ "[2304]\tvalidation_0-rmse:2.70928\n",
+ "[2305]\tvalidation_0-rmse:2.70923\n",
+ "[2306]\tvalidation_0-rmse:2.70909\n",
+ "[2307]\tvalidation_0-rmse:2.70897\n",
+ "[2308]\tvalidation_0-rmse:2.70888\n",
+ "[2309]\tvalidation_0-rmse:2.70882\n",
+ "[2310]\tvalidation_0-rmse:2.70881\n",
+ "[2311]\tvalidation_0-rmse:2.70883\n",
+ "[2312]\tvalidation_0-rmse:2.70872\n",
+ "[2313]\tvalidation_0-rmse:2.70867\n",
+ "[2314]\tvalidation_0-rmse:2.70863\n",
+ "[2315]\tvalidation_0-rmse:2.70856\n",
+ "[2316]\tvalidation_0-rmse:2.70846\n",
+ "[2317]\tvalidation_0-rmse:2.70859\n",
+ "[2318]\tvalidation_0-rmse:2.70860\n",
+ "[2319]\tvalidation_0-rmse:2.70848\n",
+ "[2320]\tvalidation_0-rmse:2.70829\n",
+ "[2321]\tvalidation_0-rmse:2.70830\n",
+ "[2322]\tvalidation_0-rmse:2.70837\n",
+ "[2323]\tvalidation_0-rmse:2.70849\n",
+ "[2324]\tvalidation_0-rmse:2.70853\n",
+ "[2325]\tvalidation_0-rmse:2.70851\n",
+ "[2326]\tvalidation_0-rmse:2.70823\n",
+ "[2327]\tvalidation_0-rmse:2.70827\n",
+ "[2328]\tvalidation_0-rmse:2.70829\n",
+ "[2329]\tvalidation_0-rmse:2.70829\n",
+ "[2330]\tvalidation_0-rmse:2.70829\n",
+ "[2331]\tvalidation_0-rmse:2.70825\n",
+ "[2332]\tvalidation_0-rmse:2.70822\n",
+ "[2333]\tvalidation_0-rmse:2.70830\n",
+ "[2334]\tvalidation_0-rmse:2.70820\n",
+ "[2335]\tvalidation_0-rmse:2.70808\n",
+ "[2336]\tvalidation_0-rmse:2.70809\n",
+ "[2337]\tvalidation_0-rmse:2.70799\n",
+ "[2338]\tvalidation_0-rmse:2.70778\n",
+ "[2339]\tvalidation_0-rmse:2.70758\n",
+ "[2340]\tvalidation_0-rmse:2.70747\n",
+ "[2341]\tvalidation_0-rmse:2.70739\n",
+ "[2342]\tvalidation_0-rmse:2.70710\n",
+ "[2343]\tvalidation_0-rmse:2.70693\n",
+ "[2344]\tvalidation_0-rmse:2.70691\n",
+ "[2345]\tvalidation_0-rmse:2.70687\n",
+ "[2346]\tvalidation_0-rmse:2.70674\n",
+ "[2347]\tvalidation_0-rmse:2.70661\n",
+ "[2348]\tvalidation_0-rmse:2.70648\n",
+ "[2349]\tvalidation_0-rmse:2.70644\n",
+ "[2350]\tvalidation_0-rmse:2.70631\n",
+ "[2351]\tvalidation_0-rmse:2.70628\n",
+ "[2352]\tvalidation_0-rmse:2.70631\n",
+ "[2353]\tvalidation_0-rmse:2.70629\n",
+ "[2354]\tvalidation_0-rmse:2.70624\n",
+ "[2355]\tvalidation_0-rmse:2.70625\n",
+ "[2356]\tvalidation_0-rmse:2.70619\n",
+ "[2357]\tvalidation_0-rmse:2.70625\n",
+ "[2358]\tvalidation_0-rmse:2.70627\n",
+ "[2359]\tvalidation_0-rmse:2.70621\n",
+ "[2360]\tvalidation_0-rmse:2.70614\n",
+ "[2361]\tvalidation_0-rmse:2.70615\n",
+ "[2362]\tvalidation_0-rmse:2.70613\n",
+ "[2363]\tvalidation_0-rmse:2.70610\n",
+ "[2364]\tvalidation_0-rmse:2.70600\n",
+ "[2365]\tvalidation_0-rmse:2.70596\n",
+ "[2366]\tvalidation_0-rmse:2.70569\n",
+ "[2367]\tvalidation_0-rmse:2.70550\n",
+ "[2368]\tvalidation_0-rmse:2.70524\n",
+ "[2369]\tvalidation_0-rmse:2.70505\n",
+ "[2370]\tvalidation_0-rmse:2.70505\n",
+ "[2371]\tvalidation_0-rmse:2.70513\n",
+ "[2372]\tvalidation_0-rmse:2.70506\n",
+ "[2373]\tvalidation_0-rmse:2.70491\n",
+ "[2374]\tvalidation_0-rmse:2.70482\n",
+ "[2375]\tvalidation_0-rmse:2.70467\n",
+ "[2376]\tvalidation_0-rmse:2.70474\n",
+ "[2377]\tvalidation_0-rmse:2.70472\n",
+ "[2378]\tvalidation_0-rmse:2.70469\n",
+ "[2379]\tvalidation_0-rmse:2.70460\n",
+ "[2380]\tvalidation_0-rmse:2.70459\n",
+ "[2381]\tvalidation_0-rmse:2.70452\n",
+ "[2382]\tvalidation_0-rmse:2.70445\n",
+ "[2383]\tvalidation_0-rmse:2.70448\n",
+ "[2384]\tvalidation_0-rmse:2.70452\n",
+ "[2385]\tvalidation_0-rmse:2.70450\n",
+ "[2386]\tvalidation_0-rmse:2.70444\n",
+ "[2387]\tvalidation_0-rmse:2.70451\n",
+ "[2388]\tvalidation_0-rmse:2.70453\n",
+ "[2389]\tvalidation_0-rmse:2.70445\n",
+ "[2390]\tvalidation_0-rmse:2.70440\n",
+ "[2391]\tvalidation_0-rmse:2.70421\n",
+ "[2392]\tvalidation_0-rmse:2.70422\n",
+ "[2393]\tvalidation_0-rmse:2.70420\n",
+ "[2394]\tvalidation_0-rmse:2.70420\n",
+ "[2395]\tvalidation_0-rmse:2.70409\n",
+ "[2396]\tvalidation_0-rmse:2.70407\n",
+ "[2397]\tvalidation_0-rmse:2.70408\n",
+ "[2398]\tvalidation_0-rmse:2.70405\n",
+ "[2399]\tvalidation_0-rmse:2.70408\n",
+ "[2400]\tvalidation_0-rmse:2.70408\n",
+ "[2401]\tvalidation_0-rmse:2.70409\n",
+ "[2402]\tvalidation_0-rmse:2.70400\n",
+ "[2403]\tvalidation_0-rmse:2.70388\n",
+ "[2404]\tvalidation_0-rmse:2.70379\n",
+ "[2405]\tvalidation_0-rmse:2.70354\n",
+ "[2406]\tvalidation_0-rmse:2.70354\n",
+ "[2407]\tvalidation_0-rmse:2.70345\n",
+ "[2408]\tvalidation_0-rmse:2.70323\n",
+ "[2409]\tvalidation_0-rmse:2.70325\n",
+ "[2410]\tvalidation_0-rmse:2.70322\n",
+ "[2411]\tvalidation_0-rmse:2.70320\n",
+ "[2412]\tvalidation_0-rmse:2.70325\n",
+ "[2413]\tvalidation_0-rmse:2.70332\n",
+ "[2414]\tvalidation_0-rmse:2.70315\n",
+ "[2415]\tvalidation_0-rmse:2.70304\n",
+ "[2416]\tvalidation_0-rmse:2.70309\n",
+ "[2417]\tvalidation_0-rmse:2.70306\n",
+ "[2418]\tvalidation_0-rmse:2.70299\n",
+ "[2419]\tvalidation_0-rmse:2.70301\n",
+ "[2420]\tvalidation_0-rmse:2.70300\n",
+ "[2421]\tvalidation_0-rmse:2.70288\n",
+ "[2422]\tvalidation_0-rmse:2.70295\n",
+ "[2423]\tvalidation_0-rmse:2.70299\n",
+ "[2424]\tvalidation_0-rmse:2.70298\n",
+ "[2425]\tvalidation_0-rmse:2.70286\n",
+ "[2426]\tvalidation_0-rmse:2.70288\n",
+ "[2427]\tvalidation_0-rmse:2.70276\n",
+ "[2428]\tvalidation_0-rmse:2.70266\n",
+ "[2429]\tvalidation_0-rmse:2.70263\n",
+ "[2430]\tvalidation_0-rmse:2.70262\n",
+ "[2431]\tvalidation_0-rmse:2.70260\n",
+ "[2432]\tvalidation_0-rmse:2.70225\n",
+ "[2433]\tvalidation_0-rmse:2.70215\n",
+ "[2434]\tvalidation_0-rmse:2.70203\n",
+ "[2435]\tvalidation_0-rmse:2.70200\n",
+ "[2436]\tvalidation_0-rmse:2.70202\n",
+ "[2437]\tvalidation_0-rmse:2.70205\n",
+ "[2438]\tvalidation_0-rmse:2.70206\n",
+ "[2439]\tvalidation_0-rmse:2.70202\n",
+ "[2440]\tvalidation_0-rmse:2.70170\n",
+ "[2441]\tvalidation_0-rmse:2.70166\n",
+ "[2442]\tvalidation_0-rmse:2.70163\n",
+ "[2443]\tvalidation_0-rmse:2.70169\n",
+ "[2444]\tvalidation_0-rmse:2.70145\n",
+ "[2445]\tvalidation_0-rmse:2.70149\n",
+ "[2446]\tvalidation_0-rmse:2.70131\n",
+ "[2447]\tvalidation_0-rmse:2.70111\n",
+ "[2448]\tvalidation_0-rmse:2.70097\n",
+ "[2449]\tvalidation_0-rmse:2.70095\n",
+ "[2450]\tvalidation_0-rmse:2.70096\n",
+ "[2451]\tvalidation_0-rmse:2.70061\n",
+ "[2452]\tvalidation_0-rmse:2.70058\n",
+ "[2453]\tvalidation_0-rmse:2.70035\n",
+ "[2454]\tvalidation_0-rmse:2.70037\n",
+ "[2455]\tvalidation_0-rmse:2.70043\n",
+ "[2456]\tvalidation_0-rmse:2.70045\n",
+ "[2457]\tvalidation_0-rmse:2.70023\n",
+ "[2458]\tvalidation_0-rmse:2.70014\n",
+ "[2459]\tvalidation_0-rmse:2.70009\n",
+ "[2460]\tvalidation_0-rmse:2.70003\n",
+ "[2461]\tvalidation_0-rmse:2.70000\n",
+ "[2462]\tvalidation_0-rmse:2.69996\n",
+ "[2463]\tvalidation_0-rmse:2.69994\n",
+ "[2464]\tvalidation_0-rmse:2.69993\n",
+ "[2465]\tvalidation_0-rmse:2.69979\n",
+ "[2466]\tvalidation_0-rmse:2.69976\n",
+ "[2467]\tvalidation_0-rmse:2.69976\n",
+ "[2468]\tvalidation_0-rmse:2.69962\n",
+ "[2469]\tvalidation_0-rmse:2.69958\n",
+ "[2470]\tvalidation_0-rmse:2.69964\n",
+ "[2471]\tvalidation_0-rmse:2.69965\n",
+ "[2472]\tvalidation_0-rmse:2.69953\n",
+ "[2473]\tvalidation_0-rmse:2.69945\n",
+ "[2474]\tvalidation_0-rmse:2.69950\n",
+ "[2475]\tvalidation_0-rmse:2.69948\n",
+ "[2476]\tvalidation_0-rmse:2.69945\n",
+ "[2477]\tvalidation_0-rmse:2.69934\n",
+ "[2478]\tvalidation_0-rmse:2.69933\n",
+ "[2479]\tvalidation_0-rmse:2.69930\n",
+ "[2480]\tvalidation_0-rmse:2.69926\n",
+ "[2481]\tvalidation_0-rmse:2.69927\n",
+ "[2482]\tvalidation_0-rmse:2.69924\n",
+ "[2483]\tvalidation_0-rmse:2.69927\n",
+ "[2484]\tvalidation_0-rmse:2.69924\n",
+ "[2485]\tvalidation_0-rmse:2.69923\n",
+ "[2486]\tvalidation_0-rmse:2.69923\n",
+ "[2487]\tvalidation_0-rmse:2.69915\n",
+ "[2488]\tvalidation_0-rmse:2.69917\n",
+ "[2489]\tvalidation_0-rmse:2.69915\n",
+ "[2490]\tvalidation_0-rmse:2.69926\n",
+ "[2491]\tvalidation_0-rmse:2.69928\n",
+ "[2492]\tvalidation_0-rmse:2.69938\n",
+ "[2493]\tvalidation_0-rmse:2.69931\n",
+ "[2494]\tvalidation_0-rmse:2.69910\n",
+ "[2495]\tvalidation_0-rmse:2.69915\n",
+ "[2496]\tvalidation_0-rmse:2.69900\n",
+ "[2497]\tvalidation_0-rmse:2.69883\n",
+ "[2498]\tvalidation_0-rmse:2.69871\n",
+ "[2499]\tvalidation_0-rmse:2.69871\n",
+ "[2500]\tvalidation_0-rmse:2.69872\n",
+ "[2501]\tvalidation_0-rmse:2.69866\n",
+ "[2502]\tvalidation_0-rmse:2.69869\n",
+ "[2503]\tvalidation_0-rmse:2.69868\n",
+ "[2504]\tvalidation_0-rmse:2.69845\n",
+ "[2505]\tvalidation_0-rmse:2.69837\n",
+ "[2506]\tvalidation_0-rmse:2.69831\n",
+ "[2507]\tvalidation_0-rmse:2.69836\n",
+ "[2508]\tvalidation_0-rmse:2.69830\n",
+ "[2509]\tvalidation_0-rmse:2.69828\n",
+ "[2510]\tvalidation_0-rmse:2.69822\n",
+ "[2511]\tvalidation_0-rmse:2.69789\n",
+ "[2512]\tvalidation_0-rmse:2.69775\n",
+ "[2513]\tvalidation_0-rmse:2.69761\n",
+ "[2514]\tvalidation_0-rmse:2.69755\n",
+ "[2515]\tvalidation_0-rmse:2.69752\n",
+ "[2516]\tvalidation_0-rmse:2.69755\n",
+ "[2517]\tvalidation_0-rmse:2.69755\n",
+ "[2518]\tvalidation_0-rmse:2.69748\n",
+ "[2519]\tvalidation_0-rmse:2.69731\n",
+ "[2520]\tvalidation_0-rmse:2.69734\n",
+ "[2521]\tvalidation_0-rmse:2.69711\n",
+ "[2522]\tvalidation_0-rmse:2.69716\n",
+ "[2523]\tvalidation_0-rmse:2.69712\n",
+ "[2524]\tvalidation_0-rmse:2.69691\n",
+ "[2525]\tvalidation_0-rmse:2.69699\n",
+ "[2526]\tvalidation_0-rmse:2.69692\n",
+ "[2527]\tvalidation_0-rmse:2.69683\n",
+ "[2528]\tvalidation_0-rmse:2.69673\n",
+ "[2529]\tvalidation_0-rmse:2.69666\n",
+ "[2530]\tvalidation_0-rmse:2.69648\n",
+ "[2531]\tvalidation_0-rmse:2.69629\n",
+ "[2532]\tvalidation_0-rmse:2.69627\n",
+ "[2533]\tvalidation_0-rmse:2.69625\n",
+ "[2534]\tvalidation_0-rmse:2.69624\n",
+ "[2535]\tvalidation_0-rmse:2.69617\n",
+ "[2536]\tvalidation_0-rmse:2.69620\n",
+ "[2537]\tvalidation_0-rmse:2.69621\n",
+ "[2538]\tvalidation_0-rmse:2.69622\n",
+ "[2539]\tvalidation_0-rmse:2.69614\n",
+ "[2540]\tvalidation_0-rmse:2.69595\n",
+ "[2541]\tvalidation_0-rmse:2.69587\n",
+ "[2542]\tvalidation_0-rmse:2.69582\n",
+ "[2543]\tvalidation_0-rmse:2.69571\n",
+ "[2544]\tvalidation_0-rmse:2.69567\n",
+ "[2545]\tvalidation_0-rmse:2.69565\n",
+ "[2546]\tvalidation_0-rmse:2.69553\n",
+ "[2547]\tvalidation_0-rmse:2.69524\n",
+ "[2548]\tvalidation_0-rmse:2.69521\n",
+ "[2549]\tvalidation_0-rmse:2.69520\n",
+ "[2550]\tvalidation_0-rmse:2.69504\n",
+ "[2551]\tvalidation_0-rmse:2.69501\n",
+ "[2552]\tvalidation_0-rmse:2.69484\n",
+ "[2553]\tvalidation_0-rmse:2.69460\n",
+ "[2554]\tvalidation_0-rmse:2.69453\n",
+ "[2555]\tvalidation_0-rmse:2.69442\n",
+ "[2556]\tvalidation_0-rmse:2.69437\n",
+ "[2557]\tvalidation_0-rmse:2.69435\n",
+ "[2558]\tvalidation_0-rmse:2.69422\n",
+ "[2559]\tvalidation_0-rmse:2.69418\n",
+ "[2560]\tvalidation_0-rmse:2.69390\n",
+ "[2561]\tvalidation_0-rmse:2.69375\n",
+ "[2562]\tvalidation_0-rmse:2.69340\n",
+ "[2563]\tvalidation_0-rmse:2.69327\n",
+ "[2564]\tvalidation_0-rmse:2.69304\n",
+ "[2565]\tvalidation_0-rmse:2.69298\n",
+ "[2566]\tvalidation_0-rmse:2.69294\n",
+ "[2567]\tvalidation_0-rmse:2.69292\n",
+ "[2568]\tvalidation_0-rmse:2.69295\n",
+ "[2569]\tvalidation_0-rmse:2.69296\n",
+ "[2570]\tvalidation_0-rmse:2.69299\n",
+ "[2571]\tvalidation_0-rmse:2.69293\n",
+ "[2572]\tvalidation_0-rmse:2.69299\n",
+ "[2573]\tvalidation_0-rmse:2.69296\n",
+ "[2574]\tvalidation_0-rmse:2.69299\n",
+ "[2575]\tvalidation_0-rmse:2.69296\n",
+ "[2576]\tvalidation_0-rmse:2.69283\n",
+ "[2577]\tvalidation_0-rmse:2.69258\n",
+ "[2578]\tvalidation_0-rmse:2.69256\n",
+ "[2579]\tvalidation_0-rmse:2.69259\n",
+ "[2580]\tvalidation_0-rmse:2.69255\n",
+ "[2581]\tvalidation_0-rmse:2.69262\n",
+ "[2582]\tvalidation_0-rmse:2.69259\n",
+ "[2583]\tvalidation_0-rmse:2.69256\n",
+ "[2584]\tvalidation_0-rmse:2.69263\n",
+ "[2585]\tvalidation_0-rmse:2.69249\n",
+ "[2586]\tvalidation_0-rmse:2.69248\n",
+ "[2587]\tvalidation_0-rmse:2.69249\n",
+ "[2588]\tvalidation_0-rmse:2.69254\n",
+ "[2589]\tvalidation_0-rmse:2.69220\n",
+ "[2590]\tvalidation_0-rmse:2.69204\n",
+ "[2591]\tvalidation_0-rmse:2.69205\n",
+ "[2592]\tvalidation_0-rmse:2.69205\n",
+ "[2593]\tvalidation_0-rmse:2.69200\n",
+ "[2594]\tvalidation_0-rmse:2.69197\n",
+ "[2595]\tvalidation_0-rmse:2.69181\n",
+ "[2596]\tvalidation_0-rmse:2.69181\n",
+ "[2597]\tvalidation_0-rmse:2.69181\n",
+ "[2598]\tvalidation_0-rmse:2.69167\n",
+ "[2599]\tvalidation_0-rmse:2.69148\n",
+ "[2600]\tvalidation_0-rmse:2.69133\n",
+ "[2601]\tvalidation_0-rmse:2.69115\n",
+ "[2602]\tvalidation_0-rmse:2.69104\n",
+ "[2603]\tvalidation_0-rmse:2.69096\n",
+ "[2604]\tvalidation_0-rmse:2.69092\n",
+ "[2605]\tvalidation_0-rmse:2.69090\n",
+ "[2606]\tvalidation_0-rmse:2.69092\n",
+ "[2607]\tvalidation_0-rmse:2.69082\n",
+ "[2608]\tvalidation_0-rmse:2.69058\n",
+ "[2609]\tvalidation_0-rmse:2.69056\n",
+ "[2610]\tvalidation_0-rmse:2.69035\n",
+ "[2611]\tvalidation_0-rmse:2.69029\n",
+ "[2612]\tvalidation_0-rmse:2.69027\n",
+ "[2613]\tvalidation_0-rmse:2.69032\n",
+ "[2614]\tvalidation_0-rmse:2.69034\n",
+ "[2615]\tvalidation_0-rmse:2.69032\n",
+ "[2616]\tvalidation_0-rmse:2.69023\n",
+ "[2617]\tvalidation_0-rmse:2.69031\n",
+ "[2618]\tvalidation_0-rmse:2.69033\n",
+ "[2619]\tvalidation_0-rmse:2.69023\n",
+ "[2620]\tvalidation_0-rmse:2.69012\n",
+ "[2621]\tvalidation_0-rmse:2.69011\n",
+ "[2622]\tvalidation_0-rmse:2.69012\n",
+ "[2623]\tvalidation_0-rmse:2.69020\n",
+ "[2624]\tvalidation_0-rmse:2.69023\n",
+ "[2625]\tvalidation_0-rmse:2.69021\n",
+ "[2626]\tvalidation_0-rmse:2.69018\n",
+ "[2627]\tvalidation_0-rmse:2.69020\n",
+ "[2628]\tvalidation_0-rmse:2.69022\n",
+ "[2629]\tvalidation_0-rmse:2.69027\n",
+ "[2630]\tvalidation_0-rmse:2.69023\n",
+ "[2631]\tvalidation_0-rmse:2.68997\n",
+ "[2632]\tvalidation_0-rmse:2.68995\n",
+ "[2633]\tvalidation_0-rmse:2.68999\n",
+ "[2634]\tvalidation_0-rmse:2.68992\n",
+ "[2635]\tvalidation_0-rmse:2.68969\n",
+ "[2636]\tvalidation_0-rmse:2.68970\n",
+ "[2637]\tvalidation_0-rmse:2.68958\n",
+ "[2638]\tvalidation_0-rmse:2.68945\n",
+ "[2639]\tvalidation_0-rmse:2.68937\n",
+ "[2640]\tvalidation_0-rmse:2.68900\n",
+ "[2641]\tvalidation_0-rmse:2.68894\n",
+ "[2642]\tvalidation_0-rmse:2.68878\n",
+ "[2643]\tvalidation_0-rmse:2.68876\n",
+ "[2644]\tvalidation_0-rmse:2.68869\n",
+ "[2645]\tvalidation_0-rmse:2.68865\n",
+ "[2646]\tvalidation_0-rmse:2.68865\n",
+ "[2647]\tvalidation_0-rmse:2.68868\n",
+ "[2648]\tvalidation_0-rmse:2.68873\n",
+ "[2649]\tvalidation_0-rmse:2.68875\n",
+ "[2650]\tvalidation_0-rmse:2.68871\n",
+ "[2651]\tvalidation_0-rmse:2.68871\n",
+ "[2652]\tvalidation_0-rmse:2.68868\n",
+ "[2653]\tvalidation_0-rmse:2.68868\n",
+ "[2654]\tvalidation_0-rmse:2.68872\n",
+ "[2655]\tvalidation_0-rmse:2.68869\n",
+ "[2656]\tvalidation_0-rmse:2.68879\n",
+ "[2657]\tvalidation_0-rmse:2.68884\n",
+ "[2658]\tvalidation_0-rmse:2.68888\n",
+ "[2659]\tvalidation_0-rmse:2.68883\n",
+ "[2660]\tvalidation_0-rmse:2.68881\n",
+ "[2661]\tvalidation_0-rmse:2.68877\n",
+ "[2662]\tvalidation_0-rmse:2.68881\n",
+ "[2663]\tvalidation_0-rmse:2.68875\n",
+ "[2664]\tvalidation_0-rmse:2.68878\n",
+ "[2665]\tvalidation_0-rmse:2.68870\n",
+ "[2666]\tvalidation_0-rmse:2.68866\n",
+ "[2667]\tvalidation_0-rmse:2.68856\n",
+ "[2668]\tvalidation_0-rmse:2.68848\n",
+ "[2669]\tvalidation_0-rmse:2.68843\n",
+ "[2670]\tvalidation_0-rmse:2.68837\n",
+ "[2671]\tvalidation_0-rmse:2.68821\n",
+ "[2672]\tvalidation_0-rmse:2.68821\n",
+ "[2673]\tvalidation_0-rmse:2.68792\n",
+ "[2674]\tvalidation_0-rmse:2.68785\n",
+ "[2675]\tvalidation_0-rmse:2.68785\n",
+ "[2676]\tvalidation_0-rmse:2.68782\n",
+ "[2677]\tvalidation_0-rmse:2.68747\n",
+ "[2678]\tvalidation_0-rmse:2.68742\n",
+ "[2679]\tvalidation_0-rmse:2.68738\n",
+ "[2680]\tvalidation_0-rmse:2.68715\n",
+ "[2681]\tvalidation_0-rmse:2.68713\n",
+ "[2682]\tvalidation_0-rmse:2.68709\n",
+ "[2683]\tvalidation_0-rmse:2.68705\n",
+ "[2684]\tvalidation_0-rmse:2.68710\n",
+ "[2685]\tvalidation_0-rmse:2.68713\n",
+ "[2686]\tvalidation_0-rmse:2.68712\n",
+ "[2687]\tvalidation_0-rmse:2.68696\n",
+ "[2688]\tvalidation_0-rmse:2.68695\n",
+ "[2689]\tvalidation_0-rmse:2.68702\n",
+ "[2690]\tvalidation_0-rmse:2.68695\n",
+ "[2691]\tvalidation_0-rmse:2.68700\n",
+ "[2692]\tvalidation_0-rmse:2.68696\n",
+ "[2693]\tvalidation_0-rmse:2.68678\n",
+ "[2694]\tvalidation_0-rmse:2.68678\n",
+ "[2695]\tvalidation_0-rmse:2.68685\n",
+ "[2696]\tvalidation_0-rmse:2.68671\n",
+ "[2697]\tvalidation_0-rmse:2.68666\n",
+ "[2698]\tvalidation_0-rmse:2.68658\n",
+ "[2699]\tvalidation_0-rmse:2.68653\n",
+ "[2700]\tvalidation_0-rmse:2.68654\n",
+ "[2701]\tvalidation_0-rmse:2.68642\n",
+ "[2702]\tvalidation_0-rmse:2.68642\n",
+ "[2703]\tvalidation_0-rmse:2.68644\n",
+ "[2704]\tvalidation_0-rmse:2.68648\n",
+ "[2705]\tvalidation_0-rmse:2.68641\n",
+ "[2706]\tvalidation_0-rmse:2.68637\n",
+ "[2707]\tvalidation_0-rmse:2.68626\n",
+ "[2708]\tvalidation_0-rmse:2.68616\n",
+ "[2709]\tvalidation_0-rmse:2.68611\n",
+ "[2710]\tvalidation_0-rmse:2.68608\n",
+ "[2711]\tvalidation_0-rmse:2.68617\n",
+ "[2712]\tvalidation_0-rmse:2.68597\n",
+ "[2713]\tvalidation_0-rmse:2.68608\n",
+ "[2714]\tvalidation_0-rmse:2.68611\n",
+ "[2715]\tvalidation_0-rmse:2.68611\n",
+ "[2716]\tvalidation_0-rmse:2.68609\n",
+ "[2717]\tvalidation_0-rmse:2.68615\n",
+ "[2718]\tvalidation_0-rmse:2.68609\n",
+ "[2719]\tvalidation_0-rmse:2.68607\n",
+ "[2720]\tvalidation_0-rmse:2.68604\n",
+ "[2721]\tvalidation_0-rmse:2.68604\n",
+ "[2722]\tvalidation_0-rmse:2.68616\n",
+ "[2723]\tvalidation_0-rmse:2.68615\n",
+ "[2724]\tvalidation_0-rmse:2.68615\n",
+ "[2725]\tvalidation_0-rmse:2.68616\n",
+ "[2726]\tvalidation_0-rmse:2.68608\n",
+ "[2727]\tvalidation_0-rmse:2.68594\n",
+ "[2728]\tvalidation_0-rmse:2.68595\n",
+ "[2729]\tvalidation_0-rmse:2.68603\n",
+ "[2730]\tvalidation_0-rmse:2.68610\n",
+ "[2731]\tvalidation_0-rmse:2.68607\n",
+ "[2732]\tvalidation_0-rmse:2.68609\n",
+ "[2733]\tvalidation_0-rmse:2.68603\n",
+ "[2734]\tvalidation_0-rmse:2.68598\n",
+ "[2735]\tvalidation_0-rmse:2.68584\n",
+ "[2736]\tvalidation_0-rmse:2.68582\n",
+ "[2737]\tvalidation_0-rmse:2.68575\n",
+ "[2738]\tvalidation_0-rmse:2.68550\n",
+ "[2739]\tvalidation_0-rmse:2.68544\n",
+ "[2740]\tvalidation_0-rmse:2.68530\n",
+ "[2741]\tvalidation_0-rmse:2.68528\n",
+ "[2742]\tvalidation_0-rmse:2.68517\n",
+ "[2743]\tvalidation_0-rmse:2.68519\n",
+ "[2744]\tvalidation_0-rmse:2.68519\n",
+ "[2745]\tvalidation_0-rmse:2.68518\n",
+ "[2746]\tvalidation_0-rmse:2.68512\n",
+ "[2747]\tvalidation_0-rmse:2.68509\n",
+ "[2748]\tvalidation_0-rmse:2.68504\n",
+ "[2749]\tvalidation_0-rmse:2.68499\n",
+ "[2750]\tvalidation_0-rmse:2.68490\n",
+ "[2751]\tvalidation_0-rmse:2.68472\n",
+ "[2752]\tvalidation_0-rmse:2.68467\n",
+ "[2753]\tvalidation_0-rmse:2.68469\n",
+ "[2754]\tvalidation_0-rmse:2.68469\n",
+ "[2755]\tvalidation_0-rmse:2.68453\n",
+ "[2756]\tvalidation_0-rmse:2.68444\n",
+ "[2757]\tvalidation_0-rmse:2.68446\n",
+ "[2758]\tvalidation_0-rmse:2.68445\n",
+ "[2759]\tvalidation_0-rmse:2.68446\n",
+ "[2760]\tvalidation_0-rmse:2.68451\n",
+ "[2761]\tvalidation_0-rmse:2.68436\n",
+ "[2762]\tvalidation_0-rmse:2.68440\n",
+ "[2763]\tvalidation_0-rmse:2.68434\n",
+ "[2764]\tvalidation_0-rmse:2.68432\n",
+ "[2765]\tvalidation_0-rmse:2.68426\n",
+ "[2766]\tvalidation_0-rmse:2.68429\n",
+ "[2767]\tvalidation_0-rmse:2.68426\n",
+ "[2768]\tvalidation_0-rmse:2.68422\n",
+ "[2769]\tvalidation_0-rmse:2.68425\n",
+ "[2770]\tvalidation_0-rmse:2.68427\n",
+ "[2771]\tvalidation_0-rmse:2.68424\n",
+ "[2772]\tvalidation_0-rmse:2.68420\n",
+ "[2773]\tvalidation_0-rmse:2.68419\n",
+ "[2774]\tvalidation_0-rmse:2.68411\n",
+ "[2775]\tvalidation_0-rmse:2.68410\n",
+ "[2776]\tvalidation_0-rmse:2.68409\n",
+ "[2777]\tvalidation_0-rmse:2.68414\n",
+ "[2778]\tvalidation_0-rmse:2.68408\n",
+ "[2779]\tvalidation_0-rmse:2.68403\n",
+ "[2780]\tvalidation_0-rmse:2.68404\n",
+ "[2781]\tvalidation_0-rmse:2.68401\n",
+ "[2782]\tvalidation_0-rmse:2.68405\n",
+ "[2783]\tvalidation_0-rmse:2.68399\n",
+ "[2784]\tvalidation_0-rmse:2.68397\n",
+ "[2785]\tvalidation_0-rmse:2.68389\n",
+ "[2786]\tvalidation_0-rmse:2.68360\n",
+ "[2787]\tvalidation_0-rmse:2.68351\n",
+ "[2788]\tvalidation_0-rmse:2.68338\n",
+ "[2789]\tvalidation_0-rmse:2.68341\n",
+ "[2790]\tvalidation_0-rmse:2.68330\n",
+ "[2791]\tvalidation_0-rmse:2.68336\n",
+ "[2792]\tvalidation_0-rmse:2.68330\n",
+ "[2793]\tvalidation_0-rmse:2.68321\n",
+ "[2794]\tvalidation_0-rmse:2.68306\n",
+ "[2795]\tvalidation_0-rmse:2.68305\n",
+ "[2796]\tvalidation_0-rmse:2.68300\n",
+ "[2797]\tvalidation_0-rmse:2.68295\n",
+ "[2798]\tvalidation_0-rmse:2.68302\n",
+ "[2799]\tvalidation_0-rmse:2.68304\n",
+ "[2800]\tvalidation_0-rmse:2.68303\n",
+ "[2801]\tvalidation_0-rmse:2.68278\n",
+ "[2802]\tvalidation_0-rmse:2.68270\n",
+ "[2803]\tvalidation_0-rmse:2.68273\n",
+ "[2804]\tvalidation_0-rmse:2.68274\n",
+ "[2805]\tvalidation_0-rmse:2.68275\n",
+ "[2806]\tvalidation_0-rmse:2.68271\n",
+ "[2807]\tvalidation_0-rmse:2.68266\n",
+ "[2808]\tvalidation_0-rmse:2.68271\n",
+ "[2809]\tvalidation_0-rmse:2.68272\n",
+ "[2810]\tvalidation_0-rmse:2.68259\n",
+ "[2811]\tvalidation_0-rmse:2.68259\n",
+ "[2812]\tvalidation_0-rmse:2.68259\n",
+ "[2813]\tvalidation_0-rmse:2.68257\n",
+ "[2814]\tvalidation_0-rmse:2.68249\n",
+ "[2815]\tvalidation_0-rmse:2.68248\n",
+ "[2816]\tvalidation_0-rmse:2.68246\n",
+ "[2817]\tvalidation_0-rmse:2.68233\n",
+ "[2818]\tvalidation_0-rmse:2.68231\n",
+ "[2819]\tvalidation_0-rmse:2.68232\n",
+ "[2820]\tvalidation_0-rmse:2.68226\n",
+ "[2821]\tvalidation_0-rmse:2.68225\n",
+ "[2822]\tvalidation_0-rmse:2.68221\n",
+ "[2823]\tvalidation_0-rmse:2.68218\n",
+ "[2824]\tvalidation_0-rmse:2.68218\n",
+ "[2825]\tvalidation_0-rmse:2.68219\n",
+ "[2826]\tvalidation_0-rmse:2.68205\n",
+ "[2827]\tvalidation_0-rmse:2.68202\n",
+ "[2828]\tvalidation_0-rmse:2.68198\n",
+ "[2829]\tvalidation_0-rmse:2.68195\n",
+ "[2830]\tvalidation_0-rmse:2.68173\n",
+ "[2831]\tvalidation_0-rmse:2.68173\n",
+ "[2832]\tvalidation_0-rmse:2.68164\n",
+ "[2833]\tvalidation_0-rmse:2.68175\n",
+ "[2834]\tvalidation_0-rmse:2.68178\n",
+ "[2835]\tvalidation_0-rmse:2.68160\n",
+ "[2836]\tvalidation_0-rmse:2.68151\n",
+ "[2837]\tvalidation_0-rmse:2.68152\n",
+ "[2838]\tvalidation_0-rmse:2.68151\n",
+ "[2839]\tvalidation_0-rmse:2.68146\n",
+ "[2840]\tvalidation_0-rmse:2.68148\n",
+ "[2841]\tvalidation_0-rmse:2.68136\n",
+ "[2842]\tvalidation_0-rmse:2.68135\n",
+ "[2843]\tvalidation_0-rmse:2.68136\n",
+ "[2844]\tvalidation_0-rmse:2.68132\n",
+ "[2845]\tvalidation_0-rmse:2.68137\n",
+ "[2846]\tvalidation_0-rmse:2.68112\n",
+ "[2847]\tvalidation_0-rmse:2.68101\n",
+ "[2848]\tvalidation_0-rmse:2.68081\n",
+ "[2849]\tvalidation_0-rmse:2.68074\n",
+ "[2850]\tvalidation_0-rmse:2.68060\n",
+ "[2851]\tvalidation_0-rmse:2.68067\n",
+ "[2852]\tvalidation_0-rmse:2.68053\n",
+ "[2853]\tvalidation_0-rmse:2.68055\n",
+ "[2854]\tvalidation_0-rmse:2.68050\n",
+ "[2855]\tvalidation_0-rmse:2.68046\n",
+ "[2856]\tvalidation_0-rmse:2.68041\n",
+ "[2857]\tvalidation_0-rmse:2.68043\n",
+ "[2858]\tvalidation_0-rmse:2.68044\n",
+ "[2859]\tvalidation_0-rmse:2.68022\n",
+ "[2860]\tvalidation_0-rmse:2.68023\n",
+ "[2861]\tvalidation_0-rmse:2.68022\n",
+ "[2862]\tvalidation_0-rmse:2.67987\n",
+ "[2863]\tvalidation_0-rmse:2.67986\n",
+ "[2864]\tvalidation_0-rmse:2.67988\n",
+ "[2865]\tvalidation_0-rmse:2.67978\n",
+ "[2866]\tvalidation_0-rmse:2.67969\n",
+ "[2867]\tvalidation_0-rmse:2.67969\n",
+ "[2868]\tvalidation_0-rmse:2.67967\n",
+ "[2869]\tvalidation_0-rmse:2.67969\n",
+ "[2870]\tvalidation_0-rmse:2.67969\n",
+ "[2871]\tvalidation_0-rmse:2.67965\n",
+ "[2872]\tvalidation_0-rmse:2.67964\n",
+ "[2873]\tvalidation_0-rmse:2.67968\n",
+ "[2874]\tvalidation_0-rmse:2.67963\n",
+ "[2875]\tvalidation_0-rmse:2.67963\n",
+ "[2876]\tvalidation_0-rmse:2.67969\n",
+ "[2877]\tvalidation_0-rmse:2.67973\n",
+ "[2878]\tvalidation_0-rmse:2.67966\n",
+ "[2879]\tvalidation_0-rmse:2.67965\n",
+ "[2880]\tvalidation_0-rmse:2.67952\n",
+ "[2881]\tvalidation_0-rmse:2.67954\n",
+ "[2882]\tvalidation_0-rmse:2.67955\n",
+ "[2883]\tvalidation_0-rmse:2.67959\n",
+ "[2884]\tvalidation_0-rmse:2.67960\n",
+ "[2885]\tvalidation_0-rmse:2.67949\n",
+ "[2886]\tvalidation_0-rmse:2.67951\n",
+ "[2887]\tvalidation_0-rmse:2.67955\n",
+ "[2888]\tvalidation_0-rmse:2.67937\n",
+ "[2889]\tvalidation_0-rmse:2.67936\n",
+ "[2890]\tvalidation_0-rmse:2.67928\n",
+ "[2891]\tvalidation_0-rmse:2.67927\n",
+ "[2892]\tvalidation_0-rmse:2.67923\n",
+ "[2893]\tvalidation_0-rmse:2.67925\n",
+ "[2894]\tvalidation_0-rmse:2.67917\n",
+ "[2895]\tvalidation_0-rmse:2.67894\n",
+ "[2896]\tvalidation_0-rmse:2.67880\n",
+ "[2897]\tvalidation_0-rmse:2.67881\n",
+ "[2898]\tvalidation_0-rmse:2.67876\n",
+ "[2899]\tvalidation_0-rmse:2.67875\n",
+ "[2900]\tvalidation_0-rmse:2.67875\n",
+ "[2901]\tvalidation_0-rmse:2.67874\n",
+ "[2902]\tvalidation_0-rmse:2.67878\n",
+ "[2903]\tvalidation_0-rmse:2.67875\n",
+ "[2904]\tvalidation_0-rmse:2.67877\n",
+ "[2905]\tvalidation_0-rmse:2.67880\n",
+ "[2906]\tvalidation_0-rmse:2.67878\n",
+ "[2907]\tvalidation_0-rmse:2.67880\n",
+ "[2908]\tvalidation_0-rmse:2.67863\n",
+ "[2909]\tvalidation_0-rmse:2.67866\n",
+ "[2910]\tvalidation_0-rmse:2.67866\n",
+ "[2911]\tvalidation_0-rmse:2.67868\n",
+ "[2912]\tvalidation_0-rmse:2.67871\n",
+ "[2913]\tvalidation_0-rmse:2.67874\n",
+ "[2914]\tvalidation_0-rmse:2.67874\n",
+ "[2915]\tvalidation_0-rmse:2.67874\n",
+ "[2916]\tvalidation_0-rmse:2.67879\n",
+ "[2917]\tvalidation_0-rmse:2.67884\n",
+ "[2918]\tvalidation_0-rmse:2.67889\n",
+ "[2919]\tvalidation_0-rmse:2.67884\n",
+ "[2920]\tvalidation_0-rmse:2.67876\n",
+ "[2921]\tvalidation_0-rmse:2.67882\n",
+ "[2922]\tvalidation_0-rmse:2.67880\n",
+ "[2923]\tvalidation_0-rmse:2.67886\n",
+ "[2924]\tvalidation_0-rmse:2.67863\n",
+ "[2925]\tvalidation_0-rmse:2.67844\n",
+ "[2926]\tvalidation_0-rmse:2.67842\n",
+ "[2927]\tvalidation_0-rmse:2.67840\n",
+ "[2928]\tvalidation_0-rmse:2.67840\n",
+ "[2929]\tvalidation_0-rmse:2.67836\n",
+ "[2930]\tvalidation_0-rmse:2.67837\n",
+ "[2931]\tvalidation_0-rmse:2.67832\n",
+ "[2932]\tvalidation_0-rmse:2.67825\n",
+ "[2933]\tvalidation_0-rmse:2.67824\n",
+ "[2934]\tvalidation_0-rmse:2.67822\n",
+ "[2935]\tvalidation_0-rmse:2.67810\n",
+ "[2936]\tvalidation_0-rmse:2.67806\n",
+ "[2937]\tvalidation_0-rmse:2.67805\n",
+ "[2938]\tvalidation_0-rmse:2.67801\n",
+ "[2939]\tvalidation_0-rmse:2.67785\n",
+ "[2940]\tvalidation_0-rmse:2.67773\n",
+ "[2941]\tvalidation_0-rmse:2.67773\n",
+ "[2942]\tvalidation_0-rmse:2.67778\n",
+ "[2943]\tvalidation_0-rmse:2.67778\n",
+ "[2944]\tvalidation_0-rmse:2.67785\n",
+ "[2945]\tvalidation_0-rmse:2.67772\n",
+ "[2946]\tvalidation_0-rmse:2.67770\n",
+ "[2947]\tvalidation_0-rmse:2.67767\n",
+ "[2948]\tvalidation_0-rmse:2.67768\n",
+ "[2949]\tvalidation_0-rmse:2.67770\n",
+ "[2950]\tvalidation_0-rmse:2.67758\n",
+ "[2951]\tvalidation_0-rmse:2.67760\n",
+ "[2952]\tvalidation_0-rmse:2.67756\n",
+ "[2953]\tvalidation_0-rmse:2.67761\n",
+ "[2954]\tvalidation_0-rmse:2.67758\n",
+ "[2955]\tvalidation_0-rmse:2.67760\n",
+ "[2956]\tvalidation_0-rmse:2.67766\n",
+ "[2957]\tvalidation_0-rmse:2.67770\n",
+ "[2958]\tvalidation_0-rmse:2.67767\n",
+ "[2959]\tvalidation_0-rmse:2.67761\n",
+ "[2960]\tvalidation_0-rmse:2.67766\n",
+ "[2961]\tvalidation_0-rmse:2.67756\n",
+ "[2962]\tvalidation_0-rmse:2.67750\n",
+ "[2963]\tvalidation_0-rmse:2.67743\n",
+ "[2964]\tvalidation_0-rmse:2.67733\n",
+ "[2965]\tvalidation_0-rmse:2.67735\n",
+ "[2966]\tvalidation_0-rmse:2.67730\n",
+ "[2967]\tvalidation_0-rmse:2.67716\n",
+ "[2968]\tvalidation_0-rmse:2.67691\n",
+ "[2969]\tvalidation_0-rmse:2.67691\n",
+ "[2970]\tvalidation_0-rmse:2.67683\n",
+ "[2971]\tvalidation_0-rmse:2.67680\n",
+ "[2972]\tvalidation_0-rmse:2.67669\n",
+ "[2973]\tvalidation_0-rmse:2.67660\n",
+ "[2974]\tvalidation_0-rmse:2.67657\n",
+ "[2975]\tvalidation_0-rmse:2.67655\n",
+ "[2976]\tvalidation_0-rmse:2.67647\n",
+ "[2977]\tvalidation_0-rmse:2.67644\n",
+ "[2978]\tvalidation_0-rmse:2.67639\n",
+ "[2979]\tvalidation_0-rmse:2.67640\n",
+ "[2980]\tvalidation_0-rmse:2.67644\n",
+ "[2981]\tvalidation_0-rmse:2.67636\n",
+ "[2982]\tvalidation_0-rmse:2.67634\n",
+ "[2983]\tvalidation_0-rmse:2.67630\n",
+ "[2984]\tvalidation_0-rmse:2.67631\n",
+ "[2985]\tvalidation_0-rmse:2.67634\n",
+ "[2986]\tvalidation_0-rmse:2.67637\n",
+ "[2987]\tvalidation_0-rmse:2.67632\n",
+ "[2988]\tvalidation_0-rmse:2.67636\n",
+ "[2989]\tvalidation_0-rmse:2.67639\n",
+ "[2990]\tvalidation_0-rmse:2.67628\n",
+ "[2991]\tvalidation_0-rmse:2.67617\n",
+ "[2992]\tvalidation_0-rmse:2.67621\n",
+ "[2993]\tvalidation_0-rmse:2.67603\n",
+ "[2994]\tvalidation_0-rmse:2.67598\n",
+ "[2995]\tvalidation_0-rmse:2.67599\n",
+ "[2996]\tvalidation_0-rmse:2.67597\n",
+ "[2997]\tvalidation_0-rmse:2.67588\n",
+ "[2998]\tvalidation_0-rmse:2.67568\n",
+ "[2999]\tvalidation_0-rmse:2.67545\n",
+ "[3000]\tvalidation_0-rmse:2.67526\n",
+ "[3001]\tvalidation_0-rmse:2.67504\n",
+ "[3002]\tvalidation_0-rmse:2.67497\n",
+ "[3003]\tvalidation_0-rmse:2.67496\n",
+ "[3004]\tvalidation_0-rmse:2.67492\n",
+ "[3005]\tvalidation_0-rmse:2.67474\n",
+ "[3006]\tvalidation_0-rmse:2.67470\n",
+ "[3007]\tvalidation_0-rmse:2.67461\n",
+ "[3008]\tvalidation_0-rmse:2.67454\n",
+ "[3009]\tvalidation_0-rmse:2.67446\n",
+ "[3010]\tvalidation_0-rmse:2.67443\n",
+ "[3011]\tvalidation_0-rmse:2.67438\n",
+ "[3012]\tvalidation_0-rmse:2.67427\n",
+ "[3013]\tvalidation_0-rmse:2.67427\n",
+ "[3014]\tvalidation_0-rmse:2.67428\n",
+ "[3015]\tvalidation_0-rmse:2.67429\n",
+ "[3016]\tvalidation_0-rmse:2.67428\n",
+ "[3017]\tvalidation_0-rmse:2.67417\n",
+ "[3018]\tvalidation_0-rmse:2.67408\n",
+ "[3019]\tvalidation_0-rmse:2.67402\n",
+ "[3020]\tvalidation_0-rmse:2.67390\n",
+ "[3021]\tvalidation_0-rmse:2.67387\n",
+ "[3022]\tvalidation_0-rmse:2.67379\n",
+ "[3023]\tvalidation_0-rmse:2.67380\n",
+ "[3024]\tvalidation_0-rmse:2.67378\n",
+ "[3025]\tvalidation_0-rmse:2.67355\n",
+ "[3026]\tvalidation_0-rmse:2.67347\n",
+ "[3027]\tvalidation_0-rmse:2.67344\n",
+ "[3028]\tvalidation_0-rmse:2.67320\n",
+ "[3029]\tvalidation_0-rmse:2.67307\n",
+ "[3030]\tvalidation_0-rmse:2.67299\n",
+ "[3031]\tvalidation_0-rmse:2.67301\n",
+ "[3032]\tvalidation_0-rmse:2.67287\n",
+ "[3033]\tvalidation_0-rmse:2.67283\n",
+ "[3034]\tvalidation_0-rmse:2.67285\n",
+ "[3035]\tvalidation_0-rmse:2.67287\n",
+ "[3036]\tvalidation_0-rmse:2.67284\n",
+ "[3037]\tvalidation_0-rmse:2.67288\n",
+ "[3038]\tvalidation_0-rmse:2.67294\n",
+ "[3039]\tvalidation_0-rmse:2.67291\n",
+ "[3040]\tvalidation_0-rmse:2.67293\n",
+ "[3041]\tvalidation_0-rmse:2.67292\n",
+ "[3042]\tvalidation_0-rmse:2.67272\n",
+ "[3043]\tvalidation_0-rmse:2.67270\n",
+ "[3044]\tvalidation_0-rmse:2.67273\n",
+ "[3045]\tvalidation_0-rmse:2.67272\n",
+ "[3046]\tvalidation_0-rmse:2.67268\n",
+ "[3047]\tvalidation_0-rmse:2.67264\n",
+ "[3048]\tvalidation_0-rmse:2.67268\n",
+ "[3049]\tvalidation_0-rmse:2.67260\n",
+ "[3050]\tvalidation_0-rmse:2.67247\n",
+ "[3051]\tvalidation_0-rmse:2.67242\n",
+ "[3052]\tvalidation_0-rmse:2.67242\n",
+ "[3053]\tvalidation_0-rmse:2.67234\n",
+ "[3054]\tvalidation_0-rmse:2.67228\n",
+ "[3055]\tvalidation_0-rmse:2.67233\n",
+ "[3056]\tvalidation_0-rmse:2.67227\n",
+ "[3057]\tvalidation_0-rmse:2.67218\n",
+ "[3058]\tvalidation_0-rmse:2.67223\n",
+ "[3059]\tvalidation_0-rmse:2.67207\n",
+ "[3060]\tvalidation_0-rmse:2.67212\n",
+ "[3061]\tvalidation_0-rmse:2.67199\n",
+ "[3062]\tvalidation_0-rmse:2.67200\n",
+ "[3063]\tvalidation_0-rmse:2.67193\n",
+ "[3064]\tvalidation_0-rmse:2.67196\n",
+ "[3065]\tvalidation_0-rmse:2.67204\n",
+ "[3066]\tvalidation_0-rmse:2.67177\n",
+ "[3067]\tvalidation_0-rmse:2.67178\n",
+ "[3068]\tvalidation_0-rmse:2.67168\n",
+ "[3069]\tvalidation_0-rmse:2.67173\n",
+ "[3070]\tvalidation_0-rmse:2.67157\n",
+ "[3071]\tvalidation_0-rmse:2.67148\n",
+ "[3072]\tvalidation_0-rmse:2.67147\n",
+ "[3073]\tvalidation_0-rmse:2.67144\n",
+ "[3074]\tvalidation_0-rmse:2.67135\n",
+ "[3075]\tvalidation_0-rmse:2.67130\n",
+ "[3076]\tvalidation_0-rmse:2.67117\n",
+ "[3077]\tvalidation_0-rmse:2.67117\n",
+ "[3078]\tvalidation_0-rmse:2.67112\n",
+ "[3079]\tvalidation_0-rmse:2.67110\n",
+ "[3080]\tvalidation_0-rmse:2.67114\n",
+ "[3081]\tvalidation_0-rmse:2.67114\n",
+ "[3082]\tvalidation_0-rmse:2.67121\n",
+ "[3083]\tvalidation_0-rmse:2.67119\n",
+ "[3084]\tvalidation_0-rmse:2.67119\n",
+ "[3085]\tvalidation_0-rmse:2.67100\n",
+ "[3086]\tvalidation_0-rmse:2.67101\n",
+ "[3087]\tvalidation_0-rmse:2.67103\n",
+ "[3088]\tvalidation_0-rmse:2.67090\n",
+ "[3089]\tvalidation_0-rmse:2.67085\n",
+ "[3090]\tvalidation_0-rmse:2.67085\n",
+ "[3091]\tvalidation_0-rmse:2.67085\n",
+ "[3092]\tvalidation_0-rmse:2.67091\n",
+ "[3093]\tvalidation_0-rmse:2.67094\n",
+ "[3094]\tvalidation_0-rmse:2.67095\n",
+ "[3095]\tvalidation_0-rmse:2.67096\n",
+ "[3096]\tvalidation_0-rmse:2.67097\n",
+ "[3097]\tvalidation_0-rmse:2.67088\n",
+ "[3098]\tvalidation_0-rmse:2.67086\n",
+ "[3099]\tvalidation_0-rmse:2.67080\n",
+ "[3100]\tvalidation_0-rmse:2.67071\n",
+ "[3101]\tvalidation_0-rmse:2.67064\n",
+ "[3102]\tvalidation_0-rmse:2.67062\n",
+ "[3103]\tvalidation_0-rmse:2.67055\n",
+ "[3104]\tvalidation_0-rmse:2.67042\n",
+ "[3105]\tvalidation_0-rmse:2.67044\n",
+ "[3106]\tvalidation_0-rmse:2.67041\n",
+ "[3107]\tvalidation_0-rmse:2.67034\n",
+ "[3108]\tvalidation_0-rmse:2.67028\n",
+ "[3109]\tvalidation_0-rmse:2.67016\n",
+ "[3110]\tvalidation_0-rmse:2.67011\n",
+ "[3111]\tvalidation_0-rmse:2.67009\n",
+ "[3112]\tvalidation_0-rmse:2.66999\n",
+ "[3113]\tvalidation_0-rmse:2.66989\n",
+ "[3114]\tvalidation_0-rmse:2.66990\n",
+ "[3115]\tvalidation_0-rmse:2.66986\n",
+ "[3116]\tvalidation_0-rmse:2.66988\n",
+ "[3117]\tvalidation_0-rmse:2.66990\n",
+ "[3118]\tvalidation_0-rmse:2.66986\n",
+ "[3119]\tvalidation_0-rmse:2.66988\n",
+ "[3120]\tvalidation_0-rmse:2.66990\n",
+ "[3121]\tvalidation_0-rmse:2.66993\n",
+ "[3122]\tvalidation_0-rmse:2.66981\n",
+ "[3123]\tvalidation_0-rmse:2.66977\n",
+ "[3124]\tvalidation_0-rmse:2.66973\n",
+ "[3125]\tvalidation_0-rmse:2.66973\n",
+ "[3126]\tvalidation_0-rmse:2.66979\n",
+ "[3127]\tvalidation_0-rmse:2.66978\n",
+ "[3128]\tvalidation_0-rmse:2.66972\n",
+ "[3129]\tvalidation_0-rmse:2.66966\n",
+ "[3130]\tvalidation_0-rmse:2.66971\n",
+ "[3131]\tvalidation_0-rmse:2.66969\n",
+ "[3132]\tvalidation_0-rmse:2.66972\n",
+ "[3133]\tvalidation_0-rmse:2.66948\n",
+ "[3134]\tvalidation_0-rmse:2.66946\n",
+ "[3135]\tvalidation_0-rmse:2.66927\n",
+ "[3136]\tvalidation_0-rmse:2.66924\n",
+ "[3137]\tvalidation_0-rmse:2.66924\n",
+ "[3138]\tvalidation_0-rmse:2.66926\n",
+ "[3139]\tvalidation_0-rmse:2.66908\n",
+ "[3140]\tvalidation_0-rmse:2.66892\n",
+ "[3141]\tvalidation_0-rmse:2.66892\n",
+ "[3142]\tvalidation_0-rmse:2.66897\n",
+ "[3143]\tvalidation_0-rmse:2.66893\n",
+ "[3144]\tvalidation_0-rmse:2.66891\n",
+ "[3145]\tvalidation_0-rmse:2.66893\n",
+ "[3146]\tvalidation_0-rmse:2.66896\n",
+ "[3147]\tvalidation_0-rmse:2.66901\n",
+ "[3148]\tvalidation_0-rmse:2.66899\n",
+ "[3149]\tvalidation_0-rmse:2.66890\n",
+ "[3150]\tvalidation_0-rmse:2.66876\n",
+ "[3151]\tvalidation_0-rmse:2.66872\n",
+ "[3152]\tvalidation_0-rmse:2.66867\n",
+ "[3153]\tvalidation_0-rmse:2.66859\n",
+ "[3154]\tvalidation_0-rmse:2.66860\n",
+ "[3155]\tvalidation_0-rmse:2.66841\n",
+ "[3156]\tvalidation_0-rmse:2.66838\n",
+ "[3157]\tvalidation_0-rmse:2.66833\n",
+ "[3158]\tvalidation_0-rmse:2.66832\n",
+ "[3159]\tvalidation_0-rmse:2.66837\n",
+ "[3160]\tvalidation_0-rmse:2.66844\n",
+ "[3161]\tvalidation_0-rmse:2.66846\n",
+ "[3162]\tvalidation_0-rmse:2.66843\n",
+ "[3163]\tvalidation_0-rmse:2.66852\n",
+ "[3164]\tvalidation_0-rmse:2.66849\n",
+ "[3165]\tvalidation_0-rmse:2.66850\n",
+ "[3166]\tvalidation_0-rmse:2.66835\n",
+ "[3167]\tvalidation_0-rmse:2.66835\n",
+ "[3168]\tvalidation_0-rmse:2.66840\n",
+ "[3169]\tvalidation_0-rmse:2.66841\n",
+ "[3170]\tvalidation_0-rmse:2.66836\n",
+ "[3171]\tvalidation_0-rmse:2.66835\n",
+ "[3172]\tvalidation_0-rmse:2.66834\n",
+ "[3173]\tvalidation_0-rmse:2.66810\n",
+ "[3174]\tvalidation_0-rmse:2.66789\n",
+ "[3175]\tvalidation_0-rmse:2.66789\n",
+ "[3176]\tvalidation_0-rmse:2.66788\n",
+ "[3177]\tvalidation_0-rmse:2.66769\n",
+ "[3178]\tvalidation_0-rmse:2.66765\n",
+ "[3179]\tvalidation_0-rmse:2.66770\n",
+ "[3180]\tvalidation_0-rmse:2.66765\n",
+ "[3181]\tvalidation_0-rmse:2.66761\n",
+ "[3182]\tvalidation_0-rmse:2.66750\n",
+ "[3183]\tvalidation_0-rmse:2.66740\n",
+ "[3184]\tvalidation_0-rmse:2.66740\n",
+ "[3185]\tvalidation_0-rmse:2.66744\n",
+ "[3186]\tvalidation_0-rmse:2.66740\n",
+ "[3187]\tvalidation_0-rmse:2.66738\n",
+ "[3188]\tvalidation_0-rmse:2.66737\n",
+ "[3189]\tvalidation_0-rmse:2.66739\n",
+ "[3190]\tvalidation_0-rmse:2.66743\n",
+ "[3191]\tvalidation_0-rmse:2.66745\n",
+ "[3192]\tvalidation_0-rmse:2.66749\n",
+ "[3193]\tvalidation_0-rmse:2.66749\n",
+ "[3194]\tvalidation_0-rmse:2.66753\n",
+ "[3195]\tvalidation_0-rmse:2.66752\n",
+ "[3196]\tvalidation_0-rmse:2.66746\n",
+ "[3197]\tvalidation_0-rmse:2.66748\n",
+ "[3198]\tvalidation_0-rmse:2.66742\n",
+ "[3199]\tvalidation_0-rmse:2.66742\n",
+ "[3200]\tvalidation_0-rmse:2.66742\n",
+ "[3201]\tvalidation_0-rmse:2.66739\n",
+ "[3202]\tvalidation_0-rmse:2.66732\n",
+ "[3203]\tvalidation_0-rmse:2.66731\n",
+ "[3204]\tvalidation_0-rmse:2.66729\n",
+ "[3205]\tvalidation_0-rmse:2.66726\n",
+ "[3206]\tvalidation_0-rmse:2.66723\n",
+ "[3207]\tvalidation_0-rmse:2.66719\n",
+ "[3208]\tvalidation_0-rmse:2.66715\n",
+ "[3209]\tvalidation_0-rmse:2.66717\n",
+ "[3210]\tvalidation_0-rmse:2.66711\n",
+ "[3211]\tvalidation_0-rmse:2.66709\n",
+ "[3212]\tvalidation_0-rmse:2.66706\n",
+ "[3213]\tvalidation_0-rmse:2.66703\n",
+ "[3214]\tvalidation_0-rmse:2.66693\n",
+ "[3215]\tvalidation_0-rmse:2.66681\n",
+ "[3216]\tvalidation_0-rmse:2.66685\n",
+ "[3217]\tvalidation_0-rmse:2.66677\n",
+ "[3218]\tvalidation_0-rmse:2.66673\n",
+ "[3219]\tvalidation_0-rmse:2.66662\n",
+ "[3220]\tvalidation_0-rmse:2.66662\n",
+ "[3221]\tvalidation_0-rmse:2.66669\n",
+ "[3222]\tvalidation_0-rmse:2.66663\n",
+ "[3223]\tvalidation_0-rmse:2.66673\n",
+ "[3224]\tvalidation_0-rmse:2.66667\n",
+ "[3225]\tvalidation_0-rmse:2.66668\n",
+ "[3226]\tvalidation_0-rmse:2.66667\n",
+ "[3227]\tvalidation_0-rmse:2.66650\n",
+ "[3228]\tvalidation_0-rmse:2.66643\n",
+ "[3229]\tvalidation_0-rmse:2.66640\n",
+ "[3230]\tvalidation_0-rmse:2.66631\n",
+ "[3231]\tvalidation_0-rmse:2.66635\n",
+ "[3232]\tvalidation_0-rmse:2.66637\n",
+ "[3233]\tvalidation_0-rmse:2.66630\n",
+ "[3234]\tvalidation_0-rmse:2.66618\n",
+ "[3235]\tvalidation_0-rmse:2.66605\n",
+ "[3236]\tvalidation_0-rmse:2.66613\n",
+ "[3237]\tvalidation_0-rmse:2.66599\n",
+ "[3238]\tvalidation_0-rmse:2.66602\n",
+ "[3239]\tvalidation_0-rmse:2.66585\n",
+ "[3240]\tvalidation_0-rmse:2.66582\n",
+ "[3241]\tvalidation_0-rmse:2.66582\n",
+ "[3242]\tvalidation_0-rmse:2.66568\n",
+ "[3243]\tvalidation_0-rmse:2.66569\n",
+ "[3244]\tvalidation_0-rmse:2.66561\n",
+ "[3245]\tvalidation_0-rmse:2.66546\n",
+ "[3246]\tvalidation_0-rmse:2.66550\n",
+ "[3247]\tvalidation_0-rmse:2.66549\n",
+ "[3248]\tvalidation_0-rmse:2.66541\n",
+ "[3249]\tvalidation_0-rmse:2.66537\n",
+ "[3250]\tvalidation_0-rmse:2.66530\n",
+ "[3251]\tvalidation_0-rmse:2.66529\n",
+ "[3252]\tvalidation_0-rmse:2.66524\n",
+ "[3253]\tvalidation_0-rmse:2.66523\n",
+ "[3254]\tvalidation_0-rmse:2.66503\n",
+ "[3255]\tvalidation_0-rmse:2.66497\n",
+ "[3256]\tvalidation_0-rmse:2.66486\n",
+ "[3257]\tvalidation_0-rmse:2.66482\n",
+ "[3258]\tvalidation_0-rmse:2.66478\n",
+ "[3259]\tvalidation_0-rmse:2.66473\n",
+ "[3260]\tvalidation_0-rmse:2.66461\n",
+ "[3261]\tvalidation_0-rmse:2.66448\n",
+ "[3262]\tvalidation_0-rmse:2.66441\n",
+ "[3263]\tvalidation_0-rmse:2.66448\n",
+ "[3264]\tvalidation_0-rmse:2.66451\n",
+ "[3265]\tvalidation_0-rmse:2.66450\n",
+ "[3266]\tvalidation_0-rmse:2.66451\n",
+ "[3267]\tvalidation_0-rmse:2.66443\n",
+ "[3268]\tvalidation_0-rmse:2.66448\n",
+ "[3269]\tvalidation_0-rmse:2.66454\n",
+ "[3270]\tvalidation_0-rmse:2.66455\n",
+ "[3271]\tvalidation_0-rmse:2.66456\n",
+ "[3272]\tvalidation_0-rmse:2.66452\n",
+ "[3273]\tvalidation_0-rmse:2.66451\n",
+ "[3274]\tvalidation_0-rmse:2.66442\n",
+ "[3275]\tvalidation_0-rmse:2.66441\n",
+ "[3276]\tvalidation_0-rmse:2.66440\n",
+ "[3277]\tvalidation_0-rmse:2.66435\n",
+ "[3278]\tvalidation_0-rmse:2.66438\n",
+ "[3279]\tvalidation_0-rmse:2.66441\n",
+ "[3280]\tvalidation_0-rmse:2.66437\n",
+ "[3281]\tvalidation_0-rmse:2.66434\n",
+ "[3282]\tvalidation_0-rmse:2.66407\n",
+ "[3283]\tvalidation_0-rmse:2.66391\n",
+ "[3284]\tvalidation_0-rmse:2.66387\n",
+ "[3285]\tvalidation_0-rmse:2.66384\n",
+ "[3286]\tvalidation_0-rmse:2.66387\n",
+ "[3287]\tvalidation_0-rmse:2.66387\n",
+ "[3288]\tvalidation_0-rmse:2.66379\n",
+ "[3289]\tvalidation_0-rmse:2.66380\n",
+ "[3290]\tvalidation_0-rmse:2.66382\n",
+ "[3291]\tvalidation_0-rmse:2.66380\n",
+ "[3292]\tvalidation_0-rmse:2.66373\n",
+ "[3293]\tvalidation_0-rmse:2.66372\n",
+ "[3294]\tvalidation_0-rmse:2.66373\n",
+ "[3295]\tvalidation_0-rmse:2.66374\n",
+ "[3296]\tvalidation_0-rmse:2.66376\n",
+ "[3297]\tvalidation_0-rmse:2.66372\n",
+ "[3298]\tvalidation_0-rmse:2.66373\n",
+ "[3299]\tvalidation_0-rmse:2.66372\n",
+ "[3300]\tvalidation_0-rmse:2.66372\n",
+ "[3301]\tvalidation_0-rmse:2.66364\n",
+ "[3302]\tvalidation_0-rmse:2.66361\n",
+ "[3303]\tvalidation_0-rmse:2.66357\n",
+ "[3304]\tvalidation_0-rmse:2.66334\n",
+ "[3305]\tvalidation_0-rmse:2.66321\n",
+ "[3306]\tvalidation_0-rmse:2.66317\n",
+ "[3307]\tvalidation_0-rmse:2.66313\n",
+ "[3308]\tvalidation_0-rmse:2.66307\n",
+ "[3309]\tvalidation_0-rmse:2.66297\n",
+ "[3310]\tvalidation_0-rmse:2.66299\n",
+ "[3311]\tvalidation_0-rmse:2.66288\n",
+ "[3312]\tvalidation_0-rmse:2.66283\n",
+ "[3313]\tvalidation_0-rmse:2.66285\n",
+ "[3314]\tvalidation_0-rmse:2.66264\n",
+ "[3315]\tvalidation_0-rmse:2.66262\n",
+ "[3316]\tvalidation_0-rmse:2.66264\n",
+ "[3317]\tvalidation_0-rmse:2.66270\n",
+ "[3318]\tvalidation_0-rmse:2.66271\n",
+ "[3319]\tvalidation_0-rmse:2.66267\n",
+ "[3320]\tvalidation_0-rmse:2.66261\n",
+ "[3321]\tvalidation_0-rmse:2.66256\n",
+ "[3322]\tvalidation_0-rmse:2.66253\n",
+ "[3323]\tvalidation_0-rmse:2.66246\n",
+ "[3324]\tvalidation_0-rmse:2.66248\n",
+ "[3325]\tvalidation_0-rmse:2.66229\n",
+ "[3326]\tvalidation_0-rmse:2.66229\n",
+ "[3327]\tvalidation_0-rmse:2.66220\n",
+ "[3328]\tvalidation_0-rmse:2.66227\n",
+ "[3329]\tvalidation_0-rmse:2.66228\n",
+ "[3330]\tvalidation_0-rmse:2.66231\n",
+ "[3331]\tvalidation_0-rmse:2.66226\n",
+ "[3332]\tvalidation_0-rmse:2.66222\n",
+ "[3333]\tvalidation_0-rmse:2.66208\n",
+ "[3334]\tvalidation_0-rmse:2.66203\n",
+ "[3335]\tvalidation_0-rmse:2.66206\n",
+ "[3336]\tvalidation_0-rmse:2.66206\n",
+ "[3337]\tvalidation_0-rmse:2.66196\n",
+ "[3338]\tvalidation_0-rmse:2.66200\n",
+ "[3339]\tvalidation_0-rmse:2.66186\n",
+ "[3340]\tvalidation_0-rmse:2.66182\n",
+ "[3341]\tvalidation_0-rmse:2.66198\n",
+ "[3342]\tvalidation_0-rmse:2.66204\n",
+ "[3343]\tvalidation_0-rmse:2.66204\n",
+ "[3344]\tvalidation_0-rmse:2.66202\n",
+ "[3345]\tvalidation_0-rmse:2.66196\n",
+ "[3346]\tvalidation_0-rmse:2.66179\n",
+ "[3347]\tvalidation_0-rmse:2.66181\n",
+ "[3348]\tvalidation_0-rmse:2.66184\n",
+ "[3349]\tvalidation_0-rmse:2.66182\n",
+ "[3350]\tvalidation_0-rmse:2.66194\n",
+ "[3351]\tvalidation_0-rmse:2.66195\n",
+ "[3352]\tvalidation_0-rmse:2.66199\n",
+ "[3353]\tvalidation_0-rmse:2.66199\n",
+ "[3354]\tvalidation_0-rmse:2.66204\n",
+ "[3355]\tvalidation_0-rmse:2.66209\n",
+ "[3356]\tvalidation_0-rmse:2.66193\n",
+ "[3357]\tvalidation_0-rmse:2.66195\n",
+ "[3358]\tvalidation_0-rmse:2.66190\n",
+ "[3359]\tvalidation_0-rmse:2.66185\n",
+ "[3360]\tvalidation_0-rmse:2.66177\n",
+ "[3361]\tvalidation_0-rmse:2.66183\n",
+ "[3362]\tvalidation_0-rmse:2.66183\n",
+ "[3363]\tvalidation_0-rmse:2.66182\n",
+ "[3364]\tvalidation_0-rmse:2.66186\n",
+ "[3365]\tvalidation_0-rmse:2.66183\n",
+ "[3366]\tvalidation_0-rmse:2.66184\n",
+ "[3367]\tvalidation_0-rmse:2.66182\n",
+ "[3368]\tvalidation_0-rmse:2.66179\n",
+ "[3369]\tvalidation_0-rmse:2.66177\n",
+ "[3370]\tvalidation_0-rmse:2.66174\n",
+ "[3371]\tvalidation_0-rmse:2.66175\n",
+ "[3372]\tvalidation_0-rmse:2.66176\n",
+ "[3373]\tvalidation_0-rmse:2.66182\n",
+ "[3374]\tvalidation_0-rmse:2.66179\n",
+ "[3375]\tvalidation_0-rmse:2.66176\n",
+ "[3376]\tvalidation_0-rmse:2.66178\n",
+ "[3377]\tvalidation_0-rmse:2.66179\n",
+ "[3378]\tvalidation_0-rmse:2.66179\n",
+ "[3379]\tvalidation_0-rmse:2.66180\n",
+ "[3380]\tvalidation_0-rmse:2.66176\n",
+ "[3381]\tvalidation_0-rmse:2.66174\n",
+ "[3382]\tvalidation_0-rmse:2.66176\n",
+ "[3383]\tvalidation_0-rmse:2.66176\n",
+ "[3384]\tvalidation_0-rmse:2.66178\n",
+ "[3385]\tvalidation_0-rmse:2.66181\n",
+ "[3386]\tvalidation_0-rmse:2.66177\n",
+ "[3387]\tvalidation_0-rmse:2.66181\n",
+ "[3388]\tvalidation_0-rmse:2.66180\n",
+ "[3389]\tvalidation_0-rmse:2.66179\n",
+ "[3390]\tvalidation_0-rmse:2.66178\n",
+ "[3391]\tvalidation_0-rmse:2.66164\n",
+ "[3392]\tvalidation_0-rmse:2.66164\n",
+ "[3393]\tvalidation_0-rmse:2.66164\n",
+ "[3394]\tvalidation_0-rmse:2.66158\n",
+ "[3395]\tvalidation_0-rmse:2.66167\n",
+ "[3396]\tvalidation_0-rmse:2.66174\n",
+ "[3397]\tvalidation_0-rmse:2.66177\n",
+ "[3398]\tvalidation_0-rmse:2.66164\n",
+ "[3399]\tvalidation_0-rmse:2.66157\n",
+ "[3400]\tvalidation_0-rmse:2.66158\n",
+ "[3401]\tvalidation_0-rmse:2.66157\n",
+ "[3402]\tvalidation_0-rmse:2.66156\n",
+ "[3403]\tvalidation_0-rmse:2.66149\n",
+ "[3404]\tvalidation_0-rmse:2.66153\n",
+ "[3405]\tvalidation_0-rmse:2.66153\n",
+ "[3406]\tvalidation_0-rmse:2.66154\n",
+ "[3407]\tvalidation_0-rmse:2.66152\n",
+ "[3408]\tvalidation_0-rmse:2.66152\n",
+ "[3409]\tvalidation_0-rmse:2.66153\n",
+ "[3410]\tvalidation_0-rmse:2.66147\n",
+ "[3411]\tvalidation_0-rmse:2.66137\n",
+ "[3412]\tvalidation_0-rmse:2.66133\n",
+ "[3413]\tvalidation_0-rmse:2.66126\n",
+ "[3414]\tvalidation_0-rmse:2.66123\n",
+ "[3415]\tvalidation_0-rmse:2.66123\n",
+ "[3416]\tvalidation_0-rmse:2.66118\n",
+ "[3417]\tvalidation_0-rmse:2.66112\n",
+ "[3418]\tvalidation_0-rmse:2.66117\n",
+ "[3419]\tvalidation_0-rmse:2.66120\n",
+ "[3420]\tvalidation_0-rmse:2.66122\n",
+ "[3421]\tvalidation_0-rmse:2.66122\n",
+ "[3422]\tvalidation_0-rmse:2.66125\n",
+ "[3423]\tvalidation_0-rmse:2.66126\n",
+ "[3424]\tvalidation_0-rmse:2.66125\n",
+ "[3425]\tvalidation_0-rmse:2.66124\n",
+ "[3426]\tvalidation_0-rmse:2.66130\n",
+ "[3427]\tvalidation_0-rmse:2.66126\n",
+ "[3428]\tvalidation_0-rmse:2.66125\n",
+ "[3429]\tvalidation_0-rmse:2.66117\n",
+ "[3430]\tvalidation_0-rmse:2.66117\n",
+ "[3431]\tvalidation_0-rmse:2.66117\n",
+ "[3432]\tvalidation_0-rmse:2.66120\n",
+ "[3433]\tvalidation_0-rmse:2.66123\n",
+ "[3434]\tvalidation_0-rmse:2.66121\n",
+ "[3435]\tvalidation_0-rmse:2.66124\n",
+ "[3436]\tvalidation_0-rmse:2.66116\n",
+ "[3437]\tvalidation_0-rmse:2.66116\n",
+ "[3438]\tvalidation_0-rmse:2.66110\n",
+ "[3439]\tvalidation_0-rmse:2.66110\n",
+ "[3440]\tvalidation_0-rmse:2.66109\n",
+ "[3441]\tvalidation_0-rmse:2.66108\n",
+ "[3442]\tvalidation_0-rmse:2.66111\n",
+ "[3443]\tvalidation_0-rmse:2.66111\n",
+ "[3444]\tvalidation_0-rmse:2.66109\n",
+ "[3445]\tvalidation_0-rmse:2.66110\n",
+ "[3446]\tvalidation_0-rmse:2.66092\n",
+ "[3447]\tvalidation_0-rmse:2.66094\n",
+ "[3448]\tvalidation_0-rmse:2.66094\n",
+ "[3449]\tvalidation_0-rmse:2.66094\n",
+ "[3450]\tvalidation_0-rmse:2.66093\n",
+ "[3451]\tvalidation_0-rmse:2.66091\n",
+ "[3452]\tvalidation_0-rmse:2.66088\n",
+ "[3453]\tvalidation_0-rmse:2.66097\n",
+ "[3454]\tvalidation_0-rmse:2.66095\n",
+ "[3455]\tvalidation_0-rmse:2.66097\n",
+ "[3456]\tvalidation_0-rmse:2.66101\n",
+ "[3457]\tvalidation_0-rmse:2.66096\n",
+ "[3458]\tvalidation_0-rmse:2.66092\n",
+ "[3459]\tvalidation_0-rmse:2.66083\n",
+ "[3460]\tvalidation_0-rmse:2.66075\n",
+ "[3461]\tvalidation_0-rmse:2.66078\n",
+ "[3462]\tvalidation_0-rmse:2.66079\n",
+ "[3463]\tvalidation_0-rmse:2.66070\n",
+ "[3464]\tvalidation_0-rmse:2.66071\n",
+ "[3465]\tvalidation_0-rmse:2.66072\n",
+ "[3466]\tvalidation_0-rmse:2.66077\n",
+ "[3467]\tvalidation_0-rmse:2.66082\n",
+ "[3468]\tvalidation_0-rmse:2.66075\n",
+ "[3469]\tvalidation_0-rmse:2.66071\n",
+ "[3470]\tvalidation_0-rmse:2.66075\n",
+ "[3471]\tvalidation_0-rmse:2.66078\n",
+ "[3472]\tvalidation_0-rmse:2.66076\n",
+ "[3473]\tvalidation_0-rmse:2.66073\n",
+ "[3474]\tvalidation_0-rmse:2.66065\n",
+ "[3475]\tvalidation_0-rmse:2.66064\n",
+ "[3476]\tvalidation_0-rmse:2.66067\n",
+ "[3477]\tvalidation_0-rmse:2.66066\n",
+ "[3478]\tvalidation_0-rmse:2.66066\n",
+ "[3479]\tvalidation_0-rmse:2.66061\n",
+ "[3480]\tvalidation_0-rmse:2.66057\n",
+ "[3481]\tvalidation_0-rmse:2.66060\n",
+ "[3482]\tvalidation_0-rmse:2.66064\n",
+ "[3483]\tvalidation_0-rmse:2.66057\n",
+ "[3484]\tvalidation_0-rmse:2.66049\n",
+ "[3485]\tvalidation_0-rmse:2.66050\n",
+ "[3486]\tvalidation_0-rmse:2.66055\n",
+ "[3487]\tvalidation_0-rmse:2.66049\n",
+ "[3488]\tvalidation_0-rmse:2.66048\n",
+ "[3489]\tvalidation_0-rmse:2.66048\n",
+ "[3490]\tvalidation_0-rmse:2.66049\n",
+ "[3491]\tvalidation_0-rmse:2.66045\n",
+ "[3492]\tvalidation_0-rmse:2.66043\n",
+ "[3493]\tvalidation_0-rmse:2.66044\n",
+ "[3494]\tvalidation_0-rmse:2.66044\n",
+ "[3495]\tvalidation_0-rmse:2.66043\n",
+ "[3496]\tvalidation_0-rmse:2.66038\n",
+ "[3497]\tvalidation_0-rmse:2.66040\n",
+ "[3498]\tvalidation_0-rmse:2.66040\n",
+ "[3499]\tvalidation_0-rmse:2.66040\n",
+ "[3500]\tvalidation_0-rmse:2.66039\n",
+ "[3501]\tvalidation_0-rmse:2.66034\n",
+ "[3502]\tvalidation_0-rmse:2.66027\n",
+ "[3503]\tvalidation_0-rmse:2.66023\n",
+ "[3504]\tvalidation_0-rmse:2.66026\n",
+ "[3505]\tvalidation_0-rmse:2.66028\n",
+ "[3506]\tvalidation_0-rmse:2.66012\n",
+ "[3507]\tvalidation_0-rmse:2.66004\n",
+ "[3508]\tvalidation_0-rmse:2.65993\n",
+ "[3509]\tvalidation_0-rmse:2.65991\n",
+ "[3510]\tvalidation_0-rmse:2.65992\n",
+ "[3511]\tvalidation_0-rmse:2.65967\n",
+ "[3512]\tvalidation_0-rmse:2.65963\n",
+ "[3513]\tvalidation_0-rmse:2.65963\n",
+ "[3514]\tvalidation_0-rmse:2.65959\n",
+ "[3515]\tvalidation_0-rmse:2.65958\n",
+ "[3516]\tvalidation_0-rmse:2.65959\n",
+ "[3517]\tvalidation_0-rmse:2.65943\n",
+ "[3518]\tvalidation_0-rmse:2.65937\n",
+ "[3519]\tvalidation_0-rmse:2.65934\n",
+ "[3520]\tvalidation_0-rmse:2.65929\n",
+ "[3521]\tvalidation_0-rmse:2.65913\n",
+ "[3522]\tvalidation_0-rmse:2.65917\n",
+ "[3523]\tvalidation_0-rmse:2.65923\n",
+ "[3524]\tvalidation_0-rmse:2.65927\n",
+ "[3525]\tvalidation_0-rmse:2.65929\n",
+ "[3526]\tvalidation_0-rmse:2.65929\n",
+ "[3527]\tvalidation_0-rmse:2.65918\n",
+ "[3528]\tvalidation_0-rmse:2.65899\n",
+ "[3529]\tvalidation_0-rmse:2.65897\n",
+ "[3530]\tvalidation_0-rmse:2.65894\n",
+ "[3531]\tvalidation_0-rmse:2.65897\n",
+ "[3532]\tvalidation_0-rmse:2.65903\n",
+ "[3533]\tvalidation_0-rmse:2.65905\n",
+ "[3534]\tvalidation_0-rmse:2.65904\n",
+ "[3535]\tvalidation_0-rmse:2.65905\n",
+ "[3536]\tvalidation_0-rmse:2.65903\n",
+ "[3537]\tvalidation_0-rmse:2.65910\n",
+ "[3538]\tvalidation_0-rmse:2.65912\n",
+ "[3539]\tvalidation_0-rmse:2.65909\n",
+ "[3540]\tvalidation_0-rmse:2.65910\n",
+ "[3541]\tvalidation_0-rmse:2.65911\n",
+ "[3542]\tvalidation_0-rmse:2.65908\n",
+ "[3543]\tvalidation_0-rmse:2.65900\n",
+ "[3544]\tvalidation_0-rmse:2.65903\n",
+ "[3545]\tvalidation_0-rmse:2.65907\n",
+ "[3546]\tvalidation_0-rmse:2.65908\n",
+ "[3547]\tvalidation_0-rmse:2.65908\n",
+ "[3548]\tvalidation_0-rmse:2.65906\n",
+ "[3549]\tvalidation_0-rmse:2.65899\n",
+ "[3550]\tvalidation_0-rmse:2.65900\n",
+ "[3551]\tvalidation_0-rmse:2.65901\n",
+ "[3552]\tvalidation_0-rmse:2.65899\n",
+ "[3553]\tvalidation_0-rmse:2.65901\n",
+ "[3554]\tvalidation_0-rmse:2.65894\n",
+ "[3555]\tvalidation_0-rmse:2.65878\n",
+ "[3556]\tvalidation_0-rmse:2.65868\n",
+ "[3557]\tvalidation_0-rmse:2.65864\n",
+ "[3558]\tvalidation_0-rmse:2.65863\n",
+ "[3559]\tvalidation_0-rmse:2.65862\n",
+ "[3560]\tvalidation_0-rmse:2.65866\n",
+ "[3561]\tvalidation_0-rmse:2.65857\n",
+ "[3562]\tvalidation_0-rmse:2.65857\n",
+ "[3563]\tvalidation_0-rmse:2.65839\n",
+ "[3564]\tvalidation_0-rmse:2.65824\n",
+ "[3565]\tvalidation_0-rmse:2.65814\n",
+ "[3566]\tvalidation_0-rmse:2.65807\n",
+ "[3567]\tvalidation_0-rmse:2.65805\n",
+ "[3568]\tvalidation_0-rmse:2.65804\n",
+ "[3569]\tvalidation_0-rmse:2.65805\n",
+ "[3570]\tvalidation_0-rmse:2.65798\n",
+ "[3571]\tvalidation_0-rmse:2.65795\n",
+ "[3572]\tvalidation_0-rmse:2.65790\n",
+ "[3573]\tvalidation_0-rmse:2.65778\n",
+ "[3574]\tvalidation_0-rmse:2.65773\n",
+ "[3575]\tvalidation_0-rmse:2.65774\n",
+ "[3576]\tvalidation_0-rmse:2.65759\n",
+ "[3577]\tvalidation_0-rmse:2.65760\n",
+ "[3578]\tvalidation_0-rmse:2.65758\n",
+ "[3579]\tvalidation_0-rmse:2.65754\n",
+ "[3580]\tvalidation_0-rmse:2.65752\n",
+ "[3581]\tvalidation_0-rmse:2.65753\n",
+ "[3582]\tvalidation_0-rmse:2.65740\n",
+ "[3583]\tvalidation_0-rmse:2.65733\n",
+ "[3584]\tvalidation_0-rmse:2.65733\n",
+ "[3585]\tvalidation_0-rmse:2.65724\n",
+ "[3586]\tvalidation_0-rmse:2.65722\n",
+ "[3587]\tvalidation_0-rmse:2.65713\n",
+ "[3588]\tvalidation_0-rmse:2.65703\n",
+ "[3589]\tvalidation_0-rmse:2.65700\n",
+ "[3590]\tvalidation_0-rmse:2.65703\n",
+ "[3591]\tvalidation_0-rmse:2.65702\n",
+ "[3592]\tvalidation_0-rmse:2.65700\n",
+ "[3593]\tvalidation_0-rmse:2.65693\n",
+ "[3594]\tvalidation_0-rmse:2.65693\n",
+ "[3595]\tvalidation_0-rmse:2.65692\n",
+ "[3596]\tvalidation_0-rmse:2.65693\n",
+ "[3597]\tvalidation_0-rmse:2.65696\n",
+ "[3598]\tvalidation_0-rmse:2.65685\n",
+ "[3599]\tvalidation_0-rmse:2.65678\n",
+ "[3600]\tvalidation_0-rmse:2.65672\n",
+ "[3601]\tvalidation_0-rmse:2.65672\n",
+ "[3602]\tvalidation_0-rmse:2.65674\n",
+ "[3603]\tvalidation_0-rmse:2.65673\n",
+ "[3604]\tvalidation_0-rmse:2.65680\n",
+ "[3605]\tvalidation_0-rmse:2.65679\n",
+ "[3606]\tvalidation_0-rmse:2.65679\n",
+ "[3607]\tvalidation_0-rmse:2.65676\n",
+ "[3608]\tvalidation_0-rmse:2.65667\n",
+ "[3609]\tvalidation_0-rmse:2.65670\n",
+ "[3610]\tvalidation_0-rmse:2.65670\n",
+ "[3611]\tvalidation_0-rmse:2.65650\n",
+ "[3612]\tvalidation_0-rmse:2.65644\n",
+ "[3613]\tvalidation_0-rmse:2.65642\n",
+ "[3614]\tvalidation_0-rmse:2.65632\n",
+ "[3615]\tvalidation_0-rmse:2.65632\n",
+ "[3616]\tvalidation_0-rmse:2.65631\n",
+ "[3617]\tvalidation_0-rmse:2.65628\n",
+ "[3618]\tvalidation_0-rmse:2.65624\n",
+ "[3619]\tvalidation_0-rmse:2.65621\n",
+ "[3620]\tvalidation_0-rmse:2.65615\n",
+ "[3621]\tvalidation_0-rmse:2.65606\n",
+ "[3622]\tvalidation_0-rmse:2.65616\n",
+ "[3623]\tvalidation_0-rmse:2.65612\n",
+ "[3624]\tvalidation_0-rmse:2.65613\n",
+ "[3625]\tvalidation_0-rmse:2.65616\n",
+ "[3626]\tvalidation_0-rmse:2.65617\n",
+ "[3627]\tvalidation_0-rmse:2.65615\n",
+ "[3628]\tvalidation_0-rmse:2.65611\n",
+ "[3629]\tvalidation_0-rmse:2.65619\n",
+ "[3630]\tvalidation_0-rmse:2.65625\n",
+ "[3631]\tvalidation_0-rmse:2.65614\n",
+ "[3632]\tvalidation_0-rmse:2.65613\n",
+ "[3633]\tvalidation_0-rmse:2.65609\n",
+ "[3634]\tvalidation_0-rmse:2.65605\n",
+ "[3635]\tvalidation_0-rmse:2.65604\n",
+ "[3636]\tvalidation_0-rmse:2.65604\n",
+ "[3637]\tvalidation_0-rmse:2.65604\n",
+ "[3638]\tvalidation_0-rmse:2.65606\n",
+ "[3639]\tvalidation_0-rmse:2.65595\n",
+ "[3640]\tvalidation_0-rmse:2.65598\n",
+ "[3641]\tvalidation_0-rmse:2.65601\n",
+ "[3642]\tvalidation_0-rmse:2.65597\n",
+ "[3643]\tvalidation_0-rmse:2.65586\n",
+ "[3644]\tvalidation_0-rmse:2.65583\n",
+ "[3645]\tvalidation_0-rmse:2.65585\n",
+ "[3646]\tvalidation_0-rmse:2.65586\n",
+ "[3647]\tvalidation_0-rmse:2.65570\n",
+ "[3648]\tvalidation_0-rmse:2.65549\n",
+ "[3649]\tvalidation_0-rmse:2.65543\n",
+ "[3650]\tvalidation_0-rmse:2.65541\n",
+ "[3651]\tvalidation_0-rmse:2.65536\n",
+ "[3652]\tvalidation_0-rmse:2.65538\n",
+ "[3653]\tvalidation_0-rmse:2.65535\n",
+ "[3654]\tvalidation_0-rmse:2.65521\n",
+ "[3655]\tvalidation_0-rmse:2.65523\n",
+ "[3656]\tvalidation_0-rmse:2.65522\n",
+ "[3657]\tvalidation_0-rmse:2.65523\n",
+ "[3658]\tvalidation_0-rmse:2.65520\n",
+ "[3659]\tvalidation_0-rmse:2.65522\n",
+ "[3660]\tvalidation_0-rmse:2.65512\n",
+ "[3661]\tvalidation_0-rmse:2.65505\n",
+ "[3662]\tvalidation_0-rmse:2.65508\n",
+ "[3663]\tvalidation_0-rmse:2.65499\n",
+ "[3664]\tvalidation_0-rmse:2.65499\n",
+ "[3665]\tvalidation_0-rmse:2.65505\n",
+ "[3666]\tvalidation_0-rmse:2.65504\n",
+ "[3667]\tvalidation_0-rmse:2.65507\n",
+ "[3668]\tvalidation_0-rmse:2.65502\n",
+ "[3669]\tvalidation_0-rmse:2.65504\n",
+ "[3670]\tvalidation_0-rmse:2.65503\n",
+ "[3671]\tvalidation_0-rmse:2.65509\n",
+ "[3672]\tvalidation_0-rmse:2.65496\n",
+ "[3673]\tvalidation_0-rmse:2.65500\n",
+ "[3674]\tvalidation_0-rmse:2.65499\n",
+ "[3675]\tvalidation_0-rmse:2.65502\n",
+ "[3676]\tvalidation_0-rmse:2.65499\n",
+ "[3677]\tvalidation_0-rmse:2.65501\n",
+ "[3678]\tvalidation_0-rmse:2.65501\n",
+ "[3679]\tvalidation_0-rmse:2.65500\n",
+ "[3680]\tvalidation_0-rmse:2.65498\n",
+ "[3681]\tvalidation_0-rmse:2.65501\n",
+ "[3682]\tvalidation_0-rmse:2.65495\n",
+ "[3683]\tvalidation_0-rmse:2.65493\n",
+ "[3684]\tvalidation_0-rmse:2.65495\n",
+ "[3685]\tvalidation_0-rmse:2.65496\n",
+ "[3686]\tvalidation_0-rmse:2.65487\n",
+ "[3687]\tvalidation_0-rmse:2.65486\n",
+ "[3688]\tvalidation_0-rmse:2.65487\n",
+ "[3689]\tvalidation_0-rmse:2.65491\n",
+ "[3690]\tvalidation_0-rmse:2.65496\n",
+ "[3691]\tvalidation_0-rmse:2.65495\n",
+ "[3692]\tvalidation_0-rmse:2.65494\n",
+ "[3693]\tvalidation_0-rmse:2.65497\n",
+ "[3694]\tvalidation_0-rmse:2.65496\n",
+ "[3695]\tvalidation_0-rmse:2.65495\n",
+ "[3696]\tvalidation_0-rmse:2.65493\n",
+ "[3697]\tvalidation_0-rmse:2.65493\n",
+ "[3698]\tvalidation_0-rmse:2.65495\n",
+ "[3699]\tvalidation_0-rmse:2.65497\n",
+ "[3700]\tvalidation_0-rmse:2.65497\n",
+ "[3701]\tvalidation_0-rmse:2.65502\n",
+ "[3702]\tvalidation_0-rmse:2.65506\n",
+ "[3703]\tvalidation_0-rmse:2.65513\n",
+ "[3704]\tvalidation_0-rmse:2.65504\n",
+ "[3705]\tvalidation_0-rmse:2.65502\n",
+ "[3706]\tvalidation_0-rmse:2.65506\n",
+ "[3707]\tvalidation_0-rmse:2.65504\n",
+ "[3708]\tvalidation_0-rmse:2.65505\n",
+ "[3709]\tvalidation_0-rmse:2.65502\n",
+ "[3710]\tvalidation_0-rmse:2.65504\n",
+ "[3711]\tvalidation_0-rmse:2.65500\n",
+ "[3712]\tvalidation_0-rmse:2.65485\n",
+ "[3713]\tvalidation_0-rmse:2.65483\n",
+ "[3714]\tvalidation_0-rmse:2.65486\n",
+ "[3715]\tvalidation_0-rmse:2.65487\n",
+ "[3716]\tvalidation_0-rmse:2.65486\n",
+ "[3717]\tvalidation_0-rmse:2.65488\n",
+ "[3718]\tvalidation_0-rmse:2.65487\n",
+ "[3719]\tvalidation_0-rmse:2.65490\n",
+ "[3720]\tvalidation_0-rmse:2.65486\n",
+ "[3721]\tvalidation_0-rmse:2.65476\n",
+ "[3722]\tvalidation_0-rmse:2.65458\n",
+ "[3723]\tvalidation_0-rmse:2.65458\n",
+ "[3724]\tvalidation_0-rmse:2.65440\n",
+ "[3725]\tvalidation_0-rmse:2.65439\n",
+ "[3726]\tvalidation_0-rmse:2.65441\n",
+ "[3727]\tvalidation_0-rmse:2.65440\n",
+ "[3728]\tvalidation_0-rmse:2.65429\n",
+ "[3729]\tvalidation_0-rmse:2.65425\n",
+ "[3730]\tvalidation_0-rmse:2.65421\n",
+ "[3731]\tvalidation_0-rmse:2.65413\n",
+ "[3732]\tvalidation_0-rmse:2.65415\n",
+ "[3733]\tvalidation_0-rmse:2.65407\n",
+ "[3734]\tvalidation_0-rmse:2.65401\n",
+ "[3735]\tvalidation_0-rmse:2.65406\n",
+ "[3736]\tvalidation_0-rmse:2.65406\n",
+ "[3737]\tvalidation_0-rmse:2.65411\n",
+ "[3738]\tvalidation_0-rmse:2.65408\n",
+ "[3739]\tvalidation_0-rmse:2.65409\n",
+ "[3740]\tvalidation_0-rmse:2.65405\n",
+ "[3741]\tvalidation_0-rmse:2.65402\n",
+ "[3742]\tvalidation_0-rmse:2.65402\n",
+ "[3743]\tvalidation_0-rmse:2.65406\n",
+ "[3744]\tvalidation_0-rmse:2.65397\n",
+ "[3745]\tvalidation_0-rmse:2.65398\n",
+ "[3746]\tvalidation_0-rmse:2.65400\n",
+ "[3747]\tvalidation_0-rmse:2.65399\n",
+ "[3748]\tvalidation_0-rmse:2.65401\n",
+ "[3749]\tvalidation_0-rmse:2.65399\n",
+ "[3750]\tvalidation_0-rmse:2.65395\n",
+ "[3751]\tvalidation_0-rmse:2.65390\n",
+ "[3752]\tvalidation_0-rmse:2.65393\n",
+ "[3753]\tvalidation_0-rmse:2.65397\n",
+ "[3754]\tvalidation_0-rmse:2.65401\n",
+ "[3755]\tvalidation_0-rmse:2.65392\n",
+ "[3756]\tvalidation_0-rmse:2.65394\n",
+ "[3757]\tvalidation_0-rmse:2.65389\n",
+ "[3758]\tvalidation_0-rmse:2.65393\n",
+ "[3759]\tvalidation_0-rmse:2.65392\n",
+ "[3760]\tvalidation_0-rmse:2.65390\n",
+ "[3761]\tvalidation_0-rmse:2.65383\n",
+ "[3762]\tvalidation_0-rmse:2.65385\n",
+ "[3763]\tvalidation_0-rmse:2.65382\n",
+ "[3764]\tvalidation_0-rmse:2.65385\n",
+ "[3765]\tvalidation_0-rmse:2.65389\n",
+ "[3766]\tvalidation_0-rmse:2.65384\n",
+ "[3767]\tvalidation_0-rmse:2.65376\n",
+ "[3768]\tvalidation_0-rmse:2.65376\n",
+ "[3769]\tvalidation_0-rmse:2.65372\n",
+ "[3770]\tvalidation_0-rmse:2.65376\n",
+ "[3771]\tvalidation_0-rmse:2.65374\n",
+ "[3772]\tvalidation_0-rmse:2.65379\n",
+ "[3773]\tvalidation_0-rmse:2.65375\n",
+ "[3774]\tvalidation_0-rmse:2.65377\n",
+ "[3775]\tvalidation_0-rmse:2.65375\n",
+ "[3776]\tvalidation_0-rmse:2.65376\n",
+ "[3777]\tvalidation_0-rmse:2.65373\n",
+ "[3778]\tvalidation_0-rmse:2.65363\n",
+ "[3779]\tvalidation_0-rmse:2.65364\n",
+ "[3780]\tvalidation_0-rmse:2.65350\n",
+ "[3781]\tvalidation_0-rmse:2.65354\n",
+ "[3782]\tvalidation_0-rmse:2.65347\n",
+ "[3783]\tvalidation_0-rmse:2.65347\n",
+ "[3784]\tvalidation_0-rmse:2.65346\n",
+ "[3785]\tvalidation_0-rmse:2.65336\n",
+ "[3786]\tvalidation_0-rmse:2.65331\n",
+ "[3787]\tvalidation_0-rmse:2.65330\n",
+ "[3788]\tvalidation_0-rmse:2.65331\n",
+ "[3789]\tvalidation_0-rmse:2.65320\n",
+ "[3790]\tvalidation_0-rmse:2.65321\n",
+ "[3791]\tvalidation_0-rmse:2.65327\n",
+ "[3792]\tvalidation_0-rmse:2.65326\n",
+ "[3793]\tvalidation_0-rmse:2.65326\n",
+ "[3794]\tvalidation_0-rmse:2.65319\n",
+ "[3795]\tvalidation_0-rmse:2.65322\n",
+ "[3796]\tvalidation_0-rmse:2.65317\n",
+ "[3797]\tvalidation_0-rmse:2.65315\n",
+ "[3798]\tvalidation_0-rmse:2.65314\n",
+ "[3799]\tvalidation_0-rmse:2.65314\n",
+ "[3800]\tvalidation_0-rmse:2.65311\n",
+ "[3801]\tvalidation_0-rmse:2.65304\n",
+ "[3802]\tvalidation_0-rmse:2.65304\n",
+ "[3803]\tvalidation_0-rmse:2.65299\n",
+ "[3804]\tvalidation_0-rmse:2.65303\n",
+ "[3805]\tvalidation_0-rmse:2.65308\n",
+ "[3806]\tvalidation_0-rmse:2.65312\n",
+ "[3807]\tvalidation_0-rmse:2.65300\n",
+ "[3808]\tvalidation_0-rmse:2.65303\n",
+ "[3809]\tvalidation_0-rmse:2.65297\n",
+ "[3810]\tvalidation_0-rmse:2.65298\n",
+ "[3811]\tvalidation_0-rmse:2.65298\n",
+ "[3812]\tvalidation_0-rmse:2.65294\n",
+ "[3813]\tvalidation_0-rmse:2.65285\n",
+ "[3814]\tvalidation_0-rmse:2.65278\n",
+ "[3815]\tvalidation_0-rmse:2.65274\n",
+ "[3816]\tvalidation_0-rmse:2.65273\n",
+ "[3817]\tvalidation_0-rmse:2.65275\n",
+ "[3818]\tvalidation_0-rmse:2.65278\n",
+ "[3819]\tvalidation_0-rmse:2.65271\n",
+ "[3820]\tvalidation_0-rmse:2.65271\n",
+ "[3821]\tvalidation_0-rmse:2.65271\n",
+ "[3822]\tvalidation_0-rmse:2.65268\n",
+ "[3823]\tvalidation_0-rmse:2.65254\n",
+ "[3824]\tvalidation_0-rmse:2.65260\n",
+ "[3825]\tvalidation_0-rmse:2.65255\n",
+ "[3826]\tvalidation_0-rmse:2.65255\n",
+ "[3827]\tvalidation_0-rmse:2.65251\n",
+ "[3828]\tvalidation_0-rmse:2.65250\n",
+ "[3829]\tvalidation_0-rmse:2.65246\n",
+ "[3830]\tvalidation_0-rmse:2.65244\n",
+ "[3831]\tvalidation_0-rmse:2.65236\n",
+ "[3832]\tvalidation_0-rmse:2.65236\n",
+ "[3833]\tvalidation_0-rmse:2.65233\n",
+ "[3834]\tvalidation_0-rmse:2.65232\n",
+ "[3835]\tvalidation_0-rmse:2.65226\n",
+ "[3836]\tvalidation_0-rmse:2.65224\n",
+ "[3837]\tvalidation_0-rmse:2.65228\n",
+ "[3838]\tvalidation_0-rmse:2.65216\n",
+ "[3839]\tvalidation_0-rmse:2.65207\n",
+ "[3840]\tvalidation_0-rmse:2.65209\n",
+ "[3841]\tvalidation_0-rmse:2.65198\n",
+ "[3842]\tvalidation_0-rmse:2.65198\n",
+ "[3843]\tvalidation_0-rmse:2.65189\n",
+ "[3844]\tvalidation_0-rmse:2.65188\n",
+ "[3845]\tvalidation_0-rmse:2.65181\n",
+ "[3846]\tvalidation_0-rmse:2.65186\n",
+ "[3847]\tvalidation_0-rmse:2.65191\n",
+ "[3848]\tvalidation_0-rmse:2.65177\n",
+ "[3849]\tvalidation_0-rmse:2.65172\n",
+ "[3850]\tvalidation_0-rmse:2.65170\n",
+ "[3851]\tvalidation_0-rmse:2.65161\n",
+ "[3852]\tvalidation_0-rmse:2.65156\n",
+ "[3853]\tvalidation_0-rmse:2.65153\n",
+ "[3854]\tvalidation_0-rmse:2.65142\n",
+ "[3855]\tvalidation_0-rmse:2.65143\n",
+ "[3856]\tvalidation_0-rmse:2.65145\n",
+ "[3857]\tvalidation_0-rmse:2.65145\n",
+ "[3858]\tvalidation_0-rmse:2.65135\n",
+ "[3859]\tvalidation_0-rmse:2.65132\n",
+ "[3860]\tvalidation_0-rmse:2.65128\n",
+ "[3861]\tvalidation_0-rmse:2.65126\n",
+ "[3862]\tvalidation_0-rmse:2.65124\n",
+ "[3863]\tvalidation_0-rmse:2.65120\n",
+ "[3864]\tvalidation_0-rmse:2.65119\n",
+ "[3865]\tvalidation_0-rmse:2.65117\n",
+ "[3866]\tvalidation_0-rmse:2.65114\n",
+ "[3867]\tvalidation_0-rmse:2.65110\n",
+ "[3868]\tvalidation_0-rmse:2.65096\n",
+ "[3869]\tvalidation_0-rmse:2.65088\n",
+ "[3870]\tvalidation_0-rmse:2.65084\n",
+ "[3871]\tvalidation_0-rmse:2.65076\n",
+ "[3872]\tvalidation_0-rmse:2.65072\n",
+ "[3873]\tvalidation_0-rmse:2.65072\n",
+ "[3874]\tvalidation_0-rmse:2.65068\n",
+ "[3875]\tvalidation_0-rmse:2.65067\n",
+ "[3876]\tvalidation_0-rmse:2.65066\n",
+ "[3877]\tvalidation_0-rmse:2.65063\n",
+ "[3878]\tvalidation_0-rmse:2.65065\n",
+ "[3879]\tvalidation_0-rmse:2.65063\n",
+ "[3880]\tvalidation_0-rmse:2.65057\n",
+ "[3881]\tvalidation_0-rmse:2.65046\n",
+ "[3882]\tvalidation_0-rmse:2.65047\n",
+ "[3883]\tvalidation_0-rmse:2.65045\n",
+ "[3884]\tvalidation_0-rmse:2.65043\n",
+ "[3885]\tvalidation_0-rmse:2.65042\n",
+ "[3886]\tvalidation_0-rmse:2.65037\n",
+ "[3887]\tvalidation_0-rmse:2.65035\n",
+ "[3888]\tvalidation_0-rmse:2.65039\n",
+ "[3889]\tvalidation_0-rmse:2.65043\n",
+ "[3890]\tvalidation_0-rmse:2.65042\n",
+ "[3891]\tvalidation_0-rmse:2.65044\n",
+ "[3892]\tvalidation_0-rmse:2.65043\n",
+ "[3893]\tvalidation_0-rmse:2.65043\n",
+ "[3894]\tvalidation_0-rmse:2.65042\n",
+ "[3895]\tvalidation_0-rmse:2.65042\n",
+ "[3896]\tvalidation_0-rmse:2.65048\n",
+ "[3897]\tvalidation_0-rmse:2.65036\n",
+ "[3898]\tvalidation_0-rmse:2.65023\n",
+ "[3899]\tvalidation_0-rmse:2.65023\n",
+ "[3900]\tvalidation_0-rmse:2.65016\n",
+ "[3901]\tvalidation_0-rmse:2.65011\n",
+ "[3902]\tvalidation_0-rmse:2.65013\n",
+ "[3903]\tvalidation_0-rmse:2.65006\n",
+ "[3904]\tvalidation_0-rmse:2.65005\n",
+ "[3905]\tvalidation_0-rmse:2.65003\n",
+ "[3906]\tvalidation_0-rmse:2.65000\n",
+ "[3907]\tvalidation_0-rmse:2.64993\n",
+ "[3908]\tvalidation_0-rmse:2.64993\n",
+ "[3909]\tvalidation_0-rmse:2.64984\n",
+ "[3910]\tvalidation_0-rmse:2.64982\n",
+ "[3911]\tvalidation_0-rmse:2.64980\n",
+ "[3912]\tvalidation_0-rmse:2.64980\n",
+ "[3913]\tvalidation_0-rmse:2.64977\n",
+ "[3914]\tvalidation_0-rmse:2.64979\n",
+ "[3915]\tvalidation_0-rmse:2.64977\n",
+ "[3916]\tvalidation_0-rmse:2.64975\n",
+ "[3917]\tvalidation_0-rmse:2.64971\n",
+ "[3918]\tvalidation_0-rmse:2.64977\n",
+ "[3919]\tvalidation_0-rmse:2.64976\n",
+ "[3920]\tvalidation_0-rmse:2.64974\n",
+ "[3921]\tvalidation_0-rmse:2.64969\n",
+ "[3922]\tvalidation_0-rmse:2.64970\n",
+ "[3923]\tvalidation_0-rmse:2.64971\n",
+ "[3924]\tvalidation_0-rmse:2.64974\n",
+ "[3925]\tvalidation_0-rmse:2.64975\n",
+ "[3926]\tvalidation_0-rmse:2.64979\n",
+ "[3927]\tvalidation_0-rmse:2.64985\n",
+ "[3928]\tvalidation_0-rmse:2.64984\n",
+ "[3929]\tvalidation_0-rmse:2.64979\n",
+ "[3930]\tvalidation_0-rmse:2.64980\n",
+ "[3931]\tvalidation_0-rmse:2.64974\n",
+ "[3932]\tvalidation_0-rmse:2.64965\n",
+ "[3933]\tvalidation_0-rmse:2.64961\n",
+ "[3934]\tvalidation_0-rmse:2.64960\n",
+ "[3935]\tvalidation_0-rmse:2.64970\n",
+ "[3936]\tvalidation_0-rmse:2.64974\n",
+ "[3937]\tvalidation_0-rmse:2.64974\n",
+ "[3938]\tvalidation_0-rmse:2.64976\n",
+ "[3939]\tvalidation_0-rmse:2.64974\n",
+ "[3940]\tvalidation_0-rmse:2.64974\n",
+ "[3941]\tvalidation_0-rmse:2.64975\n",
+ "[3942]\tvalidation_0-rmse:2.64978\n",
+ "[3943]\tvalidation_0-rmse:2.64976\n",
+ "[3944]\tvalidation_0-rmse:2.64971\n",
+ "[3945]\tvalidation_0-rmse:2.64964\n",
+ "[3946]\tvalidation_0-rmse:2.64965\n",
+ "[3947]\tvalidation_0-rmse:2.64964\n",
+ "[3948]\tvalidation_0-rmse:2.64967\n",
+ "[3949]\tvalidation_0-rmse:2.64970\n",
+ "[3950]\tvalidation_0-rmse:2.64965\n",
+ "[3951]\tvalidation_0-rmse:2.64962\n",
+ "[3952]\tvalidation_0-rmse:2.64947\n",
+ "[3953]\tvalidation_0-rmse:2.64953\n",
+ "[3954]\tvalidation_0-rmse:2.64946\n",
+ "[3955]\tvalidation_0-rmse:2.64943\n",
+ "[3956]\tvalidation_0-rmse:2.64944\n",
+ "[3957]\tvalidation_0-rmse:2.64946\n",
+ "[3958]\tvalidation_0-rmse:2.64942\n",
+ "[3959]\tvalidation_0-rmse:2.64943\n",
+ "[3960]\tvalidation_0-rmse:2.64941\n",
+ "[3961]\tvalidation_0-rmse:2.64941\n",
+ "[3962]\tvalidation_0-rmse:2.64937\n",
+ "[3963]\tvalidation_0-rmse:2.64928\n",
+ "[3964]\tvalidation_0-rmse:2.64926\n",
+ "[3965]\tvalidation_0-rmse:2.64922\n",
+ "[3966]\tvalidation_0-rmse:2.64906\n",
+ "[3967]\tvalidation_0-rmse:2.64906\n",
+ "[3968]\tvalidation_0-rmse:2.64906\n",
+ "[3969]\tvalidation_0-rmse:2.64908\n",
+ "[3970]\tvalidation_0-rmse:2.64912\n",
+ "[3971]\tvalidation_0-rmse:2.64908\n",
+ "[3972]\tvalidation_0-rmse:2.64902\n",
+ "[3973]\tvalidation_0-rmse:2.64902\n",
+ "[3974]\tvalidation_0-rmse:2.64900\n",
+ "[3975]\tvalidation_0-rmse:2.64896\n",
+ "[3976]\tvalidation_0-rmse:2.64894\n",
+ "[3977]\tvalidation_0-rmse:2.64889\n",
+ "[3978]\tvalidation_0-rmse:2.64865\n",
+ "[3979]\tvalidation_0-rmse:2.64864\n",
+ "[3980]\tvalidation_0-rmse:2.64862\n",
+ "[3981]\tvalidation_0-rmse:2.64858\n",
+ "[3982]\tvalidation_0-rmse:2.64858\n",
+ "[3983]\tvalidation_0-rmse:2.64861\n",
+ "[3984]\tvalidation_0-rmse:2.64862\n",
+ "[3985]\tvalidation_0-rmse:2.64863\n",
+ "[3986]\tvalidation_0-rmse:2.64867\n",
+ "[3987]\tvalidation_0-rmse:2.64867\n",
+ "[3988]\tvalidation_0-rmse:2.64870\n",
+ "[3989]\tvalidation_0-rmse:2.64879\n",
+ "[3990]\tvalidation_0-rmse:2.64881\n",
+ "[3991]\tvalidation_0-rmse:2.64888\n",
+ "[3992]\tvalidation_0-rmse:2.64886\n",
+ "[3993]\tvalidation_0-rmse:2.64891\n",
+ "[3994]\tvalidation_0-rmse:2.64882\n",
+ "[3995]\tvalidation_0-rmse:2.64881\n",
+ "[3996]\tvalidation_0-rmse:2.64880\n",
+ "[3997]\tvalidation_0-rmse:2.64880\n",
+ "[3998]\tvalidation_0-rmse:2.64880\n",
+ "[3999]\tvalidation_0-rmse:2.64876\n",
+ "[4000]\tvalidation_0-rmse:2.64871\n",
+ "[4001]\tvalidation_0-rmse:2.64869\n",
+ "[4002]\tvalidation_0-rmse:2.64856\n",
+ "[4003]\tvalidation_0-rmse:2.64854\n",
+ "[4004]\tvalidation_0-rmse:2.64859\n",
+ "[4005]\tvalidation_0-rmse:2.64853\n",
+ "[4006]\tvalidation_0-rmse:2.64853\n",
+ "[4007]\tvalidation_0-rmse:2.64848\n",
+ "[4008]\tvalidation_0-rmse:2.64841\n",
+ "[4009]\tvalidation_0-rmse:2.64832\n",
+ "[4010]\tvalidation_0-rmse:2.64830\n",
+ "[4011]\tvalidation_0-rmse:2.64827\n",
+ "[4012]\tvalidation_0-rmse:2.64824\n",
+ "[4013]\tvalidation_0-rmse:2.64822\n",
+ "[4014]\tvalidation_0-rmse:2.64820\n",
+ "[4015]\tvalidation_0-rmse:2.64823\n",
+ "[4016]\tvalidation_0-rmse:2.64824\n",
+ "[4017]\tvalidation_0-rmse:2.64826\n",
+ "[4018]\tvalidation_0-rmse:2.64827\n",
+ "[4019]\tvalidation_0-rmse:2.64827\n",
+ "[4020]\tvalidation_0-rmse:2.64829\n",
+ "[4021]\tvalidation_0-rmse:2.64831\n",
+ "[4022]\tvalidation_0-rmse:2.64833\n",
+ "[4023]\tvalidation_0-rmse:2.64829\n",
+ "[4024]\tvalidation_0-rmse:2.64833\n",
+ "[4025]\tvalidation_0-rmse:2.64834\n",
+ "[4026]\tvalidation_0-rmse:2.64835\n",
+ "[4027]\tvalidation_0-rmse:2.64834\n",
+ "[4028]\tvalidation_0-rmse:2.64830\n",
+ "[4029]\tvalidation_0-rmse:2.64831\n",
+ "[4030]\tvalidation_0-rmse:2.64829\n",
+ "[4031]\tvalidation_0-rmse:2.64833\n",
+ "[4032]\tvalidation_0-rmse:2.64842\n",
+ "[4033]\tvalidation_0-rmse:2.64844\n",
+ "[4034]\tvalidation_0-rmse:2.64845\n",
+ "[4035]\tvalidation_0-rmse:2.64840\n",
+ "[4036]\tvalidation_0-rmse:2.64842\n",
+ "[4037]\tvalidation_0-rmse:2.64840\n",
+ "[4038]\tvalidation_0-rmse:2.64842\n",
+ "[4039]\tvalidation_0-rmse:2.64842\n",
+ "[4040]\tvalidation_0-rmse:2.64839\n",
+ "[4041]\tvalidation_0-rmse:2.64840\n",
+ "[4042]\tvalidation_0-rmse:2.64836\n",
+ "[4043]\tvalidation_0-rmse:2.64827\n",
+ "[4044]\tvalidation_0-rmse:2.64815\n",
+ "[4045]\tvalidation_0-rmse:2.64816\n",
+ "[4046]\tvalidation_0-rmse:2.64812\n",
+ "[4047]\tvalidation_0-rmse:2.64804\n",
+ "[4048]\tvalidation_0-rmse:2.64805\n",
+ "[4049]\tvalidation_0-rmse:2.64808\n",
+ "[4050]\tvalidation_0-rmse:2.64810\n",
+ "[4051]\tvalidation_0-rmse:2.64811\n",
+ "[4052]\tvalidation_0-rmse:2.64815\n",
+ "[4053]\tvalidation_0-rmse:2.64811\n",
+ "[4054]\tvalidation_0-rmse:2.64814\n",
+ "[4055]\tvalidation_0-rmse:2.64819\n",
+ "[4056]\tvalidation_0-rmse:2.64817\n",
+ "[4057]\tvalidation_0-rmse:2.64819\n",
+ "[4058]\tvalidation_0-rmse:2.64816\n",
+ "[4059]\tvalidation_0-rmse:2.64806\n",
+ "[4060]\tvalidation_0-rmse:2.64809\n",
+ "[4061]\tvalidation_0-rmse:2.64804\n",
+ "[4062]\tvalidation_0-rmse:2.64803\n",
+ "[4063]\tvalidation_0-rmse:2.64803\n",
+ "[4064]\tvalidation_0-rmse:2.64808\n",
+ "[4065]\tvalidation_0-rmse:2.64802\n",
+ "[4066]\tvalidation_0-rmse:2.64794\n",
+ "[4067]\tvalidation_0-rmse:2.64790\n",
+ "[4068]\tvalidation_0-rmse:2.64785\n",
+ "[4069]\tvalidation_0-rmse:2.64782\n",
+ "[4070]\tvalidation_0-rmse:2.64770\n",
+ "[4071]\tvalidation_0-rmse:2.64756\n",
+ "[4072]\tvalidation_0-rmse:2.64756\n",
+ "[4073]\tvalidation_0-rmse:2.64749\n",
+ "[4074]\tvalidation_0-rmse:2.64744\n",
+ "[4075]\tvalidation_0-rmse:2.64725\n",
+ "[4076]\tvalidation_0-rmse:2.64727\n",
+ "[4077]\tvalidation_0-rmse:2.64726\n",
+ "[4078]\tvalidation_0-rmse:2.64733\n",
+ "[4079]\tvalidation_0-rmse:2.64731\n",
+ "[4080]\tvalidation_0-rmse:2.64729\n",
+ "[4081]\tvalidation_0-rmse:2.64729\n",
+ "[4082]\tvalidation_0-rmse:2.64730\n",
+ "[4083]\tvalidation_0-rmse:2.64731\n",
+ "[4084]\tvalidation_0-rmse:2.64733\n",
+ "[4085]\tvalidation_0-rmse:2.64735\n",
+ "[4086]\tvalidation_0-rmse:2.64732\n",
+ "[4087]\tvalidation_0-rmse:2.64734\n",
+ "[4088]\tvalidation_0-rmse:2.64734\n",
+ "[4089]\tvalidation_0-rmse:2.64730\n",
+ "[4090]\tvalidation_0-rmse:2.64730\n",
+ "[4091]\tvalidation_0-rmse:2.64730\n",
+ "[4092]\tvalidation_0-rmse:2.64729\n",
+ "[4093]\tvalidation_0-rmse:2.64728\n",
+ "[4094]\tvalidation_0-rmse:2.64723\n",
+ "[4095]\tvalidation_0-rmse:2.64717\n",
+ "[4096]\tvalidation_0-rmse:2.64720\n",
+ "[4097]\tvalidation_0-rmse:2.64712\n",
+ "[4098]\tvalidation_0-rmse:2.64717\n",
+ "[4099]\tvalidation_0-rmse:2.64714\n",
+ "[4100]\tvalidation_0-rmse:2.64712\n",
+ "[4101]\tvalidation_0-rmse:2.64707\n",
+ "[4102]\tvalidation_0-rmse:2.64703\n",
+ "[4103]\tvalidation_0-rmse:2.64700\n",
+ "[4104]\tvalidation_0-rmse:2.64694\n",
+ "[4105]\tvalidation_0-rmse:2.64686\n",
+ "[4106]\tvalidation_0-rmse:2.64683\n",
+ "[4107]\tvalidation_0-rmse:2.64677\n",
+ "[4108]\tvalidation_0-rmse:2.64674\n",
+ "[4109]\tvalidation_0-rmse:2.64677\n",
+ "[4110]\tvalidation_0-rmse:2.64666\n",
+ "[4111]\tvalidation_0-rmse:2.64667\n",
+ "[4112]\tvalidation_0-rmse:2.64667\n",
+ "[4113]\tvalidation_0-rmse:2.64667\n",
+ "[4114]\tvalidation_0-rmse:2.64668\n",
+ "[4115]\tvalidation_0-rmse:2.64666\n",
+ "[4116]\tvalidation_0-rmse:2.64669\n",
+ "[4117]\tvalidation_0-rmse:2.64667\n",
+ "[4118]\tvalidation_0-rmse:2.64663\n",
+ "[4119]\tvalidation_0-rmse:2.64650\n",
+ "[4120]\tvalidation_0-rmse:2.64649\n",
+ "[4121]\tvalidation_0-rmse:2.64647\n",
+ "[4122]\tvalidation_0-rmse:2.64646\n",
+ "[4123]\tvalidation_0-rmse:2.64644\n",
+ "[4124]\tvalidation_0-rmse:2.64641\n",
+ "[4125]\tvalidation_0-rmse:2.64640\n",
+ "[4126]\tvalidation_0-rmse:2.64635\n",
+ "[4127]\tvalidation_0-rmse:2.64633\n",
+ "[4128]\tvalidation_0-rmse:2.64624\n",
+ "[4129]\tvalidation_0-rmse:2.64623\n",
+ "[4130]\tvalidation_0-rmse:2.64624\n",
+ "[4131]\tvalidation_0-rmse:2.64623\n",
+ "[4132]\tvalidation_0-rmse:2.64618\n",
+ "[4133]\tvalidation_0-rmse:2.64615\n",
+ "[4134]\tvalidation_0-rmse:2.64614\n",
+ "[4135]\tvalidation_0-rmse:2.64615\n",
+ "[4136]\tvalidation_0-rmse:2.64612\n",
+ "[4137]\tvalidation_0-rmse:2.64612\n",
+ "[4138]\tvalidation_0-rmse:2.64616\n",
+ "[4139]\tvalidation_0-rmse:2.64607\n",
+ "[4140]\tvalidation_0-rmse:2.64604\n",
+ "[4141]\tvalidation_0-rmse:2.64604\n",
+ "[4142]\tvalidation_0-rmse:2.64597\n",
+ "[4143]\tvalidation_0-rmse:2.64598\n",
+ "[4144]\tvalidation_0-rmse:2.64591\n",
+ "[4145]\tvalidation_0-rmse:2.64593\n",
+ "[4146]\tvalidation_0-rmse:2.64590\n",
+ "[4147]\tvalidation_0-rmse:2.64588\n",
+ "[4148]\tvalidation_0-rmse:2.64582\n",
+ "[4149]\tvalidation_0-rmse:2.64577\n",
+ "[4150]\tvalidation_0-rmse:2.64582\n",
+ "[4151]\tvalidation_0-rmse:2.64582\n",
+ "[4152]\tvalidation_0-rmse:2.64583\n",
+ "[4153]\tvalidation_0-rmse:2.64578\n",
+ "[4154]\tvalidation_0-rmse:2.64573\n",
+ "[4155]\tvalidation_0-rmse:2.64577\n",
+ "[4156]\tvalidation_0-rmse:2.64576\n",
+ "[4157]\tvalidation_0-rmse:2.64565\n",
+ "[4158]\tvalidation_0-rmse:2.64547\n",
+ "[4159]\tvalidation_0-rmse:2.64550\n",
+ "[4160]\tvalidation_0-rmse:2.64549\n",
+ "[4161]\tvalidation_0-rmse:2.64551\n",
+ "[4162]\tvalidation_0-rmse:2.64550\n",
+ "[4163]\tvalidation_0-rmse:2.64553\n",
+ "[4164]\tvalidation_0-rmse:2.64548\n",
+ "[4165]\tvalidation_0-rmse:2.64549\n",
+ "[4166]\tvalidation_0-rmse:2.64543\n",
+ "[4167]\tvalidation_0-rmse:2.64535\n",
+ "[4168]\tvalidation_0-rmse:2.64528\n",
+ "[4169]\tvalidation_0-rmse:2.64521\n",
+ "[4170]\tvalidation_0-rmse:2.64527\n",
+ "[4171]\tvalidation_0-rmse:2.64525\n",
+ "[4172]\tvalidation_0-rmse:2.64523\n",
+ "[4173]\tvalidation_0-rmse:2.64527\n",
+ "[4174]\tvalidation_0-rmse:2.64522\n",
+ "[4175]\tvalidation_0-rmse:2.64520\n",
+ "[4176]\tvalidation_0-rmse:2.64519\n",
+ "[4177]\tvalidation_0-rmse:2.64512\n",
+ "[4178]\tvalidation_0-rmse:2.64503\n",
+ "[4179]\tvalidation_0-rmse:2.64507\n",
+ "[4180]\tvalidation_0-rmse:2.64506\n",
+ "[4181]\tvalidation_0-rmse:2.64507\n",
+ "[4182]\tvalidation_0-rmse:2.64510\n",
+ "[4183]\tvalidation_0-rmse:2.64511\n",
+ "[4184]\tvalidation_0-rmse:2.64512\n",
+ "[4185]\tvalidation_0-rmse:2.64513\n",
+ "[4186]\tvalidation_0-rmse:2.64508\n",
+ "[4187]\tvalidation_0-rmse:2.64492\n",
+ "[4188]\tvalidation_0-rmse:2.64486\n",
+ "[4189]\tvalidation_0-rmse:2.64486\n",
+ "[4190]\tvalidation_0-rmse:2.64481\n",
+ "[4191]\tvalidation_0-rmse:2.64481\n",
+ "[4192]\tvalidation_0-rmse:2.64481\n",
+ "[4193]\tvalidation_0-rmse:2.64481\n",
+ "[4194]\tvalidation_0-rmse:2.64469\n",
+ "[4195]\tvalidation_0-rmse:2.64471\n",
+ "[4196]\tvalidation_0-rmse:2.64474\n",
+ "[4197]\tvalidation_0-rmse:2.64473\n",
+ "[4198]\tvalidation_0-rmse:2.64466\n",
+ "[4199]\tvalidation_0-rmse:2.64465\n",
+ "[4200]\tvalidation_0-rmse:2.64464\n",
+ "[4201]\tvalidation_0-rmse:2.64464\n",
+ "[4202]\tvalidation_0-rmse:2.64463\n",
+ "[4203]\tvalidation_0-rmse:2.64460\n",
+ "[4204]\tvalidation_0-rmse:2.64455\n",
+ "[4205]\tvalidation_0-rmse:2.64455\n",
+ "[4206]\tvalidation_0-rmse:2.64454\n",
+ "[4207]\tvalidation_0-rmse:2.64454\n",
+ "[4208]\tvalidation_0-rmse:2.64455\n",
+ "[4209]\tvalidation_0-rmse:2.64455\n",
+ "[4210]\tvalidation_0-rmse:2.64454\n",
+ "[4211]\tvalidation_0-rmse:2.64449\n",
+ "[4212]\tvalidation_0-rmse:2.64446\n",
+ "[4213]\tvalidation_0-rmse:2.64447\n",
+ "[4214]\tvalidation_0-rmse:2.64444\n",
+ "[4215]\tvalidation_0-rmse:2.64442\n",
+ "[4216]\tvalidation_0-rmse:2.64445\n",
+ "[4217]\tvalidation_0-rmse:2.64442\n",
+ "[4218]\tvalidation_0-rmse:2.64439\n",
+ "[4219]\tvalidation_0-rmse:2.64440\n",
+ "[4220]\tvalidation_0-rmse:2.64442\n",
+ "[4221]\tvalidation_0-rmse:2.64441\n",
+ "[4222]\tvalidation_0-rmse:2.64444\n",
+ "[4223]\tvalidation_0-rmse:2.64443\n",
+ "[4224]\tvalidation_0-rmse:2.64441\n",
+ "[4225]\tvalidation_0-rmse:2.64434\n",
+ "[4226]\tvalidation_0-rmse:2.64436\n",
+ "[4227]\tvalidation_0-rmse:2.64437\n",
+ "[4228]\tvalidation_0-rmse:2.64435\n",
+ "[4229]\tvalidation_0-rmse:2.64431\n",
+ "[4230]\tvalidation_0-rmse:2.64420\n",
+ "[4231]\tvalidation_0-rmse:2.64421\n",
+ "[4232]\tvalidation_0-rmse:2.64421\n",
+ "[4233]\tvalidation_0-rmse:2.64419\n",
+ "[4234]\tvalidation_0-rmse:2.64420\n",
+ "[4235]\tvalidation_0-rmse:2.64419\n",
+ "[4236]\tvalidation_0-rmse:2.64414\n",
+ "[4237]\tvalidation_0-rmse:2.64412\n",
+ "[4238]\tvalidation_0-rmse:2.64412\n",
+ "[4239]\tvalidation_0-rmse:2.64405\n",
+ "[4240]\tvalidation_0-rmse:2.64410\n",
+ "[4241]\tvalidation_0-rmse:2.64408\n",
+ "[4242]\tvalidation_0-rmse:2.64405\n",
+ "[4243]\tvalidation_0-rmse:2.64402\n",
+ "[4244]\tvalidation_0-rmse:2.64403\n",
+ "[4245]\tvalidation_0-rmse:2.64399\n",
+ "[4246]\tvalidation_0-rmse:2.64394\n",
+ "[4247]\tvalidation_0-rmse:2.64393\n",
+ "[4248]\tvalidation_0-rmse:2.64394\n",
+ "[4249]\tvalidation_0-rmse:2.64391\n",
+ "[4250]\tvalidation_0-rmse:2.64391\n",
+ "[4251]\tvalidation_0-rmse:2.64390\n",
+ "[4252]\tvalidation_0-rmse:2.64389\n",
+ "[4253]\tvalidation_0-rmse:2.64378\n",
+ "[4254]\tvalidation_0-rmse:2.64380\n",
+ "[4255]\tvalidation_0-rmse:2.64382\n",
+ "[4256]\tvalidation_0-rmse:2.64379\n",
+ "[4257]\tvalidation_0-rmse:2.64377\n",
+ "[4258]\tvalidation_0-rmse:2.64378\n",
+ "[4259]\tvalidation_0-rmse:2.64371\n",
+ "[4260]\tvalidation_0-rmse:2.64368\n",
+ "[4261]\tvalidation_0-rmse:2.64364\n",
+ "[4262]\tvalidation_0-rmse:2.64359\n",
+ "[4263]\tvalidation_0-rmse:2.64349\n",
+ "[4264]\tvalidation_0-rmse:2.64339\n",
+ "[4265]\tvalidation_0-rmse:2.64340\n",
+ "[4266]\tvalidation_0-rmse:2.64344\n",
+ "[4267]\tvalidation_0-rmse:2.64341\n",
+ "[4268]\tvalidation_0-rmse:2.64340\n",
+ "[4269]\tvalidation_0-rmse:2.64339\n",
+ "[4270]\tvalidation_0-rmse:2.64338\n",
+ "[4271]\tvalidation_0-rmse:2.64331\n",
+ "[4272]\tvalidation_0-rmse:2.64322\n",
+ "[4273]\tvalidation_0-rmse:2.64324\n",
+ "[4274]\tvalidation_0-rmse:2.64323\n",
+ "[4275]\tvalidation_0-rmse:2.64320\n",
+ "[4276]\tvalidation_0-rmse:2.64319\n",
+ "[4277]\tvalidation_0-rmse:2.64318\n",
+ "[4278]\tvalidation_0-rmse:2.64313\n",
+ "[4279]\tvalidation_0-rmse:2.64310\n",
+ "[4280]\tvalidation_0-rmse:2.64307\n",
+ "[4281]\tvalidation_0-rmse:2.64303\n",
+ "[4282]\tvalidation_0-rmse:2.64295\n",
+ "[4283]\tvalidation_0-rmse:2.64294\n",
+ "[4284]\tvalidation_0-rmse:2.64287\n",
+ "[4285]\tvalidation_0-rmse:2.64279\n",
+ "[4286]\tvalidation_0-rmse:2.64277\n",
+ "[4287]\tvalidation_0-rmse:2.64277\n",
+ "[4288]\tvalidation_0-rmse:2.64278\n",
+ "[4289]\tvalidation_0-rmse:2.64277\n",
+ "[4290]\tvalidation_0-rmse:2.64276\n",
+ "[4291]\tvalidation_0-rmse:2.64275\n",
+ "[4292]\tvalidation_0-rmse:2.64274\n",
+ "[4293]\tvalidation_0-rmse:2.64271\n",
+ "[4294]\tvalidation_0-rmse:2.64271\n",
+ "[4295]\tvalidation_0-rmse:2.64269\n",
+ "[4296]\tvalidation_0-rmse:2.64267\n",
+ "[4297]\tvalidation_0-rmse:2.64262\n",
+ "[4298]\tvalidation_0-rmse:2.64262\n",
+ "[4299]\tvalidation_0-rmse:2.64265\n",
+ "[4300]\tvalidation_0-rmse:2.64264\n",
+ "[4301]\tvalidation_0-rmse:2.64260\n",
+ "[4302]\tvalidation_0-rmse:2.64260\n",
+ "[4303]\tvalidation_0-rmse:2.64261\n",
+ "[4304]\tvalidation_0-rmse:2.64263\n",
+ "[4305]\tvalidation_0-rmse:2.64264\n",
+ "[4306]\tvalidation_0-rmse:2.64262\n",
+ "[4307]\tvalidation_0-rmse:2.64253\n",
+ "[4308]\tvalidation_0-rmse:2.64251\n",
+ "[4309]\tvalidation_0-rmse:2.64255\n",
+ "[4310]\tvalidation_0-rmse:2.64255\n",
+ "[4311]\tvalidation_0-rmse:2.64259\n",
+ "[4312]\tvalidation_0-rmse:2.64259\n",
+ "[4313]\tvalidation_0-rmse:2.64261\n",
+ "[4314]\tvalidation_0-rmse:2.64264\n",
+ "[4315]\tvalidation_0-rmse:2.64264\n",
+ "[4316]\tvalidation_0-rmse:2.64263\n",
+ "[4317]\tvalidation_0-rmse:2.64261\n",
+ "[4318]\tvalidation_0-rmse:2.64255\n",
+ "[4319]\tvalidation_0-rmse:2.64260\n",
+ "[4320]\tvalidation_0-rmse:2.64257\n",
+ "[4321]\tvalidation_0-rmse:2.64255\n",
+ "[4322]\tvalidation_0-rmse:2.64256\n",
+ "[4323]\tvalidation_0-rmse:2.64252\n",
+ "[4324]\tvalidation_0-rmse:2.64249\n",
+ "[4325]\tvalidation_0-rmse:2.64234\n",
+ "[4326]\tvalidation_0-rmse:2.64236\n",
+ "[4327]\tvalidation_0-rmse:2.64231\n",
+ "[4328]\tvalidation_0-rmse:2.64221\n",
+ "[4329]\tvalidation_0-rmse:2.64220\n",
+ "[4330]\tvalidation_0-rmse:2.64213\n",
+ "[4331]\tvalidation_0-rmse:2.64207\n",
+ "[4332]\tvalidation_0-rmse:2.64205\n",
+ "[4333]\tvalidation_0-rmse:2.64206\n",
+ "[4334]\tvalidation_0-rmse:2.64201\n",
+ "[4335]\tvalidation_0-rmse:2.64200\n",
+ "[4336]\tvalidation_0-rmse:2.64196\n",
+ "[4337]\tvalidation_0-rmse:2.64190\n",
+ "[4338]\tvalidation_0-rmse:2.64193\n",
+ "[4339]\tvalidation_0-rmse:2.64190\n",
+ "[4340]\tvalidation_0-rmse:2.64176\n",
+ "[4341]\tvalidation_0-rmse:2.64175\n",
+ "[4342]\tvalidation_0-rmse:2.64172\n",
+ "[4343]\tvalidation_0-rmse:2.64169\n",
+ "[4344]\tvalidation_0-rmse:2.64171\n",
+ "[4345]\tvalidation_0-rmse:2.64156\n",
+ "[4346]\tvalidation_0-rmse:2.64154\n",
+ "[4347]\tvalidation_0-rmse:2.64150\n",
+ "[4348]\tvalidation_0-rmse:2.64141\n",
+ "[4349]\tvalidation_0-rmse:2.64139\n",
+ "[4350]\tvalidation_0-rmse:2.64137\n",
+ "[4351]\tvalidation_0-rmse:2.64124\n",
+ "[4352]\tvalidation_0-rmse:2.64125\n",
+ "[4353]\tvalidation_0-rmse:2.64118\n",
+ "[4354]\tvalidation_0-rmse:2.64116\n",
+ "[4355]\tvalidation_0-rmse:2.64113\n",
+ "[4356]\tvalidation_0-rmse:2.64110\n",
+ "[4357]\tvalidation_0-rmse:2.64104\n",
+ "[4358]\tvalidation_0-rmse:2.64103\n",
+ "[4359]\tvalidation_0-rmse:2.64103\n",
+ "[4360]\tvalidation_0-rmse:2.64101\n",
+ "[4361]\tvalidation_0-rmse:2.64092\n",
+ "[4362]\tvalidation_0-rmse:2.64088\n",
+ "[4363]\tvalidation_0-rmse:2.64087\n",
+ "[4364]\tvalidation_0-rmse:2.64086\n",
+ "[4365]\tvalidation_0-rmse:2.64082\n",
+ "[4366]\tvalidation_0-rmse:2.64081\n",
+ "[4367]\tvalidation_0-rmse:2.64079\n",
+ "[4368]\tvalidation_0-rmse:2.64075\n",
+ "[4369]\tvalidation_0-rmse:2.64073\n",
+ "[4370]\tvalidation_0-rmse:2.64071\n",
+ "[4371]\tvalidation_0-rmse:2.64070\n",
+ "[4372]\tvalidation_0-rmse:2.64071\n",
+ "[4373]\tvalidation_0-rmse:2.64067\n",
+ "[4374]\tvalidation_0-rmse:2.64058\n",
+ "[4375]\tvalidation_0-rmse:2.64056\n",
+ "[4376]\tvalidation_0-rmse:2.64050\n",
+ "[4377]\tvalidation_0-rmse:2.64048\n",
+ "[4378]\tvalidation_0-rmse:2.64041\n",
+ "[4379]\tvalidation_0-rmse:2.64040\n",
+ "[4380]\tvalidation_0-rmse:2.64037\n",
+ "[4381]\tvalidation_0-rmse:2.64033\n",
+ "[4382]\tvalidation_0-rmse:2.64024\n",
+ "[4383]\tvalidation_0-rmse:2.64024\n",
+ "[4384]\tvalidation_0-rmse:2.64028\n",
+ "[4385]\tvalidation_0-rmse:2.64027\n",
+ "[4386]\tvalidation_0-rmse:2.64024\n",
+ "[4387]\tvalidation_0-rmse:2.64013\n",
+ "[4388]\tvalidation_0-rmse:2.64009\n",
+ "[4389]\tvalidation_0-rmse:2.64001\n",
+ "[4390]\tvalidation_0-rmse:2.64000\n",
+ "[4391]\tvalidation_0-rmse:2.63998\n",
+ "[4392]\tvalidation_0-rmse:2.63999\n",
+ "[4393]\tvalidation_0-rmse:2.63991\n",
+ "[4394]\tvalidation_0-rmse:2.63990\n",
+ "[4395]\tvalidation_0-rmse:2.63991\n",
+ "[4396]\tvalidation_0-rmse:2.63988\n",
+ "[4397]\tvalidation_0-rmse:2.63986\n",
+ "[4398]\tvalidation_0-rmse:2.63987\n",
+ "[4399]\tvalidation_0-rmse:2.63989\n",
+ "[4400]\tvalidation_0-rmse:2.63986\n",
+ "[4401]\tvalidation_0-rmse:2.63986\n",
+ "[4402]\tvalidation_0-rmse:2.63979\n",
+ "[4403]\tvalidation_0-rmse:2.63979\n",
+ "[4404]\tvalidation_0-rmse:2.63977\n",
+ "[4405]\tvalidation_0-rmse:2.63978\n",
+ "[4406]\tvalidation_0-rmse:2.63973\n",
+ "[4407]\tvalidation_0-rmse:2.63974\n",
+ "[4408]\tvalidation_0-rmse:2.63973\n",
+ "[4409]\tvalidation_0-rmse:2.63976\n",
+ "[4410]\tvalidation_0-rmse:2.63971\n",
+ "[4411]\tvalidation_0-rmse:2.63972\n",
+ "[4412]\tvalidation_0-rmse:2.63968\n",
+ "[4413]\tvalidation_0-rmse:2.63969\n",
+ "[4414]\tvalidation_0-rmse:2.63970\n",
+ "[4415]\tvalidation_0-rmse:2.63971\n",
+ "[4416]\tvalidation_0-rmse:2.63970\n",
+ "[4417]\tvalidation_0-rmse:2.63965\n",
+ "[4418]\tvalidation_0-rmse:2.63960\n",
+ "[4419]\tvalidation_0-rmse:2.63965\n",
+ "[4420]\tvalidation_0-rmse:2.63964\n",
+ "[4421]\tvalidation_0-rmse:2.63961\n",
+ "[4422]\tvalidation_0-rmse:2.63956\n",
+ "[4423]\tvalidation_0-rmse:2.63954\n",
+ "[4424]\tvalidation_0-rmse:2.63954\n",
+ "[4425]\tvalidation_0-rmse:2.63957\n",
+ "[4426]\tvalidation_0-rmse:2.63957\n",
+ "[4427]\tvalidation_0-rmse:2.63960\n",
+ "[4428]\tvalidation_0-rmse:2.63953\n",
+ "[4429]\tvalidation_0-rmse:2.63956\n",
+ "[4430]\tvalidation_0-rmse:2.63955\n",
+ "[4431]\tvalidation_0-rmse:2.63956\n",
+ "[4432]\tvalidation_0-rmse:2.63948\n",
+ "[4433]\tvalidation_0-rmse:2.63949\n",
+ "[4434]\tvalidation_0-rmse:2.63947\n",
+ "[4435]\tvalidation_0-rmse:2.63943\n",
+ "[4436]\tvalidation_0-rmse:2.63937\n",
+ "[4437]\tvalidation_0-rmse:2.63940\n",
+ "[4438]\tvalidation_0-rmse:2.63928\n",
+ "[4439]\tvalidation_0-rmse:2.63928\n",
+ "[4440]\tvalidation_0-rmse:2.63932\n",
+ "[4441]\tvalidation_0-rmse:2.63934\n",
+ "[4442]\tvalidation_0-rmse:2.63934\n",
+ "[4443]\tvalidation_0-rmse:2.63935\n",
+ "[4444]\tvalidation_0-rmse:2.63937\n",
+ "[4445]\tvalidation_0-rmse:2.63944\n",
+ "[4446]\tvalidation_0-rmse:2.63940\n",
+ "[4447]\tvalidation_0-rmse:2.63940\n",
+ "[4448]\tvalidation_0-rmse:2.63931\n",
+ "[4449]\tvalidation_0-rmse:2.63927\n",
+ "[4450]\tvalidation_0-rmse:2.63926\n",
+ "[4451]\tvalidation_0-rmse:2.63922\n",
+ "[4452]\tvalidation_0-rmse:2.63921\n",
+ "[4453]\tvalidation_0-rmse:2.63922\n",
+ "[4454]\tvalidation_0-rmse:2.63922\n",
+ "[4455]\tvalidation_0-rmse:2.63918\n",
+ "[4456]\tvalidation_0-rmse:2.63904\n",
+ "[4457]\tvalidation_0-rmse:2.63900\n",
+ "[4458]\tvalidation_0-rmse:2.63902\n",
+ "[4459]\tvalidation_0-rmse:2.63897\n",
+ "[4460]\tvalidation_0-rmse:2.63897\n",
+ "[4461]\tvalidation_0-rmse:2.63895\n",
+ "[4462]\tvalidation_0-rmse:2.63888\n",
+ "[4463]\tvalidation_0-rmse:2.63887\n",
+ "[4464]\tvalidation_0-rmse:2.63880\n",
+ "[4465]\tvalidation_0-rmse:2.63878\n",
+ "[4466]\tvalidation_0-rmse:2.63879\n",
+ "[4467]\tvalidation_0-rmse:2.63878\n",
+ "[4468]\tvalidation_0-rmse:2.63875\n",
+ "[4469]\tvalidation_0-rmse:2.63875\n",
+ "[4470]\tvalidation_0-rmse:2.63874\n",
+ "[4471]\tvalidation_0-rmse:2.63874\n",
+ "[4472]\tvalidation_0-rmse:2.63876\n",
+ "[4473]\tvalidation_0-rmse:2.63877\n",
+ "[4474]\tvalidation_0-rmse:2.63874\n",
+ "[4475]\tvalidation_0-rmse:2.63876\n",
+ "[4476]\tvalidation_0-rmse:2.63873\n",
+ "[4477]\tvalidation_0-rmse:2.63865\n",
+ "[4478]\tvalidation_0-rmse:2.63863\n",
+ "[4479]\tvalidation_0-rmse:2.63856\n",
+ "[4480]\tvalidation_0-rmse:2.63856\n",
+ "[4481]\tvalidation_0-rmse:2.63856\n",
+ "[4482]\tvalidation_0-rmse:2.63856\n",
+ "[4483]\tvalidation_0-rmse:2.63851\n",
+ "[4484]\tvalidation_0-rmse:2.63851\n",
+ "[4485]\tvalidation_0-rmse:2.63849\n",
+ "[4486]\tvalidation_0-rmse:2.63849\n",
+ "[4487]\tvalidation_0-rmse:2.63851\n",
+ "[4488]\tvalidation_0-rmse:2.63845\n",
+ "[4489]\tvalidation_0-rmse:2.63842\n",
+ "[4490]\tvalidation_0-rmse:2.63842\n",
+ "[4491]\tvalidation_0-rmse:2.63843\n",
+ "[4492]\tvalidation_0-rmse:2.63842\n",
+ "[4493]\tvalidation_0-rmse:2.63843\n",
+ "[4494]\tvalidation_0-rmse:2.63844\n",
+ "[4495]\tvalidation_0-rmse:2.63843\n",
+ "[4496]\tvalidation_0-rmse:2.63842\n",
+ "[4497]\tvalidation_0-rmse:2.63840\n",
+ "[4498]\tvalidation_0-rmse:2.63838\n",
+ "[4499]\tvalidation_0-rmse:2.63837\n",
+ "[4500]\tvalidation_0-rmse:2.63840\n",
+ "[4501]\tvalidation_0-rmse:2.63844\n",
+ "[4502]\tvalidation_0-rmse:2.63846\n",
+ "[4503]\tvalidation_0-rmse:2.63843\n",
+ "[4504]\tvalidation_0-rmse:2.63842\n",
+ "[4505]\tvalidation_0-rmse:2.63846\n",
+ "[4506]\tvalidation_0-rmse:2.63848\n",
+ "[4507]\tvalidation_0-rmse:2.63849\n",
+ "[4508]\tvalidation_0-rmse:2.63847\n",
+ "[4509]\tvalidation_0-rmse:2.63845\n",
+ "[4510]\tvalidation_0-rmse:2.63844\n",
+ "[4511]\tvalidation_0-rmse:2.63844\n",
+ "[4512]\tvalidation_0-rmse:2.63843\n",
+ "[4513]\tvalidation_0-rmse:2.63842\n",
+ "[4514]\tvalidation_0-rmse:2.63844\n",
+ "[4515]\tvalidation_0-rmse:2.63845\n",
+ "[4516]\tvalidation_0-rmse:2.63843\n",
+ "[4517]\tvalidation_0-rmse:2.63844\n",
+ "[4518]\tvalidation_0-rmse:2.63838\n",
+ "[4519]\tvalidation_0-rmse:2.63838\n",
+ "[4520]\tvalidation_0-rmse:2.63843\n",
+ "[4521]\tvalidation_0-rmse:2.63830\n",
+ "[4522]\tvalidation_0-rmse:2.63834\n",
+ "[4523]\tvalidation_0-rmse:2.63837\n",
+ "[4524]\tvalidation_0-rmse:2.63834\n",
+ "[4525]\tvalidation_0-rmse:2.63830\n",
+ "[4526]\tvalidation_0-rmse:2.63832\n",
+ "[4527]\tvalidation_0-rmse:2.63832\n",
+ "[4528]\tvalidation_0-rmse:2.63827\n",
+ "[4529]\tvalidation_0-rmse:2.63830\n",
+ "[4530]\tvalidation_0-rmse:2.63830\n",
+ "[4531]\tvalidation_0-rmse:2.63822\n",
+ "[4532]\tvalidation_0-rmse:2.63817\n",
+ "[4533]\tvalidation_0-rmse:2.63815\n",
+ "[4534]\tvalidation_0-rmse:2.63812\n",
+ "[4535]\tvalidation_0-rmse:2.63813\n",
+ "[4536]\tvalidation_0-rmse:2.63815\n",
+ "[4537]\tvalidation_0-rmse:2.63816\n",
+ "[4538]\tvalidation_0-rmse:2.63812\n",
+ "[4539]\tvalidation_0-rmse:2.63796\n",
+ "[4540]\tvalidation_0-rmse:2.63796\n",
+ "[4541]\tvalidation_0-rmse:2.63798\n",
+ "[4542]\tvalidation_0-rmse:2.63799\n",
+ "[4543]\tvalidation_0-rmse:2.63797\n",
+ "[4544]\tvalidation_0-rmse:2.63790\n",
+ "[4545]\tvalidation_0-rmse:2.63782\n",
+ "[4546]\tvalidation_0-rmse:2.63783\n",
+ "[4547]\tvalidation_0-rmse:2.63775\n",
+ "[4548]\tvalidation_0-rmse:2.63764\n",
+ "[4549]\tvalidation_0-rmse:2.63764\n",
+ "[4550]\tvalidation_0-rmse:2.63767\n",
+ "[4551]\tvalidation_0-rmse:2.63765\n",
+ "[4552]\tvalidation_0-rmse:2.63762\n",
+ "[4553]\tvalidation_0-rmse:2.63761\n",
+ "[4554]\tvalidation_0-rmse:2.63763\n",
+ "[4555]\tvalidation_0-rmse:2.63760\n",
+ "[4556]\tvalidation_0-rmse:2.63761\n",
+ "[4557]\tvalidation_0-rmse:2.63758\n",
+ "[4558]\tvalidation_0-rmse:2.63755\n",
+ "[4559]\tvalidation_0-rmse:2.63755\n",
+ "[4560]\tvalidation_0-rmse:2.63755\n",
+ "[4561]\tvalidation_0-rmse:2.63753\n",
+ "[4562]\tvalidation_0-rmse:2.63745\n",
+ "[4563]\tvalidation_0-rmse:2.63743\n",
+ "[4564]\tvalidation_0-rmse:2.63747\n",
+ "[4565]\tvalidation_0-rmse:2.63748\n",
+ "[4566]\tvalidation_0-rmse:2.63749\n",
+ "[4567]\tvalidation_0-rmse:2.63747\n",
+ "[4568]\tvalidation_0-rmse:2.63735\n",
+ "[4569]\tvalidation_0-rmse:2.63733\n",
+ "[4570]\tvalidation_0-rmse:2.63738\n",
+ "[4571]\tvalidation_0-rmse:2.63737\n",
+ "[4572]\tvalidation_0-rmse:2.63735\n",
+ "[4573]\tvalidation_0-rmse:2.63735\n",
+ "[4574]\tvalidation_0-rmse:2.63732\n",
+ "[4575]\tvalidation_0-rmse:2.63736\n",
+ "[4576]\tvalidation_0-rmse:2.63737\n",
+ "[4577]\tvalidation_0-rmse:2.63731\n",
+ "[4578]\tvalidation_0-rmse:2.63729\n",
+ "[4579]\tvalidation_0-rmse:2.63730\n",
+ "[4580]\tvalidation_0-rmse:2.63729\n",
+ "[4581]\tvalidation_0-rmse:2.63731\n",
+ "[4582]\tvalidation_0-rmse:2.63730\n",
+ "[4583]\tvalidation_0-rmse:2.63728\n",
+ "[4584]\tvalidation_0-rmse:2.63728\n",
+ "[4585]\tvalidation_0-rmse:2.63725\n",
+ "[4586]\tvalidation_0-rmse:2.63725\n",
+ "[4587]\tvalidation_0-rmse:2.63720\n",
+ "[4588]\tvalidation_0-rmse:2.63725\n",
+ "[4589]\tvalidation_0-rmse:2.63720\n",
+ "[4590]\tvalidation_0-rmse:2.63713\n",
+ "[4591]\tvalidation_0-rmse:2.63708\n",
+ "[4592]\tvalidation_0-rmse:2.63702\n",
+ "[4593]\tvalidation_0-rmse:2.63699\n",
+ "[4594]\tvalidation_0-rmse:2.63700\n",
+ "[4595]\tvalidation_0-rmse:2.63698\n",
+ "[4596]\tvalidation_0-rmse:2.63698\n",
+ "[4597]\tvalidation_0-rmse:2.63691\n",
+ "[4598]\tvalidation_0-rmse:2.63690\n",
+ "[4599]\tvalidation_0-rmse:2.63690\n",
+ "[4600]\tvalidation_0-rmse:2.63686\n",
+ "[4601]\tvalidation_0-rmse:2.63686\n",
+ "[4602]\tvalidation_0-rmse:2.63684\n",
+ "[4603]\tvalidation_0-rmse:2.63687\n",
+ "[4604]\tvalidation_0-rmse:2.63687\n",
+ "[4605]\tvalidation_0-rmse:2.63685\n",
+ "[4606]\tvalidation_0-rmse:2.63684\n",
+ "[4607]\tvalidation_0-rmse:2.63683\n",
+ "[4608]\tvalidation_0-rmse:2.63686\n",
+ "[4609]\tvalidation_0-rmse:2.63686\n",
+ "[4610]\tvalidation_0-rmse:2.63683\n",
+ "[4611]\tvalidation_0-rmse:2.63684\n",
+ "[4612]\tvalidation_0-rmse:2.63682\n",
+ "[4613]\tvalidation_0-rmse:2.63684\n",
+ "[4614]\tvalidation_0-rmse:2.63679\n",
+ "[4615]\tvalidation_0-rmse:2.63680\n",
+ "[4616]\tvalidation_0-rmse:2.63682\n",
+ "[4617]\tvalidation_0-rmse:2.63681\n",
+ "[4618]\tvalidation_0-rmse:2.63685\n",
+ "[4619]\tvalidation_0-rmse:2.63683\n",
+ "[4620]\tvalidation_0-rmse:2.63672\n",
+ "[4621]\tvalidation_0-rmse:2.63673\n",
+ "[4622]\tvalidation_0-rmse:2.63666\n",
+ "[4623]\tvalidation_0-rmse:2.63667\n",
+ "[4624]\tvalidation_0-rmse:2.63663\n",
+ "[4625]\tvalidation_0-rmse:2.63658\n",
+ "[4626]\tvalidation_0-rmse:2.63651\n",
+ "[4627]\tvalidation_0-rmse:2.63647\n",
+ "[4628]\tvalidation_0-rmse:2.63648\n",
+ "[4629]\tvalidation_0-rmse:2.63642\n",
+ "[4630]\tvalidation_0-rmse:2.63645\n",
+ "[4631]\tvalidation_0-rmse:2.63638\n",
+ "[4632]\tvalidation_0-rmse:2.63639\n",
+ "[4633]\tvalidation_0-rmse:2.63639\n",
+ "[4634]\tvalidation_0-rmse:2.63637\n",
+ "[4635]\tvalidation_0-rmse:2.63632\n",
+ "[4636]\tvalidation_0-rmse:2.63635\n",
+ "[4637]\tvalidation_0-rmse:2.63634\n",
+ "[4638]\tvalidation_0-rmse:2.63630\n",
+ "[4639]\tvalidation_0-rmse:2.63631\n",
+ "[4640]\tvalidation_0-rmse:2.63631\n",
+ "[4641]\tvalidation_0-rmse:2.63626\n",
+ "[4642]\tvalidation_0-rmse:2.63624\n",
+ "[4643]\tvalidation_0-rmse:2.63622\n",
+ "[4644]\tvalidation_0-rmse:2.63620\n",
+ "[4645]\tvalidation_0-rmse:2.63621\n",
+ "[4646]\tvalidation_0-rmse:2.63619\n",
+ "[4647]\tvalidation_0-rmse:2.63618\n",
+ "[4648]\tvalidation_0-rmse:2.63617\n",
+ "[4649]\tvalidation_0-rmse:2.63615\n",
+ "[4650]\tvalidation_0-rmse:2.63614\n",
+ "[4651]\tvalidation_0-rmse:2.63612\n",
+ "[4652]\tvalidation_0-rmse:2.63608\n",
+ "[4653]\tvalidation_0-rmse:2.63611\n",
+ "[4654]\tvalidation_0-rmse:2.63607\n",
+ "[4655]\tvalidation_0-rmse:2.63605\n",
+ "[4656]\tvalidation_0-rmse:2.63599\n",
+ "[4657]\tvalidation_0-rmse:2.63596\n",
+ "[4658]\tvalidation_0-rmse:2.63594\n",
+ "[4659]\tvalidation_0-rmse:2.63594\n",
+ "[4660]\tvalidation_0-rmse:2.63594\n",
+ "[4661]\tvalidation_0-rmse:2.63593\n",
+ "[4662]\tvalidation_0-rmse:2.63593\n",
+ "[4663]\tvalidation_0-rmse:2.63587\n",
+ "[4664]\tvalidation_0-rmse:2.63585\n",
+ "[4665]\tvalidation_0-rmse:2.63583\n",
+ "[4666]\tvalidation_0-rmse:2.63583\n",
+ "[4667]\tvalidation_0-rmse:2.63582\n",
+ "[4668]\tvalidation_0-rmse:2.63581\n",
+ "[4669]\tvalidation_0-rmse:2.63576\n",
+ "[4670]\tvalidation_0-rmse:2.63573\n",
+ "[4671]\tvalidation_0-rmse:2.63571\n",
+ "[4672]\tvalidation_0-rmse:2.63566\n",
+ "[4673]\tvalidation_0-rmse:2.63569\n",
+ "[4674]\tvalidation_0-rmse:2.63568\n",
+ "[4675]\tvalidation_0-rmse:2.63566\n",
+ "[4676]\tvalidation_0-rmse:2.63565\n",
+ "[4677]\tvalidation_0-rmse:2.63565\n",
+ "[4678]\tvalidation_0-rmse:2.63565\n",
+ "[4679]\tvalidation_0-rmse:2.63564\n",
+ "[4680]\tvalidation_0-rmse:2.63560\n",
+ "[4681]\tvalidation_0-rmse:2.63556\n",
+ "[4682]\tvalidation_0-rmse:2.63553\n",
+ "[4683]\tvalidation_0-rmse:2.63554\n",
+ "[4684]\tvalidation_0-rmse:2.63556\n",
+ "[4685]\tvalidation_0-rmse:2.63552\n",
+ "[4686]\tvalidation_0-rmse:2.63547\n",
+ "[4687]\tvalidation_0-rmse:2.63546\n",
+ "[4688]\tvalidation_0-rmse:2.63544\n",
+ "[4689]\tvalidation_0-rmse:2.63545\n",
+ "[4690]\tvalidation_0-rmse:2.63544\n",
+ "[4691]\tvalidation_0-rmse:2.63524\n",
+ "[4692]\tvalidation_0-rmse:2.63526\n",
+ "[4693]\tvalidation_0-rmse:2.63518\n",
+ "[4694]\tvalidation_0-rmse:2.63512\n",
+ "[4695]\tvalidation_0-rmse:2.63511\n",
+ "[4696]\tvalidation_0-rmse:2.63508\n",
+ "[4697]\tvalidation_0-rmse:2.63505\n",
+ "[4698]\tvalidation_0-rmse:2.63508\n",
+ "[4699]\tvalidation_0-rmse:2.63510\n",
+ "[4700]\tvalidation_0-rmse:2.63509\n",
+ "[4701]\tvalidation_0-rmse:2.63507\n",
+ "[4702]\tvalidation_0-rmse:2.63505\n",
+ "[4703]\tvalidation_0-rmse:2.63503\n",
+ "[4704]\tvalidation_0-rmse:2.63499\n",
+ "[4705]\tvalidation_0-rmse:2.63496\n",
+ "[4706]\tvalidation_0-rmse:2.63494\n",
+ "[4707]\tvalidation_0-rmse:2.63491\n",
+ "[4708]\tvalidation_0-rmse:2.63489\n",
+ "[4709]\tvalidation_0-rmse:2.63486\n",
+ "[4710]\tvalidation_0-rmse:2.63482\n",
+ "[4711]\tvalidation_0-rmse:2.63480\n",
+ "[4712]\tvalidation_0-rmse:2.63478\n",
+ "[4713]\tvalidation_0-rmse:2.63478\n",
+ "[4714]\tvalidation_0-rmse:2.63478\n",
+ "[4715]\tvalidation_0-rmse:2.63475\n",
+ "[4716]\tvalidation_0-rmse:2.63476\n",
+ "[4717]\tvalidation_0-rmse:2.63480\n",
+ "[4718]\tvalidation_0-rmse:2.63483\n",
+ "[4719]\tvalidation_0-rmse:2.63485\n",
+ "[4720]\tvalidation_0-rmse:2.63483\n",
+ "[4721]\tvalidation_0-rmse:2.63484\n",
+ "[4722]\tvalidation_0-rmse:2.63484\n",
+ "[4723]\tvalidation_0-rmse:2.63483\n",
+ "[4724]\tvalidation_0-rmse:2.63487\n",
+ "[4725]\tvalidation_0-rmse:2.63490\n",
+ "[4726]\tvalidation_0-rmse:2.63491\n",
+ "[4727]\tvalidation_0-rmse:2.63492\n",
+ "[4728]\tvalidation_0-rmse:2.63491\n",
+ "[4729]\tvalidation_0-rmse:2.63490\n",
+ "[4730]\tvalidation_0-rmse:2.63489\n",
+ "[4731]\tvalidation_0-rmse:2.63490\n",
+ "[4732]\tvalidation_0-rmse:2.63488\n",
+ "[4733]\tvalidation_0-rmse:2.63490\n",
+ "[4734]\tvalidation_0-rmse:2.63494\n",
+ "[4735]\tvalidation_0-rmse:2.63487\n",
+ "[4736]\tvalidation_0-rmse:2.63489\n",
+ "[4737]\tvalidation_0-rmse:2.63488\n",
+ "[4738]\tvalidation_0-rmse:2.63488\n",
+ "[4739]\tvalidation_0-rmse:2.63485\n",
+ "[4740]\tvalidation_0-rmse:2.63481\n",
+ "[4741]\tvalidation_0-rmse:2.63473\n",
+ "[4742]\tvalidation_0-rmse:2.63472\n",
+ "[4743]\tvalidation_0-rmse:2.63474\n",
+ "[4744]\tvalidation_0-rmse:2.63473\n",
+ "[4745]\tvalidation_0-rmse:2.63467\n",
+ "[4746]\tvalidation_0-rmse:2.63463\n",
+ "[4747]\tvalidation_0-rmse:2.63453\n",
+ "[4748]\tvalidation_0-rmse:2.63452\n",
+ "[4749]\tvalidation_0-rmse:2.63446\n",
+ "[4750]\tvalidation_0-rmse:2.63439\n",
+ "[4751]\tvalidation_0-rmse:2.63439\n",
+ "[4752]\tvalidation_0-rmse:2.63440\n",
+ "[4753]\tvalidation_0-rmse:2.63439\n",
+ "[4754]\tvalidation_0-rmse:2.63438\n",
+ "[4755]\tvalidation_0-rmse:2.63436\n",
+ "[4756]\tvalidation_0-rmse:2.63434\n",
+ "[4757]\tvalidation_0-rmse:2.63429\n",
+ "[4758]\tvalidation_0-rmse:2.63426\n",
+ "[4759]\tvalidation_0-rmse:2.63431\n",
+ "[4760]\tvalidation_0-rmse:2.63430\n",
+ "[4761]\tvalidation_0-rmse:2.63429\n",
+ "[4762]\tvalidation_0-rmse:2.63424\n",
+ "[4763]\tvalidation_0-rmse:2.63419\n",
+ "[4764]\tvalidation_0-rmse:2.63420\n",
+ "[4765]\tvalidation_0-rmse:2.63417\n",
+ "[4766]\tvalidation_0-rmse:2.63414\n",
+ "[4767]\tvalidation_0-rmse:2.63413\n",
+ "[4768]\tvalidation_0-rmse:2.63407\n",
+ "[4769]\tvalidation_0-rmse:2.63395\n",
+ "[4770]\tvalidation_0-rmse:2.63388\n",
+ "[4771]\tvalidation_0-rmse:2.63384\n",
+ "[4772]\tvalidation_0-rmse:2.63382\n",
+ "[4773]\tvalidation_0-rmse:2.63386\n",
+ "[4774]\tvalidation_0-rmse:2.63387\n",
+ "[4775]\tvalidation_0-rmse:2.63388\n",
+ "[4776]\tvalidation_0-rmse:2.63387\n",
+ "[4777]\tvalidation_0-rmse:2.63388\n",
+ "[4778]\tvalidation_0-rmse:2.63391\n",
+ "[4779]\tvalidation_0-rmse:2.63391\n",
+ "[4780]\tvalidation_0-rmse:2.63393\n",
+ "[4781]\tvalidation_0-rmse:2.63393\n",
+ "[4782]\tvalidation_0-rmse:2.63393\n",
+ "[4783]\tvalidation_0-rmse:2.63395\n",
+ "[4784]\tvalidation_0-rmse:2.63391\n",
+ "[4785]\tvalidation_0-rmse:2.63392\n",
+ "[4786]\tvalidation_0-rmse:2.63390\n",
+ "[4787]\tvalidation_0-rmse:2.63381\n",
+ "[4788]\tvalidation_0-rmse:2.63380\n",
+ "[4789]\tvalidation_0-rmse:2.63379\n",
+ "[4790]\tvalidation_0-rmse:2.63379\n",
+ "[4791]\tvalidation_0-rmse:2.63375\n",
+ "[4792]\tvalidation_0-rmse:2.63374\n",
+ "[4793]\tvalidation_0-rmse:2.63372\n",
+ "[4794]\tvalidation_0-rmse:2.63371\n",
+ "[4795]\tvalidation_0-rmse:2.63366\n",
+ "[4796]\tvalidation_0-rmse:2.63365\n",
+ "[4797]\tvalidation_0-rmse:2.63366\n",
+ "[4798]\tvalidation_0-rmse:2.63366\n",
+ "[4799]\tvalidation_0-rmse:2.63362\n",
+ "[4800]\tvalidation_0-rmse:2.63361\n",
+ "[4801]\tvalidation_0-rmse:2.63359\n",
+ "[4802]\tvalidation_0-rmse:2.63358\n",
+ "[4803]\tvalidation_0-rmse:2.63356\n",
+ "[4804]\tvalidation_0-rmse:2.63350\n",
+ "[4805]\tvalidation_0-rmse:2.63348\n",
+ "[4806]\tvalidation_0-rmse:2.63345\n",
+ "[4807]\tvalidation_0-rmse:2.63343\n",
+ "[4808]\tvalidation_0-rmse:2.63342\n",
+ "[4809]\tvalidation_0-rmse:2.63341\n",
+ "[4810]\tvalidation_0-rmse:2.63339\n",
+ "[4811]\tvalidation_0-rmse:2.63338\n",
+ "[4812]\tvalidation_0-rmse:2.63339\n",
+ "[4813]\tvalidation_0-rmse:2.63339\n",
+ "[4814]\tvalidation_0-rmse:2.63343\n",
+ "[4815]\tvalidation_0-rmse:2.63341\n",
+ "[4816]\tvalidation_0-rmse:2.63340\n",
+ "[4817]\tvalidation_0-rmse:2.63339\n",
+ "[4818]\tvalidation_0-rmse:2.63336\n",
+ "[4819]\tvalidation_0-rmse:2.63343\n",
+ "[4820]\tvalidation_0-rmse:2.63340\n",
+ "[4821]\tvalidation_0-rmse:2.63336\n",
+ "[4822]\tvalidation_0-rmse:2.63336\n",
+ "[4823]\tvalidation_0-rmse:2.63341\n",
+ "[4824]\tvalidation_0-rmse:2.63341\n",
+ "[4825]\tvalidation_0-rmse:2.63339\n",
+ "[4826]\tvalidation_0-rmse:2.63336\n",
+ "[4827]\tvalidation_0-rmse:2.63339\n",
+ "[4828]\tvalidation_0-rmse:2.63335\n",
+ "[4829]\tvalidation_0-rmse:2.63333\n",
+ "[4830]\tvalidation_0-rmse:2.63330\n",
+ "[4831]\tvalidation_0-rmse:2.63329\n",
+ "[4832]\tvalidation_0-rmse:2.63326\n",
+ "[4833]\tvalidation_0-rmse:2.63324\n",
+ "[4834]\tvalidation_0-rmse:2.63324\n",
+ "[4835]\tvalidation_0-rmse:2.63324\n",
+ "[4836]\tvalidation_0-rmse:2.63323\n",
+ "[4837]\tvalidation_0-rmse:2.63319\n",
+ "[4838]\tvalidation_0-rmse:2.63318\n",
+ "[4839]\tvalidation_0-rmse:2.63322\n",
+ "[4840]\tvalidation_0-rmse:2.63323\n",
+ "[4841]\tvalidation_0-rmse:2.63319\n",
+ "[4842]\tvalidation_0-rmse:2.63323\n",
+ "[4843]\tvalidation_0-rmse:2.63323\n",
+ "[4844]\tvalidation_0-rmse:2.63322\n",
+ "[4845]\tvalidation_0-rmse:2.63328\n",
+ "[4846]\tvalidation_0-rmse:2.63322\n",
+ "[4847]\tvalidation_0-rmse:2.63324\n",
+ "[4848]\tvalidation_0-rmse:2.63316\n",
+ "[4849]\tvalidation_0-rmse:2.63313\n",
+ "[4850]\tvalidation_0-rmse:2.63306\n",
+ "[4851]\tvalidation_0-rmse:2.63305\n",
+ "[4852]\tvalidation_0-rmse:2.63302\n",
+ "[4853]\tvalidation_0-rmse:2.63303\n",
+ "[4854]\tvalidation_0-rmse:2.63302\n",
+ "[4855]\tvalidation_0-rmse:2.63302\n",
+ "[4856]\tvalidation_0-rmse:2.63301\n",
+ "[4857]\tvalidation_0-rmse:2.63304\n",
+ "[4858]\tvalidation_0-rmse:2.63306\n",
+ "[4859]\tvalidation_0-rmse:2.63310\n",
+ "[4860]\tvalidation_0-rmse:2.63302\n",
+ "[4861]\tvalidation_0-rmse:2.63303\n",
+ "[4862]\tvalidation_0-rmse:2.63301\n",
+ "[4863]\tvalidation_0-rmse:2.63304\n",
+ "[4864]\tvalidation_0-rmse:2.63306\n",
+ "[4865]\tvalidation_0-rmse:2.63303\n",
+ "[4866]\tvalidation_0-rmse:2.63305\n",
+ "[4867]\tvalidation_0-rmse:2.63304\n",
+ "[4868]\tvalidation_0-rmse:2.63305\n",
+ "[4869]\tvalidation_0-rmse:2.63305\n",
+ "[4870]\tvalidation_0-rmse:2.63307\n",
+ "[4871]\tvalidation_0-rmse:2.63307\n",
+ "[4872]\tvalidation_0-rmse:2.63304\n",
+ "[4873]\tvalidation_0-rmse:2.63306\n",
+ "[4874]\tvalidation_0-rmse:2.63303\n",
+ "[4875]\tvalidation_0-rmse:2.63304\n",
+ "[4876]\tvalidation_0-rmse:2.63295\n",
+ "[4877]\tvalidation_0-rmse:2.63295\n",
+ "[4878]\tvalidation_0-rmse:2.63293\n",
+ "[4879]\tvalidation_0-rmse:2.63292\n",
+ "[4880]\tvalidation_0-rmse:2.63288\n",
+ "[4881]\tvalidation_0-rmse:2.63287\n",
+ "[4882]\tvalidation_0-rmse:2.63286\n",
+ "[4883]\tvalidation_0-rmse:2.63287\n",
+ "[4884]\tvalidation_0-rmse:2.63284\n",
+ "[4885]\tvalidation_0-rmse:2.63286\n",
+ "[4886]\tvalidation_0-rmse:2.63286\n",
+ "[4887]\tvalidation_0-rmse:2.63288\n",
+ "[4888]\tvalidation_0-rmse:2.63288\n",
+ "[4889]\tvalidation_0-rmse:2.63291\n",
+ "[4890]\tvalidation_0-rmse:2.63286\n",
+ "[4891]\tvalidation_0-rmse:2.63284\n",
+ "[4892]\tvalidation_0-rmse:2.63281\n",
+ "[4893]\tvalidation_0-rmse:2.63273\n",
+ "[4894]\tvalidation_0-rmse:2.63271\n",
+ "[4895]\tvalidation_0-rmse:2.63263\n",
+ "[4896]\tvalidation_0-rmse:2.63262\n",
+ "[4897]\tvalidation_0-rmse:2.63261\n",
+ "[4898]\tvalidation_0-rmse:2.63265\n",
+ "[4899]\tvalidation_0-rmse:2.63257\n",
+ "[4900]\tvalidation_0-rmse:2.63260\n",
+ "[4901]\tvalidation_0-rmse:2.63257\n",
+ "[4902]\tvalidation_0-rmse:2.63257\n",
+ "[4903]\tvalidation_0-rmse:2.63253\n",
+ "[4904]\tvalidation_0-rmse:2.63250\n",
+ "[4905]\tvalidation_0-rmse:2.63247\n",
+ "[4906]\tvalidation_0-rmse:2.63243\n",
+ "[4907]\tvalidation_0-rmse:2.63241\n",
+ "[4908]\tvalidation_0-rmse:2.63242\n",
+ "[4909]\tvalidation_0-rmse:2.63237\n",
+ "[4910]\tvalidation_0-rmse:2.63236\n",
+ "[4911]\tvalidation_0-rmse:2.63232\n",
+ "[4912]\tvalidation_0-rmse:2.63226\n",
+ "[4913]\tvalidation_0-rmse:2.63225\n",
+ "[4914]\tvalidation_0-rmse:2.63226\n",
+ "[4915]\tvalidation_0-rmse:2.63224\n",
+ "[4916]\tvalidation_0-rmse:2.63224\n",
+ "[4917]\tvalidation_0-rmse:2.63223\n",
+ "[4918]\tvalidation_0-rmse:2.63224\n",
+ "[4919]\tvalidation_0-rmse:2.63217\n",
+ "[4920]\tvalidation_0-rmse:2.63214\n",
+ "[4921]\tvalidation_0-rmse:2.63210\n",
+ "[4922]\tvalidation_0-rmse:2.63204\n",
+ "[4923]\tvalidation_0-rmse:2.63208\n",
+ "[4924]\tvalidation_0-rmse:2.63205\n",
+ "[4925]\tvalidation_0-rmse:2.63205\n",
+ "[4926]\tvalidation_0-rmse:2.63202\n",
+ "[4927]\tvalidation_0-rmse:2.63201\n",
+ "[4928]\tvalidation_0-rmse:2.63199\n",
+ "[4929]\tvalidation_0-rmse:2.63194\n",
+ "[4930]\tvalidation_0-rmse:2.63192\n",
+ "[4931]\tvalidation_0-rmse:2.63192\n",
+ "[4932]\tvalidation_0-rmse:2.63191\n",
+ "[4933]\tvalidation_0-rmse:2.63190\n",
+ "[4934]\tvalidation_0-rmse:2.63190\n",
+ "[4935]\tvalidation_0-rmse:2.63193\n",
+ "[4936]\tvalidation_0-rmse:2.63194\n",
+ "[4937]\tvalidation_0-rmse:2.63197\n",
+ "[4938]\tvalidation_0-rmse:2.63196\n",
+ "[4939]\tvalidation_0-rmse:2.63196\n",
+ "[4940]\tvalidation_0-rmse:2.63199\n",
+ "[4941]\tvalidation_0-rmse:2.63199\n",
+ "[4942]\tvalidation_0-rmse:2.63200\n",
+ "[4943]\tvalidation_0-rmse:2.63204\n",
+ "[4944]\tvalidation_0-rmse:2.63205\n",
+ "[4945]\tvalidation_0-rmse:2.63204\n",
+ "[4946]\tvalidation_0-rmse:2.63205\n",
+ "[4947]\tvalidation_0-rmse:2.63203\n",
+ "[4948]\tvalidation_0-rmse:2.63201\n",
+ "[4949]\tvalidation_0-rmse:2.63202\n",
+ "[4950]\tvalidation_0-rmse:2.63203\n",
+ "[4951]\tvalidation_0-rmse:2.63205\n",
+ "[4952]\tvalidation_0-rmse:2.63205\n",
+ "[4953]\tvalidation_0-rmse:2.63208\n",
+ "[4954]\tvalidation_0-rmse:2.63204\n",
+ "[4955]\tvalidation_0-rmse:2.63202\n",
+ "[4956]\tvalidation_0-rmse:2.63204\n",
+ "[4957]\tvalidation_0-rmse:2.63203\n",
+ "[4958]\tvalidation_0-rmse:2.63208\n",
+ "[4959]\tvalidation_0-rmse:2.63205\n",
+ "[4960]\tvalidation_0-rmse:2.63204\n",
+ "[4961]\tvalidation_0-rmse:2.63204\n",
+ "[4962]\tvalidation_0-rmse:2.63204\n",
+ "[4963]\tvalidation_0-rmse:2.63205\n",
+ "[4964]\tvalidation_0-rmse:2.63200\n",
+ "[4965]\tvalidation_0-rmse:2.63202\n",
+ "[4966]\tvalidation_0-rmse:2.63203\n",
+ "[4967]\tvalidation_0-rmse:2.63202\n",
+ "[4968]\tvalidation_0-rmse:2.63202\n",
+ "[4969]\tvalidation_0-rmse:2.63201\n",
+ "[4970]\tvalidation_0-rmse:2.63199\n",
+ "[4971]\tvalidation_0-rmse:2.63197\n",
+ "[4972]\tvalidation_0-rmse:2.63197\n",
+ "[4973]\tvalidation_0-rmse:2.63194\n",
+ "[4974]\tvalidation_0-rmse:2.63192\n",
+ "[4975]\tvalidation_0-rmse:2.63192\n",
+ "[4976]\tvalidation_0-rmse:2.63192\n",
+ "[4977]\tvalidation_0-rmse:2.63192\n",
+ "[4978]\tvalidation_0-rmse:2.63191\n",
+ "[4979]\tvalidation_0-rmse:2.63190\n",
+ "[4980]\tvalidation_0-rmse:2.63190\n",
+ "[4981]\tvalidation_0-rmse:2.63186\n",
+ "[4982]\tvalidation_0-rmse:2.63187\n",
+ "[4983]\tvalidation_0-rmse:2.63188\n",
+ "[4984]\tvalidation_0-rmse:2.63188\n",
+ "[4985]\tvalidation_0-rmse:2.63186\n",
+ "[4986]\tvalidation_0-rmse:2.63186\n",
+ "[4987]\tvalidation_0-rmse:2.63184\n",
+ "[4988]\tvalidation_0-rmse:2.63183\n",
+ "[4989]\tvalidation_0-rmse:2.63184\n",
+ "[4990]\tvalidation_0-rmse:2.63186\n",
+ "[4991]\tvalidation_0-rmse:2.63186\n",
+ "[4992]\tvalidation_0-rmse:2.63188\n",
+ "[4993]\tvalidation_0-rmse:2.63188\n",
+ "[4994]\tvalidation_0-rmse:2.63191\n",
+ "[4995]\tvalidation_0-rmse:2.63193\n",
+ "[4996]\tvalidation_0-rmse:2.63192\n",
+ "[4997]\tvalidation_0-rmse:2.63196\n",
+ "[4998]\tvalidation_0-rmse:2.63197\n",
+ "[4999]\tvalidation_0-rmse:2.63194\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-1 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: #000;\n",
+ " --sklearn-color-text-muted: #666;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-1 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: flex;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ " align-items: start;\n",
+ " justify-content: space-between;\n",
+ " gap: 0.5em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
+ " font-size: 0.6rem;\n",
+ " font-weight: lighter;\n",
+ " color: var(--sklearn-color-text-muted);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-1 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-1 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-1 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 0.5em;\n",
+ " text-align: center;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>XGBRegressor</div></div><div><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "\n",
+ "model = XGBRegressor(n_estimators=5000, learning_rate=0.07, n_jobs=-1)\n",
+ "model.fit(X_tr, y_tr, eval_set=[(X_val, y_val)], verbose=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
"outputs": [
{
"data": {
@@ -46,211 +5821,199 @@
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
- " <th>Index</th>\n",
- " <th>patient_id</th>\n",
- " <th>cohort</th>\n",
- " <th>sexM</th>\n",
- " <th>gene</th>\n",
- " <th>age_at_diagnosis</th>\n",
- " <th>age</th>\n",
- " <th>ledd</th>\n",
- " <th>time_since_intake_on</th>\n",
- " <th>time_since_intake_off</th>\n",
+ " <th>importance</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
- " <th>0</th>\n",
- " <td>0</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>52.1</td>\n",
- " <td>607.0</td>\n",
- " <td>1.9</td>\n",
- " <td>NaN</td>\n",
+ " <th>off</th>\n",
+ " <td>0.428790</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>1</th>\n",
- " <td>1</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>53.0</td>\n",
- " <td>666.0</td>\n",
- " <td>1.9</td>\n",
- " <td>17.6</td>\n",
+ " <th>mean_off</th>\n",
+ " <td>0.302743</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
- " <td>2</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>53.9</td>\n",
- " <td>717.0</td>\n",
- " <td>1.2</td>\n",
- " <td>NaN</td>\n",
+ " <th>mean_off_prog_interaction</th>\n",
+ " <td>0.166859</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>3</th>\n",
- " <td>3</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>54.8</td>\n",
- " <td>770.0</td>\n",
- " <td>1.5</td>\n",
- " <td>NaN</td>\n",
+ " <th>max_off</th>\n",
+ " <td>0.021442</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
- " <td>4</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>56.9</td>\n",
- " <td>885.0</td>\n",
- " <td>0.3</td>\n",
- " <td>NaN</td>\n",
+ " <th>diff_off_first</th>\n",
+ " <td>0.009662</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>...</th>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
+ " <th>num_visite</th>\n",
+ " <td>0.009011</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55598</th>\n",
- " <td>55598</td>\n",
- " <td>CZTX7061</td>\n",
- " <td>A</td>\n",
- " <td>1</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>59.0</td>\n",
- " <td>60.6</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
+ " <th>diff_off</th>\n",
+ " <td>0.008413</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55599</th>\n",
- " <td>55599</td>\n",
- " <td>CZTX7061</td>\n",
- " <td>A</td>\n",
- " <td>1</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>59.0</td>\n",
- " <td>61.1</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
+ " <th>time_since_diagnosis</th>\n",
+ " <td>0.005117</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55600</th>\n",
- " <td>55600</td>\n",
- " <td>CZTX7061</td>\n",
- " <td>A</td>\n",
- " <td>1</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>59.0</td>\n",
- " <td>61.8</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
+ " <th>moyenne_geometriques_off</th>\n",
+ " <td>0.004016</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55601</th>\n",
- " <td>55601</td>\n",
- " <td>CZTX7061</td>\n",
- " <td>A</td>\n",
- " <td>1</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>59.0</td>\n",
- " <td>62.6</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
+ " <th>nb_visites</th>\n",
+ " <td>0.003306</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>55602</th>\n",
- " <td>55602</td>\n",
- " <td>CZTX7061</td>\n",
- " <td>A</td>\n",
- " <td>1</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>59.0</td>\n",
- " <td>63.5</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
+ " <th>std_off</th>\n",
+ " <td>0.003250</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>moyenne_geometriques_on</th>\n",
+ " <td>0.002813</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean_on</th>\n",
+ " <td>0.002685</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>ratio_visite</th>\n",
+ " <td>0.002469</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std_on</th>\n",
+ " <td>0.002436</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>diff_on_first</th>\n",
+ " <td>0.002194</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>est_GBA+</th>\n",
+ " <td>0.002079</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>age_at_diagnosis</th>\n",
+ " <td>0.001975</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>diff_off_max</th>\n",
+ " <td>0.001872</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>est_OTHER+</th>\n",
+ " <td>0.001810</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean_off_based_on_disease_duration</th>\n",
+ " <td>0.001805</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>diff_off_mean</th>\n",
+ " <td>0.001763</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>est_LRRK2+</th>\n",
+ " <td>0.001716</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>relative_diff_off</th>\n",
+ " <td>0.001650</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>cohort</th>\n",
+ " <td>0.001644</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>ratio_on_off</th>\n",
+ " <td>0.001326</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>age</th>\n",
+ " <td>0.001230</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>sexM</th>\n",
+ " <td>0.001116</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>time_since_last_visit</th>\n",
+ " <td>0.001107</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>diff_on</th>\n",
+ " <td>0.000985</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>relative_diff_on</th>\n",
+ " <td>0.000980</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean_off_based_on_age</th>\n",
+ " <td>0.000879</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>on</th>\n",
+ " <td>0.000861</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
- "<p>55603 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
- " Index patient_id cohort sexM gene age_at_diagnosis age ledd \\\n",
- "0 0 IPLP5212 A 0 LRRK2+ 48.5 52.1 607.0 \n",
- "1 1 IPLP5212 A 0 LRRK2+ 48.5 53.0 666.0 \n",
- "2 2 IPLP5212 A 0 LRRK2+ 48.5 53.9 717.0 \n",
- "3 3 IPLP5212 A 0 LRRK2+ 48.5 54.8 770.0 \n",
- "4 4 IPLP5212 A 0 LRRK2+ 48.5 56.9 885.0 \n",
- "... ... ... ... ... ... ... ... ... \n",
- "55598 55598 CZTX7061 A 1 LRRK2+ 59.0 60.6 NaN \n",
- "55599 55599 CZTX7061 A 1 LRRK2+ 59.0 61.1 NaN \n",
- "55600 55600 CZTX7061 A 1 LRRK2+ 59.0 61.8 NaN \n",
- "55601 55601 CZTX7061 A 1 LRRK2+ 59.0 62.6 NaN \n",
- "55602 55602 CZTX7061 A 1 LRRK2+ 59.0 63.5 NaN \n",
- "\n",
- " time_since_intake_on time_since_intake_off \n",
- "0 1.9 NaN \n",
- "1 1.9 17.6 \n",
- "2 1.2 NaN \n",
- "3 1.5 NaN \n",
- "4 0.3 NaN \n",
- "... ... ... \n",
- "55598 NaN NaN \n",
- "55599 NaN NaN \n",
- "55600 NaN NaN \n",
- "55601 NaN NaN \n",
- "55602 NaN NaN \n",
- "\n",
- "[55603 rows x 10 columns]"
+ " importance\n",
+ "off 0.428790\n",
+ "mean_off 0.302743\n",
+ "mean_off_prog_interaction 0.166859\n",
+ "max_off 0.021442\n",
+ "diff_off_first 0.009662\n",
+ "num_visite 0.009011\n",
+ "diff_off 0.008413\n",
+ "time_since_diagnosis 0.005117\n",
+ "moyenne_geometriques_off 0.004016\n",
+ "nb_visites 0.003306\n",
+ "std_off 0.003250\n",
+ "moyenne_geometriques_on 0.002813\n",
+ "mean_on 0.002685\n",
+ "ratio_visite 0.002469\n",
+ "std_on 0.002436\n",
+ "diff_on_first 0.002194\n",
+ "est_GBA+ 0.002079\n",
+ "age_at_diagnosis 0.001975\n",
+ "diff_off_max 0.001872\n",
+ "est_OTHER+ 0.001810\n",
+ "mean_off_based_on_disease_duration 0.001805\n",
+ "diff_off_mean 0.001763\n",
+ "est_LRRK2+ 0.001716\n",
+ "relative_diff_off 0.001650\n",
+ "cohort 0.001644\n",
+ "ratio_on_off 0.001326\n",
+ "age 0.001230\n",
+ "sexM 0.001116\n",
+ "time_since_last_visit 0.001107\n",
+ "diff_on 0.000985\n",
+ "relative_diff_on 0.000980\n",
+ "mean_off_based_on_age 0.000879\n",
+ "on 0.000861"
]
},
- "execution_count": 3,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "X=data.drop(['on','off'],axis=1)\n",
- "y=pd.DataFrame(data['on'])\n",
- "X"
+ "# best features\n",
+ "best_features = model.feature_importances_ \n",
+ "best_features = pd.DataFrame(best_features, index=X_train.columns, columns=['importance'])\n",
+ "best_features = best_features.sort_values(by='importance', ascending=False)\n",
+ "best_features"
]
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -274,350 +6037,5704 @@
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
- " <th>Index</th>\n",
- " <th>patient_id</th>\n",
- " <th>cohort</th>\n",
- " <th>sexM</th>\n",
- " <th>gene</th>\n",
- " <th>age_at_diagnosis</th>\n",
- " <th>age</th>\n",
- " <th>ledd</th>\n",
- " <th>time_since_intake_on</th>\n",
- " <th>time_since_intake_off</th>\n",
+ " <th>importance</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
- " <th>0</th>\n",
- " <td>0</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>52.1</td>\n",
- " <td>607.0</td>\n",
- " <td>1.9</td>\n",
- " <td>NaN</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>1</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>53.0</td>\n",
- " <td>666.0</td>\n",
- " <td>1.9</td>\n",
- " <td>17.6</td>\n",
+ " <th>off</th>\n",
+ " <td>0.428790</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
- " <td>2</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>53.9</td>\n",
- " <td>717.0</td>\n",
- " <td>1.2</td>\n",
- " <td>NaN</td>\n",
+ " <th>mean_off</th>\n",
+ " <td>0.302743</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>3</th>\n",
- " <td>3</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>54.8</td>\n",
- " <td>770.0</td>\n",
- " <td>1.5</td>\n",
- " <td>NaN</td>\n",
+ " <th>mean_off_prog_interaction</th>\n",
+ " <td>0.166859</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
- " <td>4</td>\n",
- " <td>IPLP5212</td>\n",
- " <td>A</td>\n",
- " <td>0</td>\n",
- " <td>LRRK2+</td>\n",
- " <td>48.5</td>\n",
- " <td>56.9</td>\n",
- " <td>885.0</td>\n",
- " <td>0.3</td>\n",
- " <td>NaN</td>\n",
+ " <th>max_off</th>\n",
+ " <td>0.021442</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
- " Index patient_id cohort sexM gene age_at_diagnosis age ledd \\\n",
- "0 0 IPLP5212 A 0 LRRK2+ 48.5 52.1 607.0 \n",
- "1 1 IPLP5212 A 0 LRRK2+ 48.5 53.0 666.0 \n",
- "2 2 IPLP5212 A 0 LRRK2+ 48.5 53.9 717.0 \n",
- "3 3 IPLP5212 A 0 LRRK2+ 48.5 54.8 770.0 \n",
- "4 4 IPLP5212 A 0 LRRK2+ 48.5 56.9 885.0 \n",
- "\n",
- " time_since_intake_on time_since_intake_off \n",
- "0 1.9 NaN \n",
- "1 1.9 17.6 \n",
- "2 1.2 NaN \n",
- "3 1.5 NaN \n",
- "4 0.3 NaN "
+ " importance\n",
+ "off 0.428790\n",
+ "mean_off 0.302743\n",
+ "mean_off_prog_interaction 0.166859\n",
+ "max_off 0.021442"
]
},
- "execution_count": 4,
+ "execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "X.head()"
+ "# testons avec ce qui capture au moins 90% de l'importance\n",
+ "best_features = best_features[best_features.importance > 0.01]\n",
+ "best_features \n"
]
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_clean = X_train[best_features.index]\n",
+ "X_clean_test = X_test[best_features.index]\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Performance du modèle d'imputation linéaire - MAE: 1.33, R²: 0.97\n",
- "Pourcentage de valeurs manquantes après imputation: 0.00%\n",
- "Variable 'disease_duration' ajoutée avec succès.\n"
+ "[0]\tvalidation_0-rmse:15.45468\n",
+ "[1]\tvalidation_0-rmse:14.48242\n",
+ "[2]\tvalidation_0-rmse:13.58369\n",
+ "[3]\tvalidation_0-rmse:12.74731\n",
+ "[4]\tvalidation_0-rmse:11.97664\n",
+ "[5]\tvalidation_0-rmse:11.26262\n",
+ "[6]\tvalidation_0-rmse:10.60624\n",
+ "[7]\tvalidation_0-rmse:9.99898\n",
+ "[8]\tvalidation_0-rmse:9.43851\n",
+ "[9]\tvalidation_0-rmse:8.92491\n",
+ "[10]\tvalidation_0-rmse:8.45004\n",
+ "[11]\tvalidation_0-rmse:8.01502\n",
+ "[12]\tvalidation_0-rmse:7.61749\n",
+ "[13]\tvalidation_0-rmse:7.25272\n",
+ "[14]\tvalidation_0-rmse:6.92000\n",
+ "[15]\tvalidation_0-rmse:6.61722\n",
+ "[16]\tvalidation_0-rmse:6.34011\n",
+ "[17]\tvalidation_0-rmse:6.08856\n",
+ "[18]\tvalidation_0-rmse:5.86099\n",
+ "[19]\tvalidation_0-rmse:5.65261\n",
+ "[20]\tvalidation_0-rmse:5.46472\n",
+ "[21]\tvalidation_0-rmse:5.29464\n",
+ "[22]\tvalidation_0-rmse:5.14201\n",
+ "[23]\tvalidation_0-rmse:5.00491\n",
+ "[24]\tvalidation_0-rmse:4.88209\n",
+ "[25]\tvalidation_0-rmse:4.77120\n",
+ "[26]\tvalidation_0-rmse:4.67087\n",
+ "[27]\tvalidation_0-rmse:4.57988\n",
+ "[28]\tvalidation_0-rmse:4.50132\n",
+ "[29]\tvalidation_0-rmse:4.43009\n",
+ "[30]\tvalidation_0-rmse:4.36540\n",
+ "[31]\tvalidation_0-rmse:4.30855\n",
+ "[32]\tvalidation_0-rmse:4.25649\n",
+ "[33]\tvalidation_0-rmse:4.20978\n",
+ "[34]\tvalidation_0-rmse:4.16818\n",
+ "[35]\tvalidation_0-rmse:4.13113\n",
+ "[36]\tvalidation_0-rmse:4.09751\n",
+ "[37]\tvalidation_0-rmse:4.06758\n",
+ "[38]\tvalidation_0-rmse:4.04096\n",
+ "[39]\tvalidation_0-rmse:4.01670\n",
+ "[40]\tvalidation_0-rmse:3.99507\n",
+ "[41]\tvalidation_0-rmse:3.97548\n",
+ "[42]\tvalidation_0-rmse:3.95831\n",
+ "[43]\tvalidation_0-rmse:3.94211\n",
+ "[44]\tvalidation_0-rmse:3.92776\n",
+ "[45]\tvalidation_0-rmse:3.91460\n",
+ "[46]\tvalidation_0-rmse:3.90277\n",
+ "[47]\tvalidation_0-rmse:3.89158\n",
+ "[48]\tvalidation_0-rmse:3.88107\n",
+ "[49]\tvalidation_0-rmse:3.87217\n",
+ "[50]\tvalidation_0-rmse:3.86284\n",
+ "[51]\tvalidation_0-rmse:3.85529\n",
+ "[52]\tvalidation_0-rmse:3.84826\n",
+ "[53]\tvalidation_0-rmse:3.84095\n",
+ "[54]\tvalidation_0-rmse:3.83376\n",
+ "[55]\tvalidation_0-rmse:3.82769\n",
+ "[56]\tvalidation_0-rmse:3.82118\n",
+ "[57]\tvalidation_0-rmse:3.81546\n",
+ "[58]\tvalidation_0-rmse:3.80982\n",
+ "[59]\tvalidation_0-rmse:3.80521\n",
+ "[60]\tvalidation_0-rmse:3.80061\n",
+ "[61]\tvalidation_0-rmse:3.79627\n",
+ "[62]\tvalidation_0-rmse:3.79194\n",
+ "[63]\tvalidation_0-rmse:3.78829\n",
+ "[64]\tvalidation_0-rmse:3.78433\n",
+ "[65]\tvalidation_0-rmse:3.78006\n",
+ "[66]\tvalidation_0-rmse:3.77619\n",
+ "[67]\tvalidation_0-rmse:3.77280\n",
+ "[68]\tvalidation_0-rmse:3.76966\n",
+ "[69]\tvalidation_0-rmse:3.76663\n",
+ "[70]\tvalidation_0-rmse:3.76402\n",
+ "[71]\tvalidation_0-rmse:3.76003\n",
+ "[72]\tvalidation_0-rmse:3.75808\n",
+ "[73]\tvalidation_0-rmse:3.75411\n",
+ "[74]\tvalidation_0-rmse:3.75176\n",
+ "[75]\tvalidation_0-rmse:3.74870\n",
+ "[76]\tvalidation_0-rmse:3.74494\n",
+ "[77]\tvalidation_0-rmse:3.74211\n",
+ "[78]\tvalidation_0-rmse:3.73978\n",
+ "[79]\tvalidation_0-rmse:3.73605\n",
+ "[80]\tvalidation_0-rmse:3.73401\n",
+ "[81]\tvalidation_0-rmse:3.73172\n",
+ "[82]\tvalidation_0-rmse:3.72911\n",
+ "[83]\tvalidation_0-rmse:3.72695\n",
+ "[84]\tvalidation_0-rmse:3.72596\n",
+ "[85]\tvalidation_0-rmse:3.72259\n",
+ "[86]\tvalidation_0-rmse:3.72121\n",
+ "[87]\tvalidation_0-rmse:3.71953\n",
+ "[88]\tvalidation_0-rmse:3.71691\n",
+ "[89]\tvalidation_0-rmse:3.71477\n",
+ "[90]\tvalidation_0-rmse:3.71383\n",
+ "[91]\tvalidation_0-rmse:3.71226\n",
+ "[92]\tvalidation_0-rmse:3.70997\n",
+ "[93]\tvalidation_0-rmse:3.70916\n",
+ "[94]\tvalidation_0-rmse:3.70833\n",
+ "[95]\tvalidation_0-rmse:3.70628\n",
+ "[96]\tvalidation_0-rmse:3.70576\n",
+ "[97]\tvalidation_0-rmse:3.70451\n",
+ "[98]\tvalidation_0-rmse:3.70313\n",
+ "[99]\tvalidation_0-rmse:3.70184\n",
+ "[100]\tvalidation_0-rmse:3.70095\n",
+ "[101]\tvalidation_0-rmse:3.69990\n",
+ "[102]\tvalidation_0-rmse:3.69892\n",
+ "[103]\tvalidation_0-rmse:3.69766\n",
+ "[104]\tvalidation_0-rmse:3.69298\n",
+ "[105]\tvalidation_0-rmse:3.69163\n",
+ "[106]\tvalidation_0-rmse:3.68920\n",
+ "[107]\tvalidation_0-rmse:3.68861\n",
+ "[108]\tvalidation_0-rmse:3.68686\n",
+ "[109]\tvalidation_0-rmse:3.68549\n",
+ "[110]\tvalidation_0-rmse:3.68420\n",
+ "[111]\tvalidation_0-rmse:3.68402\n",
+ "[112]\tvalidation_0-rmse:3.68278\n",
+ "[113]\tvalidation_0-rmse:3.68082\n",
+ "[114]\tvalidation_0-rmse:3.68048\n",
+ "[115]\tvalidation_0-rmse:3.67665\n",
+ "[116]\tvalidation_0-rmse:3.67436\n",
+ "[117]\tvalidation_0-rmse:3.67210\n",
+ "[118]\tvalidation_0-rmse:3.67191\n",
+ "[119]\tvalidation_0-rmse:3.66982\n",
+ "[120]\tvalidation_0-rmse:3.66690\n",
+ "[121]\tvalidation_0-rmse:3.66380\n",
+ "[122]\tvalidation_0-rmse:3.66191\n",
+ "[123]\tvalidation_0-rmse:3.65953\n",
+ "[124]\tvalidation_0-rmse:3.65587\n",
+ "[125]\tvalidation_0-rmse:3.65493\n",
+ "[126]\tvalidation_0-rmse:3.65312\n",
+ "[127]\tvalidation_0-rmse:3.65097\n",
+ "[128]\tvalidation_0-rmse:3.64919\n",
+ "[129]\tvalidation_0-rmse:3.64819\n",
+ "[130]\tvalidation_0-rmse:3.64658\n",
+ "[131]\tvalidation_0-rmse:3.64561\n",
+ "[132]\tvalidation_0-rmse:3.64544\n",
+ "[133]\tvalidation_0-rmse:3.64372\n",
+ "[134]\tvalidation_0-rmse:3.63937\n",
+ "[135]\tvalidation_0-rmse:3.63810\n",
+ "[136]\tvalidation_0-rmse:3.63796\n",
+ "[137]\tvalidation_0-rmse:3.63785\n",
+ "[138]\tvalidation_0-rmse:3.63656\n",
+ "[139]\tvalidation_0-rmse:3.63451\n",
+ "[140]\tvalidation_0-rmse:3.63292\n",
+ "[141]\tvalidation_0-rmse:3.63080\n",
+ "[142]\tvalidation_0-rmse:3.62780\n",
+ "[143]\tvalidation_0-rmse:3.62612\n",
+ "[144]\tvalidation_0-rmse:3.62475\n",
+ "[145]\tvalidation_0-rmse:3.62407\n",
+ "[146]\tvalidation_0-rmse:3.62273\n",
+ "[147]\tvalidation_0-rmse:3.62052\n",
+ "[148]\tvalidation_0-rmse:3.61891\n",
+ "[149]\tvalidation_0-rmse:3.61719\n",
+ "[150]\tvalidation_0-rmse:3.61575\n",
+ "[151]\tvalidation_0-rmse:3.61428\n",
+ "[152]\tvalidation_0-rmse:3.61225\n",
+ "[153]\tvalidation_0-rmse:3.61145\n",
+ "[154]\tvalidation_0-rmse:3.60988\n",
+ "[155]\tvalidation_0-rmse:3.60718\n",
+ "[156]\tvalidation_0-rmse:3.60439\n",
+ "[157]\tvalidation_0-rmse:3.60379\n",
+ "[158]\tvalidation_0-rmse:3.60054\n",
+ "[159]\tvalidation_0-rmse:3.59975\n",
+ "[160]\tvalidation_0-rmse:3.59908\n",
+ "[161]\tvalidation_0-rmse:3.59689\n",
+ "[162]\tvalidation_0-rmse:3.59578\n",
+ "[163]\tvalidation_0-rmse:3.59213\n",
+ "[164]\tvalidation_0-rmse:3.59092\n",
+ "[165]\tvalidation_0-rmse:3.58931\n",
+ "[166]\tvalidation_0-rmse:3.58629\n",
+ "[167]\tvalidation_0-rmse:3.58403\n",
+ "[168]\tvalidation_0-rmse:3.58311\n",
+ "[169]\tvalidation_0-rmse:3.58218\n",
+ "[170]\tvalidation_0-rmse:3.58045\n",
+ "[171]\tvalidation_0-rmse:3.57805\n",
+ "[172]\tvalidation_0-rmse:3.57701\n",
+ "[173]\tvalidation_0-rmse:3.57359\n",
+ "[174]\tvalidation_0-rmse:3.57007\n",
+ "[175]\tvalidation_0-rmse:3.56871\n",
+ "[176]\tvalidation_0-rmse:3.56633\n",
+ "[177]\tvalidation_0-rmse:3.56495\n",
+ "[178]\tvalidation_0-rmse:3.56391\n",
+ "[179]\tvalidation_0-rmse:3.56066\n",
+ "[180]\tvalidation_0-rmse:3.55980\n",
+ "[181]\tvalidation_0-rmse:3.55861\n",
+ "[182]\tvalidation_0-rmse:3.55796\n",
+ "[183]\tvalidation_0-rmse:3.55592\n",
+ "[184]\tvalidation_0-rmse:3.55362\n",
+ "[185]\tvalidation_0-rmse:3.55281\n",
+ "[186]\tvalidation_0-rmse:3.55006\n",
+ "[187]\tvalidation_0-rmse:3.54807\n",
+ "[188]\tvalidation_0-rmse:3.54598\n",
+ "[189]\tvalidation_0-rmse:3.54432\n",
+ "[190]\tvalidation_0-rmse:3.54177\n",
+ "[191]\tvalidation_0-rmse:3.53967\n",
+ "[192]\tvalidation_0-rmse:3.53829\n",
+ "[193]\tvalidation_0-rmse:3.53686\n",
+ "[194]\tvalidation_0-rmse:3.53601\n",
+ "[195]\tvalidation_0-rmse:3.53468\n",
+ "[196]\tvalidation_0-rmse:3.53188\n",
+ "[197]\tvalidation_0-rmse:3.53142\n",
+ "[198]\tvalidation_0-rmse:3.53009\n",
+ "[199]\tvalidation_0-rmse:3.52832\n",
+ "[200]\tvalidation_0-rmse:3.52762\n",
+ "[201]\tvalidation_0-rmse:3.52588\n",
+ "[202]\tvalidation_0-rmse:3.52470\n",
+ "[203]\tvalidation_0-rmse:3.52357\n",
+ "[204]\tvalidation_0-rmse:3.52233\n",
+ "[205]\tvalidation_0-rmse:3.52059\n",
+ "[206]\tvalidation_0-rmse:3.51887\n",
+ "[207]\tvalidation_0-rmse:3.51720\n",
+ "[208]\tvalidation_0-rmse:3.51705\n",
+ "[209]\tvalidation_0-rmse:3.51635\n",
+ "[210]\tvalidation_0-rmse:3.51513\n",
+ "[211]\tvalidation_0-rmse:3.51289\n",
+ "[212]\tvalidation_0-rmse:3.51133\n",
+ "[213]\tvalidation_0-rmse:3.50941\n",
+ "[214]\tvalidation_0-rmse:3.50928\n",
+ "[215]\tvalidation_0-rmse:3.50768\n",
+ "[216]\tvalidation_0-rmse:3.50736\n",
+ "[217]\tvalidation_0-rmse:3.50406\n",
+ "[218]\tvalidation_0-rmse:3.50064\n",
+ "[219]\tvalidation_0-rmse:3.49894\n",
+ "[220]\tvalidation_0-rmse:3.49769\n",
+ "[221]\tvalidation_0-rmse:3.49568\n",
+ "[222]\tvalidation_0-rmse:3.49496\n",
+ "[223]\tvalidation_0-rmse:3.49264\n",
+ "[224]\tvalidation_0-rmse:3.49206\n",
+ "[225]\tvalidation_0-rmse:3.49042\n",
+ "[226]\tvalidation_0-rmse:3.48822\n",
+ "[227]\tvalidation_0-rmse:3.48594\n",
+ "[228]\tvalidation_0-rmse:3.48470\n",
+ "[229]\tvalidation_0-rmse:3.48279\n",
+ "[230]\tvalidation_0-rmse:3.48069\n",
+ "[231]\tvalidation_0-rmse:3.47939\n",
+ "[232]\tvalidation_0-rmse:3.47876\n",
+ "[233]\tvalidation_0-rmse:3.47727\n",
+ "[234]\tvalidation_0-rmse:3.47653\n",
+ "[235]\tvalidation_0-rmse:3.47565\n",
+ "[236]\tvalidation_0-rmse:3.47419\n",
+ "[237]\tvalidation_0-rmse:3.47179\n",
+ "[238]\tvalidation_0-rmse:3.47048\n",
+ "[239]\tvalidation_0-rmse:3.47037\n",
+ "[240]\tvalidation_0-rmse:3.46857\n",
+ "[241]\tvalidation_0-rmse:3.46653\n",
+ "[242]\tvalidation_0-rmse:3.46509\n",
+ "[243]\tvalidation_0-rmse:3.46441\n",
+ "[244]\tvalidation_0-rmse:3.46286\n",
+ "[245]\tvalidation_0-rmse:3.46155\n",
+ "[246]\tvalidation_0-rmse:3.45824\n",
+ "[247]\tvalidation_0-rmse:3.45758\n",
+ "[248]\tvalidation_0-rmse:3.45496\n",
+ "[249]\tvalidation_0-rmse:3.45243\n",
+ "[250]\tvalidation_0-rmse:3.45084\n",
+ "[251]\tvalidation_0-rmse:3.44930\n",
+ "[252]\tvalidation_0-rmse:3.44796\n",
+ "[253]\tvalidation_0-rmse:3.44604\n",
+ "[254]\tvalidation_0-rmse:3.44489\n",
+ "[255]\tvalidation_0-rmse:3.44364\n",
+ "[256]\tvalidation_0-rmse:3.44234\n",
+ "[257]\tvalidation_0-rmse:3.44149\n",
+ "[258]\tvalidation_0-rmse:3.44031\n",
+ "[259]\tvalidation_0-rmse:3.43905\n",
+ "[260]\tvalidation_0-rmse:3.43793\n",
+ "[261]\tvalidation_0-rmse:3.43661\n",
+ "[262]\tvalidation_0-rmse:3.43528\n",
+ "[263]\tvalidation_0-rmse:3.43380\n",
+ "[264]\tvalidation_0-rmse:3.43311\n",
+ "[265]\tvalidation_0-rmse:3.43194\n",
+ "[266]\tvalidation_0-rmse:3.42983\n",
+ "[267]\tvalidation_0-rmse:3.42702\n",
+ "[268]\tvalidation_0-rmse:3.42576\n",
+ "[269]\tvalidation_0-rmse:3.42417\n",
+ "[270]\tvalidation_0-rmse:3.42258\n",
+ "[271]\tvalidation_0-rmse:3.42170\n",
+ "[272]\tvalidation_0-rmse:3.42073\n",
+ "[273]\tvalidation_0-rmse:3.41946\n",
+ "[274]\tvalidation_0-rmse:3.41809\n",
+ "[275]\tvalidation_0-rmse:3.41662\n",
+ "[276]\tvalidation_0-rmse:3.41470\n",
+ "[277]\tvalidation_0-rmse:3.41360\n",
+ "[278]\tvalidation_0-rmse:3.41209\n",
+ "[279]\tvalidation_0-rmse:3.41199\n",
+ "[280]\tvalidation_0-rmse:3.41132\n",
+ "[281]\tvalidation_0-rmse:3.40984\n",
+ "[282]\tvalidation_0-rmse:3.40859\n",
+ "[283]\tvalidation_0-rmse:3.40739\n",
+ "[284]\tvalidation_0-rmse:3.40612\n",
+ "[285]\tvalidation_0-rmse:3.40483\n",
+ "[286]\tvalidation_0-rmse:3.40401\n",
+ "[287]\tvalidation_0-rmse:3.40139\n",
+ "[288]\tvalidation_0-rmse:3.40012\n",
+ "[289]\tvalidation_0-rmse:3.39907\n",
+ "[290]\tvalidation_0-rmse:3.39665\n",
+ "[291]\tvalidation_0-rmse:3.39557\n",
+ "[292]\tvalidation_0-rmse:3.39365\n",
+ "[293]\tvalidation_0-rmse:3.39284\n",
+ "[294]\tvalidation_0-rmse:3.39147\n",
+ "[295]\tvalidation_0-rmse:3.39025\n",
+ "[296]\tvalidation_0-rmse:3.38855\n",
+ "[297]\tvalidation_0-rmse:3.38798\n",
+ "[298]\tvalidation_0-rmse:3.38695\n",
+ "[299]\tvalidation_0-rmse:3.38684\n",
+ "[300]\tvalidation_0-rmse:3.38542\n",
+ "[301]\tvalidation_0-rmse:3.38386\n",
+ "[302]\tvalidation_0-rmse:3.38279\n",
+ "[303]\tvalidation_0-rmse:3.38176\n",
+ "[304]\tvalidation_0-rmse:3.37999\n",
+ "[305]\tvalidation_0-rmse:3.37829\n",
+ "[306]\tvalidation_0-rmse:3.37745\n",
+ "[307]\tvalidation_0-rmse:3.37652\n",
+ "[308]\tvalidation_0-rmse:3.37393\n",
+ "[309]\tvalidation_0-rmse:3.37280\n",
+ "[310]\tvalidation_0-rmse:3.37155\n",
+ "[311]\tvalidation_0-rmse:3.37011\n",
+ "[312]\tvalidation_0-rmse:3.36889\n",
+ "[313]\tvalidation_0-rmse:3.36629\n",
+ "[314]\tvalidation_0-rmse:3.36531\n",
+ "[315]\tvalidation_0-rmse:3.36272\n",
+ "[316]\tvalidation_0-rmse:3.36149\n",
+ "[317]\tvalidation_0-rmse:3.36048\n",
+ "[318]\tvalidation_0-rmse:3.35966\n",
+ "[319]\tvalidation_0-rmse:3.35880\n",
+ "[320]\tvalidation_0-rmse:3.35805\n",
+ "[321]\tvalidation_0-rmse:3.35712\n",
+ "[322]\tvalidation_0-rmse:3.35672\n",
+ "[323]\tvalidation_0-rmse:3.35555\n",
+ "[324]\tvalidation_0-rmse:3.35460\n",
+ "[325]\tvalidation_0-rmse:3.35248\n",
+ "[326]\tvalidation_0-rmse:3.35042\n",
+ "[327]\tvalidation_0-rmse:3.34960\n",
+ "[328]\tvalidation_0-rmse:3.34948\n",
+ "[329]\tvalidation_0-rmse:3.34911\n",
+ "[330]\tvalidation_0-rmse:3.34781\n",
+ "[331]\tvalidation_0-rmse:3.34671\n",
+ "[332]\tvalidation_0-rmse:3.34599\n",
+ "[333]\tvalidation_0-rmse:3.34380\n",
+ "[334]\tvalidation_0-rmse:3.34264\n",
+ "[335]\tvalidation_0-rmse:3.34165\n",
+ "[336]\tvalidation_0-rmse:3.34037\n",
+ "[337]\tvalidation_0-rmse:3.33995\n",
+ "[338]\tvalidation_0-rmse:3.33931\n",
+ "[339]\tvalidation_0-rmse:3.33904\n",
+ "[340]\tvalidation_0-rmse:3.33783\n",
+ "[341]\tvalidation_0-rmse:3.33708\n",
+ "[342]\tvalidation_0-rmse:3.33577\n",
+ "[343]\tvalidation_0-rmse:3.33457\n",
+ "[344]\tvalidation_0-rmse:3.33371\n",
+ "[345]\tvalidation_0-rmse:3.33359\n",
+ "[346]\tvalidation_0-rmse:3.33234\n",
+ "[347]\tvalidation_0-rmse:3.33120\n",
+ "[348]\tvalidation_0-rmse:3.32971\n",
+ "[349]\tvalidation_0-rmse:3.32877\n",
+ "[350]\tvalidation_0-rmse:3.32757\n",
+ "[351]\tvalidation_0-rmse:3.32649\n",
+ "[352]\tvalidation_0-rmse:3.32494\n",
+ "[353]\tvalidation_0-rmse:3.32364\n",
+ "[354]\tvalidation_0-rmse:3.32131\n",
+ "[355]\tvalidation_0-rmse:3.32089\n",
+ "[356]\tvalidation_0-rmse:3.31993\n",
+ "[357]\tvalidation_0-rmse:3.31986\n",
+ "[358]\tvalidation_0-rmse:3.31699\n",
+ "[359]\tvalidation_0-rmse:3.31586\n",
+ "[360]\tvalidation_0-rmse:3.31540\n",
+ "[361]\tvalidation_0-rmse:3.31414\n",
+ "[362]\tvalidation_0-rmse:3.31349\n",
+ "[363]\tvalidation_0-rmse:3.31274\n",
+ "[364]\tvalidation_0-rmse:3.31096\n",
+ "[365]\tvalidation_0-rmse:3.31004\n",
+ "[366]\tvalidation_0-rmse:3.30772\n",
+ "[367]\tvalidation_0-rmse:3.30689\n",
+ "[368]\tvalidation_0-rmse:3.30679\n",
+ "[369]\tvalidation_0-rmse:3.30598\n",
+ "[370]\tvalidation_0-rmse:3.30511\n",
+ "[371]\tvalidation_0-rmse:3.30382\n",
+ "[372]\tvalidation_0-rmse:3.30274\n",
+ "[373]\tvalidation_0-rmse:3.30181\n",
+ "[374]\tvalidation_0-rmse:3.30079\n",
+ "[375]\tvalidation_0-rmse:3.30019\n",
+ "[376]\tvalidation_0-rmse:3.29968\n",
+ "[377]\tvalidation_0-rmse:3.29824\n",
+ "[378]\tvalidation_0-rmse:3.29738\n",
+ "[379]\tvalidation_0-rmse:3.29630\n",
+ "[380]\tvalidation_0-rmse:3.29587\n",
+ "[381]\tvalidation_0-rmse:3.29556\n",
+ "[382]\tvalidation_0-rmse:3.29353\n",
+ "[383]\tvalidation_0-rmse:3.29266\n",
+ "[384]\tvalidation_0-rmse:3.29014\n",
+ "[385]\tvalidation_0-rmse:3.28882\n",
+ "[386]\tvalidation_0-rmse:3.28683\n",
+ "[387]\tvalidation_0-rmse:3.28556\n",
+ "[388]\tvalidation_0-rmse:3.28365\n",
+ "[389]\tvalidation_0-rmse:3.28202\n",
+ "[390]\tvalidation_0-rmse:3.27976\n",
+ "[391]\tvalidation_0-rmse:3.27809\n",
+ "[392]\tvalidation_0-rmse:3.27665\n",
+ "[393]\tvalidation_0-rmse:3.27523\n",
+ "[394]\tvalidation_0-rmse:3.27410\n",
+ "[395]\tvalidation_0-rmse:3.27289\n",
+ "[396]\tvalidation_0-rmse:3.27115\n",
+ "[397]\tvalidation_0-rmse:3.27007\n",
+ "[398]\tvalidation_0-rmse:3.26965\n",
+ "[399]\tvalidation_0-rmse:3.26904\n",
+ "[400]\tvalidation_0-rmse:3.26791\n",
+ "[401]\tvalidation_0-rmse:3.26680\n",
+ "[402]\tvalidation_0-rmse:3.26576\n",
+ "[403]\tvalidation_0-rmse:3.26512\n",
+ "[404]\tvalidation_0-rmse:3.26475\n",
+ "[405]\tvalidation_0-rmse:3.26214\n",
+ "[406]\tvalidation_0-rmse:3.26100\n",
+ "[407]\tvalidation_0-rmse:3.26043\n",
+ "[408]\tvalidation_0-rmse:3.26029\n",
+ "[409]\tvalidation_0-rmse:3.25854\n",
+ "[410]\tvalidation_0-rmse:3.25760\n",
+ "[411]\tvalidation_0-rmse:3.25609\n",
+ "[412]\tvalidation_0-rmse:3.25503\n",
+ "[413]\tvalidation_0-rmse:3.25309\n",
+ "[414]\tvalidation_0-rmse:3.25136\n",
+ "[415]\tvalidation_0-rmse:3.25096\n",
+ "[416]\tvalidation_0-rmse:3.24860\n",
+ "[417]\tvalidation_0-rmse:3.24792\n",
+ "[418]\tvalidation_0-rmse:3.24725\n",
+ "[419]\tvalidation_0-rmse:3.24552\n",
+ "[420]\tvalidation_0-rmse:3.24453\n",
+ "[421]\tvalidation_0-rmse:3.24390\n",
+ "[422]\tvalidation_0-rmse:3.24276\n",
+ "[423]\tvalidation_0-rmse:3.24145\n",
+ "[424]\tvalidation_0-rmse:3.24070\n",
+ "[425]\tvalidation_0-rmse:3.23957\n",
+ "[426]\tvalidation_0-rmse:3.23893\n",
+ "[427]\tvalidation_0-rmse:3.23809\n",
+ "[428]\tvalidation_0-rmse:3.23669\n",
+ "[429]\tvalidation_0-rmse:3.23598\n",
+ "[430]\tvalidation_0-rmse:3.23499\n",
+ "[431]\tvalidation_0-rmse:3.23383\n",
+ "[432]\tvalidation_0-rmse:3.23281\n",
+ "[433]\tvalidation_0-rmse:3.23186\n",
+ "[434]\tvalidation_0-rmse:3.23061\n",
+ "[435]\tvalidation_0-rmse:3.22984\n",
+ "[436]\tvalidation_0-rmse:3.22837\n",
+ "[437]\tvalidation_0-rmse:3.22768\n",
+ "[438]\tvalidation_0-rmse:3.22699\n",
+ "[439]\tvalidation_0-rmse:3.22600\n",
+ "[440]\tvalidation_0-rmse:3.22429\n",
+ "[441]\tvalidation_0-rmse:3.22232\n",
+ "[442]\tvalidation_0-rmse:3.22035\n",
+ "[443]\tvalidation_0-rmse:3.21849\n",
+ "[444]\tvalidation_0-rmse:3.21763\n",
+ "[445]\tvalidation_0-rmse:3.21637\n",
+ "[446]\tvalidation_0-rmse:3.21500\n",
+ "[447]\tvalidation_0-rmse:3.21311\n",
+ "[448]\tvalidation_0-rmse:3.21172\n",
+ "[449]\tvalidation_0-rmse:3.21096\n",
+ "[450]\tvalidation_0-rmse:3.20960\n",
+ "[451]\tvalidation_0-rmse:3.20868\n",
+ "[452]\tvalidation_0-rmse:3.20824\n",
+ "[453]\tvalidation_0-rmse:3.20740\n",
+ "[454]\tvalidation_0-rmse:3.20674\n",
+ "[455]\tvalidation_0-rmse:3.20588\n",
+ "[456]\tvalidation_0-rmse:3.20406\n",
+ "[457]\tvalidation_0-rmse:3.20304\n",
+ "[458]\tvalidation_0-rmse:3.20220\n",
+ "[459]\tvalidation_0-rmse:3.20147\n",
+ "[460]\tvalidation_0-rmse:3.20044\n",
+ "[461]\tvalidation_0-rmse:3.19900\n",
+ "[462]\tvalidation_0-rmse:3.19839\n",
+ "[463]\tvalidation_0-rmse:3.19773\n",
+ "[464]\tvalidation_0-rmse:3.19675\n",
+ "[465]\tvalidation_0-rmse:3.19653\n",
+ "[466]\tvalidation_0-rmse:3.19632\n",
+ "[467]\tvalidation_0-rmse:3.19517\n",
+ "[468]\tvalidation_0-rmse:3.19459\n",
+ "[469]\tvalidation_0-rmse:3.19411\n",
+ "[470]\tvalidation_0-rmse:3.19362\n",
+ "[471]\tvalidation_0-rmse:3.19273\n",
+ "[472]\tvalidation_0-rmse:3.19223\n",
+ "[473]\tvalidation_0-rmse:3.19107\n",
+ "[474]\tvalidation_0-rmse:3.19059\n",
+ "[475]\tvalidation_0-rmse:3.18938\n",
+ "[476]\tvalidation_0-rmse:3.18893\n",
+ "[477]\tvalidation_0-rmse:3.18783\n",
+ "[478]\tvalidation_0-rmse:3.18692\n",
+ "[479]\tvalidation_0-rmse:3.18652\n",
+ "[480]\tvalidation_0-rmse:3.18517\n",
+ "[481]\tvalidation_0-rmse:3.18433\n",
+ "[482]\tvalidation_0-rmse:3.18352\n",
+ "[483]\tvalidation_0-rmse:3.18183\n",
+ "[484]\tvalidation_0-rmse:3.18109\n",
+ "[485]\tvalidation_0-rmse:3.17995\n",
+ "[486]\tvalidation_0-rmse:3.17916\n",
+ "[487]\tvalidation_0-rmse:3.17802\n",
+ "[488]\tvalidation_0-rmse:3.17718\n",
+ "[489]\tvalidation_0-rmse:3.17642\n",
+ "[490]\tvalidation_0-rmse:3.17602\n",
+ "[491]\tvalidation_0-rmse:3.17464\n",
+ "[492]\tvalidation_0-rmse:3.17393\n",
+ "[493]\tvalidation_0-rmse:3.17293\n",
+ "[494]\tvalidation_0-rmse:3.17209\n",
+ "[495]\tvalidation_0-rmse:3.17096\n",
+ "[496]\tvalidation_0-rmse:3.17040\n",
+ "[497]\tvalidation_0-rmse:3.16951\n",
+ "[498]\tvalidation_0-rmse:3.16850\n",
+ "[499]\tvalidation_0-rmse:3.16789\n",
+ "[500]\tvalidation_0-rmse:3.16748\n",
+ "[501]\tvalidation_0-rmse:3.16710\n",
+ "[502]\tvalidation_0-rmse:3.16684\n",
+ "[503]\tvalidation_0-rmse:3.16567\n",
+ "[504]\tvalidation_0-rmse:3.16531\n",
+ "[505]\tvalidation_0-rmse:3.16514\n",
+ "[506]\tvalidation_0-rmse:3.16394\n",
+ "[507]\tvalidation_0-rmse:3.16284\n",
+ "[508]\tvalidation_0-rmse:3.16239\n",
+ "[509]\tvalidation_0-rmse:3.16098\n",
+ "[510]\tvalidation_0-rmse:3.15992\n",
+ "[511]\tvalidation_0-rmse:3.15891\n",
+ "[512]\tvalidation_0-rmse:3.15801\n",
+ "[513]\tvalidation_0-rmse:3.15711\n",
+ "[514]\tvalidation_0-rmse:3.15548\n",
+ "[515]\tvalidation_0-rmse:3.15447\n",
+ "[516]\tvalidation_0-rmse:3.15381\n",
+ "[517]\tvalidation_0-rmse:3.15189\n",
+ "[518]\tvalidation_0-rmse:3.15077\n",
+ "[519]\tvalidation_0-rmse:3.14995\n",
+ "[520]\tvalidation_0-rmse:3.14916\n",
+ "[521]\tvalidation_0-rmse:3.14852\n",
+ "[522]\tvalidation_0-rmse:3.14750\n",
+ "[523]\tvalidation_0-rmse:3.14679\n",
+ "[524]\tvalidation_0-rmse:3.14588\n",
+ "[525]\tvalidation_0-rmse:3.14497\n",
+ "[526]\tvalidation_0-rmse:3.14393\n",
+ "[527]\tvalidation_0-rmse:3.14329\n",
+ "[528]\tvalidation_0-rmse:3.14224\n",
+ "[529]\tvalidation_0-rmse:3.14184\n",
+ "[530]\tvalidation_0-rmse:3.14084\n",
+ "[531]\tvalidation_0-rmse:3.14008\n",
+ "[532]\tvalidation_0-rmse:3.13933\n",
+ "[533]\tvalidation_0-rmse:3.13849\n",
+ "[534]\tvalidation_0-rmse:3.13746\n",
+ "[535]\tvalidation_0-rmse:3.13687\n",
+ "[536]\tvalidation_0-rmse:3.13634\n",
+ "[537]\tvalidation_0-rmse:3.13538\n",
+ "[538]\tvalidation_0-rmse:3.13470\n",
+ "[539]\tvalidation_0-rmse:3.13362\n",
+ "[540]\tvalidation_0-rmse:3.13292\n",
+ "[541]\tvalidation_0-rmse:3.13229\n",
+ "[542]\tvalidation_0-rmse:3.13158\n",
+ "[543]\tvalidation_0-rmse:3.13077\n",
+ "[544]\tvalidation_0-rmse:3.13004\n",
+ "[545]\tvalidation_0-rmse:3.12941\n",
+ "[546]\tvalidation_0-rmse:3.12833\n",
+ "[547]\tvalidation_0-rmse:3.12789\n",
+ "[548]\tvalidation_0-rmse:3.12705\n",
+ "[549]\tvalidation_0-rmse:3.12627\n",
+ "[550]\tvalidation_0-rmse:3.12580\n",
+ "[551]\tvalidation_0-rmse:3.12511\n",
+ "[552]\tvalidation_0-rmse:3.12416\n",
+ "[553]\tvalidation_0-rmse:3.12296\n",
+ "[554]\tvalidation_0-rmse:3.12231\n",
+ "[555]\tvalidation_0-rmse:3.12103\n",
+ "[556]\tvalidation_0-rmse:3.11948\n",
+ "[557]\tvalidation_0-rmse:3.11717\n",
+ "[558]\tvalidation_0-rmse:3.11635\n",
+ "[559]\tvalidation_0-rmse:3.11484\n",
+ "[560]\tvalidation_0-rmse:3.11426\n",
+ "[561]\tvalidation_0-rmse:3.11230\n",
+ "[562]\tvalidation_0-rmse:3.11084\n",
+ "[563]\tvalidation_0-rmse:3.11057\n",
+ "[564]\tvalidation_0-rmse:3.10993\n",
+ "[565]\tvalidation_0-rmse:3.10963\n",
+ "[566]\tvalidation_0-rmse:3.10860\n",
+ "[567]\tvalidation_0-rmse:3.10793\n",
+ "[568]\tvalidation_0-rmse:3.10771\n",
+ "[569]\tvalidation_0-rmse:3.10671\n",
+ "[570]\tvalidation_0-rmse:3.10586\n",
+ "[571]\tvalidation_0-rmse:3.10557\n",
+ "[572]\tvalidation_0-rmse:3.10426\n",
+ "[573]\tvalidation_0-rmse:3.10349\n",
+ "[574]\tvalidation_0-rmse:3.10277\n",
+ "[575]\tvalidation_0-rmse:3.10186\n",
+ "[576]\tvalidation_0-rmse:3.10123\n",
+ "[577]\tvalidation_0-rmse:3.10066\n",
+ "[578]\tvalidation_0-rmse:3.10004\n",
+ "[579]\tvalidation_0-rmse:3.09940\n",
+ "[580]\tvalidation_0-rmse:3.09828\n",
+ "[581]\tvalidation_0-rmse:3.09772\n",
+ "[582]\tvalidation_0-rmse:3.09707\n",
+ "[583]\tvalidation_0-rmse:3.09662\n",
+ "[584]\tvalidation_0-rmse:3.09549\n",
+ "[585]\tvalidation_0-rmse:3.09443\n",
+ "[586]\tvalidation_0-rmse:3.09380\n",
+ "[587]\tvalidation_0-rmse:3.09334\n",
+ "[588]\tvalidation_0-rmse:3.09317\n",
+ "[589]\tvalidation_0-rmse:3.09268\n",
+ "[590]\tvalidation_0-rmse:3.09212\n",
+ "[591]\tvalidation_0-rmse:3.09153\n",
+ "[592]\tvalidation_0-rmse:3.09102\n",
+ "[593]\tvalidation_0-rmse:3.09031\n",
+ "[594]\tvalidation_0-rmse:3.08980\n",
+ "[595]\tvalidation_0-rmse:3.08904\n",
+ "[596]\tvalidation_0-rmse:3.08819\n",
+ "[597]\tvalidation_0-rmse:3.08719\n",
+ "[598]\tvalidation_0-rmse:3.08677\n",
+ "[599]\tvalidation_0-rmse:3.08623\n",
+ "[600]\tvalidation_0-rmse:3.08569\n",
+ "[601]\tvalidation_0-rmse:3.08526\n",
+ "[602]\tvalidation_0-rmse:3.08490\n",
+ "[603]\tvalidation_0-rmse:3.08433\n",
+ "[604]\tvalidation_0-rmse:3.08395\n",
+ "[605]\tvalidation_0-rmse:3.08369\n",
+ "[606]\tvalidation_0-rmse:3.08323\n",
+ "[607]\tvalidation_0-rmse:3.08288\n",
+ "[608]\tvalidation_0-rmse:3.08179\n",
+ "[609]\tvalidation_0-rmse:3.08047\n",
+ "[610]\tvalidation_0-rmse:3.07911\n",
+ "[611]\tvalidation_0-rmse:3.07863\n",
+ "[612]\tvalidation_0-rmse:3.07823\n",
+ "[613]\tvalidation_0-rmse:3.07785\n",
+ "[614]\tvalidation_0-rmse:3.07728\n",
+ "[615]\tvalidation_0-rmse:3.07684\n",
+ "[616]\tvalidation_0-rmse:3.07540\n",
+ "[617]\tvalidation_0-rmse:3.07414\n",
+ "[618]\tvalidation_0-rmse:3.07376\n",
+ "[619]\tvalidation_0-rmse:3.07266\n",
+ "[620]\tvalidation_0-rmse:3.07210\n",
+ "[621]\tvalidation_0-rmse:3.07199\n",
+ "[622]\tvalidation_0-rmse:3.07083\n",
+ "[623]\tvalidation_0-rmse:3.07027\n",
+ "[624]\tvalidation_0-rmse:3.06892\n",
+ "[625]\tvalidation_0-rmse:3.06819\n",
+ "[626]\tvalidation_0-rmse:3.06792\n",
+ "[627]\tvalidation_0-rmse:3.06769\n",
+ "[628]\tvalidation_0-rmse:3.06640\n",
+ "[629]\tvalidation_0-rmse:3.06540\n",
+ "[630]\tvalidation_0-rmse:3.06478\n",
+ "[631]\tvalidation_0-rmse:3.06357\n",
+ "[632]\tvalidation_0-rmse:3.06272\n",
+ "[633]\tvalidation_0-rmse:3.06116\n",
+ "[634]\tvalidation_0-rmse:3.06027\n",
+ "[635]\tvalidation_0-rmse:3.05949\n",
+ "[636]\tvalidation_0-rmse:3.05876\n",
+ "[637]\tvalidation_0-rmse:3.05806\n",
+ "[638]\tvalidation_0-rmse:3.05764\n",
+ "[639]\tvalidation_0-rmse:3.05644\n",
+ "[640]\tvalidation_0-rmse:3.05569\n",
+ "[641]\tvalidation_0-rmse:3.05453\n",
+ "[642]\tvalidation_0-rmse:3.05371\n",
+ "[643]\tvalidation_0-rmse:3.05290\n",
+ "[644]\tvalidation_0-rmse:3.05226\n",
+ "[645]\tvalidation_0-rmse:3.05101\n",
+ "[646]\tvalidation_0-rmse:3.05030\n",
+ "[647]\tvalidation_0-rmse:3.04868\n",
+ "[648]\tvalidation_0-rmse:3.04780\n",
+ "[649]\tvalidation_0-rmse:3.04752\n",
+ "[650]\tvalidation_0-rmse:3.04654\n",
+ "[651]\tvalidation_0-rmse:3.04623\n",
+ "[652]\tvalidation_0-rmse:3.04537\n",
+ "[653]\tvalidation_0-rmse:3.04429\n",
+ "[654]\tvalidation_0-rmse:3.04365\n",
+ "[655]\tvalidation_0-rmse:3.04294\n",
+ "[656]\tvalidation_0-rmse:3.04215\n",
+ "[657]\tvalidation_0-rmse:3.04154\n",
+ "[658]\tvalidation_0-rmse:3.04090\n",
+ "[659]\tvalidation_0-rmse:3.04040\n",
+ "[660]\tvalidation_0-rmse:3.03945\n",
+ "[661]\tvalidation_0-rmse:3.03859\n",
+ "[662]\tvalidation_0-rmse:3.03674\n",
+ "[663]\tvalidation_0-rmse:3.03509\n",
+ "[664]\tvalidation_0-rmse:3.03452\n",
+ "[665]\tvalidation_0-rmse:3.03389\n",
+ "[666]\tvalidation_0-rmse:3.03273\n",
+ "[667]\tvalidation_0-rmse:3.03217\n",
+ "[668]\tvalidation_0-rmse:3.03209\n",
+ "[669]\tvalidation_0-rmse:3.03149\n",
+ "[670]\tvalidation_0-rmse:3.03099\n",
+ "[671]\tvalidation_0-rmse:3.02883\n",
+ "[672]\tvalidation_0-rmse:3.02834\n",
+ "[673]\tvalidation_0-rmse:3.02775\n",
+ "[674]\tvalidation_0-rmse:3.02662\n",
+ "[675]\tvalidation_0-rmse:3.02625\n",
+ "[676]\tvalidation_0-rmse:3.02515\n",
+ "[677]\tvalidation_0-rmse:3.02359\n",
+ "[678]\tvalidation_0-rmse:3.02304\n",
+ "[679]\tvalidation_0-rmse:3.02277\n",
+ "[680]\tvalidation_0-rmse:3.02222\n",
+ "[681]\tvalidation_0-rmse:3.02152\n",
+ "[682]\tvalidation_0-rmse:3.02087\n",
+ "[683]\tvalidation_0-rmse:3.02003\n",
+ "[684]\tvalidation_0-rmse:3.01927\n",
+ "[685]\tvalidation_0-rmse:3.01854\n",
+ "[686]\tvalidation_0-rmse:3.01771\n",
+ "[687]\tvalidation_0-rmse:3.01700\n",
+ "[688]\tvalidation_0-rmse:3.01599\n",
+ "[689]\tvalidation_0-rmse:3.01521\n",
+ "[690]\tvalidation_0-rmse:3.01449\n",
+ "[691]\tvalidation_0-rmse:3.01391\n",
+ "[692]\tvalidation_0-rmse:3.01294\n",
+ "[693]\tvalidation_0-rmse:3.01195\n",
+ "[694]\tvalidation_0-rmse:3.01104\n",
+ "[695]\tvalidation_0-rmse:3.01048\n",
+ "[696]\tvalidation_0-rmse:3.00946\n",
+ "[697]\tvalidation_0-rmse:3.00883\n",
+ "[698]\tvalidation_0-rmse:3.00822\n",
+ "[699]\tvalidation_0-rmse:3.00738\n",
+ "[700]\tvalidation_0-rmse:3.00634\n",
+ "[701]\tvalidation_0-rmse:3.00557\n",
+ "[702]\tvalidation_0-rmse:3.00480\n",
+ "[703]\tvalidation_0-rmse:3.00406\n",
+ "[704]\tvalidation_0-rmse:3.00317\n",
+ "[705]\tvalidation_0-rmse:3.00243\n",
+ "[706]\tvalidation_0-rmse:3.00154\n",
+ "[707]\tvalidation_0-rmse:3.00030\n",
+ "[708]\tvalidation_0-rmse:2.99967\n",
+ "[709]\tvalidation_0-rmse:2.99882\n",
+ "[710]\tvalidation_0-rmse:2.99812\n",
+ "[711]\tvalidation_0-rmse:2.99647\n",
+ "[712]\tvalidation_0-rmse:2.99583\n",
+ "[713]\tvalidation_0-rmse:2.99519\n",
+ "[714]\tvalidation_0-rmse:2.99387\n",
+ "[715]\tvalidation_0-rmse:2.99313\n",
+ "[716]\tvalidation_0-rmse:2.99264\n",
+ "[717]\tvalidation_0-rmse:2.99145\n",
+ "[718]\tvalidation_0-rmse:2.99089\n",
+ "[719]\tvalidation_0-rmse:2.99043\n",
+ "[720]\tvalidation_0-rmse:2.99027\n",
+ "[721]\tvalidation_0-rmse:2.98925\n",
+ "[722]\tvalidation_0-rmse:2.98875\n",
+ "[723]\tvalidation_0-rmse:2.98806\n",
+ "[724]\tvalidation_0-rmse:2.98708\n",
+ "[725]\tvalidation_0-rmse:2.98661\n",
+ "[726]\tvalidation_0-rmse:2.98628\n",
+ "[727]\tvalidation_0-rmse:2.98564\n",
+ "[728]\tvalidation_0-rmse:2.98510\n",
+ "[729]\tvalidation_0-rmse:2.98410\n",
+ "[730]\tvalidation_0-rmse:2.98348\n",
+ "[731]\tvalidation_0-rmse:2.98313\n",
+ "[732]\tvalidation_0-rmse:2.98236\n",
+ "[733]\tvalidation_0-rmse:2.98190\n",
+ "[734]\tvalidation_0-rmse:2.98159\n",
+ "[735]\tvalidation_0-rmse:2.98091\n",
+ "[736]\tvalidation_0-rmse:2.98010\n",
+ "[737]\tvalidation_0-rmse:2.97950\n",
+ "[738]\tvalidation_0-rmse:2.97887\n",
+ "[739]\tvalidation_0-rmse:2.97838\n",
+ "[740]\tvalidation_0-rmse:2.97771\n",
+ "[741]\tvalidation_0-rmse:2.97733\n",
+ "[742]\tvalidation_0-rmse:2.97692\n",
+ "[743]\tvalidation_0-rmse:2.97669\n",
+ "[744]\tvalidation_0-rmse:2.97581\n",
+ "[745]\tvalidation_0-rmse:2.97470\n",
+ "[746]\tvalidation_0-rmse:2.97427\n",
+ "[747]\tvalidation_0-rmse:2.97391\n",
+ "[748]\tvalidation_0-rmse:2.97345\n",
+ "[749]\tvalidation_0-rmse:2.97320\n",
+ "[750]\tvalidation_0-rmse:2.97271\n",
+ "[751]\tvalidation_0-rmse:2.97213\n",
+ "[752]\tvalidation_0-rmse:2.97177\n",
+ "[753]\tvalidation_0-rmse:2.97068\n",
+ "[754]\tvalidation_0-rmse:2.96979\n",
+ "[755]\tvalidation_0-rmse:2.96942\n",
+ "[756]\tvalidation_0-rmse:2.96897\n",
+ "[757]\tvalidation_0-rmse:2.96862\n",
+ "[758]\tvalidation_0-rmse:2.96805\n",
+ "[759]\tvalidation_0-rmse:2.96752\n",
+ "[760]\tvalidation_0-rmse:2.96661\n",
+ "[761]\tvalidation_0-rmse:2.96606\n",
+ "[762]\tvalidation_0-rmse:2.96532\n",
+ "[763]\tvalidation_0-rmse:2.96477\n",
+ "[764]\tvalidation_0-rmse:2.96428\n",
+ "[765]\tvalidation_0-rmse:2.96381\n",
+ "[766]\tvalidation_0-rmse:2.96331\n",
+ "[767]\tvalidation_0-rmse:2.96231\n",
+ "[768]\tvalidation_0-rmse:2.96113\n",
+ "[769]\tvalidation_0-rmse:2.96035\n",
+ "[770]\tvalidation_0-rmse:2.95848\n",
+ "[771]\tvalidation_0-rmse:2.95762\n",
+ "[772]\tvalidation_0-rmse:2.95672\n",
+ "[773]\tvalidation_0-rmse:2.95585\n",
+ "[774]\tvalidation_0-rmse:2.95493\n",
+ "[775]\tvalidation_0-rmse:2.95452\n",
+ "[776]\tvalidation_0-rmse:2.95413\n",
+ "[777]\tvalidation_0-rmse:2.95322\n",
+ "[778]\tvalidation_0-rmse:2.95275\n",
+ "[779]\tvalidation_0-rmse:2.95231\n",
+ "[780]\tvalidation_0-rmse:2.95208\n",
+ "[781]\tvalidation_0-rmse:2.95084\n",
+ "[782]\tvalidation_0-rmse:2.95046\n",
+ "[783]\tvalidation_0-rmse:2.94986\n",
+ "[784]\tvalidation_0-rmse:2.94898\n",
+ "[785]\tvalidation_0-rmse:2.94866\n",
+ "[786]\tvalidation_0-rmse:2.94769\n",
+ "[787]\tvalidation_0-rmse:2.94681\n",
+ "[788]\tvalidation_0-rmse:2.94648\n",
+ "[789]\tvalidation_0-rmse:2.94610\n",
+ "[790]\tvalidation_0-rmse:2.94583\n",
+ "[791]\tvalidation_0-rmse:2.94527\n",
+ "[792]\tvalidation_0-rmse:2.94475\n",
+ "[793]\tvalidation_0-rmse:2.94399\n",
+ "[794]\tvalidation_0-rmse:2.94374\n",
+ "[795]\tvalidation_0-rmse:2.94279\n",
+ "[796]\tvalidation_0-rmse:2.94208\n",
+ "[797]\tvalidation_0-rmse:2.94123\n",
+ "[798]\tvalidation_0-rmse:2.94089\n",
+ "[799]\tvalidation_0-rmse:2.94005\n",
+ "[800]\tvalidation_0-rmse:2.93946\n",
+ "[801]\tvalidation_0-rmse:2.93862\n",
+ "[802]\tvalidation_0-rmse:2.93839\n",
+ "[803]\tvalidation_0-rmse:2.93812\n",
+ "[804]\tvalidation_0-rmse:2.93760\n",
+ "[805]\tvalidation_0-rmse:2.93715\n",
+ "[806]\tvalidation_0-rmse:2.93678\n",
+ "[807]\tvalidation_0-rmse:2.93638\n",
+ "[808]\tvalidation_0-rmse:2.93566\n",
+ "[809]\tvalidation_0-rmse:2.93513\n",
+ "[810]\tvalidation_0-rmse:2.93464\n",
+ "[811]\tvalidation_0-rmse:2.93408\n",
+ "[812]\tvalidation_0-rmse:2.93341\n",
+ "[813]\tvalidation_0-rmse:2.93319\n",
+ "[814]\tvalidation_0-rmse:2.93274\n",
+ "[815]\tvalidation_0-rmse:2.93193\n",
+ "[816]\tvalidation_0-rmse:2.93143\n",
+ "[817]\tvalidation_0-rmse:2.93049\n",
+ "[818]\tvalidation_0-rmse:2.92970\n",
+ "[819]\tvalidation_0-rmse:2.92914\n",
+ "[820]\tvalidation_0-rmse:2.92880\n",
+ "[821]\tvalidation_0-rmse:2.92654\n",
+ "[822]\tvalidation_0-rmse:2.92584\n",
+ "[823]\tvalidation_0-rmse:2.92537\n",
+ "[824]\tvalidation_0-rmse:2.92433\n",
+ "[825]\tvalidation_0-rmse:2.92362\n",
+ "[826]\tvalidation_0-rmse:2.92321\n",
+ "[827]\tvalidation_0-rmse:2.92304\n",
+ "[828]\tvalidation_0-rmse:2.92271\n",
+ "[829]\tvalidation_0-rmse:2.92183\n",
+ "[830]\tvalidation_0-rmse:2.92115\n",
+ "[831]\tvalidation_0-rmse:2.92060\n",
+ "[832]\tvalidation_0-rmse:2.92007\n",
+ "[833]\tvalidation_0-rmse:2.91920\n",
+ "[834]\tvalidation_0-rmse:2.91870\n",
+ "[835]\tvalidation_0-rmse:2.91807\n",
+ "[836]\tvalidation_0-rmse:2.91702\n",
+ "[837]\tvalidation_0-rmse:2.91644\n",
+ "[838]\tvalidation_0-rmse:2.91568\n",
+ "[839]\tvalidation_0-rmse:2.91510\n",
+ "[840]\tvalidation_0-rmse:2.91449\n",
+ "[841]\tvalidation_0-rmse:2.91400\n",
+ "[842]\tvalidation_0-rmse:2.91353\n",
+ "[843]\tvalidation_0-rmse:2.91310\n",
+ "[844]\tvalidation_0-rmse:2.91206\n",
+ "[845]\tvalidation_0-rmse:2.91112\n",
+ "[846]\tvalidation_0-rmse:2.91043\n",
+ "[847]\tvalidation_0-rmse:2.90970\n",
+ "[848]\tvalidation_0-rmse:2.90913\n",
+ "[849]\tvalidation_0-rmse:2.90659\n",
+ "[850]\tvalidation_0-rmse:2.90572\n",
+ "[851]\tvalidation_0-rmse:2.90506\n",
+ "[852]\tvalidation_0-rmse:2.90456\n",
+ "[853]\tvalidation_0-rmse:2.90378\n",
+ "[854]\tvalidation_0-rmse:2.90318\n",
+ "[855]\tvalidation_0-rmse:2.90246\n",
+ "[856]\tvalidation_0-rmse:2.90175\n",
+ "[857]\tvalidation_0-rmse:2.90089\n",
+ "[858]\tvalidation_0-rmse:2.90011\n",
+ "[859]\tvalidation_0-rmse:2.89968\n",
+ "[860]\tvalidation_0-rmse:2.89938\n",
+ "[861]\tvalidation_0-rmse:2.89908\n",
+ "[862]\tvalidation_0-rmse:2.89895\n",
+ "[863]\tvalidation_0-rmse:2.89884\n",
+ "[864]\tvalidation_0-rmse:2.89757\n",
+ "[865]\tvalidation_0-rmse:2.89669\n",
+ "[866]\tvalidation_0-rmse:2.89617\n",
+ "[867]\tvalidation_0-rmse:2.89546\n",
+ "[868]\tvalidation_0-rmse:2.89482\n",
+ "[869]\tvalidation_0-rmse:2.89401\n",
+ "[870]\tvalidation_0-rmse:2.89201\n",
+ "[871]\tvalidation_0-rmse:2.89115\n",
+ "[872]\tvalidation_0-rmse:2.89058\n",
+ "[873]\tvalidation_0-rmse:2.88966\n",
+ "[874]\tvalidation_0-rmse:2.88933\n",
+ "[875]\tvalidation_0-rmse:2.88879\n",
+ "[876]\tvalidation_0-rmse:2.88827\n",
+ "[877]\tvalidation_0-rmse:2.88747\n",
+ "[878]\tvalidation_0-rmse:2.88654\n",
+ "[879]\tvalidation_0-rmse:2.88596\n",
+ "[880]\tvalidation_0-rmse:2.88547\n",
+ "[881]\tvalidation_0-rmse:2.88506\n",
+ "[882]\tvalidation_0-rmse:2.88465\n",
+ "[883]\tvalidation_0-rmse:2.88432\n",
+ "[884]\tvalidation_0-rmse:2.88382\n",
+ "[885]\tvalidation_0-rmse:2.88343\n",
+ "[886]\tvalidation_0-rmse:2.88277\n",
+ "[887]\tvalidation_0-rmse:2.88219\n",
+ "[888]\tvalidation_0-rmse:2.88185\n",
+ "[889]\tvalidation_0-rmse:2.88139\n",
+ "[890]\tvalidation_0-rmse:2.88022\n",
+ "[891]\tvalidation_0-rmse:2.87939\n",
+ "[892]\tvalidation_0-rmse:2.87877\n",
+ "[893]\tvalidation_0-rmse:2.87834\n",
+ "[894]\tvalidation_0-rmse:2.87794\n",
+ "[895]\tvalidation_0-rmse:2.87649\n",
+ "[896]\tvalidation_0-rmse:2.87580\n",
+ "[897]\tvalidation_0-rmse:2.87475\n",
+ "[898]\tvalidation_0-rmse:2.87374\n",
+ "[899]\tvalidation_0-rmse:2.87271\n",
+ "[900]\tvalidation_0-rmse:2.87223\n",
+ "[901]\tvalidation_0-rmse:2.87083\n",
+ "[902]\tvalidation_0-rmse:2.86988\n",
+ "[903]\tvalidation_0-rmse:2.86939\n",
+ "[904]\tvalidation_0-rmse:2.86815\n",
+ "[905]\tvalidation_0-rmse:2.86753\n",
+ "[906]\tvalidation_0-rmse:2.86646\n",
+ "[907]\tvalidation_0-rmse:2.86606\n",
+ "[908]\tvalidation_0-rmse:2.86565\n",
+ "[909]\tvalidation_0-rmse:2.86469\n",
+ "[910]\tvalidation_0-rmse:2.86361\n",
+ "[911]\tvalidation_0-rmse:2.86298\n",
+ "[912]\tvalidation_0-rmse:2.86226\n",
+ "[913]\tvalidation_0-rmse:2.86093\n",
+ "[914]\tvalidation_0-rmse:2.86049\n",
+ "[915]\tvalidation_0-rmse:2.85895\n",
+ "[916]\tvalidation_0-rmse:2.85771\n",
+ "[917]\tvalidation_0-rmse:2.85703\n",
+ "[918]\tvalidation_0-rmse:2.85658\n",
+ "[919]\tvalidation_0-rmse:2.85636\n",
+ "[920]\tvalidation_0-rmse:2.85586\n",
+ "[921]\tvalidation_0-rmse:2.85530\n",
+ "[922]\tvalidation_0-rmse:2.85479\n",
+ "[923]\tvalidation_0-rmse:2.85427\n",
+ "[924]\tvalidation_0-rmse:2.85388\n",
+ "[925]\tvalidation_0-rmse:2.85326\n",
+ "[926]\tvalidation_0-rmse:2.85273\n",
+ "[927]\tvalidation_0-rmse:2.85216\n",
+ "[928]\tvalidation_0-rmse:2.85142\n",
+ "[929]\tvalidation_0-rmse:2.85092\n",
+ "[930]\tvalidation_0-rmse:2.85027\n",
+ "[931]\tvalidation_0-rmse:2.84945\n",
+ "[932]\tvalidation_0-rmse:2.84913\n",
+ "[933]\tvalidation_0-rmse:2.84836\n",
+ "[934]\tvalidation_0-rmse:2.84743\n",
+ "[935]\tvalidation_0-rmse:2.84706\n",
+ "[936]\tvalidation_0-rmse:2.84592\n",
+ "[937]\tvalidation_0-rmse:2.84417\n",
+ "[938]\tvalidation_0-rmse:2.84376\n",
+ "[939]\tvalidation_0-rmse:2.84269\n",
+ "[940]\tvalidation_0-rmse:2.84229\n",
+ "[941]\tvalidation_0-rmse:2.84060\n",
+ "[942]\tvalidation_0-rmse:2.84037\n",
+ "[943]\tvalidation_0-rmse:2.83920\n",
+ "[944]\tvalidation_0-rmse:2.83869\n",
+ "[945]\tvalidation_0-rmse:2.83783\n",
+ "[946]\tvalidation_0-rmse:2.83637\n",
+ "[947]\tvalidation_0-rmse:2.83561\n",
+ "[948]\tvalidation_0-rmse:2.83421\n",
+ "[949]\tvalidation_0-rmse:2.83360\n",
+ "[950]\tvalidation_0-rmse:2.83285\n",
+ "[951]\tvalidation_0-rmse:2.83213\n",
+ "[952]\tvalidation_0-rmse:2.83142\n",
+ "[953]\tvalidation_0-rmse:2.83075\n",
+ "[954]\tvalidation_0-rmse:2.83032\n",
+ "[955]\tvalidation_0-rmse:2.82920\n",
+ "[956]\tvalidation_0-rmse:2.82833\n",
+ "[957]\tvalidation_0-rmse:2.82785\n",
+ "[958]\tvalidation_0-rmse:2.82740\n",
+ "[959]\tvalidation_0-rmse:2.82677\n",
+ "[960]\tvalidation_0-rmse:2.82613\n",
+ "[961]\tvalidation_0-rmse:2.82547\n",
+ "[962]\tvalidation_0-rmse:2.82537\n",
+ "[963]\tvalidation_0-rmse:2.82506\n",
+ "[964]\tvalidation_0-rmse:2.82476\n",
+ "[965]\tvalidation_0-rmse:2.82436\n",
+ "[966]\tvalidation_0-rmse:2.82369\n",
+ "[967]\tvalidation_0-rmse:2.82328\n",
+ "[968]\tvalidation_0-rmse:2.82279\n",
+ "[969]\tvalidation_0-rmse:2.82204\n",
+ "[970]\tvalidation_0-rmse:2.82158\n",
+ "[971]\tvalidation_0-rmse:2.82122\n",
+ "[972]\tvalidation_0-rmse:2.82088\n",
+ "[973]\tvalidation_0-rmse:2.82049\n",
+ "[974]\tvalidation_0-rmse:2.82008\n",
+ "[975]\tvalidation_0-rmse:2.81983\n",
+ "[976]\tvalidation_0-rmse:2.81940\n",
+ "[977]\tvalidation_0-rmse:2.81902\n",
+ "[978]\tvalidation_0-rmse:2.81865\n",
+ "[979]\tvalidation_0-rmse:2.81796\n",
+ "[980]\tvalidation_0-rmse:2.81732\n",
+ "[981]\tvalidation_0-rmse:2.81647\n",
+ "[982]\tvalidation_0-rmse:2.81560\n",
+ "[983]\tvalidation_0-rmse:2.81536\n",
+ "[984]\tvalidation_0-rmse:2.81437\n",
+ "[985]\tvalidation_0-rmse:2.81398\n",
+ "[986]\tvalidation_0-rmse:2.81366\n",
+ "[987]\tvalidation_0-rmse:2.81258\n",
+ "[988]\tvalidation_0-rmse:2.81202\n",
+ "[989]\tvalidation_0-rmse:2.81131\n",
+ "[990]\tvalidation_0-rmse:2.81076\n",
+ "[991]\tvalidation_0-rmse:2.81026\n",
+ "[992]\tvalidation_0-rmse:2.80964\n",
+ "[993]\tvalidation_0-rmse:2.80911\n",
+ "[994]\tvalidation_0-rmse:2.80888\n",
+ "[995]\tvalidation_0-rmse:2.80857\n",
+ "[996]\tvalidation_0-rmse:2.80774\n",
+ "[997]\tvalidation_0-rmse:2.80695\n",
+ "[998]\tvalidation_0-rmse:2.80672\n",
+ "[999]\tvalidation_0-rmse:2.80574\n",
+ "[1000]\tvalidation_0-rmse:2.80405\n",
+ "[1001]\tvalidation_0-rmse:2.80360\n",
+ "[1002]\tvalidation_0-rmse:2.80326\n",
+ "[1003]\tvalidation_0-rmse:2.80294\n",
+ "[1004]\tvalidation_0-rmse:2.80220\n",
+ "[1005]\tvalidation_0-rmse:2.80207\n",
+ "[1006]\tvalidation_0-rmse:2.80203\n",
+ "[1007]\tvalidation_0-rmse:2.80136\n",
+ "[1008]\tvalidation_0-rmse:2.80089\n",
+ "[1009]\tvalidation_0-rmse:2.80022\n",
+ "[1010]\tvalidation_0-rmse:2.80005\n",
+ "[1011]\tvalidation_0-rmse:2.79974\n",
+ "[1012]\tvalidation_0-rmse:2.79938\n",
+ "[1013]\tvalidation_0-rmse:2.79863\n",
+ "[1014]\tvalidation_0-rmse:2.79770\n",
+ "[1015]\tvalidation_0-rmse:2.79721\n",
+ "[1016]\tvalidation_0-rmse:2.79692\n",
+ "[1017]\tvalidation_0-rmse:2.79643\n",
+ "[1018]\tvalidation_0-rmse:2.79588\n",
+ "[1019]\tvalidation_0-rmse:2.79523\n",
+ "[1020]\tvalidation_0-rmse:2.79481\n",
+ "[1021]\tvalidation_0-rmse:2.79382\n",
+ "[1022]\tvalidation_0-rmse:2.79304\n",
+ "[1023]\tvalidation_0-rmse:2.79258\n",
+ "[1024]\tvalidation_0-rmse:2.79200\n",
+ "[1025]\tvalidation_0-rmse:2.79114\n",
+ "[1026]\tvalidation_0-rmse:2.79074\n",
+ "[1027]\tvalidation_0-rmse:2.78929\n",
+ "[1028]\tvalidation_0-rmse:2.78895\n",
+ "[1029]\tvalidation_0-rmse:2.78829\n",
+ "[1030]\tvalidation_0-rmse:2.78787\n",
+ "[1031]\tvalidation_0-rmse:2.78623\n",
+ "[1032]\tvalidation_0-rmse:2.78557\n",
+ "[1033]\tvalidation_0-rmse:2.78516\n",
+ "[1034]\tvalidation_0-rmse:2.78453\n",
+ "[1035]\tvalidation_0-rmse:2.78399\n",
+ "[1036]\tvalidation_0-rmse:2.78292\n",
+ "[1037]\tvalidation_0-rmse:2.78238\n",
+ "[1038]\tvalidation_0-rmse:2.78187\n",
+ "[1039]\tvalidation_0-rmse:2.78117\n",
+ "[1040]\tvalidation_0-rmse:2.78074\n",
+ "[1041]\tvalidation_0-rmse:2.78016\n",
+ "[1042]\tvalidation_0-rmse:2.77920\n",
+ "[1043]\tvalidation_0-rmse:2.77828\n",
+ "[1044]\tvalidation_0-rmse:2.77706\n",
+ "[1045]\tvalidation_0-rmse:2.77673\n",
+ "[1046]\tvalidation_0-rmse:2.77628\n",
+ "[1047]\tvalidation_0-rmse:2.77529\n",
+ "[1048]\tvalidation_0-rmse:2.77496\n",
+ "[1049]\tvalidation_0-rmse:2.77427\n",
+ "[1050]\tvalidation_0-rmse:2.77367\n",
+ "[1051]\tvalidation_0-rmse:2.77287\n",
+ "[1052]\tvalidation_0-rmse:2.77223\n",
+ "[1053]\tvalidation_0-rmse:2.77195\n",
+ "[1054]\tvalidation_0-rmse:2.77133\n",
+ "[1055]\tvalidation_0-rmse:2.77076\n",
+ "[1056]\tvalidation_0-rmse:2.77022\n",
+ "[1057]\tvalidation_0-rmse:2.76996\n",
+ "[1058]\tvalidation_0-rmse:2.76950\n",
+ "[1059]\tvalidation_0-rmse:2.76929\n",
+ "[1060]\tvalidation_0-rmse:2.76879\n",
+ "[1061]\tvalidation_0-rmse:2.76845\n",
+ "[1062]\tvalidation_0-rmse:2.76780\n",
+ "[1063]\tvalidation_0-rmse:2.76735\n",
+ "[1064]\tvalidation_0-rmse:2.76679\n",
+ "[1065]\tvalidation_0-rmse:2.76623\n",
+ "[1066]\tvalidation_0-rmse:2.76549\n",
+ "[1067]\tvalidation_0-rmse:2.76507\n",
+ "[1068]\tvalidation_0-rmse:2.76435\n",
+ "[1069]\tvalidation_0-rmse:2.76406\n",
+ "[1070]\tvalidation_0-rmse:2.76353\n",
+ "[1071]\tvalidation_0-rmse:2.76329\n",
+ "[1072]\tvalidation_0-rmse:2.76313\n",
+ "[1073]\tvalidation_0-rmse:2.76262\n",
+ "[1074]\tvalidation_0-rmse:2.76230\n",
+ "[1075]\tvalidation_0-rmse:2.76184\n",
+ "[1076]\tvalidation_0-rmse:2.76107\n",
+ "[1077]\tvalidation_0-rmse:2.76093\n",
+ "[1078]\tvalidation_0-rmse:2.76057\n",
+ "[1079]\tvalidation_0-rmse:2.76007\n",
+ "[1080]\tvalidation_0-rmse:2.75988\n",
+ "[1081]\tvalidation_0-rmse:2.75930\n",
+ "[1082]\tvalidation_0-rmse:2.75870\n",
+ "[1083]\tvalidation_0-rmse:2.75843\n",
+ "[1084]\tvalidation_0-rmse:2.75808\n",
+ "[1085]\tvalidation_0-rmse:2.75738\n",
+ "[1086]\tvalidation_0-rmse:2.75671\n",
+ "[1087]\tvalidation_0-rmse:2.75616\n",
+ "[1088]\tvalidation_0-rmse:2.75570\n",
+ "[1089]\tvalidation_0-rmse:2.75547\n",
+ "[1090]\tvalidation_0-rmse:2.75507\n",
+ "[1091]\tvalidation_0-rmse:2.75415\n",
+ "[1092]\tvalidation_0-rmse:2.75314\n",
+ "[1093]\tvalidation_0-rmse:2.75225\n",
+ "[1094]\tvalidation_0-rmse:2.75212\n",
+ "[1095]\tvalidation_0-rmse:2.75107\n",
+ "[1096]\tvalidation_0-rmse:2.75025\n",
+ "[1097]\tvalidation_0-rmse:2.74977\n",
+ "[1098]\tvalidation_0-rmse:2.74866\n",
+ "[1099]\tvalidation_0-rmse:2.74823\n",
+ "[1100]\tvalidation_0-rmse:2.74706\n",
+ "[1101]\tvalidation_0-rmse:2.74653\n",
+ "[1102]\tvalidation_0-rmse:2.74612\n",
+ "[1103]\tvalidation_0-rmse:2.74587\n",
+ "[1104]\tvalidation_0-rmse:2.74520\n",
+ "[1105]\tvalidation_0-rmse:2.74479\n",
+ "[1106]\tvalidation_0-rmse:2.74429\n",
+ "[1107]\tvalidation_0-rmse:2.74403\n",
+ "[1108]\tvalidation_0-rmse:2.74343\n",
+ "[1109]\tvalidation_0-rmse:2.74319\n",
+ "[1110]\tvalidation_0-rmse:2.74282\n",
+ "[1111]\tvalidation_0-rmse:2.74241\n",
+ "[1112]\tvalidation_0-rmse:2.74155\n",
+ "[1113]\tvalidation_0-rmse:2.74122\n",
+ "[1114]\tvalidation_0-rmse:2.74063\n",
+ "[1115]\tvalidation_0-rmse:2.73998\n",
+ "[1116]\tvalidation_0-rmse:2.73914\n",
+ "[1117]\tvalidation_0-rmse:2.73866\n",
+ "[1118]\tvalidation_0-rmse:2.73812\n",
+ "[1119]\tvalidation_0-rmse:2.73773\n",
+ "[1120]\tvalidation_0-rmse:2.73729\n",
+ "[1121]\tvalidation_0-rmse:2.73693\n",
+ "[1122]\tvalidation_0-rmse:2.73663\n",
+ "[1123]\tvalidation_0-rmse:2.73616\n",
+ "[1124]\tvalidation_0-rmse:2.73565\n",
+ "[1125]\tvalidation_0-rmse:2.73511\n",
+ "[1126]\tvalidation_0-rmse:2.73499\n",
+ "[1127]\tvalidation_0-rmse:2.73423\n",
+ "[1128]\tvalidation_0-rmse:2.73357\n",
+ "[1129]\tvalidation_0-rmse:2.73306\n",
+ "[1130]\tvalidation_0-rmse:2.73244\n",
+ "[1131]\tvalidation_0-rmse:2.73208\n",
+ "[1132]\tvalidation_0-rmse:2.73198\n",
+ "[1133]\tvalidation_0-rmse:2.73142\n",
+ "[1134]\tvalidation_0-rmse:2.73025\n",
+ "[1135]\tvalidation_0-rmse:2.72951\n",
+ "[1136]\tvalidation_0-rmse:2.72892\n",
+ "[1137]\tvalidation_0-rmse:2.72823\n",
+ "[1138]\tvalidation_0-rmse:2.72712\n",
+ "[1139]\tvalidation_0-rmse:2.72640\n",
+ "[1140]\tvalidation_0-rmse:2.72588\n",
+ "[1141]\tvalidation_0-rmse:2.72538\n",
+ "[1142]\tvalidation_0-rmse:2.72490\n",
+ "[1143]\tvalidation_0-rmse:2.72425\n",
+ "[1144]\tvalidation_0-rmse:2.72389\n",
+ "[1145]\tvalidation_0-rmse:2.72344\n",
+ "[1146]\tvalidation_0-rmse:2.72267\n",
+ "[1147]\tvalidation_0-rmse:2.72205\n",
+ "[1148]\tvalidation_0-rmse:2.72168\n",
+ "[1149]\tvalidation_0-rmse:2.72151\n",
+ "[1150]\tvalidation_0-rmse:2.72022\n",
+ "[1151]\tvalidation_0-rmse:2.71990\n",
+ "[1152]\tvalidation_0-rmse:2.71959\n",
+ "[1153]\tvalidation_0-rmse:2.71902\n",
+ "[1154]\tvalidation_0-rmse:2.71865\n",
+ "[1155]\tvalidation_0-rmse:2.71774\n",
+ "[1156]\tvalidation_0-rmse:2.71651\n",
+ "[1157]\tvalidation_0-rmse:2.71495\n",
+ "[1158]\tvalidation_0-rmse:2.71393\n",
+ "[1159]\tvalidation_0-rmse:2.71264\n",
+ "[1160]\tvalidation_0-rmse:2.71232\n",
+ "[1161]\tvalidation_0-rmse:2.71139\n",
+ "[1162]\tvalidation_0-rmse:2.71107\n",
+ "[1163]\tvalidation_0-rmse:2.71061\n",
+ "[1164]\tvalidation_0-rmse:2.71020\n",
+ "[1165]\tvalidation_0-rmse:2.70952\n",
+ "[1166]\tvalidation_0-rmse:2.70910\n",
+ "[1167]\tvalidation_0-rmse:2.70832\n",
+ "[1168]\tvalidation_0-rmse:2.70773\n",
+ "[1169]\tvalidation_0-rmse:2.70725\n",
+ "[1170]\tvalidation_0-rmse:2.70666\n",
+ "[1171]\tvalidation_0-rmse:2.70602\n",
+ "[1172]\tvalidation_0-rmse:2.70575\n",
+ "[1173]\tvalidation_0-rmse:2.70519\n",
+ "[1174]\tvalidation_0-rmse:2.70488\n",
+ "[1175]\tvalidation_0-rmse:2.70437\n",
+ "[1176]\tvalidation_0-rmse:2.70383\n",
+ "[1177]\tvalidation_0-rmse:2.70353\n",
+ "[1178]\tvalidation_0-rmse:2.70287\n",
+ "[1179]\tvalidation_0-rmse:2.70236\n",
+ "[1180]\tvalidation_0-rmse:2.70156\n",
+ "[1181]\tvalidation_0-rmse:2.70100\n",
+ "[1182]\tvalidation_0-rmse:2.70042\n",
+ "[1183]\tvalidation_0-rmse:2.70010\n",
+ "[1184]\tvalidation_0-rmse:2.69983\n",
+ "[1185]\tvalidation_0-rmse:2.69920\n",
+ "[1186]\tvalidation_0-rmse:2.69865\n",
+ "[1187]\tvalidation_0-rmse:2.69824\n",
+ "[1188]\tvalidation_0-rmse:2.69744\n",
+ "[1189]\tvalidation_0-rmse:2.69685\n",
+ "[1190]\tvalidation_0-rmse:2.69648\n",
+ "[1191]\tvalidation_0-rmse:2.69590\n",
+ "[1192]\tvalidation_0-rmse:2.69511\n",
+ "[1193]\tvalidation_0-rmse:2.69456\n",
+ "[1194]\tvalidation_0-rmse:2.69369\n",
+ "[1195]\tvalidation_0-rmse:2.69325\n",
+ "[1196]\tvalidation_0-rmse:2.69303\n",
+ "[1197]\tvalidation_0-rmse:2.69224\n",
+ "[1198]\tvalidation_0-rmse:2.69088\n",
+ "[1199]\tvalidation_0-rmse:2.69012\n",
+ "[1200]\tvalidation_0-rmse:2.68941\n",
+ "[1201]\tvalidation_0-rmse:2.68868\n",
+ "[1202]\tvalidation_0-rmse:2.68783\n",
+ "[1203]\tvalidation_0-rmse:2.68747\n",
+ "[1204]\tvalidation_0-rmse:2.68644\n",
+ "[1205]\tvalidation_0-rmse:2.68600\n",
+ "[1206]\tvalidation_0-rmse:2.68556\n",
+ "[1207]\tvalidation_0-rmse:2.68537\n",
+ "[1208]\tvalidation_0-rmse:2.68488\n",
+ "[1209]\tvalidation_0-rmse:2.68386\n",
+ "[1210]\tvalidation_0-rmse:2.68336\n",
+ "[1211]\tvalidation_0-rmse:2.68286\n",
+ "[1212]\tvalidation_0-rmse:2.68218\n",
+ "[1213]\tvalidation_0-rmse:2.68210\n",
+ "[1214]\tvalidation_0-rmse:2.68185\n",
+ "[1215]\tvalidation_0-rmse:2.68122\n",
+ "[1216]\tvalidation_0-rmse:2.68034\n",
+ "[1217]\tvalidation_0-rmse:2.67968\n",
+ "[1218]\tvalidation_0-rmse:2.67945\n",
+ "[1219]\tvalidation_0-rmse:2.67859\n",
+ "[1220]\tvalidation_0-rmse:2.67799\n",
+ "[1221]\tvalidation_0-rmse:2.67732\n",
+ "[1222]\tvalidation_0-rmse:2.67681\n",
+ "[1223]\tvalidation_0-rmse:2.67618\n",
+ "[1224]\tvalidation_0-rmse:2.67534\n",
+ "[1225]\tvalidation_0-rmse:2.67467\n",
+ "[1226]\tvalidation_0-rmse:2.67382\n",
+ "[1227]\tvalidation_0-rmse:2.67353\n",
+ "[1228]\tvalidation_0-rmse:2.67275\n",
+ "[1229]\tvalidation_0-rmse:2.67206\n",
+ "[1230]\tvalidation_0-rmse:2.67115\n",
+ "[1231]\tvalidation_0-rmse:2.67043\n",
+ "[1232]\tvalidation_0-rmse:2.67011\n",
+ "[1233]\tvalidation_0-rmse:2.66947\n",
+ "[1234]\tvalidation_0-rmse:2.66909\n",
+ "[1235]\tvalidation_0-rmse:2.66845\n",
+ "[1236]\tvalidation_0-rmse:2.66785\n",
+ "[1237]\tvalidation_0-rmse:2.66735\n",
+ "[1238]\tvalidation_0-rmse:2.66649\n",
+ "[1239]\tvalidation_0-rmse:2.66571\n",
+ "[1240]\tvalidation_0-rmse:2.66542\n",
+ "[1241]\tvalidation_0-rmse:2.66510\n",
+ "[1242]\tvalidation_0-rmse:2.66461\n",
+ "[1243]\tvalidation_0-rmse:2.66374\n",
+ "[1244]\tvalidation_0-rmse:2.66313\n",
+ "[1245]\tvalidation_0-rmse:2.66265\n",
+ "[1246]\tvalidation_0-rmse:2.66189\n",
+ "[1247]\tvalidation_0-rmse:2.66119\n",
+ "[1248]\tvalidation_0-rmse:2.66070\n",
+ "[1249]\tvalidation_0-rmse:2.66005\n",
+ "[1250]\tvalidation_0-rmse:2.65943\n",
+ "[1251]\tvalidation_0-rmse:2.65904\n",
+ "[1252]\tvalidation_0-rmse:2.65808\n",
+ "[1253]\tvalidation_0-rmse:2.65795\n",
+ "[1254]\tvalidation_0-rmse:2.65752\n",
+ "[1255]\tvalidation_0-rmse:2.65699\n",
+ "[1256]\tvalidation_0-rmse:2.65654\n",
+ "[1257]\tvalidation_0-rmse:2.65567\n",
+ "[1258]\tvalidation_0-rmse:2.65515\n",
+ "[1259]\tvalidation_0-rmse:2.65503\n",
+ "[1260]\tvalidation_0-rmse:2.65427\n",
+ "[1261]\tvalidation_0-rmse:2.65391\n",
+ "[1262]\tvalidation_0-rmse:2.65325\n",
+ "[1263]\tvalidation_0-rmse:2.65291\n",
+ "[1264]\tvalidation_0-rmse:2.65230\n",
+ "[1265]\tvalidation_0-rmse:2.65172\n",
+ "[1266]\tvalidation_0-rmse:2.65108\n",
+ "[1267]\tvalidation_0-rmse:2.65060\n",
+ "[1268]\tvalidation_0-rmse:2.65032\n",
+ "[1269]\tvalidation_0-rmse:2.64966\n",
+ "[1270]\tvalidation_0-rmse:2.64921\n",
+ "[1271]\tvalidation_0-rmse:2.64875\n",
+ "[1272]\tvalidation_0-rmse:2.64827\n",
+ "[1273]\tvalidation_0-rmse:2.64774\n",
+ "[1274]\tvalidation_0-rmse:2.64728\n",
+ "[1275]\tvalidation_0-rmse:2.64666\n",
+ "[1276]\tvalidation_0-rmse:2.64598\n",
+ "[1277]\tvalidation_0-rmse:2.64567\n",
+ "[1278]\tvalidation_0-rmse:2.64512\n",
+ "[1279]\tvalidation_0-rmse:2.64462\n",
+ "[1280]\tvalidation_0-rmse:2.64383\n",
+ "[1281]\tvalidation_0-rmse:2.64346\n",
+ "[1282]\tvalidation_0-rmse:2.64289\n",
+ "[1283]\tvalidation_0-rmse:2.64252\n",
+ "[1284]\tvalidation_0-rmse:2.64209\n",
+ "[1285]\tvalidation_0-rmse:2.64139\n",
+ "[1286]\tvalidation_0-rmse:2.64119\n",
+ "[1287]\tvalidation_0-rmse:2.64107\n",
+ "[1288]\tvalidation_0-rmse:2.64075\n",
+ "[1289]\tvalidation_0-rmse:2.64005\n",
+ "[1290]\tvalidation_0-rmse:2.63963\n",
+ "[1291]\tvalidation_0-rmse:2.63887\n",
+ "[1292]\tvalidation_0-rmse:2.63829\n",
+ "[1293]\tvalidation_0-rmse:2.63796\n",
+ "[1294]\tvalidation_0-rmse:2.63752\n",
+ "[1295]\tvalidation_0-rmse:2.63715\n",
+ "[1296]\tvalidation_0-rmse:2.63697\n",
+ "[1297]\tvalidation_0-rmse:2.63632\n",
+ "[1298]\tvalidation_0-rmse:2.63603\n",
+ "[1299]\tvalidation_0-rmse:2.63587\n",
+ "[1300]\tvalidation_0-rmse:2.63575\n",
+ "[1301]\tvalidation_0-rmse:2.63550\n",
+ "[1302]\tvalidation_0-rmse:2.63516\n",
+ "[1303]\tvalidation_0-rmse:2.63474\n",
+ "[1304]\tvalidation_0-rmse:2.63430\n",
+ "[1305]\tvalidation_0-rmse:2.63413\n",
+ "[1306]\tvalidation_0-rmse:2.63370\n",
+ "[1307]\tvalidation_0-rmse:2.63355\n",
+ "[1308]\tvalidation_0-rmse:2.63317\n",
+ "[1309]\tvalidation_0-rmse:2.63292\n",
+ "[1310]\tvalidation_0-rmse:2.63263\n",
+ "[1311]\tvalidation_0-rmse:2.63224\n",
+ "[1312]\tvalidation_0-rmse:2.63157\n",
+ "[1313]\tvalidation_0-rmse:2.63093\n",
+ "[1314]\tvalidation_0-rmse:2.63025\n",
+ "[1315]\tvalidation_0-rmse:2.63006\n",
+ "[1316]\tvalidation_0-rmse:2.62946\n",
+ "[1317]\tvalidation_0-rmse:2.62902\n",
+ "[1318]\tvalidation_0-rmse:2.62855\n",
+ "[1319]\tvalidation_0-rmse:2.62799\n",
+ "[1320]\tvalidation_0-rmse:2.62751\n",
+ "[1321]\tvalidation_0-rmse:2.62710\n",
+ "[1322]\tvalidation_0-rmse:2.62668\n",
+ "[1323]\tvalidation_0-rmse:2.62617\n",
+ "[1324]\tvalidation_0-rmse:2.62565\n",
+ "[1325]\tvalidation_0-rmse:2.62514\n",
+ "[1326]\tvalidation_0-rmse:2.62456\n",
+ "[1327]\tvalidation_0-rmse:2.62408\n",
+ "[1328]\tvalidation_0-rmse:2.62340\n",
+ "[1329]\tvalidation_0-rmse:2.62322\n",
+ "[1330]\tvalidation_0-rmse:2.62298\n",
+ "[1331]\tvalidation_0-rmse:2.62258\n",
+ "[1332]\tvalidation_0-rmse:2.62194\n",
+ "[1333]\tvalidation_0-rmse:2.62156\n",
+ "[1334]\tvalidation_0-rmse:2.62113\n",
+ "[1335]\tvalidation_0-rmse:2.62061\n",
+ "[1336]\tvalidation_0-rmse:2.62031\n",
+ "[1337]\tvalidation_0-rmse:2.61962\n",
+ "[1338]\tvalidation_0-rmse:2.61931\n",
+ "[1339]\tvalidation_0-rmse:2.61884\n",
+ "[1340]\tvalidation_0-rmse:2.61819\n",
+ "[1341]\tvalidation_0-rmse:2.61728\n",
+ "[1342]\tvalidation_0-rmse:2.61696\n",
+ "[1343]\tvalidation_0-rmse:2.61652\n",
+ "[1344]\tvalidation_0-rmse:2.61574\n",
+ "[1345]\tvalidation_0-rmse:2.61554\n",
+ "[1346]\tvalidation_0-rmse:2.61550\n",
+ "[1347]\tvalidation_0-rmse:2.61521\n",
+ "[1348]\tvalidation_0-rmse:2.61481\n",
+ "[1349]\tvalidation_0-rmse:2.61416\n",
+ "[1350]\tvalidation_0-rmse:2.61393\n",
+ "[1351]\tvalidation_0-rmse:2.61377\n",
+ "[1352]\tvalidation_0-rmse:2.61308\n",
+ "[1353]\tvalidation_0-rmse:2.61220\n",
+ "[1354]\tvalidation_0-rmse:2.61110\n",
+ "[1355]\tvalidation_0-rmse:2.61020\n",
+ "[1356]\tvalidation_0-rmse:2.60977\n",
+ "[1357]\tvalidation_0-rmse:2.60949\n",
+ "[1358]\tvalidation_0-rmse:2.60916\n",
+ "[1359]\tvalidation_0-rmse:2.60890\n",
+ "[1360]\tvalidation_0-rmse:2.60871\n",
+ "[1361]\tvalidation_0-rmse:2.60846\n",
+ "[1362]\tvalidation_0-rmse:2.60824\n",
+ "[1363]\tvalidation_0-rmse:2.60763\n",
+ "[1364]\tvalidation_0-rmse:2.60758\n",
+ "[1365]\tvalidation_0-rmse:2.60740\n",
+ "[1366]\tvalidation_0-rmse:2.60730\n",
+ "[1367]\tvalidation_0-rmse:2.60695\n",
+ "[1368]\tvalidation_0-rmse:2.60594\n",
+ "[1369]\tvalidation_0-rmse:2.60534\n",
+ "[1370]\tvalidation_0-rmse:2.60481\n",
+ "[1371]\tvalidation_0-rmse:2.60367\n",
+ "[1372]\tvalidation_0-rmse:2.60336\n",
+ "[1373]\tvalidation_0-rmse:2.60256\n",
+ "[1374]\tvalidation_0-rmse:2.60211\n",
+ "[1375]\tvalidation_0-rmse:2.60168\n",
+ "[1376]\tvalidation_0-rmse:2.60125\n",
+ "[1377]\tvalidation_0-rmse:2.60084\n",
+ "[1378]\tvalidation_0-rmse:2.60045\n",
+ "[1379]\tvalidation_0-rmse:2.59939\n",
+ "[1380]\tvalidation_0-rmse:2.59880\n",
+ "[1381]\tvalidation_0-rmse:2.59822\n",
+ "[1382]\tvalidation_0-rmse:2.59728\n",
+ "[1383]\tvalidation_0-rmse:2.59694\n",
+ "[1384]\tvalidation_0-rmse:2.59644\n",
+ "[1385]\tvalidation_0-rmse:2.59577\n",
+ "[1386]\tvalidation_0-rmse:2.59520\n",
+ "[1387]\tvalidation_0-rmse:2.59455\n",
+ "[1388]\tvalidation_0-rmse:2.59346\n",
+ "[1389]\tvalidation_0-rmse:2.59298\n",
+ "[1390]\tvalidation_0-rmse:2.59235\n",
+ "[1391]\tvalidation_0-rmse:2.59154\n",
+ "[1392]\tvalidation_0-rmse:2.59038\n",
+ "[1393]\tvalidation_0-rmse:2.58976\n",
+ "[1394]\tvalidation_0-rmse:2.58941\n",
+ "[1395]\tvalidation_0-rmse:2.58888\n",
+ "[1396]\tvalidation_0-rmse:2.58824\n",
+ "[1397]\tvalidation_0-rmse:2.58788\n",
+ "[1398]\tvalidation_0-rmse:2.58733\n",
+ "[1399]\tvalidation_0-rmse:2.58655\n",
+ "[1400]\tvalidation_0-rmse:2.58533\n",
+ "[1401]\tvalidation_0-rmse:2.58512\n",
+ "[1402]\tvalidation_0-rmse:2.58429\n",
+ "[1403]\tvalidation_0-rmse:2.58392\n",
+ "[1404]\tvalidation_0-rmse:2.58355\n",
+ "[1405]\tvalidation_0-rmse:2.58304\n",
+ "[1406]\tvalidation_0-rmse:2.58232\n",
+ "[1407]\tvalidation_0-rmse:2.58192\n",
+ "[1408]\tvalidation_0-rmse:2.58180\n",
+ "[1409]\tvalidation_0-rmse:2.58141\n",
+ "[1410]\tvalidation_0-rmse:2.58105\n",
+ "[1411]\tvalidation_0-rmse:2.58020\n",
+ "[1412]\tvalidation_0-rmse:2.57966\n",
+ "[1413]\tvalidation_0-rmse:2.57921\n",
+ "[1414]\tvalidation_0-rmse:2.57842\n",
+ "[1415]\tvalidation_0-rmse:2.57773\n",
+ "[1416]\tvalidation_0-rmse:2.57740\n",
+ "[1417]\tvalidation_0-rmse:2.57714\n",
+ "[1418]\tvalidation_0-rmse:2.57640\n",
+ "[1419]\tvalidation_0-rmse:2.57588\n",
+ "[1420]\tvalidation_0-rmse:2.57554\n",
+ "[1421]\tvalidation_0-rmse:2.57496\n",
+ "[1422]\tvalidation_0-rmse:2.57435\n",
+ "[1423]\tvalidation_0-rmse:2.57412\n",
+ "[1424]\tvalidation_0-rmse:2.57365\n",
+ "[1425]\tvalidation_0-rmse:2.57300\n",
+ "[1426]\tvalidation_0-rmse:2.57224\n",
+ "[1427]\tvalidation_0-rmse:2.57215\n",
+ "[1428]\tvalidation_0-rmse:2.57142\n",
+ "[1429]\tvalidation_0-rmse:2.57111\n",
+ "[1430]\tvalidation_0-rmse:2.57045\n",
+ "[1431]\tvalidation_0-rmse:2.57026\n",
+ "[1432]\tvalidation_0-rmse:2.56990\n",
+ "[1433]\tvalidation_0-rmse:2.56905\n",
+ "[1434]\tvalidation_0-rmse:2.56834\n",
+ "[1435]\tvalidation_0-rmse:2.56817\n",
+ "[1436]\tvalidation_0-rmse:2.56750\n",
+ "[1437]\tvalidation_0-rmse:2.56712\n",
+ "[1438]\tvalidation_0-rmse:2.56659\n",
+ "[1439]\tvalidation_0-rmse:2.56621\n",
+ "[1440]\tvalidation_0-rmse:2.56604\n",
+ "[1441]\tvalidation_0-rmse:2.56504\n",
+ "[1442]\tvalidation_0-rmse:2.56445\n",
+ "[1443]\tvalidation_0-rmse:2.56371\n",
+ "[1444]\tvalidation_0-rmse:2.56337\n",
+ "[1445]\tvalidation_0-rmse:2.56330\n",
+ "[1446]\tvalidation_0-rmse:2.56290\n",
+ "[1447]\tvalidation_0-rmse:2.56240\n",
+ "[1448]\tvalidation_0-rmse:2.56173\n",
+ "[1449]\tvalidation_0-rmse:2.56163\n",
+ "[1450]\tvalidation_0-rmse:2.56140\n",
+ "[1451]\tvalidation_0-rmse:2.56093\n",
+ "[1452]\tvalidation_0-rmse:2.56075\n",
+ "[1453]\tvalidation_0-rmse:2.56031\n",
+ "[1454]\tvalidation_0-rmse:2.55942\n",
+ "[1455]\tvalidation_0-rmse:2.55878\n",
+ "[1456]\tvalidation_0-rmse:2.55858\n",
+ "[1457]\tvalidation_0-rmse:2.55826\n",
+ "[1458]\tvalidation_0-rmse:2.55792\n",
+ "[1459]\tvalidation_0-rmse:2.55726\n",
+ "[1460]\tvalidation_0-rmse:2.55677\n",
+ "[1461]\tvalidation_0-rmse:2.55603\n",
+ "[1462]\tvalidation_0-rmse:2.55567\n",
+ "[1463]\tvalidation_0-rmse:2.55509\n",
+ "[1464]\tvalidation_0-rmse:2.55452\n",
+ "[1465]\tvalidation_0-rmse:2.55398\n",
+ "[1466]\tvalidation_0-rmse:2.55341\n",
+ "[1467]\tvalidation_0-rmse:2.55325\n",
+ "[1468]\tvalidation_0-rmse:2.55303\n",
+ "[1469]\tvalidation_0-rmse:2.55253\n",
+ "[1470]\tvalidation_0-rmse:2.55204\n",
+ "[1471]\tvalidation_0-rmse:2.55152\n",
+ "[1472]\tvalidation_0-rmse:2.55114\n",
+ "[1473]\tvalidation_0-rmse:2.55095\n",
+ "[1474]\tvalidation_0-rmse:2.55039\n",
+ "[1475]\tvalidation_0-rmse:2.54971\n",
+ "[1476]\tvalidation_0-rmse:2.54947\n",
+ "[1477]\tvalidation_0-rmse:2.54912\n",
+ "[1478]\tvalidation_0-rmse:2.54859\n",
+ "[1479]\tvalidation_0-rmse:2.54811\n",
+ "[1480]\tvalidation_0-rmse:2.54761\n",
+ "[1481]\tvalidation_0-rmse:2.54725\n",
+ "[1482]\tvalidation_0-rmse:2.54679\n",
+ "[1483]\tvalidation_0-rmse:2.54643\n",
+ "[1484]\tvalidation_0-rmse:2.54565\n",
+ "[1485]\tvalidation_0-rmse:2.54561\n",
+ "[1486]\tvalidation_0-rmse:2.54547\n",
+ "[1487]\tvalidation_0-rmse:2.54489\n",
+ "[1488]\tvalidation_0-rmse:2.54457\n",
+ "[1489]\tvalidation_0-rmse:2.54296\n",
+ "[1490]\tvalidation_0-rmse:2.54222\n",
+ "[1491]\tvalidation_0-rmse:2.54112\n",
+ "[1492]\tvalidation_0-rmse:2.54061\n",
+ "[1493]\tvalidation_0-rmse:2.53984\n",
+ "[1494]\tvalidation_0-rmse:2.53863\n",
+ "[1495]\tvalidation_0-rmse:2.53822\n",
+ "[1496]\tvalidation_0-rmse:2.53778\n",
+ "[1497]\tvalidation_0-rmse:2.53740\n",
+ "[1498]\tvalidation_0-rmse:2.53728\n",
+ "[1499]\tvalidation_0-rmse:2.53718\n",
+ "[1500]\tvalidation_0-rmse:2.53668\n",
+ "[1501]\tvalidation_0-rmse:2.53490\n",
+ "[1502]\tvalidation_0-rmse:2.53458\n",
+ "[1503]\tvalidation_0-rmse:2.53309\n",
+ "[1504]\tvalidation_0-rmse:2.53187\n",
+ "[1505]\tvalidation_0-rmse:2.53150\n",
+ "[1506]\tvalidation_0-rmse:2.53041\n",
+ "[1507]\tvalidation_0-rmse:2.53005\n",
+ "[1508]\tvalidation_0-rmse:2.52861\n",
+ "[1509]\tvalidation_0-rmse:2.52788\n",
+ "[1510]\tvalidation_0-rmse:2.52725\n",
+ "[1511]\tvalidation_0-rmse:2.52694\n",
+ "[1512]\tvalidation_0-rmse:2.52620\n",
+ "[1513]\tvalidation_0-rmse:2.52576\n",
+ "[1514]\tvalidation_0-rmse:2.52544\n",
+ "[1515]\tvalidation_0-rmse:2.52502\n",
+ "[1516]\tvalidation_0-rmse:2.52482\n",
+ "[1517]\tvalidation_0-rmse:2.52416\n",
+ "[1518]\tvalidation_0-rmse:2.52378\n",
+ "[1519]\tvalidation_0-rmse:2.52364\n",
+ "[1520]\tvalidation_0-rmse:2.52320\n",
+ "[1521]\tvalidation_0-rmse:2.52280\n",
+ "[1522]\tvalidation_0-rmse:2.52224\n",
+ "[1523]\tvalidation_0-rmse:2.52189\n",
+ "[1524]\tvalidation_0-rmse:2.52153\n",
+ "[1525]\tvalidation_0-rmse:2.52058\n",
+ "[1526]\tvalidation_0-rmse:2.51998\n",
+ "[1527]\tvalidation_0-rmse:2.51882\n",
+ "[1528]\tvalidation_0-rmse:2.51838\n",
+ "[1529]\tvalidation_0-rmse:2.51768\n",
+ "[1530]\tvalidation_0-rmse:2.51664\n",
+ "[1531]\tvalidation_0-rmse:2.51580\n",
+ "[1532]\tvalidation_0-rmse:2.51512\n",
+ "[1533]\tvalidation_0-rmse:2.51453\n",
+ "[1534]\tvalidation_0-rmse:2.51409\n",
+ "[1535]\tvalidation_0-rmse:2.51370\n",
+ "[1536]\tvalidation_0-rmse:2.51316\n",
+ "[1537]\tvalidation_0-rmse:2.51260\n",
+ "[1538]\tvalidation_0-rmse:2.51191\n",
+ "[1539]\tvalidation_0-rmse:2.51127\n",
+ "[1540]\tvalidation_0-rmse:2.51089\n",
+ "[1541]\tvalidation_0-rmse:2.51057\n",
+ "[1542]\tvalidation_0-rmse:2.51014\n",
+ "[1543]\tvalidation_0-rmse:2.50993\n",
+ "[1544]\tvalidation_0-rmse:2.50940\n",
+ "[1545]\tvalidation_0-rmse:2.50883\n",
+ "[1546]\tvalidation_0-rmse:2.50791\n",
+ "[1547]\tvalidation_0-rmse:2.50751\n",
+ "[1548]\tvalidation_0-rmse:2.50680\n",
+ "[1549]\tvalidation_0-rmse:2.50653\n",
+ "[1550]\tvalidation_0-rmse:2.50588\n",
+ "[1551]\tvalidation_0-rmse:2.50507\n",
+ "[1552]\tvalidation_0-rmse:2.50441\n",
+ "[1553]\tvalidation_0-rmse:2.50363\n",
+ "[1554]\tvalidation_0-rmse:2.50324\n",
+ "[1555]\tvalidation_0-rmse:2.50262\n",
+ "[1556]\tvalidation_0-rmse:2.50233\n",
+ "[1557]\tvalidation_0-rmse:2.50154\n",
+ "[1558]\tvalidation_0-rmse:2.50085\n",
+ "[1559]\tvalidation_0-rmse:2.50042\n",
+ "[1560]\tvalidation_0-rmse:2.50021\n",
+ "[1561]\tvalidation_0-rmse:2.49982\n",
+ "[1562]\tvalidation_0-rmse:2.49949\n",
+ "[1563]\tvalidation_0-rmse:2.49923\n",
+ "[1564]\tvalidation_0-rmse:2.49850\n",
+ "[1565]\tvalidation_0-rmse:2.49829\n",
+ "[1566]\tvalidation_0-rmse:2.49799\n",
+ "[1567]\tvalidation_0-rmse:2.49790\n",
+ "[1568]\tvalidation_0-rmse:2.49770\n",
+ "[1569]\tvalidation_0-rmse:2.49745\n",
+ "[1570]\tvalidation_0-rmse:2.49695\n",
+ "[1571]\tvalidation_0-rmse:2.49635\n",
+ "[1572]\tvalidation_0-rmse:2.49569\n",
+ "[1573]\tvalidation_0-rmse:2.49536\n",
+ "[1574]\tvalidation_0-rmse:2.49503\n",
+ "[1575]\tvalidation_0-rmse:2.49468\n",
+ "[1576]\tvalidation_0-rmse:2.49436\n",
+ "[1577]\tvalidation_0-rmse:2.49410\n",
+ "[1578]\tvalidation_0-rmse:2.49311\n",
+ "[1579]\tvalidation_0-rmse:2.49237\n",
+ "[1580]\tvalidation_0-rmse:2.49166\n",
+ "[1581]\tvalidation_0-rmse:2.49096\n",
+ "[1582]\tvalidation_0-rmse:2.49060\n",
+ "[1583]\tvalidation_0-rmse:2.49017\n",
+ "[1584]\tvalidation_0-rmse:2.48988\n",
+ "[1585]\tvalidation_0-rmse:2.48981\n",
+ "[1586]\tvalidation_0-rmse:2.48970\n",
+ "[1587]\tvalidation_0-rmse:2.48928\n",
+ "[1588]\tvalidation_0-rmse:2.48898\n",
+ "[1589]\tvalidation_0-rmse:2.48855\n",
+ "[1590]\tvalidation_0-rmse:2.48804\n",
+ "[1591]\tvalidation_0-rmse:2.48786\n",
+ "[1592]\tvalidation_0-rmse:2.48753\n",
+ "[1593]\tvalidation_0-rmse:2.48716\n",
+ "[1594]\tvalidation_0-rmse:2.48652\n",
+ "[1595]\tvalidation_0-rmse:2.48636\n",
+ "[1596]\tvalidation_0-rmse:2.48549\n",
+ "[1597]\tvalidation_0-rmse:2.48542\n",
+ "[1598]\tvalidation_0-rmse:2.48495\n",
+ "[1599]\tvalidation_0-rmse:2.48462\n",
+ "[1600]\tvalidation_0-rmse:2.48430\n",
+ "[1601]\tvalidation_0-rmse:2.48423\n",
+ "[1602]\tvalidation_0-rmse:2.48328\n",
+ "[1603]\tvalidation_0-rmse:2.48278\n",
+ "[1604]\tvalidation_0-rmse:2.48230\n",
+ "[1605]\tvalidation_0-rmse:2.48204\n",
+ "[1606]\tvalidation_0-rmse:2.48158\n",
+ "[1607]\tvalidation_0-rmse:2.48133\n",
+ "[1608]\tvalidation_0-rmse:2.48126\n",
+ "[1609]\tvalidation_0-rmse:2.48068\n",
+ "[1610]\tvalidation_0-rmse:2.47991\n",
+ "[1611]\tvalidation_0-rmse:2.47960\n",
+ "[1612]\tvalidation_0-rmse:2.47948\n",
+ "[1613]\tvalidation_0-rmse:2.47935\n",
+ "[1614]\tvalidation_0-rmse:2.47890\n",
+ "[1615]\tvalidation_0-rmse:2.47839\n",
+ "[1616]\tvalidation_0-rmse:2.47833\n",
+ "[1617]\tvalidation_0-rmse:2.47775\n",
+ "[1618]\tvalidation_0-rmse:2.47765\n",
+ "[1619]\tvalidation_0-rmse:2.47714\n",
+ "[1620]\tvalidation_0-rmse:2.47685\n",
+ "[1621]\tvalidation_0-rmse:2.47660\n",
+ "[1622]\tvalidation_0-rmse:2.47643\n",
+ "[1623]\tvalidation_0-rmse:2.47589\n",
+ "[1624]\tvalidation_0-rmse:2.47569\n",
+ "[1625]\tvalidation_0-rmse:2.47501\n",
+ "[1626]\tvalidation_0-rmse:2.47415\n",
+ "[1627]\tvalidation_0-rmse:2.47360\n",
+ "[1628]\tvalidation_0-rmse:2.47326\n",
+ "[1629]\tvalidation_0-rmse:2.47242\n",
+ "[1630]\tvalidation_0-rmse:2.47126\n",
+ "[1631]\tvalidation_0-rmse:2.47068\n",
+ "[1632]\tvalidation_0-rmse:2.47007\n",
+ "[1633]\tvalidation_0-rmse:2.46964\n",
+ "[1634]\tvalidation_0-rmse:2.46910\n",
+ "[1635]\tvalidation_0-rmse:2.46847\n",
+ "[1636]\tvalidation_0-rmse:2.46800\n",
+ "[1637]\tvalidation_0-rmse:2.46774\n",
+ "[1638]\tvalidation_0-rmse:2.46733\n",
+ "[1639]\tvalidation_0-rmse:2.46682\n",
+ "[1640]\tvalidation_0-rmse:2.46594\n",
+ "[1641]\tvalidation_0-rmse:2.46571\n",
+ "[1642]\tvalidation_0-rmse:2.46556\n",
+ "[1643]\tvalidation_0-rmse:2.46478\n",
+ "[1644]\tvalidation_0-rmse:2.46469\n",
+ "[1645]\tvalidation_0-rmse:2.46436\n",
+ "[1646]\tvalidation_0-rmse:2.46428\n",
+ "[1647]\tvalidation_0-rmse:2.46418\n",
+ "[1648]\tvalidation_0-rmse:2.46374\n",
+ "[1649]\tvalidation_0-rmse:2.46351\n",
+ "[1650]\tvalidation_0-rmse:2.46346\n",
+ "[1651]\tvalidation_0-rmse:2.46311\n",
+ "[1652]\tvalidation_0-rmse:2.46286\n",
+ "[1653]\tvalidation_0-rmse:2.46263\n",
+ "[1654]\tvalidation_0-rmse:2.46219\n",
+ "[1655]\tvalidation_0-rmse:2.46196\n",
+ "[1656]\tvalidation_0-rmse:2.46124\n",
+ "[1657]\tvalidation_0-rmse:2.46061\n",
+ "[1658]\tvalidation_0-rmse:2.45996\n",
+ "[1659]\tvalidation_0-rmse:2.45942\n",
+ "[1660]\tvalidation_0-rmse:2.45891\n",
+ "[1661]\tvalidation_0-rmse:2.45868\n",
+ "[1662]\tvalidation_0-rmse:2.45847\n",
+ "[1663]\tvalidation_0-rmse:2.45826\n",
+ "[1664]\tvalidation_0-rmse:2.45800\n",
+ "[1665]\tvalidation_0-rmse:2.45794\n",
+ "[1666]\tvalidation_0-rmse:2.45774\n",
+ "[1667]\tvalidation_0-rmse:2.45756\n",
+ "[1668]\tvalidation_0-rmse:2.45741\n",
+ "[1669]\tvalidation_0-rmse:2.45715\n",
+ "[1670]\tvalidation_0-rmse:2.45709\n",
+ "[1671]\tvalidation_0-rmse:2.45688\n",
+ "[1672]\tvalidation_0-rmse:2.45673\n",
+ "[1673]\tvalidation_0-rmse:2.45664\n",
+ "[1674]\tvalidation_0-rmse:2.45617\n",
+ "[1675]\tvalidation_0-rmse:2.45572\n",
+ "[1676]\tvalidation_0-rmse:2.45556\n",
+ "[1677]\tvalidation_0-rmse:2.45518\n",
+ "[1678]\tvalidation_0-rmse:2.45499\n",
+ "[1679]\tvalidation_0-rmse:2.45465\n",
+ "[1680]\tvalidation_0-rmse:2.45442\n",
+ "[1681]\tvalidation_0-rmse:2.45434\n",
+ "[1682]\tvalidation_0-rmse:2.45387\n",
+ "[1683]\tvalidation_0-rmse:2.45363\n",
+ "[1684]\tvalidation_0-rmse:2.45335\n",
+ "[1685]\tvalidation_0-rmse:2.45301\n",
+ "[1686]\tvalidation_0-rmse:2.45264\n",
+ "[1687]\tvalidation_0-rmse:2.45214\n",
+ "[1688]\tvalidation_0-rmse:2.45165\n",
+ "[1689]\tvalidation_0-rmse:2.45135\n",
+ "[1690]\tvalidation_0-rmse:2.45101\n",
+ "[1691]\tvalidation_0-rmse:2.45086\n",
+ "[1692]\tvalidation_0-rmse:2.45069\n",
+ "[1693]\tvalidation_0-rmse:2.45022\n",
+ "[1694]\tvalidation_0-rmse:2.44999\n",
+ "[1695]\tvalidation_0-rmse:2.44960\n",
+ "[1696]\tvalidation_0-rmse:2.44957\n",
+ "[1697]\tvalidation_0-rmse:2.44914\n",
+ "[1698]\tvalidation_0-rmse:2.44878\n",
+ "[1699]\tvalidation_0-rmse:2.44823\n",
+ "[1700]\tvalidation_0-rmse:2.44786\n",
+ "[1701]\tvalidation_0-rmse:2.44737\n",
+ "[1702]\tvalidation_0-rmse:2.44675\n",
+ "[1703]\tvalidation_0-rmse:2.44592\n",
+ "[1704]\tvalidation_0-rmse:2.44521\n",
+ "[1705]\tvalidation_0-rmse:2.44485\n",
+ "[1706]\tvalidation_0-rmse:2.44445\n",
+ "[1707]\tvalidation_0-rmse:2.44394\n",
+ "[1708]\tvalidation_0-rmse:2.44348\n",
+ "[1709]\tvalidation_0-rmse:2.44321\n",
+ "[1710]\tvalidation_0-rmse:2.44303\n",
+ "[1711]\tvalidation_0-rmse:2.44243\n",
+ "[1712]\tvalidation_0-rmse:2.44192\n",
+ "[1713]\tvalidation_0-rmse:2.44158\n",
+ "[1714]\tvalidation_0-rmse:2.44119\n",
+ "[1715]\tvalidation_0-rmse:2.44077\n",
+ "[1716]\tvalidation_0-rmse:2.44045\n",
+ "[1717]\tvalidation_0-rmse:2.44001\n",
+ "[1718]\tvalidation_0-rmse:2.43960\n",
+ "[1719]\tvalidation_0-rmse:2.43922\n",
+ "[1720]\tvalidation_0-rmse:2.43880\n",
+ "[1721]\tvalidation_0-rmse:2.43809\n",
+ "[1722]\tvalidation_0-rmse:2.43746\n",
+ "[1723]\tvalidation_0-rmse:2.43702\n",
+ "[1724]\tvalidation_0-rmse:2.43668\n",
+ "[1725]\tvalidation_0-rmse:2.43627\n",
+ "[1726]\tvalidation_0-rmse:2.43599\n",
+ "[1727]\tvalidation_0-rmse:2.43543\n",
+ "[1728]\tvalidation_0-rmse:2.43478\n",
+ "[1729]\tvalidation_0-rmse:2.43445\n",
+ "[1730]\tvalidation_0-rmse:2.43431\n",
+ "[1731]\tvalidation_0-rmse:2.43357\n",
+ "[1732]\tvalidation_0-rmse:2.43303\n",
+ "[1733]\tvalidation_0-rmse:2.43292\n",
+ "[1734]\tvalidation_0-rmse:2.43196\n",
+ "[1735]\tvalidation_0-rmse:2.43134\n",
+ "[1736]\tvalidation_0-rmse:2.43086\n",
+ "[1737]\tvalidation_0-rmse:2.43059\n",
+ "[1738]\tvalidation_0-rmse:2.43043\n",
+ "[1739]\tvalidation_0-rmse:2.42995\n",
+ "[1740]\tvalidation_0-rmse:2.42958\n",
+ "[1741]\tvalidation_0-rmse:2.42935\n",
+ "[1742]\tvalidation_0-rmse:2.42845\n",
+ "[1743]\tvalidation_0-rmse:2.42831\n",
+ "[1744]\tvalidation_0-rmse:2.42802\n",
+ "[1745]\tvalidation_0-rmse:2.42756\n",
+ "[1746]\tvalidation_0-rmse:2.42734\n",
+ "[1747]\tvalidation_0-rmse:2.42692\n",
+ "[1748]\tvalidation_0-rmse:2.42661\n",
+ "[1749]\tvalidation_0-rmse:2.42589\n",
+ "[1750]\tvalidation_0-rmse:2.42425\n",
+ "[1751]\tvalidation_0-rmse:2.42392\n",
+ "[1752]\tvalidation_0-rmse:2.42366\n",
+ "[1753]\tvalidation_0-rmse:2.42312\n",
+ "[1754]\tvalidation_0-rmse:2.42207\n",
+ "[1755]\tvalidation_0-rmse:2.42127\n",
+ "[1756]\tvalidation_0-rmse:2.42070\n",
+ "[1757]\tvalidation_0-rmse:2.42015\n",
+ "[1758]\tvalidation_0-rmse:2.41975\n",
+ "[1759]\tvalidation_0-rmse:2.41922\n",
+ "[1760]\tvalidation_0-rmse:2.41844\n",
+ "[1761]\tvalidation_0-rmse:2.41791\n",
+ "[1762]\tvalidation_0-rmse:2.41748\n",
+ "[1763]\tvalidation_0-rmse:2.41722\n",
+ "[1764]\tvalidation_0-rmse:2.41684\n",
+ "[1765]\tvalidation_0-rmse:2.41634\n",
+ "[1766]\tvalidation_0-rmse:2.41609\n",
+ "[1767]\tvalidation_0-rmse:2.41584\n",
+ "[1768]\tvalidation_0-rmse:2.41546\n",
+ "[1769]\tvalidation_0-rmse:2.41436\n",
+ "[1770]\tvalidation_0-rmse:2.41399\n",
+ "[1771]\tvalidation_0-rmse:2.41336\n",
+ "[1772]\tvalidation_0-rmse:2.41204\n",
+ "[1773]\tvalidation_0-rmse:2.41155\n",
+ "[1774]\tvalidation_0-rmse:2.41108\n",
+ "[1775]\tvalidation_0-rmse:2.41059\n",
+ "[1776]\tvalidation_0-rmse:2.41010\n",
+ "[1777]\tvalidation_0-rmse:2.40962\n",
+ "[1778]\tvalidation_0-rmse:2.40869\n",
+ "[1779]\tvalidation_0-rmse:2.40805\n",
+ "[1780]\tvalidation_0-rmse:2.40758\n",
+ "[1781]\tvalidation_0-rmse:2.40700\n",
+ "[1782]\tvalidation_0-rmse:2.40641\n",
+ "[1783]\tvalidation_0-rmse:2.40603\n",
+ "[1784]\tvalidation_0-rmse:2.40545\n",
+ "[1785]\tvalidation_0-rmse:2.40467\n",
+ "[1786]\tvalidation_0-rmse:2.40417\n",
+ "[1787]\tvalidation_0-rmse:2.40389\n",
+ "[1788]\tvalidation_0-rmse:2.40349\n",
+ "[1789]\tvalidation_0-rmse:2.40318\n",
+ "[1790]\tvalidation_0-rmse:2.40293\n",
+ "[1791]\tvalidation_0-rmse:2.40240\n",
+ "[1792]\tvalidation_0-rmse:2.40208\n",
+ "[1793]\tvalidation_0-rmse:2.40171\n",
+ "[1794]\tvalidation_0-rmse:2.40106\n",
+ "[1795]\tvalidation_0-rmse:2.40078\n",
+ "[1796]\tvalidation_0-rmse:2.40067\n",
+ "[1797]\tvalidation_0-rmse:2.40022\n",
+ "[1798]\tvalidation_0-rmse:2.39982\n",
+ "[1799]\tvalidation_0-rmse:2.39951\n",
+ "[1800]\tvalidation_0-rmse:2.39908\n",
+ "[1801]\tvalidation_0-rmse:2.39841\n",
+ "[1802]\tvalidation_0-rmse:2.39807\n",
+ "[1803]\tvalidation_0-rmse:2.39771\n",
+ "[1804]\tvalidation_0-rmse:2.39729\n",
+ "[1805]\tvalidation_0-rmse:2.39704\n",
+ "[1806]\tvalidation_0-rmse:2.39683\n",
+ "[1807]\tvalidation_0-rmse:2.39651\n",
+ "[1808]\tvalidation_0-rmse:2.39606\n",
+ "[1809]\tvalidation_0-rmse:2.39576\n",
+ "[1810]\tvalidation_0-rmse:2.39549\n",
+ "[1811]\tvalidation_0-rmse:2.39518\n",
+ "[1812]\tvalidation_0-rmse:2.39479\n",
+ "[1813]\tvalidation_0-rmse:2.39456\n",
+ "[1814]\tvalidation_0-rmse:2.39418\n",
+ "[1815]\tvalidation_0-rmse:2.39367\n",
+ "[1816]\tvalidation_0-rmse:2.39283\n",
+ "[1817]\tvalidation_0-rmse:2.39262\n",
+ "[1818]\tvalidation_0-rmse:2.39183\n",
+ "[1819]\tvalidation_0-rmse:2.39161\n",
+ "[1820]\tvalidation_0-rmse:2.39141\n",
+ "[1821]\tvalidation_0-rmse:2.39097\n",
+ "[1822]\tvalidation_0-rmse:2.39054\n",
+ "[1823]\tvalidation_0-rmse:2.39021\n",
+ "[1824]\tvalidation_0-rmse:2.38928\n",
+ "[1825]\tvalidation_0-rmse:2.38866\n",
+ "[1826]\tvalidation_0-rmse:2.38840\n",
+ "[1827]\tvalidation_0-rmse:2.38746\n",
+ "[1828]\tvalidation_0-rmse:2.38709\n",
+ "[1829]\tvalidation_0-rmse:2.38681\n",
+ "[1830]\tvalidation_0-rmse:2.38656\n",
+ "[1831]\tvalidation_0-rmse:2.38593\n",
+ "[1832]\tvalidation_0-rmse:2.38534\n",
+ "[1833]\tvalidation_0-rmse:2.38490\n",
+ "[1834]\tvalidation_0-rmse:2.38460\n",
+ "[1835]\tvalidation_0-rmse:2.38423\n",
+ "[1836]\tvalidation_0-rmse:2.38379\n",
+ "[1837]\tvalidation_0-rmse:2.38333\n",
+ "[1838]\tvalidation_0-rmse:2.38282\n",
+ "[1839]\tvalidation_0-rmse:2.38259\n",
+ "[1840]\tvalidation_0-rmse:2.38187\n",
+ "[1841]\tvalidation_0-rmse:2.38168\n",
+ "[1842]\tvalidation_0-rmse:2.38108\n",
+ "[1843]\tvalidation_0-rmse:2.38054\n",
+ "[1844]\tvalidation_0-rmse:2.37996\n",
+ "[1845]\tvalidation_0-rmse:2.37976\n",
+ "[1846]\tvalidation_0-rmse:2.37925\n",
+ "[1847]\tvalidation_0-rmse:2.37866\n",
+ "[1848]\tvalidation_0-rmse:2.37821\n",
+ "[1849]\tvalidation_0-rmse:2.37796\n",
+ "[1850]\tvalidation_0-rmse:2.37747\n",
+ "[1851]\tvalidation_0-rmse:2.37714\n",
+ "[1852]\tvalidation_0-rmse:2.37691\n",
+ "[1853]\tvalidation_0-rmse:2.37661\n",
+ "[1854]\tvalidation_0-rmse:2.37610\n",
+ "[1855]\tvalidation_0-rmse:2.37591\n",
+ "[1856]\tvalidation_0-rmse:2.37543\n",
+ "[1857]\tvalidation_0-rmse:2.37497\n",
+ "[1858]\tvalidation_0-rmse:2.37457\n",
+ "[1859]\tvalidation_0-rmse:2.37401\n",
+ "[1860]\tvalidation_0-rmse:2.37363\n",
+ "[1861]\tvalidation_0-rmse:2.37329\n",
+ "[1862]\tvalidation_0-rmse:2.37316\n",
+ "[1863]\tvalidation_0-rmse:2.37297\n",
+ "[1864]\tvalidation_0-rmse:2.37275\n",
+ "[1865]\tvalidation_0-rmse:2.37272\n",
+ "[1866]\tvalidation_0-rmse:2.37258\n",
+ "[1867]\tvalidation_0-rmse:2.37210\n",
+ "[1868]\tvalidation_0-rmse:2.37154\n",
+ "[1869]\tvalidation_0-rmse:2.37135\n",
+ "[1870]\tvalidation_0-rmse:2.37105\n",
+ "[1871]\tvalidation_0-rmse:2.37063\n",
+ "[1872]\tvalidation_0-rmse:2.37003\n",
+ "[1873]\tvalidation_0-rmse:2.36962\n",
+ "[1874]\tvalidation_0-rmse:2.36929\n",
+ "[1875]\tvalidation_0-rmse:2.36875\n",
+ "[1876]\tvalidation_0-rmse:2.36833\n",
+ "[1877]\tvalidation_0-rmse:2.36789\n",
+ "[1878]\tvalidation_0-rmse:2.36751\n",
+ "[1879]\tvalidation_0-rmse:2.36700\n",
+ "[1880]\tvalidation_0-rmse:2.36599\n",
+ "[1881]\tvalidation_0-rmse:2.36536\n",
+ "[1882]\tvalidation_0-rmse:2.36464\n",
+ "[1883]\tvalidation_0-rmse:2.36440\n",
+ "[1884]\tvalidation_0-rmse:2.36403\n",
+ "[1885]\tvalidation_0-rmse:2.36332\n",
+ "[1886]\tvalidation_0-rmse:2.36261\n",
+ "[1887]\tvalidation_0-rmse:2.36202\n",
+ "[1888]\tvalidation_0-rmse:2.36170\n",
+ "[1889]\tvalidation_0-rmse:2.36117\n",
+ "[1890]\tvalidation_0-rmse:2.36096\n",
+ "[1891]\tvalidation_0-rmse:2.36047\n",
+ "[1892]\tvalidation_0-rmse:2.36036\n",
+ "[1893]\tvalidation_0-rmse:2.35998\n",
+ "[1894]\tvalidation_0-rmse:2.35930\n",
+ "[1895]\tvalidation_0-rmse:2.35894\n",
+ "[1896]\tvalidation_0-rmse:2.35848\n",
+ "[1897]\tvalidation_0-rmse:2.35806\n",
+ "[1898]\tvalidation_0-rmse:2.35790\n",
+ "[1899]\tvalidation_0-rmse:2.35735\n",
+ "[1900]\tvalidation_0-rmse:2.35681\n",
+ "[1901]\tvalidation_0-rmse:2.35653\n",
+ "[1902]\tvalidation_0-rmse:2.35628\n",
+ "[1903]\tvalidation_0-rmse:2.35591\n",
+ "[1904]\tvalidation_0-rmse:2.35539\n",
+ "[1905]\tvalidation_0-rmse:2.35494\n",
+ "[1906]\tvalidation_0-rmse:2.35462\n",
+ "[1907]\tvalidation_0-rmse:2.35424\n",
+ "[1908]\tvalidation_0-rmse:2.35403\n",
+ "[1909]\tvalidation_0-rmse:2.35376\n",
+ "[1910]\tvalidation_0-rmse:2.35312\n",
+ "[1911]\tvalidation_0-rmse:2.35260\n",
+ "[1912]\tvalidation_0-rmse:2.35215\n",
+ "[1913]\tvalidation_0-rmse:2.35186\n",
+ "[1914]\tvalidation_0-rmse:2.35147\n",
+ "[1915]\tvalidation_0-rmse:2.35087\n",
+ "[1916]\tvalidation_0-rmse:2.35059\n",
+ "[1917]\tvalidation_0-rmse:2.35024\n",
+ "[1918]\tvalidation_0-rmse:2.34956\n",
+ "[1919]\tvalidation_0-rmse:2.34922\n",
+ "[1920]\tvalidation_0-rmse:2.34888\n",
+ "[1921]\tvalidation_0-rmse:2.34853\n",
+ "[1922]\tvalidation_0-rmse:2.34817\n",
+ "[1923]\tvalidation_0-rmse:2.34788\n",
+ "[1924]\tvalidation_0-rmse:2.34784\n",
+ "[1925]\tvalidation_0-rmse:2.34766\n",
+ "[1926]\tvalidation_0-rmse:2.34742\n",
+ "[1927]\tvalidation_0-rmse:2.34737\n",
+ "[1928]\tvalidation_0-rmse:2.34703\n",
+ "[1929]\tvalidation_0-rmse:2.34655\n",
+ "[1930]\tvalidation_0-rmse:2.34619\n",
+ "[1931]\tvalidation_0-rmse:2.34602\n",
+ "[1932]\tvalidation_0-rmse:2.34560\n",
+ "[1933]\tvalidation_0-rmse:2.34525\n",
+ "[1934]\tvalidation_0-rmse:2.34497\n",
+ "[1935]\tvalidation_0-rmse:2.34484\n",
+ "[1936]\tvalidation_0-rmse:2.34449\n",
+ "[1937]\tvalidation_0-rmse:2.34417\n",
+ "[1938]\tvalidation_0-rmse:2.34367\n",
+ "[1939]\tvalidation_0-rmse:2.34341\n",
+ "[1940]\tvalidation_0-rmse:2.34307\n",
+ "[1941]\tvalidation_0-rmse:2.34252\n",
+ "[1942]\tvalidation_0-rmse:2.34232\n",
+ "[1943]\tvalidation_0-rmse:2.34205\n",
+ "[1944]\tvalidation_0-rmse:2.34163\n",
+ "[1945]\tvalidation_0-rmse:2.34121\n",
+ "[1946]\tvalidation_0-rmse:2.34101\n",
+ "[1947]\tvalidation_0-rmse:2.34076\n",
+ "[1948]\tvalidation_0-rmse:2.34061\n",
+ "[1949]\tvalidation_0-rmse:2.34039\n",
+ "[1950]\tvalidation_0-rmse:2.33993\n",
+ "[1951]\tvalidation_0-rmse:2.33973\n",
+ "[1952]\tvalidation_0-rmse:2.33952\n",
+ "[1953]\tvalidation_0-rmse:2.33925\n",
+ "[1954]\tvalidation_0-rmse:2.33902\n",
+ "[1955]\tvalidation_0-rmse:2.33859\n",
+ "[1956]\tvalidation_0-rmse:2.33770\n",
+ "[1957]\tvalidation_0-rmse:2.33708\n",
+ "[1958]\tvalidation_0-rmse:2.33675\n",
+ "[1959]\tvalidation_0-rmse:2.33630\n",
+ "[1960]\tvalidation_0-rmse:2.33593\n",
+ "[1961]\tvalidation_0-rmse:2.33550\n",
+ "[1962]\tvalidation_0-rmse:2.33532\n",
+ "[1963]\tvalidation_0-rmse:2.33520\n",
+ "[1964]\tvalidation_0-rmse:2.33478\n",
+ "[1965]\tvalidation_0-rmse:2.33435\n",
+ "[1966]\tvalidation_0-rmse:2.33378\n",
+ "[1967]\tvalidation_0-rmse:2.33336\n",
+ "[1968]\tvalidation_0-rmse:2.33292\n",
+ "[1969]\tvalidation_0-rmse:2.33249\n",
+ "[1970]\tvalidation_0-rmse:2.33224\n",
+ "[1971]\tvalidation_0-rmse:2.33189\n",
+ "[1972]\tvalidation_0-rmse:2.33158\n",
+ "[1973]\tvalidation_0-rmse:2.33132\n",
+ "[1974]\tvalidation_0-rmse:2.33083\n",
+ "[1975]\tvalidation_0-rmse:2.33063\n",
+ "[1976]\tvalidation_0-rmse:2.33029\n",
+ "[1977]\tvalidation_0-rmse:2.33006\n",
+ "[1978]\tvalidation_0-rmse:2.32990\n",
+ "[1979]\tvalidation_0-rmse:2.32942\n",
+ "[1980]\tvalidation_0-rmse:2.32877\n",
+ "[1981]\tvalidation_0-rmse:2.32874\n",
+ "[1982]\tvalidation_0-rmse:2.32832\n",
+ "[1983]\tvalidation_0-rmse:2.32796\n",
+ "[1984]\tvalidation_0-rmse:2.32768\n",
+ "[1985]\tvalidation_0-rmse:2.32722\n",
+ "[1986]\tvalidation_0-rmse:2.32676\n",
+ "[1987]\tvalidation_0-rmse:2.32643\n",
+ "[1988]\tvalidation_0-rmse:2.32563\n",
+ "[1989]\tvalidation_0-rmse:2.32540\n",
+ "[1990]\tvalidation_0-rmse:2.32438\n",
+ "[1991]\tvalidation_0-rmse:2.32409\n",
+ "[1992]\tvalidation_0-rmse:2.32329\n",
+ "[1993]\tvalidation_0-rmse:2.32282\n",
+ "[1994]\tvalidation_0-rmse:2.32223\n",
+ "[1995]\tvalidation_0-rmse:2.32201\n",
+ "[1996]\tvalidation_0-rmse:2.32169\n",
+ "[1997]\tvalidation_0-rmse:2.32115\n",
+ "[1998]\tvalidation_0-rmse:2.32069\n",
+ "[1999]\tvalidation_0-rmse:2.32049\n",
+ "[2000]\tvalidation_0-rmse:2.31954\n",
+ "[2001]\tvalidation_0-rmse:2.31921\n",
+ "[2002]\tvalidation_0-rmse:2.31884\n",
+ "[2003]\tvalidation_0-rmse:2.31848\n",
+ "[2004]\tvalidation_0-rmse:2.31809\n",
+ "[2005]\tvalidation_0-rmse:2.31792\n",
+ "[2006]\tvalidation_0-rmse:2.31742\n",
+ "[2007]\tvalidation_0-rmse:2.31690\n",
+ "[2008]\tvalidation_0-rmse:2.31644\n",
+ "[2009]\tvalidation_0-rmse:2.31609\n",
+ "[2010]\tvalidation_0-rmse:2.31581\n",
+ "[2011]\tvalidation_0-rmse:2.31548\n",
+ "[2012]\tvalidation_0-rmse:2.31525\n",
+ "[2013]\tvalidation_0-rmse:2.31496\n",
+ "[2014]\tvalidation_0-rmse:2.31453\n",
+ "[2015]\tvalidation_0-rmse:2.31433\n",
+ "[2016]\tvalidation_0-rmse:2.31386\n",
+ "[2017]\tvalidation_0-rmse:2.31349\n",
+ "[2018]\tvalidation_0-rmse:2.31313\n",
+ "[2019]\tvalidation_0-rmse:2.31284\n",
+ "[2020]\tvalidation_0-rmse:2.31257\n",
+ "[2021]\tvalidation_0-rmse:2.31240\n",
+ "[2022]\tvalidation_0-rmse:2.31183\n",
+ "[2023]\tvalidation_0-rmse:2.31152\n",
+ "[2024]\tvalidation_0-rmse:2.31142\n",
+ "[2025]\tvalidation_0-rmse:2.31113\n",
+ "[2026]\tvalidation_0-rmse:2.31092\n",
+ "[2027]\tvalidation_0-rmse:2.31061\n",
+ "[2028]\tvalidation_0-rmse:2.31037\n",
+ "[2029]\tvalidation_0-rmse:2.31019\n",
+ "[2030]\tvalidation_0-rmse:2.30999\n",
+ "[2031]\tvalidation_0-rmse:2.30969\n",
+ "[2032]\tvalidation_0-rmse:2.30922\n",
+ "[2033]\tvalidation_0-rmse:2.30893\n",
+ "[2034]\tvalidation_0-rmse:2.30850\n",
+ "[2035]\tvalidation_0-rmse:2.30822\n",
+ "[2036]\tvalidation_0-rmse:2.30808\n",
+ "[2037]\tvalidation_0-rmse:2.30771\n",
+ "[2038]\tvalidation_0-rmse:2.30722\n",
+ "[2039]\tvalidation_0-rmse:2.30643\n",
+ "[2040]\tvalidation_0-rmse:2.30614\n",
+ "[2041]\tvalidation_0-rmse:2.30566\n",
+ "[2042]\tvalidation_0-rmse:2.30511\n",
+ "[2043]\tvalidation_0-rmse:2.30487\n",
+ "[2044]\tvalidation_0-rmse:2.30454\n",
+ "[2045]\tvalidation_0-rmse:2.30357\n",
+ "[2046]\tvalidation_0-rmse:2.30340\n",
+ "[2047]\tvalidation_0-rmse:2.30269\n",
+ "[2048]\tvalidation_0-rmse:2.30233\n",
+ "[2049]\tvalidation_0-rmse:2.30217\n",
+ "[2050]\tvalidation_0-rmse:2.30209\n",
+ "[2051]\tvalidation_0-rmse:2.30156\n",
+ "[2052]\tvalidation_0-rmse:2.30119\n",
+ "[2053]\tvalidation_0-rmse:2.30076\n",
+ "[2054]\tvalidation_0-rmse:2.30009\n",
+ "[2055]\tvalidation_0-rmse:2.29990\n",
+ "[2056]\tvalidation_0-rmse:2.29955\n",
+ "[2057]\tvalidation_0-rmse:2.29918\n",
+ "[2058]\tvalidation_0-rmse:2.29908\n",
+ "[2059]\tvalidation_0-rmse:2.29903\n",
+ "[2060]\tvalidation_0-rmse:2.29843\n",
+ "[2061]\tvalidation_0-rmse:2.29815\n",
+ "[2062]\tvalidation_0-rmse:2.29798\n",
+ "[2063]\tvalidation_0-rmse:2.29760\n",
+ "[2064]\tvalidation_0-rmse:2.29703\n",
+ "[2065]\tvalidation_0-rmse:2.29666\n",
+ "[2066]\tvalidation_0-rmse:2.29625\n",
+ "[2067]\tvalidation_0-rmse:2.29583\n",
+ "[2068]\tvalidation_0-rmse:2.29556\n",
+ "[2069]\tvalidation_0-rmse:2.29517\n",
+ "[2070]\tvalidation_0-rmse:2.29469\n",
+ "[2071]\tvalidation_0-rmse:2.29434\n",
+ "[2072]\tvalidation_0-rmse:2.29421\n",
+ "[2073]\tvalidation_0-rmse:2.29385\n",
+ "[2074]\tvalidation_0-rmse:2.29319\n",
+ "[2075]\tvalidation_0-rmse:2.29295\n",
+ "[2076]\tvalidation_0-rmse:2.29285\n",
+ "[2077]\tvalidation_0-rmse:2.29242\n",
+ "[2078]\tvalidation_0-rmse:2.29190\n",
+ "[2079]\tvalidation_0-rmse:2.29160\n",
+ "[2080]\tvalidation_0-rmse:2.29135\n",
+ "[2081]\tvalidation_0-rmse:2.29089\n",
+ "[2082]\tvalidation_0-rmse:2.29056\n",
+ "[2083]\tvalidation_0-rmse:2.29030\n",
+ "[2084]\tvalidation_0-rmse:2.28994\n",
+ "[2085]\tvalidation_0-rmse:2.28941\n",
+ "[2086]\tvalidation_0-rmse:2.28897\n",
+ "[2087]\tvalidation_0-rmse:2.28871\n",
+ "[2088]\tvalidation_0-rmse:2.28866\n",
+ "[2089]\tvalidation_0-rmse:2.28853\n",
+ "[2090]\tvalidation_0-rmse:2.28830\n",
+ "[2091]\tvalidation_0-rmse:2.28747\n",
+ "[2092]\tvalidation_0-rmse:2.28707\n",
+ "[2093]\tvalidation_0-rmse:2.28687\n",
+ "[2094]\tvalidation_0-rmse:2.28673\n",
+ "[2095]\tvalidation_0-rmse:2.28639\n",
+ "[2096]\tvalidation_0-rmse:2.28553\n",
+ "[2097]\tvalidation_0-rmse:2.28513\n",
+ "[2098]\tvalidation_0-rmse:2.28452\n",
+ "[2099]\tvalidation_0-rmse:2.28427\n",
+ "[2100]\tvalidation_0-rmse:2.28383\n",
+ "[2101]\tvalidation_0-rmse:2.28339\n",
+ "[2102]\tvalidation_0-rmse:2.28320\n",
+ "[2103]\tvalidation_0-rmse:2.28269\n",
+ "[2104]\tvalidation_0-rmse:2.28257\n",
+ "[2105]\tvalidation_0-rmse:2.28242\n",
+ "[2106]\tvalidation_0-rmse:2.28215\n",
+ "[2107]\tvalidation_0-rmse:2.28165\n",
+ "[2108]\tvalidation_0-rmse:2.28124\n",
+ "[2109]\tvalidation_0-rmse:2.28092\n",
+ "[2110]\tvalidation_0-rmse:2.27990\n",
+ "[2111]\tvalidation_0-rmse:2.27962\n",
+ "[2112]\tvalidation_0-rmse:2.27926\n",
+ "[2113]\tvalidation_0-rmse:2.27859\n",
+ "[2114]\tvalidation_0-rmse:2.27756\n",
+ "[2115]\tvalidation_0-rmse:2.27704\n",
+ "[2116]\tvalidation_0-rmse:2.27664\n",
+ "[2117]\tvalidation_0-rmse:2.27628\n",
+ "[2118]\tvalidation_0-rmse:2.27606\n",
+ "[2119]\tvalidation_0-rmse:2.27568\n",
+ "[2120]\tvalidation_0-rmse:2.27522\n",
+ "[2121]\tvalidation_0-rmse:2.27488\n",
+ "[2122]\tvalidation_0-rmse:2.27428\n",
+ "[2123]\tvalidation_0-rmse:2.27387\n",
+ "[2124]\tvalidation_0-rmse:2.27378\n",
+ "[2125]\tvalidation_0-rmse:2.27351\n",
+ "[2126]\tvalidation_0-rmse:2.27296\n",
+ "[2127]\tvalidation_0-rmse:2.27251\n",
+ "[2128]\tvalidation_0-rmse:2.27214\n",
+ "[2129]\tvalidation_0-rmse:2.27166\n",
+ "[2130]\tvalidation_0-rmse:2.27094\n",
+ "[2131]\tvalidation_0-rmse:2.27057\n",
+ "[2132]\tvalidation_0-rmse:2.27004\n",
+ "[2133]\tvalidation_0-rmse:2.26961\n",
+ "[2134]\tvalidation_0-rmse:2.26918\n",
+ "[2135]\tvalidation_0-rmse:2.26882\n",
+ "[2136]\tvalidation_0-rmse:2.26853\n",
+ "[2137]\tvalidation_0-rmse:2.26818\n",
+ "[2138]\tvalidation_0-rmse:2.26799\n",
+ "[2139]\tvalidation_0-rmse:2.26757\n",
+ "[2140]\tvalidation_0-rmse:2.26726\n",
+ "[2141]\tvalidation_0-rmse:2.26707\n",
+ "[2142]\tvalidation_0-rmse:2.26668\n",
+ "[2143]\tvalidation_0-rmse:2.26642\n",
+ "[2144]\tvalidation_0-rmse:2.26624\n",
+ "[2145]\tvalidation_0-rmse:2.26563\n",
+ "[2146]\tvalidation_0-rmse:2.26485\n",
+ "[2147]\tvalidation_0-rmse:2.26408\n",
+ "[2148]\tvalidation_0-rmse:2.26341\n",
+ "[2149]\tvalidation_0-rmse:2.26311\n",
+ "[2150]\tvalidation_0-rmse:2.26264\n",
+ "[2151]\tvalidation_0-rmse:2.26227\n",
+ "[2152]\tvalidation_0-rmse:2.26183\n",
+ "[2153]\tvalidation_0-rmse:2.26128\n",
+ "[2154]\tvalidation_0-rmse:2.26102\n",
+ "[2155]\tvalidation_0-rmse:2.26050\n",
+ "[2156]\tvalidation_0-rmse:2.26009\n",
+ "[2157]\tvalidation_0-rmse:2.25975\n",
+ "[2158]\tvalidation_0-rmse:2.25932\n",
+ "[2159]\tvalidation_0-rmse:2.25834\n",
+ "[2160]\tvalidation_0-rmse:2.25816\n",
+ "[2161]\tvalidation_0-rmse:2.25791\n",
+ "[2162]\tvalidation_0-rmse:2.25760\n",
+ "[2163]\tvalidation_0-rmse:2.25708\n",
+ "[2164]\tvalidation_0-rmse:2.25658\n",
+ "[2165]\tvalidation_0-rmse:2.25621\n",
+ "[2166]\tvalidation_0-rmse:2.25571\n",
+ "[2167]\tvalidation_0-rmse:2.25513\n",
+ "[2168]\tvalidation_0-rmse:2.25460\n",
+ "[2169]\tvalidation_0-rmse:2.25427\n",
+ "[2170]\tvalidation_0-rmse:2.25307\n",
+ "[2171]\tvalidation_0-rmse:2.25257\n",
+ "[2172]\tvalidation_0-rmse:2.25239\n",
+ "[2173]\tvalidation_0-rmse:2.25214\n",
+ "[2174]\tvalidation_0-rmse:2.25125\n",
+ "[2175]\tvalidation_0-rmse:2.25095\n",
+ "[2176]\tvalidation_0-rmse:2.25069\n",
+ "[2177]\tvalidation_0-rmse:2.25003\n",
+ "[2178]\tvalidation_0-rmse:2.24968\n",
+ "[2179]\tvalidation_0-rmse:2.24926\n",
+ "[2180]\tvalidation_0-rmse:2.24887\n",
+ "[2181]\tvalidation_0-rmse:2.24851\n",
+ "[2182]\tvalidation_0-rmse:2.24781\n",
+ "[2183]\tvalidation_0-rmse:2.24750\n",
+ "[2184]\tvalidation_0-rmse:2.24722\n",
+ "[2185]\tvalidation_0-rmse:2.24712\n",
+ "[2186]\tvalidation_0-rmse:2.24663\n",
+ "[2187]\tvalidation_0-rmse:2.24609\n",
+ "[2188]\tvalidation_0-rmse:2.24560\n",
+ "[2189]\tvalidation_0-rmse:2.24537\n",
+ "[2190]\tvalidation_0-rmse:2.24501\n",
+ "[2191]\tvalidation_0-rmse:2.24464\n",
+ "[2192]\tvalidation_0-rmse:2.24410\n",
+ "[2193]\tvalidation_0-rmse:2.24383\n",
+ "[2194]\tvalidation_0-rmse:2.24338\n",
+ "[2195]\tvalidation_0-rmse:2.24299\n",
+ "[2196]\tvalidation_0-rmse:2.24259\n",
+ "[2197]\tvalidation_0-rmse:2.24210\n",
+ "[2198]\tvalidation_0-rmse:2.24175\n",
+ "[2199]\tvalidation_0-rmse:2.24090\n",
+ "[2200]\tvalidation_0-rmse:2.24081\n",
+ "[2201]\tvalidation_0-rmse:2.24012\n",
+ "[2202]\tvalidation_0-rmse:2.23938\n",
+ "[2203]\tvalidation_0-rmse:2.23930\n",
+ "[2204]\tvalidation_0-rmse:2.23895\n",
+ "[2205]\tvalidation_0-rmse:2.23882\n",
+ "[2206]\tvalidation_0-rmse:2.23843\n",
+ "[2207]\tvalidation_0-rmse:2.23783\n",
+ "[2208]\tvalidation_0-rmse:2.23725\n",
+ "[2209]\tvalidation_0-rmse:2.23671\n",
+ "[2210]\tvalidation_0-rmse:2.23605\n",
+ "[2211]\tvalidation_0-rmse:2.23571\n",
+ "[2212]\tvalidation_0-rmse:2.23493\n",
+ "[2213]\tvalidation_0-rmse:2.23448\n",
+ "[2214]\tvalidation_0-rmse:2.23384\n",
+ "[2215]\tvalidation_0-rmse:2.23343\n",
+ "[2216]\tvalidation_0-rmse:2.23294\n",
+ "[2217]\tvalidation_0-rmse:2.23245\n",
+ "[2218]\tvalidation_0-rmse:2.23204\n",
+ "[2219]\tvalidation_0-rmse:2.23102\n",
+ "[2220]\tvalidation_0-rmse:2.23021\n",
+ "[2221]\tvalidation_0-rmse:2.22983\n",
+ "[2222]\tvalidation_0-rmse:2.22900\n",
+ "[2223]\tvalidation_0-rmse:2.22854\n",
+ "[2224]\tvalidation_0-rmse:2.22823\n",
+ "[2225]\tvalidation_0-rmse:2.22763\n",
+ "[2226]\tvalidation_0-rmse:2.22714\n",
+ "[2227]\tvalidation_0-rmse:2.22697\n",
+ "[2228]\tvalidation_0-rmse:2.22670\n",
+ "[2229]\tvalidation_0-rmse:2.22616\n",
+ "[2230]\tvalidation_0-rmse:2.22564\n",
+ "[2231]\tvalidation_0-rmse:2.22503\n",
+ "[2232]\tvalidation_0-rmse:2.22475\n",
+ "[2233]\tvalidation_0-rmse:2.22404\n",
+ "[2234]\tvalidation_0-rmse:2.22368\n",
+ "[2235]\tvalidation_0-rmse:2.22334\n",
+ "[2236]\tvalidation_0-rmse:2.22290\n",
+ "[2237]\tvalidation_0-rmse:2.22261\n",
+ "[2238]\tvalidation_0-rmse:2.22251\n",
+ "[2239]\tvalidation_0-rmse:2.22227\n",
+ "[2240]\tvalidation_0-rmse:2.22123\n",
+ "[2241]\tvalidation_0-rmse:2.22053\n",
+ "[2242]\tvalidation_0-rmse:2.22024\n",
+ "[2243]\tvalidation_0-rmse:2.21971\n",
+ "[2244]\tvalidation_0-rmse:2.21942\n",
+ "[2245]\tvalidation_0-rmse:2.21912\n",
+ "[2246]\tvalidation_0-rmse:2.21902\n",
+ "[2247]\tvalidation_0-rmse:2.21832\n",
+ "[2248]\tvalidation_0-rmse:2.21823\n",
+ "[2249]\tvalidation_0-rmse:2.21776\n",
+ "[2250]\tvalidation_0-rmse:2.21743\n",
+ "[2251]\tvalidation_0-rmse:2.21711\n",
+ "[2252]\tvalidation_0-rmse:2.21673\n",
+ "[2253]\tvalidation_0-rmse:2.21621\n",
+ "[2254]\tvalidation_0-rmse:2.21584\n",
+ "[2255]\tvalidation_0-rmse:2.21526\n",
+ "[2256]\tvalidation_0-rmse:2.21504\n",
+ "[2257]\tvalidation_0-rmse:2.21453\n",
+ "[2258]\tvalidation_0-rmse:2.21433\n",
+ "[2259]\tvalidation_0-rmse:2.21418\n",
+ "[2260]\tvalidation_0-rmse:2.21412\n",
+ "[2261]\tvalidation_0-rmse:2.21361\n",
+ "[2262]\tvalidation_0-rmse:2.21345\n",
+ "[2263]\tvalidation_0-rmse:2.21326\n",
+ "[2264]\tvalidation_0-rmse:2.21300\n",
+ "[2265]\tvalidation_0-rmse:2.21266\n",
+ "[2266]\tvalidation_0-rmse:2.21227\n",
+ "[2267]\tvalidation_0-rmse:2.21189\n",
+ "[2268]\tvalidation_0-rmse:2.21146\n",
+ "[2269]\tvalidation_0-rmse:2.21109\n",
+ "[2270]\tvalidation_0-rmse:2.21081\n",
+ "[2271]\tvalidation_0-rmse:2.21032\n",
+ "[2272]\tvalidation_0-rmse:2.21000\n",
+ "[2273]\tvalidation_0-rmse:2.20969\n",
+ "[2274]\tvalidation_0-rmse:2.20929\n",
+ "[2275]\tvalidation_0-rmse:2.20892\n",
+ "[2276]\tvalidation_0-rmse:2.20859\n",
+ "[2277]\tvalidation_0-rmse:2.20829\n",
+ "[2278]\tvalidation_0-rmse:2.20803\n",
+ "[2279]\tvalidation_0-rmse:2.20769\n",
+ "[2280]\tvalidation_0-rmse:2.20724\n",
+ "[2281]\tvalidation_0-rmse:2.20687\n",
+ "[2282]\tvalidation_0-rmse:2.20661\n",
+ "[2283]\tvalidation_0-rmse:2.20612\n",
+ "[2284]\tvalidation_0-rmse:2.20558\n",
+ "[2285]\tvalidation_0-rmse:2.20541\n",
+ "[2286]\tvalidation_0-rmse:2.20526\n",
+ "[2287]\tvalidation_0-rmse:2.20460\n",
+ "[2288]\tvalidation_0-rmse:2.20423\n",
+ "[2289]\tvalidation_0-rmse:2.20360\n",
+ "[2290]\tvalidation_0-rmse:2.20326\n",
+ "[2291]\tvalidation_0-rmse:2.20288\n",
+ "[2292]\tvalidation_0-rmse:2.20235\n",
+ "[2293]\tvalidation_0-rmse:2.20197\n",
+ "[2294]\tvalidation_0-rmse:2.20160\n",
+ "[2295]\tvalidation_0-rmse:2.20138\n",
+ "[2296]\tvalidation_0-rmse:2.20111\n",
+ "[2297]\tvalidation_0-rmse:2.20103\n",
+ "[2298]\tvalidation_0-rmse:2.20097\n",
+ "[2299]\tvalidation_0-rmse:2.20081\n",
+ "[2300]\tvalidation_0-rmse:2.20057\n",
+ "[2301]\tvalidation_0-rmse:2.20022\n",
+ "[2302]\tvalidation_0-rmse:2.20017\n",
+ "[2303]\tvalidation_0-rmse:2.19998\n",
+ "[2304]\tvalidation_0-rmse:2.19980\n",
+ "[2305]\tvalidation_0-rmse:2.19926\n",
+ "[2306]\tvalidation_0-rmse:2.19890\n",
+ "[2307]\tvalidation_0-rmse:2.19833\n",
+ "[2308]\tvalidation_0-rmse:2.19792\n",
+ "[2309]\tvalidation_0-rmse:2.19728\n",
+ "[2310]\tvalidation_0-rmse:2.19676\n",
+ "[2311]\tvalidation_0-rmse:2.19617\n",
+ "[2312]\tvalidation_0-rmse:2.19571\n",
+ "[2313]\tvalidation_0-rmse:2.19525\n",
+ "[2314]\tvalidation_0-rmse:2.19503\n",
+ "[2315]\tvalidation_0-rmse:2.19451\n",
+ "[2316]\tvalidation_0-rmse:2.19400\n",
+ "[2317]\tvalidation_0-rmse:2.19381\n",
+ "[2318]\tvalidation_0-rmse:2.19291\n",
+ "[2319]\tvalidation_0-rmse:2.19274\n",
+ "[2320]\tvalidation_0-rmse:2.19260\n",
+ "[2321]\tvalidation_0-rmse:2.19256\n",
+ "[2322]\tvalidation_0-rmse:2.19233\n",
+ "[2323]\tvalidation_0-rmse:2.19188\n",
+ "[2324]\tvalidation_0-rmse:2.19146\n",
+ "[2325]\tvalidation_0-rmse:2.19075\n",
+ "[2326]\tvalidation_0-rmse:2.19012\n",
+ "[2327]\tvalidation_0-rmse:2.18992\n",
+ "[2328]\tvalidation_0-rmse:2.18978\n",
+ "[2329]\tvalidation_0-rmse:2.18936\n",
+ "[2330]\tvalidation_0-rmse:2.18810\n",
+ "[2331]\tvalidation_0-rmse:2.18759\n",
+ "[2332]\tvalidation_0-rmse:2.18723\n",
+ "[2333]\tvalidation_0-rmse:2.18683\n",
+ "[2334]\tvalidation_0-rmse:2.18649\n",
+ "[2335]\tvalidation_0-rmse:2.18617\n",
+ "[2336]\tvalidation_0-rmse:2.18567\n",
+ "[2337]\tvalidation_0-rmse:2.18545\n",
+ "[2338]\tvalidation_0-rmse:2.18504\n",
+ "[2339]\tvalidation_0-rmse:2.18489\n",
+ "[2340]\tvalidation_0-rmse:2.18466\n",
+ "[2341]\tvalidation_0-rmse:2.18379\n",
+ "[2342]\tvalidation_0-rmse:2.18351\n",
+ "[2343]\tvalidation_0-rmse:2.18281\n",
+ "[2344]\tvalidation_0-rmse:2.18249\n",
+ "[2345]\tvalidation_0-rmse:2.18163\n",
+ "[2346]\tvalidation_0-rmse:2.18117\n",
+ "[2347]\tvalidation_0-rmse:2.18077\n",
+ "[2348]\tvalidation_0-rmse:2.18035\n",
+ "[2349]\tvalidation_0-rmse:2.18005\n",
+ "[2350]\tvalidation_0-rmse:2.17982\n",
+ "[2351]\tvalidation_0-rmse:2.17929\n",
+ "[2352]\tvalidation_0-rmse:2.17903\n",
+ "[2353]\tvalidation_0-rmse:2.17873\n",
+ "[2354]\tvalidation_0-rmse:2.17856\n",
+ "[2355]\tvalidation_0-rmse:2.17813\n",
+ "[2356]\tvalidation_0-rmse:2.17794\n",
+ "[2357]\tvalidation_0-rmse:2.17781\n",
+ "[2358]\tvalidation_0-rmse:2.17741\n",
+ "[2359]\tvalidation_0-rmse:2.17696\n",
+ "[2360]\tvalidation_0-rmse:2.17659\n",
+ "[2361]\tvalidation_0-rmse:2.17638\n",
+ "[2362]\tvalidation_0-rmse:2.17599\n",
+ "[2363]\tvalidation_0-rmse:2.17584\n",
+ "[2364]\tvalidation_0-rmse:2.17562\n",
+ "[2365]\tvalidation_0-rmse:2.17555\n",
+ "[2366]\tvalidation_0-rmse:2.17542\n",
+ "[2367]\tvalidation_0-rmse:2.17504\n",
+ "[2368]\tvalidation_0-rmse:2.17475\n",
+ "[2369]\tvalidation_0-rmse:2.17442\n",
+ "[2370]\tvalidation_0-rmse:2.17408\n",
+ "[2371]\tvalidation_0-rmse:2.17368\n",
+ "[2372]\tvalidation_0-rmse:2.17324\n",
+ "[2373]\tvalidation_0-rmse:2.17260\n",
+ "[2374]\tvalidation_0-rmse:2.17237\n",
+ "[2375]\tvalidation_0-rmse:2.17194\n",
+ "[2376]\tvalidation_0-rmse:2.17185\n",
+ "[2377]\tvalidation_0-rmse:2.17163\n",
+ "[2378]\tvalidation_0-rmse:2.17131\n",
+ "[2379]\tvalidation_0-rmse:2.17074\n",
+ "[2380]\tvalidation_0-rmse:2.17039\n",
+ "[2381]\tvalidation_0-rmse:2.16996\n",
+ "[2382]\tvalidation_0-rmse:2.16958\n",
+ "[2383]\tvalidation_0-rmse:2.16902\n",
+ "[2384]\tvalidation_0-rmse:2.16888\n",
+ "[2385]\tvalidation_0-rmse:2.16824\n",
+ "[2386]\tvalidation_0-rmse:2.16744\n",
+ "[2387]\tvalidation_0-rmse:2.16708\n",
+ "[2388]\tvalidation_0-rmse:2.16651\n",
+ "[2389]\tvalidation_0-rmse:2.16624\n",
+ "[2390]\tvalidation_0-rmse:2.16569\n",
+ "[2391]\tvalidation_0-rmse:2.16535\n",
+ "[2392]\tvalidation_0-rmse:2.16477\n",
+ "[2393]\tvalidation_0-rmse:2.16436\n",
+ "[2394]\tvalidation_0-rmse:2.16386\n",
+ "[2395]\tvalidation_0-rmse:2.16339\n",
+ "[2396]\tvalidation_0-rmse:2.16313\n",
+ "[2397]\tvalidation_0-rmse:2.16282\n",
+ "[2398]\tvalidation_0-rmse:2.16231\n",
+ "[2399]\tvalidation_0-rmse:2.16192\n",
+ "[2400]\tvalidation_0-rmse:2.16143\n",
+ "[2401]\tvalidation_0-rmse:2.16102\n",
+ "[2402]\tvalidation_0-rmse:2.16054\n",
+ "[2403]\tvalidation_0-rmse:2.16024\n",
+ "[2404]\tvalidation_0-rmse:2.15991\n",
+ "[2405]\tvalidation_0-rmse:2.15938\n",
+ "[2406]\tvalidation_0-rmse:2.15899\n",
+ "[2407]\tvalidation_0-rmse:2.15889\n",
+ "[2408]\tvalidation_0-rmse:2.15864\n",
+ "[2409]\tvalidation_0-rmse:2.15814\n",
+ "[2410]\tvalidation_0-rmse:2.15776\n",
+ "[2411]\tvalidation_0-rmse:2.15739\n",
+ "[2412]\tvalidation_0-rmse:2.15699\n",
+ "[2413]\tvalidation_0-rmse:2.15671\n",
+ "[2414]\tvalidation_0-rmse:2.15629\n",
+ "[2415]\tvalidation_0-rmse:2.15606\n",
+ "[2416]\tvalidation_0-rmse:2.15571\n",
+ "[2417]\tvalidation_0-rmse:2.15544\n",
+ "[2418]\tvalidation_0-rmse:2.15515\n",
+ "[2419]\tvalidation_0-rmse:2.15492\n",
+ "[2420]\tvalidation_0-rmse:2.15485\n",
+ "[2421]\tvalidation_0-rmse:2.15444\n",
+ "[2422]\tvalidation_0-rmse:2.15420\n",
+ "[2423]\tvalidation_0-rmse:2.15408\n",
+ "[2424]\tvalidation_0-rmse:2.15389\n",
+ "[2425]\tvalidation_0-rmse:2.15342\n",
+ "[2426]\tvalidation_0-rmse:2.15312\n",
+ "[2427]\tvalidation_0-rmse:2.15295\n",
+ "[2428]\tvalidation_0-rmse:2.15270\n",
+ "[2429]\tvalidation_0-rmse:2.15249\n",
+ "[2430]\tvalidation_0-rmse:2.15221\n",
+ "[2431]\tvalidation_0-rmse:2.15176\n",
+ "[2432]\tvalidation_0-rmse:2.15156\n",
+ "[2433]\tvalidation_0-rmse:2.15139\n",
+ "[2434]\tvalidation_0-rmse:2.15115\n",
+ "[2435]\tvalidation_0-rmse:2.15047\n",
+ "[2436]\tvalidation_0-rmse:2.15009\n",
+ "[2437]\tvalidation_0-rmse:2.14993\n",
+ "[2438]\tvalidation_0-rmse:2.14974\n",
+ "[2439]\tvalidation_0-rmse:2.14931\n",
+ "[2440]\tvalidation_0-rmse:2.14903\n",
+ "[2441]\tvalidation_0-rmse:2.14868\n",
+ "[2442]\tvalidation_0-rmse:2.14815\n",
+ "[2443]\tvalidation_0-rmse:2.14786\n",
+ "[2444]\tvalidation_0-rmse:2.14760\n",
+ "[2445]\tvalidation_0-rmse:2.14698\n",
+ "[2446]\tvalidation_0-rmse:2.14688\n",
+ "[2447]\tvalidation_0-rmse:2.14669\n",
+ "[2448]\tvalidation_0-rmse:2.14648\n",
+ "[2449]\tvalidation_0-rmse:2.14643\n",
+ "[2450]\tvalidation_0-rmse:2.14585\n",
+ "[2451]\tvalidation_0-rmse:2.14577\n",
+ "[2452]\tvalidation_0-rmse:2.14564\n",
+ "[2453]\tvalidation_0-rmse:2.14528\n",
+ "[2454]\tvalidation_0-rmse:2.14507\n",
+ "[2455]\tvalidation_0-rmse:2.14459\n",
+ "[2456]\tvalidation_0-rmse:2.14446\n",
+ "[2457]\tvalidation_0-rmse:2.14406\n",
+ "[2458]\tvalidation_0-rmse:2.14382\n",
+ "[2459]\tvalidation_0-rmse:2.14361\n",
+ "[2460]\tvalidation_0-rmse:2.14329\n",
+ "[2461]\tvalidation_0-rmse:2.14315\n",
+ "[2462]\tvalidation_0-rmse:2.14291\n",
+ "[2463]\tvalidation_0-rmse:2.14259\n",
+ "[2464]\tvalidation_0-rmse:2.14240\n",
+ "[2465]\tvalidation_0-rmse:2.14204\n",
+ "[2466]\tvalidation_0-rmse:2.14164\n",
+ "[2467]\tvalidation_0-rmse:2.14155\n",
+ "[2468]\tvalidation_0-rmse:2.14128\n",
+ "[2469]\tvalidation_0-rmse:2.14079\n",
+ "[2470]\tvalidation_0-rmse:2.14055\n",
+ "[2471]\tvalidation_0-rmse:2.14037\n",
+ "[2472]\tvalidation_0-rmse:2.13971\n",
+ "[2473]\tvalidation_0-rmse:2.13935\n",
+ "[2474]\tvalidation_0-rmse:2.13901\n",
+ "[2475]\tvalidation_0-rmse:2.13884\n",
+ "[2476]\tvalidation_0-rmse:2.13847\n",
+ "[2477]\tvalidation_0-rmse:2.13781\n",
+ "[2478]\tvalidation_0-rmse:2.13735\n",
+ "[2479]\tvalidation_0-rmse:2.13706\n",
+ "[2480]\tvalidation_0-rmse:2.13658\n",
+ "[2481]\tvalidation_0-rmse:2.13629\n",
+ "[2482]\tvalidation_0-rmse:2.13591\n",
+ "[2483]\tvalidation_0-rmse:2.13576\n",
+ "[2484]\tvalidation_0-rmse:2.13568\n",
+ "[2485]\tvalidation_0-rmse:2.13506\n",
+ "[2486]\tvalidation_0-rmse:2.13497\n",
+ "[2487]\tvalidation_0-rmse:2.13464\n",
+ "[2488]\tvalidation_0-rmse:2.13409\n",
+ "[2489]\tvalidation_0-rmse:2.13406\n",
+ "[2490]\tvalidation_0-rmse:2.13395\n",
+ "[2491]\tvalidation_0-rmse:2.13376\n",
+ "[2492]\tvalidation_0-rmse:2.13345\n",
+ "[2493]\tvalidation_0-rmse:2.13312\n",
+ "[2494]\tvalidation_0-rmse:2.13278\n",
+ "[2495]\tvalidation_0-rmse:2.13241\n",
+ "[2496]\tvalidation_0-rmse:2.13207\n",
+ "[2497]\tvalidation_0-rmse:2.13177\n",
+ "[2498]\tvalidation_0-rmse:2.13143\n",
+ "[2499]\tvalidation_0-rmse:2.13113\n",
+ "[2500]\tvalidation_0-rmse:2.13097\n",
+ "[2501]\tvalidation_0-rmse:2.13077\n",
+ "[2502]\tvalidation_0-rmse:2.13066\n",
+ "[2503]\tvalidation_0-rmse:2.13051\n",
+ "[2504]\tvalidation_0-rmse:2.12998\n",
+ "[2505]\tvalidation_0-rmse:2.12970\n",
+ "[2506]\tvalidation_0-rmse:2.12954\n",
+ "[2507]\tvalidation_0-rmse:2.12937\n",
+ "[2508]\tvalidation_0-rmse:2.12914\n",
+ "[2509]\tvalidation_0-rmse:2.12871\n",
+ "[2510]\tvalidation_0-rmse:2.12844\n",
+ "[2511]\tvalidation_0-rmse:2.12818\n",
+ "[2512]\tvalidation_0-rmse:2.12788\n",
+ "[2513]\tvalidation_0-rmse:2.12764\n",
+ "[2514]\tvalidation_0-rmse:2.12716\n",
+ "[2515]\tvalidation_0-rmse:2.12652\n",
+ "[2516]\tvalidation_0-rmse:2.12607\n",
+ "[2517]\tvalidation_0-rmse:2.12591\n",
+ "[2518]\tvalidation_0-rmse:2.12558\n",
+ "[2519]\tvalidation_0-rmse:2.12525\n",
+ "[2520]\tvalidation_0-rmse:2.12485\n",
+ "[2521]\tvalidation_0-rmse:2.12470\n",
+ "[2522]\tvalidation_0-rmse:2.12428\n",
+ "[2523]\tvalidation_0-rmse:2.12399\n",
+ "[2524]\tvalidation_0-rmse:2.12377\n",
+ "[2525]\tvalidation_0-rmse:2.12330\n",
+ "[2526]\tvalidation_0-rmse:2.12316\n",
+ "[2527]\tvalidation_0-rmse:2.12306\n",
+ "[2528]\tvalidation_0-rmse:2.12276\n",
+ "[2529]\tvalidation_0-rmse:2.12256\n",
+ "[2530]\tvalidation_0-rmse:2.12232\n",
+ "[2531]\tvalidation_0-rmse:2.12213\n",
+ "[2532]\tvalidation_0-rmse:2.12172\n",
+ "[2533]\tvalidation_0-rmse:2.12142\n",
+ "[2534]\tvalidation_0-rmse:2.12133\n",
+ "[2535]\tvalidation_0-rmse:2.12110\n",
+ "[2536]\tvalidation_0-rmse:2.12086\n",
+ "[2537]\tvalidation_0-rmse:2.12069\n",
+ "[2538]\tvalidation_0-rmse:2.12046\n",
+ "[2539]\tvalidation_0-rmse:2.12032\n",
+ "[2540]\tvalidation_0-rmse:2.12008\n",
+ "[2541]\tvalidation_0-rmse:2.11983\n",
+ "[2542]\tvalidation_0-rmse:2.11965\n",
+ "[2543]\tvalidation_0-rmse:2.11943\n",
+ "[2544]\tvalidation_0-rmse:2.11911\n",
+ "[2545]\tvalidation_0-rmse:2.11898\n",
+ "[2546]\tvalidation_0-rmse:2.11874\n",
+ "[2547]\tvalidation_0-rmse:2.11862\n",
+ "[2548]\tvalidation_0-rmse:2.11841\n",
+ "[2549]\tvalidation_0-rmse:2.11790\n",
+ "[2550]\tvalidation_0-rmse:2.11716\n",
+ "[2551]\tvalidation_0-rmse:2.11681\n",
+ "[2552]\tvalidation_0-rmse:2.11642\n",
+ "[2553]\tvalidation_0-rmse:2.11610\n",
+ "[2554]\tvalidation_0-rmse:2.11562\n",
+ "[2555]\tvalidation_0-rmse:2.11537\n",
+ "[2556]\tvalidation_0-rmse:2.11459\n",
+ "[2557]\tvalidation_0-rmse:2.11424\n",
+ "[2558]\tvalidation_0-rmse:2.11394\n",
+ "[2559]\tvalidation_0-rmse:2.11367\n",
+ "[2560]\tvalidation_0-rmse:2.11335\n",
+ "[2561]\tvalidation_0-rmse:2.11295\n",
+ "[2562]\tvalidation_0-rmse:2.11278\n",
+ "[2563]\tvalidation_0-rmse:2.11254\n",
+ "[2564]\tvalidation_0-rmse:2.11233\n",
+ "[2565]\tvalidation_0-rmse:2.11182\n",
+ "[2566]\tvalidation_0-rmse:2.11154\n",
+ "[2567]\tvalidation_0-rmse:2.11127\n",
+ "[2568]\tvalidation_0-rmse:2.11087\n",
+ "[2569]\tvalidation_0-rmse:2.11065\n",
+ "[2570]\tvalidation_0-rmse:2.11031\n",
+ "[2571]\tvalidation_0-rmse:2.10994\n",
+ "[2572]\tvalidation_0-rmse:2.10954\n",
+ "[2573]\tvalidation_0-rmse:2.10885\n",
+ "[2574]\tvalidation_0-rmse:2.10838\n",
+ "[2575]\tvalidation_0-rmse:2.10805\n",
+ "[2576]\tvalidation_0-rmse:2.10745\n",
+ "[2577]\tvalidation_0-rmse:2.10709\n",
+ "[2578]\tvalidation_0-rmse:2.10667\n",
+ "[2579]\tvalidation_0-rmse:2.10614\n",
+ "[2580]\tvalidation_0-rmse:2.10605\n",
+ "[2581]\tvalidation_0-rmse:2.10570\n",
+ "[2582]\tvalidation_0-rmse:2.10534\n",
+ "[2583]\tvalidation_0-rmse:2.10493\n",
+ "[2584]\tvalidation_0-rmse:2.10463\n",
+ "[2585]\tvalidation_0-rmse:2.10420\n",
+ "[2586]\tvalidation_0-rmse:2.10400\n",
+ "[2587]\tvalidation_0-rmse:2.10389\n",
+ "[2588]\tvalidation_0-rmse:2.10366\n",
+ "[2589]\tvalidation_0-rmse:2.10334\n",
+ "[2590]\tvalidation_0-rmse:2.10299\n",
+ "[2591]\tvalidation_0-rmse:2.10266\n",
+ "[2592]\tvalidation_0-rmse:2.10228\n",
+ "[2593]\tvalidation_0-rmse:2.10200\n",
+ "[2594]\tvalidation_0-rmse:2.10193\n",
+ "[2595]\tvalidation_0-rmse:2.10145\n",
+ "[2596]\tvalidation_0-rmse:2.10118\n",
+ "[2597]\tvalidation_0-rmse:2.10074\n",
+ "[2598]\tvalidation_0-rmse:2.10036\n",
+ "[2599]\tvalidation_0-rmse:2.10017\n",
+ "[2600]\tvalidation_0-rmse:2.10005\n",
+ "[2601]\tvalidation_0-rmse:2.09978\n",
+ "[2602]\tvalidation_0-rmse:2.09929\n",
+ "[2603]\tvalidation_0-rmse:2.09887\n",
+ "[2604]\tvalidation_0-rmse:2.09845\n",
+ "[2605]\tvalidation_0-rmse:2.09809\n",
+ "[2606]\tvalidation_0-rmse:2.09761\n",
+ "[2607]\tvalidation_0-rmse:2.09731\n",
+ "[2608]\tvalidation_0-rmse:2.09695\n",
+ "[2609]\tvalidation_0-rmse:2.09668\n",
+ "[2610]\tvalidation_0-rmse:2.09656\n",
+ "[2611]\tvalidation_0-rmse:2.09625\n",
+ "[2612]\tvalidation_0-rmse:2.09603\n",
+ "[2613]\tvalidation_0-rmse:2.09558\n",
+ "[2614]\tvalidation_0-rmse:2.09481\n",
+ "[2615]\tvalidation_0-rmse:2.09452\n",
+ "[2616]\tvalidation_0-rmse:2.09400\n",
+ "[2617]\tvalidation_0-rmse:2.09364\n",
+ "[2618]\tvalidation_0-rmse:2.09306\n",
+ "[2619]\tvalidation_0-rmse:2.09298\n",
+ "[2620]\tvalidation_0-rmse:2.09274\n",
+ "[2621]\tvalidation_0-rmse:2.09253\n",
+ "[2622]\tvalidation_0-rmse:2.09218\n",
+ "[2623]\tvalidation_0-rmse:2.09195\n",
+ "[2624]\tvalidation_0-rmse:2.09152\n",
+ "[2625]\tvalidation_0-rmse:2.09125\n",
+ "[2626]\tvalidation_0-rmse:2.09100\n",
+ "[2627]\tvalidation_0-rmse:2.09056\n",
+ "[2628]\tvalidation_0-rmse:2.09024\n",
+ "[2629]\tvalidation_0-rmse:2.08993\n",
+ "[2630]\tvalidation_0-rmse:2.08978\n",
+ "[2631]\tvalidation_0-rmse:2.08954\n",
+ "[2632]\tvalidation_0-rmse:2.08933\n",
+ "[2633]\tvalidation_0-rmse:2.08885\n",
+ "[2634]\tvalidation_0-rmse:2.08844\n",
+ "[2635]\tvalidation_0-rmse:2.08809\n",
+ "[2636]\tvalidation_0-rmse:2.08795\n",
+ "[2637]\tvalidation_0-rmse:2.08768\n",
+ "[2638]\tvalidation_0-rmse:2.08735\n",
+ "[2639]\tvalidation_0-rmse:2.08707\n",
+ "[2640]\tvalidation_0-rmse:2.08671\n",
+ "[2641]\tvalidation_0-rmse:2.08599\n",
+ "[2642]\tvalidation_0-rmse:2.08563\n",
+ "[2643]\tvalidation_0-rmse:2.08549\n",
+ "[2644]\tvalidation_0-rmse:2.08515\n",
+ "[2645]\tvalidation_0-rmse:2.08502\n",
+ "[2646]\tvalidation_0-rmse:2.08448\n",
+ "[2647]\tvalidation_0-rmse:2.08370\n",
+ "[2648]\tvalidation_0-rmse:2.08317\n",
+ "[2649]\tvalidation_0-rmse:2.08301\n",
+ "[2650]\tvalidation_0-rmse:2.08288\n",
+ "[2651]\tvalidation_0-rmse:2.08266\n",
+ "[2652]\tvalidation_0-rmse:2.08256\n",
+ "[2653]\tvalidation_0-rmse:2.08205\n",
+ "[2654]\tvalidation_0-rmse:2.08196\n",
+ "[2655]\tvalidation_0-rmse:2.08142\n",
+ "[2656]\tvalidation_0-rmse:2.08106\n",
+ "[2657]\tvalidation_0-rmse:2.08080\n",
+ "[2658]\tvalidation_0-rmse:2.08056\n",
+ "[2659]\tvalidation_0-rmse:2.08005\n",
+ "[2660]\tvalidation_0-rmse:2.07967\n",
+ "[2661]\tvalidation_0-rmse:2.07930\n",
+ "[2662]\tvalidation_0-rmse:2.07922\n",
+ "[2663]\tvalidation_0-rmse:2.07863\n",
+ "[2664]\tvalidation_0-rmse:2.07839\n",
+ "[2665]\tvalidation_0-rmse:2.07805\n",
+ "[2666]\tvalidation_0-rmse:2.07759\n",
+ "[2667]\tvalidation_0-rmse:2.07742\n",
+ "[2668]\tvalidation_0-rmse:2.07705\n",
+ "[2669]\tvalidation_0-rmse:2.07697\n",
+ "[2670]\tvalidation_0-rmse:2.07687\n",
+ "[2671]\tvalidation_0-rmse:2.07640\n",
+ "[2672]\tvalidation_0-rmse:2.07630\n",
+ "[2673]\tvalidation_0-rmse:2.07605\n",
+ "[2674]\tvalidation_0-rmse:2.07574\n",
+ "[2675]\tvalidation_0-rmse:2.07567\n",
+ "[2676]\tvalidation_0-rmse:2.07544\n",
+ "[2677]\tvalidation_0-rmse:2.07533\n",
+ "[2678]\tvalidation_0-rmse:2.07498\n",
+ "[2679]\tvalidation_0-rmse:2.07478\n",
+ "[2680]\tvalidation_0-rmse:2.07472\n",
+ "[2681]\tvalidation_0-rmse:2.07448\n",
+ "[2682]\tvalidation_0-rmse:2.07419\n",
+ "[2683]\tvalidation_0-rmse:2.07399\n",
+ "[2684]\tvalidation_0-rmse:2.07373\n",
+ "[2685]\tvalidation_0-rmse:2.07354\n",
+ "[2686]\tvalidation_0-rmse:2.07322\n",
+ "[2687]\tvalidation_0-rmse:2.07300\n",
+ "[2688]\tvalidation_0-rmse:2.07267\n",
+ "[2689]\tvalidation_0-rmse:2.07234\n",
+ "[2690]\tvalidation_0-rmse:2.07190\n",
+ "[2691]\tvalidation_0-rmse:2.07166\n",
+ "[2692]\tvalidation_0-rmse:2.07095\n",
+ "[2693]\tvalidation_0-rmse:2.07081\n",
+ "[2694]\tvalidation_0-rmse:2.07047\n",
+ "[2695]\tvalidation_0-rmse:2.07016\n",
+ "[2696]\tvalidation_0-rmse:2.06982\n",
+ "[2697]\tvalidation_0-rmse:2.06957\n",
+ "[2698]\tvalidation_0-rmse:2.06918\n",
+ "[2699]\tvalidation_0-rmse:2.06866\n",
+ "[2700]\tvalidation_0-rmse:2.06841\n",
+ "[2701]\tvalidation_0-rmse:2.06828\n",
+ "[2702]\tvalidation_0-rmse:2.06802\n",
+ "[2703]\tvalidation_0-rmse:2.06765\n",
+ "[2704]\tvalidation_0-rmse:2.06743\n",
+ "[2705]\tvalidation_0-rmse:2.06740\n",
+ "[2706]\tvalidation_0-rmse:2.06720\n",
+ "[2707]\tvalidation_0-rmse:2.06690\n",
+ "[2708]\tvalidation_0-rmse:2.06644\n",
+ "[2709]\tvalidation_0-rmse:2.06626\n",
+ "[2710]\tvalidation_0-rmse:2.06567\n",
+ "[2711]\tvalidation_0-rmse:2.06530\n",
+ "[2712]\tvalidation_0-rmse:2.06488\n",
+ "[2713]\tvalidation_0-rmse:2.06466\n",
+ "[2714]\tvalidation_0-rmse:2.06445\n",
+ "[2715]\tvalidation_0-rmse:2.06417\n",
+ "[2716]\tvalidation_0-rmse:2.06398\n",
+ "[2717]\tvalidation_0-rmse:2.06387\n",
+ "[2718]\tvalidation_0-rmse:2.06373\n",
+ "[2719]\tvalidation_0-rmse:2.06362\n",
+ "[2720]\tvalidation_0-rmse:2.06343\n",
+ "[2721]\tvalidation_0-rmse:2.06310\n",
+ "[2722]\tvalidation_0-rmse:2.06257\n",
+ "[2723]\tvalidation_0-rmse:2.06235\n",
+ "[2724]\tvalidation_0-rmse:2.06191\n",
+ "[2725]\tvalidation_0-rmse:2.06160\n",
+ "[2726]\tvalidation_0-rmse:2.06136\n",
+ "[2727]\tvalidation_0-rmse:2.06108\n",
+ "[2728]\tvalidation_0-rmse:2.06072\n",
+ "[2729]\tvalidation_0-rmse:2.06067\n",
+ "[2730]\tvalidation_0-rmse:2.05999\n",
+ "[2731]\tvalidation_0-rmse:2.05968\n",
+ "[2732]\tvalidation_0-rmse:2.05931\n",
+ "[2733]\tvalidation_0-rmse:2.05900\n",
+ "[2734]\tvalidation_0-rmse:2.05874\n",
+ "[2735]\tvalidation_0-rmse:2.05853\n",
+ "[2736]\tvalidation_0-rmse:2.05832\n",
+ "[2737]\tvalidation_0-rmse:2.05789\n",
+ "[2738]\tvalidation_0-rmse:2.05767\n",
+ "[2739]\tvalidation_0-rmse:2.05742\n",
+ "[2740]\tvalidation_0-rmse:2.05695\n",
+ "[2741]\tvalidation_0-rmse:2.05661\n",
+ "[2742]\tvalidation_0-rmse:2.05589\n",
+ "[2743]\tvalidation_0-rmse:2.05558\n",
+ "[2744]\tvalidation_0-rmse:2.05520\n",
+ "[2745]\tvalidation_0-rmse:2.05492\n",
+ "[2746]\tvalidation_0-rmse:2.05445\n",
+ "[2747]\tvalidation_0-rmse:2.05405\n",
+ "[2748]\tvalidation_0-rmse:2.05354\n",
+ "[2749]\tvalidation_0-rmse:2.05298\n",
+ "[2750]\tvalidation_0-rmse:2.05232\n",
+ "[2751]\tvalidation_0-rmse:2.05195\n",
+ "[2752]\tvalidation_0-rmse:2.05165\n",
+ "[2753]\tvalidation_0-rmse:2.05126\n",
+ "[2754]\tvalidation_0-rmse:2.05093\n",
+ "[2755]\tvalidation_0-rmse:2.05090\n",
+ "[2756]\tvalidation_0-rmse:2.05076\n",
+ "[2757]\tvalidation_0-rmse:2.05055\n",
+ "[2758]\tvalidation_0-rmse:2.05040\n",
+ "[2759]\tvalidation_0-rmse:2.05024\n",
+ "[2760]\tvalidation_0-rmse:2.05020\n",
+ "[2761]\tvalidation_0-rmse:2.05014\n",
+ "[2762]\tvalidation_0-rmse:2.04985\n",
+ "[2763]\tvalidation_0-rmse:2.04942\n",
+ "[2764]\tvalidation_0-rmse:2.04913\n",
+ "[2765]\tvalidation_0-rmse:2.04893\n",
+ "[2766]\tvalidation_0-rmse:2.04857\n",
+ "[2767]\tvalidation_0-rmse:2.04811\n",
+ "[2768]\tvalidation_0-rmse:2.04759\n",
+ "[2769]\tvalidation_0-rmse:2.04713\n",
+ "[2770]\tvalidation_0-rmse:2.04641\n",
+ "[2771]\tvalidation_0-rmse:2.04610\n",
+ "[2772]\tvalidation_0-rmse:2.04587\n",
+ "[2773]\tvalidation_0-rmse:2.04542\n",
+ "[2774]\tvalidation_0-rmse:2.04527\n",
+ "[2775]\tvalidation_0-rmse:2.04484\n",
+ "[2776]\tvalidation_0-rmse:2.04445\n",
+ "[2777]\tvalidation_0-rmse:2.04407\n",
+ "[2778]\tvalidation_0-rmse:2.04381\n",
+ "[2779]\tvalidation_0-rmse:2.04358\n",
+ "[2780]\tvalidation_0-rmse:2.04321\n",
+ "[2781]\tvalidation_0-rmse:2.04264\n",
+ "[2782]\tvalidation_0-rmse:2.04216\n",
+ "[2783]\tvalidation_0-rmse:2.04179\n",
+ "[2784]\tvalidation_0-rmse:2.04153\n",
+ "[2785]\tvalidation_0-rmse:2.04144\n",
+ "[2786]\tvalidation_0-rmse:2.04133\n",
+ "[2787]\tvalidation_0-rmse:2.04126\n",
+ "[2788]\tvalidation_0-rmse:2.04106\n",
+ "[2789]\tvalidation_0-rmse:2.04056\n",
+ "[2790]\tvalidation_0-rmse:2.03997\n",
+ "[2791]\tvalidation_0-rmse:2.03978\n",
+ "[2792]\tvalidation_0-rmse:2.03946\n",
+ "[2793]\tvalidation_0-rmse:2.03939\n",
+ "[2794]\tvalidation_0-rmse:2.03908\n",
+ "[2795]\tvalidation_0-rmse:2.03891\n",
+ "[2796]\tvalidation_0-rmse:2.03863\n",
+ "[2797]\tvalidation_0-rmse:2.03854\n",
+ "[2798]\tvalidation_0-rmse:2.03836\n",
+ "[2799]\tvalidation_0-rmse:2.03819\n",
+ "[2800]\tvalidation_0-rmse:2.03809\n",
+ "[2801]\tvalidation_0-rmse:2.03750\n",
+ "[2802]\tvalidation_0-rmse:2.03734\n",
+ "[2803]\tvalidation_0-rmse:2.03703\n",
+ "[2804]\tvalidation_0-rmse:2.03689\n",
+ "[2805]\tvalidation_0-rmse:2.03656\n",
+ "[2806]\tvalidation_0-rmse:2.03649\n",
+ "[2807]\tvalidation_0-rmse:2.03631\n",
+ "[2808]\tvalidation_0-rmse:2.03556\n",
+ "[2809]\tvalidation_0-rmse:2.03528\n",
+ "[2810]\tvalidation_0-rmse:2.03518\n",
+ "[2811]\tvalidation_0-rmse:2.03489\n",
+ "[2812]\tvalidation_0-rmse:2.03440\n",
+ "[2813]\tvalidation_0-rmse:2.03413\n",
+ "[2814]\tvalidation_0-rmse:2.03366\n",
+ "[2815]\tvalidation_0-rmse:2.03346\n",
+ "[2816]\tvalidation_0-rmse:2.03284\n",
+ "[2817]\tvalidation_0-rmse:2.03269\n",
+ "[2818]\tvalidation_0-rmse:2.03235\n",
+ "[2819]\tvalidation_0-rmse:2.03173\n",
+ "[2820]\tvalidation_0-rmse:2.03143\n",
+ "[2821]\tvalidation_0-rmse:2.03126\n",
+ "[2822]\tvalidation_0-rmse:2.03088\n",
+ "[2823]\tvalidation_0-rmse:2.03073\n",
+ "[2824]\tvalidation_0-rmse:2.03037\n",
+ "[2825]\tvalidation_0-rmse:2.02986\n",
+ "[2826]\tvalidation_0-rmse:2.02967\n",
+ "[2827]\tvalidation_0-rmse:2.02923\n",
+ "[2828]\tvalidation_0-rmse:2.02918\n",
+ "[2829]\tvalidation_0-rmse:2.02881\n",
+ "[2830]\tvalidation_0-rmse:2.02862\n",
+ "[2831]\tvalidation_0-rmse:2.02840\n",
+ "[2832]\tvalidation_0-rmse:2.02822\n",
+ "[2833]\tvalidation_0-rmse:2.02812\n",
+ "[2834]\tvalidation_0-rmse:2.02774\n",
+ "[2835]\tvalidation_0-rmse:2.02725\n",
+ "[2836]\tvalidation_0-rmse:2.02696\n",
+ "[2837]\tvalidation_0-rmse:2.02644\n",
+ "[2838]\tvalidation_0-rmse:2.02607\n",
+ "[2839]\tvalidation_0-rmse:2.02594\n",
+ "[2840]\tvalidation_0-rmse:2.02572\n",
+ "[2841]\tvalidation_0-rmse:2.02536\n",
+ "[2842]\tvalidation_0-rmse:2.02509\n",
+ "[2843]\tvalidation_0-rmse:2.02476\n",
+ "[2844]\tvalidation_0-rmse:2.02437\n",
+ "[2845]\tvalidation_0-rmse:2.02417\n",
+ "[2846]\tvalidation_0-rmse:2.02374\n",
+ "[2847]\tvalidation_0-rmse:2.02356\n",
+ "[2848]\tvalidation_0-rmse:2.02332\n",
+ "[2849]\tvalidation_0-rmse:2.02292\n",
+ "[2850]\tvalidation_0-rmse:2.02217\n",
+ "[2851]\tvalidation_0-rmse:2.02189\n",
+ "[2852]\tvalidation_0-rmse:2.02153\n",
+ "[2853]\tvalidation_0-rmse:2.02117\n",
+ "[2854]\tvalidation_0-rmse:2.02090\n",
+ "[2855]\tvalidation_0-rmse:2.02015\n",
+ "[2856]\tvalidation_0-rmse:2.01973\n",
+ "[2857]\tvalidation_0-rmse:2.01919\n",
+ "[2858]\tvalidation_0-rmse:2.01865\n",
+ "[2859]\tvalidation_0-rmse:2.01839\n",
+ "[2860]\tvalidation_0-rmse:2.01800\n",
+ "[2861]\tvalidation_0-rmse:2.01786\n",
+ "[2862]\tvalidation_0-rmse:2.01774\n",
+ "[2863]\tvalidation_0-rmse:2.01735\n",
+ "[2864]\tvalidation_0-rmse:2.01713\n",
+ "[2865]\tvalidation_0-rmse:2.01698\n",
+ "[2866]\tvalidation_0-rmse:2.01651\n",
+ "[2867]\tvalidation_0-rmse:2.01595\n",
+ "[2868]\tvalidation_0-rmse:2.01576\n",
+ "[2869]\tvalidation_0-rmse:2.01566\n",
+ "[2870]\tvalidation_0-rmse:2.01558\n",
+ "[2871]\tvalidation_0-rmse:2.01523\n",
+ "[2872]\tvalidation_0-rmse:2.01471\n",
+ "[2873]\tvalidation_0-rmse:2.01449\n",
+ "[2874]\tvalidation_0-rmse:2.01402\n",
+ "[2875]\tvalidation_0-rmse:2.01387\n",
+ "[2876]\tvalidation_0-rmse:2.01375\n",
+ "[2877]\tvalidation_0-rmse:2.01361\n",
+ "[2878]\tvalidation_0-rmse:2.01347\n",
+ "[2879]\tvalidation_0-rmse:2.01338\n",
+ "[2880]\tvalidation_0-rmse:2.01284\n",
+ "[2881]\tvalidation_0-rmse:2.01262\n",
+ "[2882]\tvalidation_0-rmse:2.01245\n",
+ "[2883]\tvalidation_0-rmse:2.01213\n",
+ "[2884]\tvalidation_0-rmse:2.01183\n",
+ "[2885]\tvalidation_0-rmse:2.01136\n",
+ "[2886]\tvalidation_0-rmse:2.01089\n",
+ "[2887]\tvalidation_0-rmse:2.01067\n",
+ "[2888]\tvalidation_0-rmse:2.01038\n",
+ "[2889]\tvalidation_0-rmse:2.01009\n",
+ "[2890]\tvalidation_0-rmse:2.00978\n",
+ "[2891]\tvalidation_0-rmse:2.00928\n",
+ "[2892]\tvalidation_0-rmse:2.00901\n",
+ "[2893]\tvalidation_0-rmse:2.00877\n",
+ "[2894]\tvalidation_0-rmse:2.00854\n",
+ "[2895]\tvalidation_0-rmse:2.00845\n",
+ "[2896]\tvalidation_0-rmse:2.00809\n",
+ "[2897]\tvalidation_0-rmse:2.00783\n",
+ "[2898]\tvalidation_0-rmse:2.00754\n",
+ "[2899]\tvalidation_0-rmse:2.00734\n",
+ "[2900]\tvalidation_0-rmse:2.00711\n",
+ "[2901]\tvalidation_0-rmse:2.00686\n",
+ "[2902]\tvalidation_0-rmse:2.00658\n",
+ "[2903]\tvalidation_0-rmse:2.00645\n",
+ "[2904]\tvalidation_0-rmse:2.00613\n",
+ "[2905]\tvalidation_0-rmse:2.00564\n",
+ "[2906]\tvalidation_0-rmse:2.00531\n",
+ "[2907]\tvalidation_0-rmse:2.00510\n",
+ "[2908]\tvalidation_0-rmse:2.00481\n",
+ "[2909]\tvalidation_0-rmse:2.00423\n",
+ "[2910]\tvalidation_0-rmse:2.00396\n",
+ "[2911]\tvalidation_0-rmse:2.00342\n",
+ "[2912]\tvalidation_0-rmse:2.00316\n",
+ "[2913]\tvalidation_0-rmse:2.00282\n",
+ "[2914]\tvalidation_0-rmse:2.00253\n",
+ "[2915]\tvalidation_0-rmse:2.00224\n",
+ "[2916]\tvalidation_0-rmse:2.00186\n",
+ "[2917]\tvalidation_0-rmse:2.00140\n",
+ "[2918]\tvalidation_0-rmse:2.00119\n",
+ "[2919]\tvalidation_0-rmse:2.00085\n",
+ "[2920]\tvalidation_0-rmse:2.00050\n",
+ "[2921]\tvalidation_0-rmse:2.00031\n",
+ "[2922]\tvalidation_0-rmse:1.99994\n",
+ "[2923]\tvalidation_0-rmse:1.99927\n",
+ "[2924]\tvalidation_0-rmse:1.99873\n",
+ "[2925]\tvalidation_0-rmse:1.99841\n",
+ "[2926]\tvalidation_0-rmse:1.99821\n",
+ "[2927]\tvalidation_0-rmse:1.99785\n",
+ "[2928]\tvalidation_0-rmse:1.99736\n",
+ "[2929]\tvalidation_0-rmse:1.99711\n",
+ "[2930]\tvalidation_0-rmse:1.99685\n",
+ "[2931]\tvalidation_0-rmse:1.99669\n",
+ "[2932]\tvalidation_0-rmse:1.99652\n",
+ "[2933]\tvalidation_0-rmse:1.99644\n",
+ "[2934]\tvalidation_0-rmse:1.99617\n",
+ "[2935]\tvalidation_0-rmse:1.99585\n",
+ "[2936]\tvalidation_0-rmse:1.99564\n",
+ "[2937]\tvalidation_0-rmse:1.99537\n",
+ "[2938]\tvalidation_0-rmse:1.99531\n",
+ "[2939]\tvalidation_0-rmse:1.99485\n",
+ "[2940]\tvalidation_0-rmse:1.99442\n",
+ "[2941]\tvalidation_0-rmse:1.99406\n",
+ "[2942]\tvalidation_0-rmse:1.99399\n",
+ "[2943]\tvalidation_0-rmse:1.99350\n",
+ "[2944]\tvalidation_0-rmse:1.99305\n",
+ "[2945]\tvalidation_0-rmse:1.99288\n",
+ "[2946]\tvalidation_0-rmse:1.99246\n",
+ "[2947]\tvalidation_0-rmse:1.99224\n",
+ "[2948]\tvalidation_0-rmse:1.99199\n",
+ "[2949]\tvalidation_0-rmse:1.99129\n",
+ "[2950]\tvalidation_0-rmse:1.99105\n",
+ "[2951]\tvalidation_0-rmse:1.99076\n",
+ "[2952]\tvalidation_0-rmse:1.99049\n",
+ "[2953]\tvalidation_0-rmse:1.99013\n",
+ "[2954]\tvalidation_0-rmse:1.98979\n",
+ "[2955]\tvalidation_0-rmse:1.98928\n",
+ "[2956]\tvalidation_0-rmse:1.98881\n",
+ "[2957]\tvalidation_0-rmse:1.98856\n",
+ "[2958]\tvalidation_0-rmse:1.98829\n",
+ "[2959]\tvalidation_0-rmse:1.98812\n",
+ "[2960]\tvalidation_0-rmse:1.98787\n",
+ "[2961]\tvalidation_0-rmse:1.98755\n",
+ "[2962]\tvalidation_0-rmse:1.98738\n",
+ "[2963]\tvalidation_0-rmse:1.98695\n",
+ "[2964]\tvalidation_0-rmse:1.98672\n",
+ "[2965]\tvalidation_0-rmse:1.98651\n",
+ "[2966]\tvalidation_0-rmse:1.98640\n",
+ "[2967]\tvalidation_0-rmse:1.98623\n",
+ "[2968]\tvalidation_0-rmse:1.98598\n",
+ "[2969]\tvalidation_0-rmse:1.98552\n",
+ "[2970]\tvalidation_0-rmse:1.98521\n",
+ "[2971]\tvalidation_0-rmse:1.98491\n",
+ "[2972]\tvalidation_0-rmse:1.98452\n",
+ "[2973]\tvalidation_0-rmse:1.98432\n",
+ "[2974]\tvalidation_0-rmse:1.98389\n",
+ "[2975]\tvalidation_0-rmse:1.98369\n",
+ "[2976]\tvalidation_0-rmse:1.98345\n",
+ "[2977]\tvalidation_0-rmse:1.98308\n",
+ "[2978]\tvalidation_0-rmse:1.98284\n",
+ "[2979]\tvalidation_0-rmse:1.98272\n",
+ "[2980]\tvalidation_0-rmse:1.98248\n",
+ "[2981]\tvalidation_0-rmse:1.98205\n",
+ "[2982]\tvalidation_0-rmse:1.98162\n",
+ "[2983]\tvalidation_0-rmse:1.98155\n",
+ "[2984]\tvalidation_0-rmse:1.98137\n",
+ "[2985]\tvalidation_0-rmse:1.98085\n",
+ "[2986]\tvalidation_0-rmse:1.98066\n",
+ "[2987]\tvalidation_0-rmse:1.98053\n",
+ "[2988]\tvalidation_0-rmse:1.98046\n",
+ "[2989]\tvalidation_0-rmse:1.98025\n",
+ "[2990]\tvalidation_0-rmse:1.97991\n",
+ "[2991]\tvalidation_0-rmse:1.97961\n",
+ "[2992]\tvalidation_0-rmse:1.97944\n",
+ "[2993]\tvalidation_0-rmse:1.97923\n",
+ "[2994]\tvalidation_0-rmse:1.97905\n",
+ "[2995]\tvalidation_0-rmse:1.97898\n",
+ "[2996]\tvalidation_0-rmse:1.97895\n",
+ "[2997]\tvalidation_0-rmse:1.97877\n",
+ "[2998]\tvalidation_0-rmse:1.97860\n",
+ "[2999]\tvalidation_0-rmse:1.97826\n",
+ "[3000]\tvalidation_0-rmse:1.97799\n",
+ "[3001]\tvalidation_0-rmse:1.97782\n",
+ "[3002]\tvalidation_0-rmse:1.97747\n",
+ "[3003]\tvalidation_0-rmse:1.97711\n",
+ "[3004]\tvalidation_0-rmse:1.97675\n",
+ "[3005]\tvalidation_0-rmse:1.97636\n",
+ "[3006]\tvalidation_0-rmse:1.97594\n",
+ "[3007]\tvalidation_0-rmse:1.97573\n",
+ "[3008]\tvalidation_0-rmse:1.97514\n",
+ "[3009]\tvalidation_0-rmse:1.97496\n",
+ "[3010]\tvalidation_0-rmse:1.97479\n",
+ "[3011]\tvalidation_0-rmse:1.97474\n",
+ "[3012]\tvalidation_0-rmse:1.97458\n",
+ "[3013]\tvalidation_0-rmse:1.97445\n",
+ "[3014]\tvalidation_0-rmse:1.97415\n",
+ "[3015]\tvalidation_0-rmse:1.97407\n",
+ "[3016]\tvalidation_0-rmse:1.97387\n",
+ "[3017]\tvalidation_0-rmse:1.97358\n",
+ "[3018]\tvalidation_0-rmse:1.97336\n",
+ "[3019]\tvalidation_0-rmse:1.97302\n",
+ "[3020]\tvalidation_0-rmse:1.97279\n",
+ "[3021]\tvalidation_0-rmse:1.97270\n",
+ "[3022]\tvalidation_0-rmse:1.97235\n",
+ "[3023]\tvalidation_0-rmse:1.97186\n",
+ "[3024]\tvalidation_0-rmse:1.97146\n",
+ "[3025]\tvalidation_0-rmse:1.97103\n",
+ "[3026]\tvalidation_0-rmse:1.97062\n",
+ "[3027]\tvalidation_0-rmse:1.97030\n",
+ "[3028]\tvalidation_0-rmse:1.97000\n",
+ "[3029]\tvalidation_0-rmse:1.96989\n",
+ "[3030]\tvalidation_0-rmse:1.96968\n",
+ "[3031]\tvalidation_0-rmse:1.96952\n",
+ "[3032]\tvalidation_0-rmse:1.96910\n",
+ "[3033]\tvalidation_0-rmse:1.96880\n",
+ "[3034]\tvalidation_0-rmse:1.96870\n",
+ "[3035]\tvalidation_0-rmse:1.96821\n",
+ "[3036]\tvalidation_0-rmse:1.96808\n",
+ "[3037]\tvalidation_0-rmse:1.96788\n",
+ "[3038]\tvalidation_0-rmse:1.96756\n",
+ "[3039]\tvalidation_0-rmse:1.96734\n",
+ "[3040]\tvalidation_0-rmse:1.96717\n",
+ "[3041]\tvalidation_0-rmse:1.96675\n",
+ "[3042]\tvalidation_0-rmse:1.96651\n",
+ "[3043]\tvalidation_0-rmse:1.96613\n",
+ "[3044]\tvalidation_0-rmse:1.96541\n",
+ "[3045]\tvalidation_0-rmse:1.96508\n",
+ "[3046]\tvalidation_0-rmse:1.96479\n",
+ "[3047]\tvalidation_0-rmse:1.96471\n",
+ "[3048]\tvalidation_0-rmse:1.96427\n",
+ "[3049]\tvalidation_0-rmse:1.96392\n",
+ "[3050]\tvalidation_0-rmse:1.96368\n",
+ "[3051]\tvalidation_0-rmse:1.96339\n",
+ "[3052]\tvalidation_0-rmse:1.96309\n",
+ "[3053]\tvalidation_0-rmse:1.96273\n",
+ "[3054]\tvalidation_0-rmse:1.96249\n",
+ "[3055]\tvalidation_0-rmse:1.96226\n",
+ "[3056]\tvalidation_0-rmse:1.96188\n",
+ "[3057]\tvalidation_0-rmse:1.96133\n",
+ "[3058]\tvalidation_0-rmse:1.96115\n",
+ "[3059]\tvalidation_0-rmse:1.96087\n",
+ "[3060]\tvalidation_0-rmse:1.96060\n",
+ "[3061]\tvalidation_0-rmse:1.96028\n",
+ "[3062]\tvalidation_0-rmse:1.96002\n",
+ "[3063]\tvalidation_0-rmse:1.95973\n",
+ "[3064]\tvalidation_0-rmse:1.95953\n",
+ "[3065]\tvalidation_0-rmse:1.95919\n",
+ "[3066]\tvalidation_0-rmse:1.95890\n",
+ "[3067]\tvalidation_0-rmse:1.95873\n",
+ "[3068]\tvalidation_0-rmse:1.95856\n",
+ "[3069]\tvalidation_0-rmse:1.95838\n",
+ "[3070]\tvalidation_0-rmse:1.95818\n",
+ "[3071]\tvalidation_0-rmse:1.95774\n",
+ "[3072]\tvalidation_0-rmse:1.95716\n",
+ "[3073]\tvalidation_0-rmse:1.95684\n",
+ "[3074]\tvalidation_0-rmse:1.95655\n",
+ "[3075]\tvalidation_0-rmse:1.95636\n",
+ "[3076]\tvalidation_0-rmse:1.95601\n",
+ "[3077]\tvalidation_0-rmse:1.95560\n",
+ "[3078]\tvalidation_0-rmse:1.95515\n",
+ "[3079]\tvalidation_0-rmse:1.95493\n",
+ "[3080]\tvalidation_0-rmse:1.95455\n",
+ "[3081]\tvalidation_0-rmse:1.95434\n",
+ "[3082]\tvalidation_0-rmse:1.95398\n",
+ "[3083]\tvalidation_0-rmse:1.95378\n",
+ "[3084]\tvalidation_0-rmse:1.95359\n",
+ "[3085]\tvalidation_0-rmse:1.95345\n",
+ "[3086]\tvalidation_0-rmse:1.95326\n",
+ "[3087]\tvalidation_0-rmse:1.95313\n",
+ "[3088]\tvalidation_0-rmse:1.95284\n",
+ "[3089]\tvalidation_0-rmse:1.95255\n",
+ "[3090]\tvalidation_0-rmse:1.95234\n",
+ "[3091]\tvalidation_0-rmse:1.95226\n",
+ "[3092]\tvalidation_0-rmse:1.95210\n",
+ "[3093]\tvalidation_0-rmse:1.95195\n",
+ "[3094]\tvalidation_0-rmse:1.95188\n",
+ "[3095]\tvalidation_0-rmse:1.95169\n",
+ "[3096]\tvalidation_0-rmse:1.95149\n",
+ "[3097]\tvalidation_0-rmse:1.95114\n",
+ "[3098]\tvalidation_0-rmse:1.95075\n",
+ "[3099]\tvalidation_0-rmse:1.95043\n",
+ "[3100]\tvalidation_0-rmse:1.95013\n",
+ "[3101]\tvalidation_0-rmse:1.94986\n",
+ "[3102]\tvalidation_0-rmse:1.94963\n",
+ "[3103]\tvalidation_0-rmse:1.94932\n",
+ "[3104]\tvalidation_0-rmse:1.94922\n",
+ "[3105]\tvalidation_0-rmse:1.94902\n",
+ "[3106]\tvalidation_0-rmse:1.94888\n",
+ "[3107]\tvalidation_0-rmse:1.94861\n",
+ "[3108]\tvalidation_0-rmse:1.94834\n",
+ "[3109]\tvalidation_0-rmse:1.94820\n",
+ "[3110]\tvalidation_0-rmse:1.94809\n",
+ "[3111]\tvalidation_0-rmse:1.94793\n",
+ "[3112]\tvalidation_0-rmse:1.94759\n",
+ "[3113]\tvalidation_0-rmse:1.94723\n",
+ "[3114]\tvalidation_0-rmse:1.94701\n",
+ "[3115]\tvalidation_0-rmse:1.94684\n",
+ "[3116]\tvalidation_0-rmse:1.94674\n",
+ "[3117]\tvalidation_0-rmse:1.94648\n",
+ "[3118]\tvalidation_0-rmse:1.94606\n",
+ "[3119]\tvalidation_0-rmse:1.94577\n",
+ "[3120]\tvalidation_0-rmse:1.94539\n",
+ "[3121]\tvalidation_0-rmse:1.94514\n",
+ "[3122]\tvalidation_0-rmse:1.94499\n",
+ "[3123]\tvalidation_0-rmse:1.94463\n",
+ "[3124]\tvalidation_0-rmse:1.94426\n",
+ "[3125]\tvalidation_0-rmse:1.94411\n",
+ "[3126]\tvalidation_0-rmse:1.94393\n",
+ "[3127]\tvalidation_0-rmse:1.94367\n",
+ "[3128]\tvalidation_0-rmse:1.94350\n",
+ "[3129]\tvalidation_0-rmse:1.94323\n",
+ "[3130]\tvalidation_0-rmse:1.94293\n",
+ "[3131]\tvalidation_0-rmse:1.94280\n",
+ "[3132]\tvalidation_0-rmse:1.94250\n",
+ "[3133]\tvalidation_0-rmse:1.94235\n",
+ "[3134]\tvalidation_0-rmse:1.94189\n",
+ "[3135]\tvalidation_0-rmse:1.94166\n",
+ "[3136]\tvalidation_0-rmse:1.94148\n",
+ "[3137]\tvalidation_0-rmse:1.94121\n",
+ "[3138]\tvalidation_0-rmse:1.94104\n",
+ "[3139]\tvalidation_0-rmse:1.94101\n",
+ "[3140]\tvalidation_0-rmse:1.94084\n",
+ "[3141]\tvalidation_0-rmse:1.94075\n",
+ "[3142]\tvalidation_0-rmse:1.94058\n",
+ "[3143]\tvalidation_0-rmse:1.94004\n",
+ "[3144]\tvalidation_0-rmse:1.93969\n",
+ "[3145]\tvalidation_0-rmse:1.93911\n",
+ "[3146]\tvalidation_0-rmse:1.93890\n",
+ "[3147]\tvalidation_0-rmse:1.93870\n",
+ "[3148]\tvalidation_0-rmse:1.93840\n",
+ "[3149]\tvalidation_0-rmse:1.93822\n",
+ "[3150]\tvalidation_0-rmse:1.93810\n",
+ "[3151]\tvalidation_0-rmse:1.93797\n",
+ "[3152]\tvalidation_0-rmse:1.93781\n",
+ "[3153]\tvalidation_0-rmse:1.93761\n",
+ "[3154]\tvalidation_0-rmse:1.93747\n",
+ "[3155]\tvalidation_0-rmse:1.93728\n",
+ "[3156]\tvalidation_0-rmse:1.93694\n",
+ "[3157]\tvalidation_0-rmse:1.93633\n",
+ "[3158]\tvalidation_0-rmse:1.93620\n",
+ "[3159]\tvalidation_0-rmse:1.93588\n",
+ "[3160]\tvalidation_0-rmse:1.93557\n",
+ "[3161]\tvalidation_0-rmse:1.93536\n",
+ "[3162]\tvalidation_0-rmse:1.93520\n",
+ "[3163]\tvalidation_0-rmse:1.93505\n",
+ "[3164]\tvalidation_0-rmse:1.93469\n",
+ "[3165]\tvalidation_0-rmse:1.93449\n",
+ "[3166]\tvalidation_0-rmse:1.93417\n",
+ "[3167]\tvalidation_0-rmse:1.93379\n",
+ "[3168]\tvalidation_0-rmse:1.93360\n",
+ "[3169]\tvalidation_0-rmse:1.93338\n",
+ "[3170]\tvalidation_0-rmse:1.93303\n",
+ "[3171]\tvalidation_0-rmse:1.93284\n",
+ "[3172]\tvalidation_0-rmse:1.93257\n",
+ "[3173]\tvalidation_0-rmse:1.93233\n",
+ "[3174]\tvalidation_0-rmse:1.93217\n",
+ "[3175]\tvalidation_0-rmse:1.93206\n",
+ "[3176]\tvalidation_0-rmse:1.93190\n",
+ "[3177]\tvalidation_0-rmse:1.93180\n",
+ "[3178]\tvalidation_0-rmse:1.93150\n",
+ "[3179]\tvalidation_0-rmse:1.93120\n",
+ "[3180]\tvalidation_0-rmse:1.93114\n",
+ "[3181]\tvalidation_0-rmse:1.93086\n",
+ "[3182]\tvalidation_0-rmse:1.93077\n",
+ "[3183]\tvalidation_0-rmse:1.93050\n",
+ "[3184]\tvalidation_0-rmse:1.93027\n",
+ "[3185]\tvalidation_0-rmse:1.92983\n",
+ "[3186]\tvalidation_0-rmse:1.92955\n",
+ "[3187]\tvalidation_0-rmse:1.92925\n",
+ "[3188]\tvalidation_0-rmse:1.92919\n",
+ "[3189]\tvalidation_0-rmse:1.92910\n",
+ "[3190]\tvalidation_0-rmse:1.92867\n",
+ "[3191]\tvalidation_0-rmse:1.92853\n",
+ "[3192]\tvalidation_0-rmse:1.92826\n",
+ "[3193]\tvalidation_0-rmse:1.92807\n",
+ "[3194]\tvalidation_0-rmse:1.92791\n",
+ "[3195]\tvalidation_0-rmse:1.92766\n",
+ "[3196]\tvalidation_0-rmse:1.92745\n",
+ "[3197]\tvalidation_0-rmse:1.92722\n",
+ "[3198]\tvalidation_0-rmse:1.92698\n",
+ "[3199]\tvalidation_0-rmse:1.92686\n",
+ "[3200]\tvalidation_0-rmse:1.92669\n",
+ "[3201]\tvalidation_0-rmse:1.92643\n",
+ "[3202]\tvalidation_0-rmse:1.92619\n",
+ "[3203]\tvalidation_0-rmse:1.92601\n",
+ "[3204]\tvalidation_0-rmse:1.92586\n",
+ "[3205]\tvalidation_0-rmse:1.92571\n",
+ "[3206]\tvalidation_0-rmse:1.92559\n",
+ "[3207]\tvalidation_0-rmse:1.92535\n",
+ "[3208]\tvalidation_0-rmse:1.92503\n",
+ "[3209]\tvalidation_0-rmse:1.92477\n",
+ "[3210]\tvalidation_0-rmse:1.92460\n",
+ "[3211]\tvalidation_0-rmse:1.92442\n",
+ "[3212]\tvalidation_0-rmse:1.92431\n",
+ "[3213]\tvalidation_0-rmse:1.92413\n",
+ "[3214]\tvalidation_0-rmse:1.92374\n",
+ "[3215]\tvalidation_0-rmse:1.92351\n",
+ "[3216]\tvalidation_0-rmse:1.92299\n",
+ "[3217]\tvalidation_0-rmse:1.92248\n",
+ "[3218]\tvalidation_0-rmse:1.92229\n",
+ "[3219]\tvalidation_0-rmse:1.92209\n",
+ "[3220]\tvalidation_0-rmse:1.92182\n",
+ "[3221]\tvalidation_0-rmse:1.92163\n",
+ "[3222]\tvalidation_0-rmse:1.92124\n",
+ "[3223]\tvalidation_0-rmse:1.92102\n",
+ "[3224]\tvalidation_0-rmse:1.92066\n",
+ "[3225]\tvalidation_0-rmse:1.92034\n",
+ "[3226]\tvalidation_0-rmse:1.92008\n",
+ "[3227]\tvalidation_0-rmse:1.91981\n",
+ "[3228]\tvalidation_0-rmse:1.91950\n",
+ "[3229]\tvalidation_0-rmse:1.91927\n",
+ "[3230]\tvalidation_0-rmse:1.91894\n",
+ "[3231]\tvalidation_0-rmse:1.91864\n",
+ "[3232]\tvalidation_0-rmse:1.91840\n",
+ "[3233]\tvalidation_0-rmse:1.91814\n",
+ "[3234]\tvalidation_0-rmse:1.91753\n",
+ "[3235]\tvalidation_0-rmse:1.91718\n",
+ "[3236]\tvalidation_0-rmse:1.91698\n",
+ "[3237]\tvalidation_0-rmse:1.91667\n",
+ "[3238]\tvalidation_0-rmse:1.91648\n",
+ "[3239]\tvalidation_0-rmse:1.91619\n",
+ "[3240]\tvalidation_0-rmse:1.91559\n",
+ "[3241]\tvalidation_0-rmse:1.91529\n",
+ "[3242]\tvalidation_0-rmse:1.91505\n",
+ "[3243]\tvalidation_0-rmse:1.91471\n",
+ "[3244]\tvalidation_0-rmse:1.91465\n",
+ "[3245]\tvalidation_0-rmse:1.91442\n",
+ "[3246]\tvalidation_0-rmse:1.91422\n",
+ "[3247]\tvalidation_0-rmse:1.91385\n",
+ "[3248]\tvalidation_0-rmse:1.91367\n",
+ "[3249]\tvalidation_0-rmse:1.91346\n",
+ "[3250]\tvalidation_0-rmse:1.91321\n",
+ "[3251]\tvalidation_0-rmse:1.91311\n",
+ "[3252]\tvalidation_0-rmse:1.91283\n",
+ "[3253]\tvalidation_0-rmse:1.91266\n",
+ "[3254]\tvalidation_0-rmse:1.91227\n",
+ "[3255]\tvalidation_0-rmse:1.91193\n",
+ "[3256]\tvalidation_0-rmse:1.91173\n",
+ "[3257]\tvalidation_0-rmse:1.91152\n",
+ "[3258]\tvalidation_0-rmse:1.91134\n",
+ "[3259]\tvalidation_0-rmse:1.91130\n",
+ "[3260]\tvalidation_0-rmse:1.91097\n",
+ "[3261]\tvalidation_0-rmse:1.91063\n",
+ "[3262]\tvalidation_0-rmse:1.91044\n",
+ "[3263]\tvalidation_0-rmse:1.91034\n",
+ "[3264]\tvalidation_0-rmse:1.90988\n",
+ "[3265]\tvalidation_0-rmse:1.90962\n",
+ "[3266]\tvalidation_0-rmse:1.90956\n",
+ "[3267]\tvalidation_0-rmse:1.90906\n",
+ "[3268]\tvalidation_0-rmse:1.90875\n",
+ "[3269]\tvalidation_0-rmse:1.90837\n",
+ "[3270]\tvalidation_0-rmse:1.90818\n",
+ "[3271]\tvalidation_0-rmse:1.90802\n",
+ "[3272]\tvalidation_0-rmse:1.90784\n",
+ "[3273]\tvalidation_0-rmse:1.90763\n",
+ "[3274]\tvalidation_0-rmse:1.90749\n",
+ "[3275]\tvalidation_0-rmse:1.90722\n",
+ "[3276]\tvalidation_0-rmse:1.90706\n",
+ "[3277]\tvalidation_0-rmse:1.90676\n",
+ "[3278]\tvalidation_0-rmse:1.90639\n",
+ "[3279]\tvalidation_0-rmse:1.90602\n",
+ "[3280]\tvalidation_0-rmse:1.90547\n",
+ "[3281]\tvalidation_0-rmse:1.90515\n",
+ "[3282]\tvalidation_0-rmse:1.90484\n",
+ "[3283]\tvalidation_0-rmse:1.90447\n",
+ "[3284]\tvalidation_0-rmse:1.90418\n",
+ "[3285]\tvalidation_0-rmse:1.90385\n",
+ "[3286]\tvalidation_0-rmse:1.90379\n",
+ "[3287]\tvalidation_0-rmse:1.90348\n",
+ "[3288]\tvalidation_0-rmse:1.90333\n",
+ "[3289]\tvalidation_0-rmse:1.90313\n",
+ "[3290]\tvalidation_0-rmse:1.90283\n",
+ "[3291]\tvalidation_0-rmse:1.90238\n",
+ "[3292]\tvalidation_0-rmse:1.90210\n",
+ "[3293]\tvalidation_0-rmse:1.90184\n",
+ "[3294]\tvalidation_0-rmse:1.90164\n",
+ "[3295]\tvalidation_0-rmse:1.90138\n",
+ "[3296]\tvalidation_0-rmse:1.90111\n",
+ "[3297]\tvalidation_0-rmse:1.90087\n",
+ "[3298]\tvalidation_0-rmse:1.90062\n",
+ "[3299]\tvalidation_0-rmse:1.90040\n",
+ "[3300]\tvalidation_0-rmse:1.90026\n",
+ "[3301]\tvalidation_0-rmse:1.90006\n",
+ "[3302]\tvalidation_0-rmse:1.89978\n",
+ "[3303]\tvalidation_0-rmse:1.89958\n",
+ "[3304]\tvalidation_0-rmse:1.89931\n",
+ "[3305]\tvalidation_0-rmse:1.89917\n",
+ "[3306]\tvalidation_0-rmse:1.89886\n",
+ "[3307]\tvalidation_0-rmse:1.89860\n",
+ "[3308]\tvalidation_0-rmse:1.89805\n",
+ "[3309]\tvalidation_0-rmse:1.89785\n",
+ "[3310]\tvalidation_0-rmse:1.89733\n",
+ "[3311]\tvalidation_0-rmse:1.89686\n",
+ "[3312]\tvalidation_0-rmse:1.89681\n",
+ "[3313]\tvalidation_0-rmse:1.89666\n",
+ "[3314]\tvalidation_0-rmse:1.89641\n",
+ "[3315]\tvalidation_0-rmse:1.89616\n",
+ "[3316]\tvalidation_0-rmse:1.89559\n",
+ "[3317]\tvalidation_0-rmse:1.89535\n",
+ "[3318]\tvalidation_0-rmse:1.89512\n",
+ "[3319]\tvalidation_0-rmse:1.89459\n",
+ "[3320]\tvalidation_0-rmse:1.89426\n",
+ "[3321]\tvalidation_0-rmse:1.89399\n",
+ "[3322]\tvalidation_0-rmse:1.89383\n",
+ "[3323]\tvalidation_0-rmse:1.89377\n",
+ "[3324]\tvalidation_0-rmse:1.89349\n",
+ "[3325]\tvalidation_0-rmse:1.89335\n",
+ "[3326]\tvalidation_0-rmse:1.89322\n",
+ "[3327]\tvalidation_0-rmse:1.89287\n",
+ "[3328]\tvalidation_0-rmse:1.89267\n",
+ "[3329]\tvalidation_0-rmse:1.89243\n",
+ "[3330]\tvalidation_0-rmse:1.89213\n",
+ "[3331]\tvalidation_0-rmse:1.89200\n",
+ "[3332]\tvalidation_0-rmse:1.89180\n",
+ "[3333]\tvalidation_0-rmse:1.89135\n",
+ "[3334]\tvalidation_0-rmse:1.89108\n",
+ "[3335]\tvalidation_0-rmse:1.89089\n",
+ "[3336]\tvalidation_0-rmse:1.89067\n",
+ "[3337]\tvalidation_0-rmse:1.89043\n",
+ "[3338]\tvalidation_0-rmse:1.89020\n",
+ "[3339]\tvalidation_0-rmse:1.89006\n",
+ "[3340]\tvalidation_0-rmse:1.88973\n",
+ "[3341]\tvalidation_0-rmse:1.88925\n",
+ "[3342]\tvalidation_0-rmse:1.88896\n",
+ "[3343]\tvalidation_0-rmse:1.88864\n",
+ "[3344]\tvalidation_0-rmse:1.88811\n",
+ "[3345]\tvalidation_0-rmse:1.88799\n",
+ "[3346]\tvalidation_0-rmse:1.88773\n",
+ "[3347]\tvalidation_0-rmse:1.88755\n",
+ "[3348]\tvalidation_0-rmse:1.88736\n",
+ "[3349]\tvalidation_0-rmse:1.88715\n",
+ "[3350]\tvalidation_0-rmse:1.88703\n",
+ "[3351]\tvalidation_0-rmse:1.88662\n",
+ "[3352]\tvalidation_0-rmse:1.88623\n",
+ "[3353]\tvalidation_0-rmse:1.88613\n",
+ "[3354]\tvalidation_0-rmse:1.88584\n",
+ "[3355]\tvalidation_0-rmse:1.88561\n",
+ "[3356]\tvalidation_0-rmse:1.88552\n",
+ "[3357]\tvalidation_0-rmse:1.88531\n",
+ "[3358]\tvalidation_0-rmse:1.88516\n",
+ "[3359]\tvalidation_0-rmse:1.88499\n",
+ "[3360]\tvalidation_0-rmse:1.88485\n",
+ "[3361]\tvalidation_0-rmse:1.88450\n",
+ "[3362]\tvalidation_0-rmse:1.88440\n",
+ "[3363]\tvalidation_0-rmse:1.88393\n",
+ "[3364]\tvalidation_0-rmse:1.88372\n",
+ "[3365]\tvalidation_0-rmse:1.88343\n",
+ "[3366]\tvalidation_0-rmse:1.88331\n",
+ "[3367]\tvalidation_0-rmse:1.88303\n",
+ "[3368]\tvalidation_0-rmse:1.88286\n",
+ "[3369]\tvalidation_0-rmse:1.88257\n",
+ "[3370]\tvalidation_0-rmse:1.88236\n",
+ "[3371]\tvalidation_0-rmse:1.88223\n",
+ "[3372]\tvalidation_0-rmse:1.88203\n",
+ "[3373]\tvalidation_0-rmse:1.88171\n",
+ "[3374]\tvalidation_0-rmse:1.88147\n",
+ "[3375]\tvalidation_0-rmse:1.88122\n",
+ "[3376]\tvalidation_0-rmse:1.88081\n",
+ "[3377]\tvalidation_0-rmse:1.88072\n",
+ "[3378]\tvalidation_0-rmse:1.88049\n",
+ "[3379]\tvalidation_0-rmse:1.88020\n",
+ "[3380]\tvalidation_0-rmse:1.88013\n",
+ "[3381]\tvalidation_0-rmse:1.88003\n",
+ "[3382]\tvalidation_0-rmse:1.87985\n",
+ "[3383]\tvalidation_0-rmse:1.87963\n",
+ "[3384]\tvalidation_0-rmse:1.87913\n",
+ "[3385]\tvalidation_0-rmse:1.87889\n",
+ "[3386]\tvalidation_0-rmse:1.87849\n",
+ "[3387]\tvalidation_0-rmse:1.87812\n",
+ "[3388]\tvalidation_0-rmse:1.87784\n",
+ "[3389]\tvalidation_0-rmse:1.87738\n",
+ "[3390]\tvalidation_0-rmse:1.87709\n",
+ "[3391]\tvalidation_0-rmse:1.87672\n",
+ "[3392]\tvalidation_0-rmse:1.87650\n",
+ "[3393]\tvalidation_0-rmse:1.87621\n",
+ "[3394]\tvalidation_0-rmse:1.87603\n",
+ "[3395]\tvalidation_0-rmse:1.87586\n",
+ "[3396]\tvalidation_0-rmse:1.87564\n",
+ "[3397]\tvalidation_0-rmse:1.87549\n",
+ "[3398]\tvalidation_0-rmse:1.87515\n",
+ "[3399]\tvalidation_0-rmse:1.87476\n",
+ "[3400]\tvalidation_0-rmse:1.87439\n",
+ "[3401]\tvalidation_0-rmse:1.87429\n",
+ "[3402]\tvalidation_0-rmse:1.87404\n",
+ "[3403]\tvalidation_0-rmse:1.87380\n",
+ "[3404]\tvalidation_0-rmse:1.87357\n",
+ "[3405]\tvalidation_0-rmse:1.87308\n",
+ "[3406]\tvalidation_0-rmse:1.87263\n",
+ "[3407]\tvalidation_0-rmse:1.87237\n",
+ "[3408]\tvalidation_0-rmse:1.87212\n",
+ "[3409]\tvalidation_0-rmse:1.87195\n",
+ "[3410]\tvalidation_0-rmse:1.87170\n",
+ "[3411]\tvalidation_0-rmse:1.87149\n",
+ "[3412]\tvalidation_0-rmse:1.87128\n",
+ "[3413]\tvalidation_0-rmse:1.87095\n",
+ "[3414]\tvalidation_0-rmse:1.87071\n",
+ "[3415]\tvalidation_0-rmse:1.87039\n",
+ "[3416]\tvalidation_0-rmse:1.87009\n",
+ "[3417]\tvalidation_0-rmse:1.86975\n",
+ "[3418]\tvalidation_0-rmse:1.86949\n",
+ "[3419]\tvalidation_0-rmse:1.86914\n",
+ "[3420]\tvalidation_0-rmse:1.86875\n",
+ "[3421]\tvalidation_0-rmse:1.86831\n",
+ "[3422]\tvalidation_0-rmse:1.86804\n",
+ "[3423]\tvalidation_0-rmse:1.86788\n",
+ "[3424]\tvalidation_0-rmse:1.86766\n",
+ "[3425]\tvalidation_0-rmse:1.86741\n",
+ "[3426]\tvalidation_0-rmse:1.86713\n",
+ "[3427]\tvalidation_0-rmse:1.86680\n",
+ "[3428]\tvalidation_0-rmse:1.86656\n",
+ "[3429]\tvalidation_0-rmse:1.86603\n",
+ "[3430]\tvalidation_0-rmse:1.86573\n",
+ "[3431]\tvalidation_0-rmse:1.86557\n",
+ "[3432]\tvalidation_0-rmse:1.86515\n",
+ "[3433]\tvalidation_0-rmse:1.86484\n",
+ "[3434]\tvalidation_0-rmse:1.86456\n",
+ "[3435]\tvalidation_0-rmse:1.86434\n",
+ "[3436]\tvalidation_0-rmse:1.86412\n",
+ "[3437]\tvalidation_0-rmse:1.86386\n",
+ "[3438]\tvalidation_0-rmse:1.86354\n",
+ "[3439]\tvalidation_0-rmse:1.86322\n",
+ "[3440]\tvalidation_0-rmse:1.86301\n",
+ "[3441]\tvalidation_0-rmse:1.86273\n",
+ "[3442]\tvalidation_0-rmse:1.86256\n",
+ "[3443]\tvalidation_0-rmse:1.86235\n",
+ "[3444]\tvalidation_0-rmse:1.86206\n",
+ "[3445]\tvalidation_0-rmse:1.86190\n",
+ "[3446]\tvalidation_0-rmse:1.86165\n",
+ "[3447]\tvalidation_0-rmse:1.86120\n",
+ "[3448]\tvalidation_0-rmse:1.86099\n",
+ "[3449]\tvalidation_0-rmse:1.86040\n",
+ "[3450]\tvalidation_0-rmse:1.86013\n",
+ "[3451]\tvalidation_0-rmse:1.85976\n",
+ "[3452]\tvalidation_0-rmse:1.85960\n",
+ "[3453]\tvalidation_0-rmse:1.85945\n",
+ "[3454]\tvalidation_0-rmse:1.85927\n",
+ "[3455]\tvalidation_0-rmse:1.85894\n",
+ "[3456]\tvalidation_0-rmse:1.85869\n",
+ "[3457]\tvalidation_0-rmse:1.85803\n",
+ "[3458]\tvalidation_0-rmse:1.85766\n",
+ "[3459]\tvalidation_0-rmse:1.85743\n",
+ "[3460]\tvalidation_0-rmse:1.85705\n",
+ "[3461]\tvalidation_0-rmse:1.85698\n",
+ "[3462]\tvalidation_0-rmse:1.85674\n",
+ "[3463]\tvalidation_0-rmse:1.85656\n",
+ "[3464]\tvalidation_0-rmse:1.85639\n",
+ "[3465]\tvalidation_0-rmse:1.85607\n",
+ "[3466]\tvalidation_0-rmse:1.85593\n",
+ "[3467]\tvalidation_0-rmse:1.85573\n",
+ "[3468]\tvalidation_0-rmse:1.85538\n",
+ "[3469]\tvalidation_0-rmse:1.85521\n",
+ "[3470]\tvalidation_0-rmse:1.85473\n",
+ "[3471]\tvalidation_0-rmse:1.85456\n",
+ "[3472]\tvalidation_0-rmse:1.85425\n",
+ "[3473]\tvalidation_0-rmse:1.85384\n",
+ "[3474]\tvalidation_0-rmse:1.85335\n",
+ "[3475]\tvalidation_0-rmse:1.85313\n",
+ "[3476]\tvalidation_0-rmse:1.85303\n",
+ "[3477]\tvalidation_0-rmse:1.85281\n",
+ "[3478]\tvalidation_0-rmse:1.85250\n",
+ "[3479]\tvalidation_0-rmse:1.85236\n",
+ "[3480]\tvalidation_0-rmse:1.85224\n",
+ "[3481]\tvalidation_0-rmse:1.85206\n",
+ "[3482]\tvalidation_0-rmse:1.85185\n",
+ "[3483]\tvalidation_0-rmse:1.85126\n",
+ "[3484]\tvalidation_0-rmse:1.85097\n",
+ "[3485]\tvalidation_0-rmse:1.85050\n",
+ "[3486]\tvalidation_0-rmse:1.84998\n",
+ "[3487]\tvalidation_0-rmse:1.84978\n",
+ "[3488]\tvalidation_0-rmse:1.84937\n",
+ "[3489]\tvalidation_0-rmse:1.84908\n",
+ "[3490]\tvalidation_0-rmse:1.84888\n",
+ "[3491]\tvalidation_0-rmse:1.84870\n",
+ "[3492]\tvalidation_0-rmse:1.84857\n",
+ "[3493]\tvalidation_0-rmse:1.84833\n",
+ "[3494]\tvalidation_0-rmse:1.84819\n",
+ "[3495]\tvalidation_0-rmse:1.84792\n",
+ "[3496]\tvalidation_0-rmse:1.84763\n",
+ "[3497]\tvalidation_0-rmse:1.84747\n",
+ "[3498]\tvalidation_0-rmse:1.84733\n",
+ "[3499]\tvalidation_0-rmse:1.84704\n",
+ "[3500]\tvalidation_0-rmse:1.84672\n",
+ "[3501]\tvalidation_0-rmse:1.84636\n",
+ "[3502]\tvalidation_0-rmse:1.84600\n",
+ "[3503]\tvalidation_0-rmse:1.84550\n",
+ "[3504]\tvalidation_0-rmse:1.84517\n",
+ "[3505]\tvalidation_0-rmse:1.84473\n",
+ "[3506]\tvalidation_0-rmse:1.84452\n",
+ "[3507]\tvalidation_0-rmse:1.84422\n",
+ "[3508]\tvalidation_0-rmse:1.84398\n",
+ "[3509]\tvalidation_0-rmse:1.84371\n",
+ "[3510]\tvalidation_0-rmse:1.84354\n",
+ "[3511]\tvalidation_0-rmse:1.84338\n",
+ "[3512]\tvalidation_0-rmse:1.84327\n",
+ "[3513]\tvalidation_0-rmse:1.84305\n",
+ "[3514]\tvalidation_0-rmse:1.84270\n",
+ "[3515]\tvalidation_0-rmse:1.84230\n",
+ "[3516]\tvalidation_0-rmse:1.84189\n",
+ "[3517]\tvalidation_0-rmse:1.84164\n",
+ "[3518]\tvalidation_0-rmse:1.84130\n",
+ "[3519]\tvalidation_0-rmse:1.84104\n",
+ "[3520]\tvalidation_0-rmse:1.84073\n",
+ "[3521]\tvalidation_0-rmse:1.84052\n",
+ "[3522]\tvalidation_0-rmse:1.84028\n",
+ "[3523]\tvalidation_0-rmse:1.84019\n",
+ "[3524]\tvalidation_0-rmse:1.84004\n",
+ "[3525]\tvalidation_0-rmse:1.83974\n",
+ "[3526]\tvalidation_0-rmse:1.83959\n",
+ "[3527]\tvalidation_0-rmse:1.83944\n",
+ "[3528]\tvalidation_0-rmse:1.83937\n",
+ "[3529]\tvalidation_0-rmse:1.83930\n",
+ "[3530]\tvalidation_0-rmse:1.83902\n",
+ "[3531]\tvalidation_0-rmse:1.83873\n",
+ "[3532]\tvalidation_0-rmse:1.83831\n",
+ "[3533]\tvalidation_0-rmse:1.83816\n",
+ "[3534]\tvalidation_0-rmse:1.83799\n",
+ "[3535]\tvalidation_0-rmse:1.83770\n",
+ "[3536]\tvalidation_0-rmse:1.83740\n",
+ "[3537]\tvalidation_0-rmse:1.83698\n",
+ "[3538]\tvalidation_0-rmse:1.83679\n",
+ "[3539]\tvalidation_0-rmse:1.83652\n",
+ "[3540]\tvalidation_0-rmse:1.83621\n",
+ "[3541]\tvalidation_0-rmse:1.83606\n",
+ "[3542]\tvalidation_0-rmse:1.83539\n",
+ "[3543]\tvalidation_0-rmse:1.83507\n",
+ "[3544]\tvalidation_0-rmse:1.83485\n",
+ "[3545]\tvalidation_0-rmse:1.83453\n",
+ "[3546]\tvalidation_0-rmse:1.83438\n",
+ "[3547]\tvalidation_0-rmse:1.83401\n",
+ "[3548]\tvalidation_0-rmse:1.83386\n",
+ "[3549]\tvalidation_0-rmse:1.83350\n",
+ "[3550]\tvalidation_0-rmse:1.83314\n",
+ "[3551]\tvalidation_0-rmse:1.83286\n",
+ "[3552]\tvalidation_0-rmse:1.83264\n",
+ "[3553]\tvalidation_0-rmse:1.83218\n",
+ "[3554]\tvalidation_0-rmse:1.83148\n",
+ "[3555]\tvalidation_0-rmse:1.83124\n",
+ "[3556]\tvalidation_0-rmse:1.83106\n",
+ "[3557]\tvalidation_0-rmse:1.83060\n",
+ "[3558]\tvalidation_0-rmse:1.83023\n",
+ "[3559]\tvalidation_0-rmse:1.83006\n",
+ "[3560]\tvalidation_0-rmse:1.82962\n",
+ "[3561]\tvalidation_0-rmse:1.82907\n",
+ "[3562]\tvalidation_0-rmse:1.82883\n",
+ "[3563]\tvalidation_0-rmse:1.82865\n",
+ "[3564]\tvalidation_0-rmse:1.82851\n",
+ "[3565]\tvalidation_0-rmse:1.82829\n",
+ "[3566]\tvalidation_0-rmse:1.82814\n",
+ "[3567]\tvalidation_0-rmse:1.82767\n",
+ "[3568]\tvalidation_0-rmse:1.82736\n",
+ "[3569]\tvalidation_0-rmse:1.82726\n",
+ "[3570]\tvalidation_0-rmse:1.82716\n",
+ "[3571]\tvalidation_0-rmse:1.82714\n",
+ "[3572]\tvalidation_0-rmse:1.82693\n",
+ "[3573]\tvalidation_0-rmse:1.82668\n",
+ "[3574]\tvalidation_0-rmse:1.82645\n",
+ "[3575]\tvalidation_0-rmse:1.82633\n",
+ "[3576]\tvalidation_0-rmse:1.82608\n",
+ "[3577]\tvalidation_0-rmse:1.82602\n",
+ "[3578]\tvalidation_0-rmse:1.82569\n",
+ "[3579]\tvalidation_0-rmse:1.82551\n",
+ "[3580]\tvalidation_0-rmse:1.82516\n",
+ "[3581]\tvalidation_0-rmse:1.82477\n",
+ "[3582]\tvalidation_0-rmse:1.82444\n",
+ "[3583]\tvalidation_0-rmse:1.82393\n",
+ "[3584]\tvalidation_0-rmse:1.82359\n",
+ "[3585]\tvalidation_0-rmse:1.82343\n",
+ "[3586]\tvalidation_0-rmse:1.82308\n",
+ "[3587]\tvalidation_0-rmse:1.82298\n",
+ "[3588]\tvalidation_0-rmse:1.82289\n",
+ "[3589]\tvalidation_0-rmse:1.82268\n",
+ "[3590]\tvalidation_0-rmse:1.82248\n",
+ "[3591]\tvalidation_0-rmse:1.82234\n",
+ "[3592]\tvalidation_0-rmse:1.82199\n",
+ "[3593]\tvalidation_0-rmse:1.82161\n",
+ "[3594]\tvalidation_0-rmse:1.82153\n",
+ "[3595]\tvalidation_0-rmse:1.82126\n",
+ "[3596]\tvalidation_0-rmse:1.82098\n",
+ "[3597]\tvalidation_0-rmse:1.82073\n",
+ "[3598]\tvalidation_0-rmse:1.82031\n",
+ "[3599]\tvalidation_0-rmse:1.81976\n",
+ "[3600]\tvalidation_0-rmse:1.81946\n",
+ "[3601]\tvalidation_0-rmse:1.81908\n",
+ "[3602]\tvalidation_0-rmse:1.81868\n",
+ "[3603]\tvalidation_0-rmse:1.81851\n",
+ "[3604]\tvalidation_0-rmse:1.81831\n",
+ "[3605]\tvalidation_0-rmse:1.81812\n",
+ "[3606]\tvalidation_0-rmse:1.81794\n",
+ "[3607]\tvalidation_0-rmse:1.81784\n",
+ "[3608]\tvalidation_0-rmse:1.81755\n",
+ "[3609]\tvalidation_0-rmse:1.81734\n",
+ "[3610]\tvalidation_0-rmse:1.81702\n",
+ "[3611]\tvalidation_0-rmse:1.81677\n",
+ "[3612]\tvalidation_0-rmse:1.81653\n",
+ "[3613]\tvalidation_0-rmse:1.81641\n",
+ "[3614]\tvalidation_0-rmse:1.81612\n",
+ "[3615]\tvalidation_0-rmse:1.81601\n",
+ "[3616]\tvalidation_0-rmse:1.81586\n",
+ "[3617]\tvalidation_0-rmse:1.81566\n",
+ "[3618]\tvalidation_0-rmse:1.81541\n",
+ "[3619]\tvalidation_0-rmse:1.81518\n",
+ "[3620]\tvalidation_0-rmse:1.81511\n",
+ "[3621]\tvalidation_0-rmse:1.81502\n",
+ "[3622]\tvalidation_0-rmse:1.81481\n",
+ "[3623]\tvalidation_0-rmse:1.81445\n",
+ "[3624]\tvalidation_0-rmse:1.81425\n",
+ "[3625]\tvalidation_0-rmse:1.81407\n",
+ "[3626]\tvalidation_0-rmse:1.81376\n",
+ "[3627]\tvalidation_0-rmse:1.81348\n",
+ "[3628]\tvalidation_0-rmse:1.81310\n",
+ "[3629]\tvalidation_0-rmse:1.81276\n",
+ "[3630]\tvalidation_0-rmse:1.81261\n",
+ "[3631]\tvalidation_0-rmse:1.81238\n",
+ "[3632]\tvalidation_0-rmse:1.81222\n",
+ "[3633]\tvalidation_0-rmse:1.81203\n",
+ "[3634]\tvalidation_0-rmse:1.81178\n",
+ "[3635]\tvalidation_0-rmse:1.81135\n",
+ "[3636]\tvalidation_0-rmse:1.81096\n",
+ "[3637]\tvalidation_0-rmse:1.81057\n",
+ "[3638]\tvalidation_0-rmse:1.81022\n",
+ "[3639]\tvalidation_0-rmse:1.81006\n",
+ "[3640]\tvalidation_0-rmse:1.80987\n",
+ "[3641]\tvalidation_0-rmse:1.80967\n",
+ "[3642]\tvalidation_0-rmse:1.80946\n",
+ "[3643]\tvalidation_0-rmse:1.80930\n",
+ "[3644]\tvalidation_0-rmse:1.80892\n",
+ "[3645]\tvalidation_0-rmse:1.80872\n",
+ "[3646]\tvalidation_0-rmse:1.80862\n",
+ "[3647]\tvalidation_0-rmse:1.80838\n",
+ "[3648]\tvalidation_0-rmse:1.80825\n",
+ "[3649]\tvalidation_0-rmse:1.80809\n",
+ "[3650]\tvalidation_0-rmse:1.80786\n",
+ "[3651]\tvalidation_0-rmse:1.80773\n",
+ "[3652]\tvalidation_0-rmse:1.80735\n",
+ "[3653]\tvalidation_0-rmse:1.80718\n",
+ "[3654]\tvalidation_0-rmse:1.80705\n",
+ "[3655]\tvalidation_0-rmse:1.80680\n",
+ "[3656]\tvalidation_0-rmse:1.80658\n",
+ "[3657]\tvalidation_0-rmse:1.80643\n",
+ "[3658]\tvalidation_0-rmse:1.80628\n",
+ "[3659]\tvalidation_0-rmse:1.80604\n",
+ "[3660]\tvalidation_0-rmse:1.80589\n",
+ "[3661]\tvalidation_0-rmse:1.80569\n",
+ "[3662]\tvalidation_0-rmse:1.80552\n",
+ "[3663]\tvalidation_0-rmse:1.80522\n",
+ "[3664]\tvalidation_0-rmse:1.80505\n",
+ "[3665]\tvalidation_0-rmse:1.80495\n",
+ "[3666]\tvalidation_0-rmse:1.80481\n",
+ "[3667]\tvalidation_0-rmse:1.80449\n",
+ "[3668]\tvalidation_0-rmse:1.80414\n",
+ "[3669]\tvalidation_0-rmse:1.80393\n",
+ "[3670]\tvalidation_0-rmse:1.80363\n",
+ "[3671]\tvalidation_0-rmse:1.80329\n",
+ "[3672]\tvalidation_0-rmse:1.80303\n",
+ "[3673]\tvalidation_0-rmse:1.80287\n",
+ "[3674]\tvalidation_0-rmse:1.80257\n",
+ "[3675]\tvalidation_0-rmse:1.80248\n",
+ "[3676]\tvalidation_0-rmse:1.80234\n",
+ "[3677]\tvalidation_0-rmse:1.80220\n",
+ "[3678]\tvalidation_0-rmse:1.80193\n",
+ "[3679]\tvalidation_0-rmse:1.80172\n",
+ "[3680]\tvalidation_0-rmse:1.80163\n",
+ "[3681]\tvalidation_0-rmse:1.80143\n",
+ "[3682]\tvalidation_0-rmse:1.80115\n",
+ "[3683]\tvalidation_0-rmse:1.80093\n",
+ "[3684]\tvalidation_0-rmse:1.80061\n",
+ "[3685]\tvalidation_0-rmse:1.80059\n",
+ "[3686]\tvalidation_0-rmse:1.80042\n",
+ "[3687]\tvalidation_0-rmse:1.80023\n",
+ "[3688]\tvalidation_0-rmse:1.80014\n",
+ "[3689]\tvalidation_0-rmse:1.80012\n",
+ "[3690]\tvalidation_0-rmse:1.79972\n",
+ "[3691]\tvalidation_0-rmse:1.79956\n",
+ "[3692]\tvalidation_0-rmse:1.79946\n",
+ "[3693]\tvalidation_0-rmse:1.79915\n",
+ "[3694]\tvalidation_0-rmse:1.79913\n",
+ "[3695]\tvalidation_0-rmse:1.79884\n",
+ "[3696]\tvalidation_0-rmse:1.79864\n",
+ "[3697]\tvalidation_0-rmse:1.79847\n",
+ "[3698]\tvalidation_0-rmse:1.79839\n",
+ "[3699]\tvalidation_0-rmse:1.79805\n",
+ "[3700]\tvalidation_0-rmse:1.79784\n",
+ "[3701]\tvalidation_0-rmse:1.79782\n",
+ "[3702]\tvalidation_0-rmse:1.79778\n",
+ "[3703]\tvalidation_0-rmse:1.79741\n",
+ "[3704]\tvalidation_0-rmse:1.79714\n",
+ "[3705]\tvalidation_0-rmse:1.79686\n",
+ "[3706]\tvalidation_0-rmse:1.79682\n",
+ "[3707]\tvalidation_0-rmse:1.79636\n",
+ "[3708]\tvalidation_0-rmse:1.79630\n",
+ "[3709]\tvalidation_0-rmse:1.79629\n",
+ "[3710]\tvalidation_0-rmse:1.79617\n",
+ "[3711]\tvalidation_0-rmse:1.79589\n",
+ "[3712]\tvalidation_0-rmse:1.79584\n",
+ "[3713]\tvalidation_0-rmse:1.79562\n",
+ "[3714]\tvalidation_0-rmse:1.79546\n",
+ "[3715]\tvalidation_0-rmse:1.79525\n",
+ "[3716]\tvalidation_0-rmse:1.79492\n",
+ "[3717]\tvalidation_0-rmse:1.79460\n",
+ "[3718]\tvalidation_0-rmse:1.79448\n",
+ "[3719]\tvalidation_0-rmse:1.79424\n",
+ "[3720]\tvalidation_0-rmse:1.79412\n",
+ "[3721]\tvalidation_0-rmse:1.79376\n",
+ "[3722]\tvalidation_0-rmse:1.79368\n",
+ "[3723]\tvalidation_0-rmse:1.79344\n",
+ "[3724]\tvalidation_0-rmse:1.79333\n",
+ "[3725]\tvalidation_0-rmse:1.79329\n",
+ "[3726]\tvalidation_0-rmse:1.79323\n",
+ "[3727]\tvalidation_0-rmse:1.79307\n",
+ "[3728]\tvalidation_0-rmse:1.79292\n",
+ "[3729]\tvalidation_0-rmse:1.79268\n",
+ "[3730]\tvalidation_0-rmse:1.79254\n",
+ "[3731]\tvalidation_0-rmse:1.79222\n",
+ "[3732]\tvalidation_0-rmse:1.79176\n",
+ "[3733]\tvalidation_0-rmse:1.79149\n",
+ "[3734]\tvalidation_0-rmse:1.79130\n",
+ "[3735]\tvalidation_0-rmse:1.79108\n",
+ "[3736]\tvalidation_0-rmse:1.79066\n",
+ "[3737]\tvalidation_0-rmse:1.79054\n",
+ "[3738]\tvalidation_0-rmse:1.79024\n",
+ "[3739]\tvalidation_0-rmse:1.79010\n",
+ "[3740]\tvalidation_0-rmse:1.78999\n",
+ "[3741]\tvalidation_0-rmse:1.78972\n",
+ "[3742]\tvalidation_0-rmse:1.78937\n",
+ "[3743]\tvalidation_0-rmse:1.78915\n",
+ "[3744]\tvalidation_0-rmse:1.78885\n",
+ "[3745]\tvalidation_0-rmse:1.78861\n",
+ "[3746]\tvalidation_0-rmse:1.78834\n",
+ "[3747]\tvalidation_0-rmse:1.78785\n",
+ "[3748]\tvalidation_0-rmse:1.78769\n",
+ "[3749]\tvalidation_0-rmse:1.78714\n",
+ "[3750]\tvalidation_0-rmse:1.78693\n",
+ "[3751]\tvalidation_0-rmse:1.78679\n",
+ "[3752]\tvalidation_0-rmse:1.78644\n",
+ "[3753]\tvalidation_0-rmse:1.78628\n",
+ "[3754]\tvalidation_0-rmse:1.78579\n",
+ "[3755]\tvalidation_0-rmse:1.78568\n",
+ "[3756]\tvalidation_0-rmse:1.78548\n",
+ "[3757]\tvalidation_0-rmse:1.78528\n",
+ "[3758]\tvalidation_0-rmse:1.78516\n",
+ "[3759]\tvalidation_0-rmse:1.78487\n",
+ "[3760]\tvalidation_0-rmse:1.78454\n",
+ "[3761]\tvalidation_0-rmse:1.78443\n",
+ "[3762]\tvalidation_0-rmse:1.78417\n",
+ "[3763]\tvalidation_0-rmse:1.78400\n",
+ "[3764]\tvalidation_0-rmse:1.78377\n",
+ "[3765]\tvalidation_0-rmse:1.78360\n",
+ "[3766]\tvalidation_0-rmse:1.78350\n",
+ "[3767]\tvalidation_0-rmse:1.78328\n",
+ "[3768]\tvalidation_0-rmse:1.78298\n",
+ "[3769]\tvalidation_0-rmse:1.78272\n",
+ "[3770]\tvalidation_0-rmse:1.78253\n",
+ "[3771]\tvalidation_0-rmse:1.78223\n",
+ "[3772]\tvalidation_0-rmse:1.78210\n",
+ "[3773]\tvalidation_0-rmse:1.78181\n",
+ "[3774]\tvalidation_0-rmse:1.78166\n",
+ "[3775]\tvalidation_0-rmse:1.78140\n",
+ "[3776]\tvalidation_0-rmse:1.78116\n",
+ "[3777]\tvalidation_0-rmse:1.78092\n",
+ "[3778]\tvalidation_0-rmse:1.78076\n",
+ "[3779]\tvalidation_0-rmse:1.78056\n",
+ "[3780]\tvalidation_0-rmse:1.78031\n",
+ "[3781]\tvalidation_0-rmse:1.78006\n",
+ "[3782]\tvalidation_0-rmse:1.77945\n",
+ "[3783]\tvalidation_0-rmse:1.77916\n",
+ "[3784]\tvalidation_0-rmse:1.77896\n",
+ "[3785]\tvalidation_0-rmse:1.77860\n",
+ "[3786]\tvalidation_0-rmse:1.77841\n",
+ "[3787]\tvalidation_0-rmse:1.77831\n",
+ "[3788]\tvalidation_0-rmse:1.77799\n",
+ "[3789]\tvalidation_0-rmse:1.77775\n",
+ "[3790]\tvalidation_0-rmse:1.77750\n",
+ "[3791]\tvalidation_0-rmse:1.77724\n",
+ "[3792]\tvalidation_0-rmse:1.77704\n",
+ "[3793]\tvalidation_0-rmse:1.77681\n",
+ "[3794]\tvalidation_0-rmse:1.77659\n",
+ "[3795]\tvalidation_0-rmse:1.77631\n",
+ "[3796]\tvalidation_0-rmse:1.77603\n",
+ "[3797]\tvalidation_0-rmse:1.77577\n",
+ "[3798]\tvalidation_0-rmse:1.77557\n",
+ "[3799]\tvalidation_0-rmse:1.77529\n",
+ "[3800]\tvalidation_0-rmse:1.77505\n",
+ "[3801]\tvalidation_0-rmse:1.77458\n",
+ "[3802]\tvalidation_0-rmse:1.77423\n",
+ "[3803]\tvalidation_0-rmse:1.77413\n",
+ "[3804]\tvalidation_0-rmse:1.77398\n",
+ "[3805]\tvalidation_0-rmse:1.77375\n",
+ "[3806]\tvalidation_0-rmse:1.77362\n",
+ "[3807]\tvalidation_0-rmse:1.77348\n",
+ "[3808]\tvalidation_0-rmse:1.77312\n",
+ "[3809]\tvalidation_0-rmse:1.77290\n",
+ "[3810]\tvalidation_0-rmse:1.77267\n",
+ "[3811]\tvalidation_0-rmse:1.77259\n",
+ "[3812]\tvalidation_0-rmse:1.77250\n",
+ "[3813]\tvalidation_0-rmse:1.77228\n",
+ "[3814]\tvalidation_0-rmse:1.77214\n",
+ "[3815]\tvalidation_0-rmse:1.77175\n",
+ "[3816]\tvalidation_0-rmse:1.77152\n",
+ "[3817]\tvalidation_0-rmse:1.77131\n",
+ "[3818]\tvalidation_0-rmse:1.77114\n",
+ "[3819]\tvalidation_0-rmse:1.77094\n",
+ "[3820]\tvalidation_0-rmse:1.77081\n",
+ "[3821]\tvalidation_0-rmse:1.77055\n",
+ "[3822]\tvalidation_0-rmse:1.77035\n",
+ "[3823]\tvalidation_0-rmse:1.77022\n",
+ "[3824]\tvalidation_0-rmse:1.77016\n",
+ "[3825]\tvalidation_0-rmse:1.76998\n",
+ "[3826]\tvalidation_0-rmse:1.76993\n",
+ "[3827]\tvalidation_0-rmse:1.76970\n",
+ "[3828]\tvalidation_0-rmse:1.76952\n",
+ "[3829]\tvalidation_0-rmse:1.76942\n",
+ "[3830]\tvalidation_0-rmse:1.76897\n",
+ "[3831]\tvalidation_0-rmse:1.76894\n",
+ "[3832]\tvalidation_0-rmse:1.76876\n",
+ "[3833]\tvalidation_0-rmse:1.76856\n",
+ "[3834]\tvalidation_0-rmse:1.76842\n",
+ "[3835]\tvalidation_0-rmse:1.76803\n",
+ "[3836]\tvalidation_0-rmse:1.76772\n",
+ "[3837]\tvalidation_0-rmse:1.76748\n",
+ "[3838]\tvalidation_0-rmse:1.76710\n",
+ "[3839]\tvalidation_0-rmse:1.76689\n",
+ "[3840]\tvalidation_0-rmse:1.76670\n",
+ "[3841]\tvalidation_0-rmse:1.76662\n",
+ "[3842]\tvalidation_0-rmse:1.76645\n",
+ "[3843]\tvalidation_0-rmse:1.76635\n",
+ "[3844]\tvalidation_0-rmse:1.76629\n",
+ "[3845]\tvalidation_0-rmse:1.76611\n",
+ "[3846]\tvalidation_0-rmse:1.76593\n",
+ "[3847]\tvalidation_0-rmse:1.76563\n",
+ "[3848]\tvalidation_0-rmse:1.76548\n",
+ "[3849]\tvalidation_0-rmse:1.76541\n",
+ "[3850]\tvalidation_0-rmse:1.76501\n",
+ "[3851]\tvalidation_0-rmse:1.76490\n",
+ "[3852]\tvalidation_0-rmse:1.76456\n",
+ "[3853]\tvalidation_0-rmse:1.76428\n",
+ "[3854]\tvalidation_0-rmse:1.76394\n",
+ "[3855]\tvalidation_0-rmse:1.76363\n",
+ "[3856]\tvalidation_0-rmse:1.76346\n",
+ "[3857]\tvalidation_0-rmse:1.76325\n",
+ "[3858]\tvalidation_0-rmse:1.76301\n",
+ "[3859]\tvalidation_0-rmse:1.76287\n",
+ "[3860]\tvalidation_0-rmse:1.76284\n",
+ "[3861]\tvalidation_0-rmse:1.76255\n",
+ "[3862]\tvalidation_0-rmse:1.76243\n",
+ "[3863]\tvalidation_0-rmse:1.76221\n",
+ "[3864]\tvalidation_0-rmse:1.76190\n",
+ "[3865]\tvalidation_0-rmse:1.76151\n",
+ "[3866]\tvalidation_0-rmse:1.76138\n",
+ "[3867]\tvalidation_0-rmse:1.76112\n",
+ "[3868]\tvalidation_0-rmse:1.76078\n",
+ "[3869]\tvalidation_0-rmse:1.76059\n",
+ "[3870]\tvalidation_0-rmse:1.76026\n",
+ "[3871]\tvalidation_0-rmse:1.76007\n",
+ "[3872]\tvalidation_0-rmse:1.75987\n",
+ "[3873]\tvalidation_0-rmse:1.75963\n",
+ "[3874]\tvalidation_0-rmse:1.75932\n",
+ "[3875]\tvalidation_0-rmse:1.75911\n",
+ "[3876]\tvalidation_0-rmse:1.75892\n",
+ "[3877]\tvalidation_0-rmse:1.75866\n",
+ "[3878]\tvalidation_0-rmse:1.75860\n",
+ "[3879]\tvalidation_0-rmse:1.75822\n",
+ "[3880]\tvalidation_0-rmse:1.75791\n",
+ "[3881]\tvalidation_0-rmse:1.75758\n",
+ "[3882]\tvalidation_0-rmse:1.75732\n",
+ "[3883]\tvalidation_0-rmse:1.75720\n",
+ "[3884]\tvalidation_0-rmse:1.75698\n",
+ "[3885]\tvalidation_0-rmse:1.75673\n",
+ "[3886]\tvalidation_0-rmse:1.75633\n",
+ "[3887]\tvalidation_0-rmse:1.75618\n",
+ "[3888]\tvalidation_0-rmse:1.75606\n",
+ "[3889]\tvalidation_0-rmse:1.75582\n",
+ "[3890]\tvalidation_0-rmse:1.75562\n",
+ "[3891]\tvalidation_0-rmse:1.75534\n",
+ "[3892]\tvalidation_0-rmse:1.75513\n",
+ "[3893]\tvalidation_0-rmse:1.75489\n",
+ "[3894]\tvalidation_0-rmse:1.75474\n",
+ "[3895]\tvalidation_0-rmse:1.75457\n",
+ "[3896]\tvalidation_0-rmse:1.75434\n",
+ "[3897]\tvalidation_0-rmse:1.75410\n",
+ "[3898]\tvalidation_0-rmse:1.75389\n",
+ "[3899]\tvalidation_0-rmse:1.75361\n",
+ "[3900]\tvalidation_0-rmse:1.75313\n",
+ "[3901]\tvalidation_0-rmse:1.75291\n",
+ "[3902]\tvalidation_0-rmse:1.75257\n",
+ "[3903]\tvalidation_0-rmse:1.75235\n",
+ "[3904]\tvalidation_0-rmse:1.75207\n",
+ "[3905]\tvalidation_0-rmse:1.75185\n",
+ "[3906]\tvalidation_0-rmse:1.75175\n",
+ "[3907]\tvalidation_0-rmse:1.75155\n",
+ "[3908]\tvalidation_0-rmse:1.75124\n",
+ "[3909]\tvalidation_0-rmse:1.75101\n",
+ "[3910]\tvalidation_0-rmse:1.75076\n",
+ "[3911]\tvalidation_0-rmse:1.75056\n",
+ "[3912]\tvalidation_0-rmse:1.75043\n",
+ "[3913]\tvalidation_0-rmse:1.75018\n",
+ "[3914]\tvalidation_0-rmse:1.74980\n",
+ "[3915]\tvalidation_0-rmse:1.74958\n",
+ "[3916]\tvalidation_0-rmse:1.74936\n",
+ "[3917]\tvalidation_0-rmse:1.74914\n",
+ "[3918]\tvalidation_0-rmse:1.74903\n",
+ "[3919]\tvalidation_0-rmse:1.74890\n",
+ "[3920]\tvalidation_0-rmse:1.74858\n",
+ "[3921]\tvalidation_0-rmse:1.74840\n",
+ "[3922]\tvalidation_0-rmse:1.74822\n",
+ "[3923]\tvalidation_0-rmse:1.74811\n",
+ "[3924]\tvalidation_0-rmse:1.74794\n",
+ "[3925]\tvalidation_0-rmse:1.74773\n",
+ "[3926]\tvalidation_0-rmse:1.74763\n",
+ "[3927]\tvalidation_0-rmse:1.74747\n",
+ "[3928]\tvalidation_0-rmse:1.74733\n",
+ "[3929]\tvalidation_0-rmse:1.74699\n",
+ "[3930]\tvalidation_0-rmse:1.74633\n",
+ "[3931]\tvalidation_0-rmse:1.74622\n",
+ "[3932]\tvalidation_0-rmse:1.74599\n",
+ "[3933]\tvalidation_0-rmse:1.74579\n",
+ "[3934]\tvalidation_0-rmse:1.74569\n",
+ "[3935]\tvalidation_0-rmse:1.74555\n",
+ "[3936]\tvalidation_0-rmse:1.74549\n",
+ "[3937]\tvalidation_0-rmse:1.74517\n",
+ "[3938]\tvalidation_0-rmse:1.74503\n",
+ "[3939]\tvalidation_0-rmse:1.74475\n",
+ "[3940]\tvalidation_0-rmse:1.74440\n",
+ "[3941]\tvalidation_0-rmse:1.74425\n",
+ "[3942]\tvalidation_0-rmse:1.74396\n",
+ "[3943]\tvalidation_0-rmse:1.74386\n",
+ "[3944]\tvalidation_0-rmse:1.74354\n",
+ "[3945]\tvalidation_0-rmse:1.74336\n",
+ "[3946]\tvalidation_0-rmse:1.74323\n",
+ "[3947]\tvalidation_0-rmse:1.74306\n",
+ "[3948]\tvalidation_0-rmse:1.74274\n",
+ "[3949]\tvalidation_0-rmse:1.74235\n",
+ "[3950]\tvalidation_0-rmse:1.74218\n",
+ "[3951]\tvalidation_0-rmse:1.74175\n",
+ "[3952]\tvalidation_0-rmse:1.74146\n",
+ "[3953]\tvalidation_0-rmse:1.74111\n",
+ "[3954]\tvalidation_0-rmse:1.74096\n",
+ "[3955]\tvalidation_0-rmse:1.74087\n",
+ "[3956]\tvalidation_0-rmse:1.74050\n",
+ "[3957]\tvalidation_0-rmse:1.74028\n",
+ "[3958]\tvalidation_0-rmse:1.74009\n",
+ "[3959]\tvalidation_0-rmse:1.73985\n",
+ "[3960]\tvalidation_0-rmse:1.73974\n",
+ "[3961]\tvalidation_0-rmse:1.73953\n",
+ "[3962]\tvalidation_0-rmse:1.73947\n",
+ "[3963]\tvalidation_0-rmse:1.73927\n",
+ "[3964]\tvalidation_0-rmse:1.73896\n",
+ "[3965]\tvalidation_0-rmse:1.73867\n",
+ "[3966]\tvalidation_0-rmse:1.73838\n",
+ "[3967]\tvalidation_0-rmse:1.73812\n",
+ "[3968]\tvalidation_0-rmse:1.73780\n",
+ "[3969]\tvalidation_0-rmse:1.73744\n",
+ "[3970]\tvalidation_0-rmse:1.73735\n",
+ "[3971]\tvalidation_0-rmse:1.73706\n",
+ "[3972]\tvalidation_0-rmse:1.73690\n",
+ "[3973]\tvalidation_0-rmse:1.73675\n",
+ "[3974]\tvalidation_0-rmse:1.73668\n",
+ "[3975]\tvalidation_0-rmse:1.73628\n",
+ "[3976]\tvalidation_0-rmse:1.73599\n",
+ "[3977]\tvalidation_0-rmse:1.73566\n",
+ "[3978]\tvalidation_0-rmse:1.73537\n",
+ "[3979]\tvalidation_0-rmse:1.73529\n",
+ "[3980]\tvalidation_0-rmse:1.73506\n",
+ "[3981]\tvalidation_0-rmse:1.73482\n",
+ "[3982]\tvalidation_0-rmse:1.73456\n",
+ "[3983]\tvalidation_0-rmse:1.73436\n",
+ "[3984]\tvalidation_0-rmse:1.73419\n",
+ "[3985]\tvalidation_0-rmse:1.73395\n",
+ "[3986]\tvalidation_0-rmse:1.73369\n",
+ "[3987]\tvalidation_0-rmse:1.73352\n",
+ "[3988]\tvalidation_0-rmse:1.73339\n",
+ "[3989]\tvalidation_0-rmse:1.73335\n",
+ "[3990]\tvalidation_0-rmse:1.73290\n",
+ "[3991]\tvalidation_0-rmse:1.73272\n",
+ "[3992]\tvalidation_0-rmse:1.73256\n",
+ "[3993]\tvalidation_0-rmse:1.73222\n",
+ "[3994]\tvalidation_0-rmse:1.73196\n",
+ "[3995]\tvalidation_0-rmse:1.73161\n",
+ "[3996]\tvalidation_0-rmse:1.73144\n",
+ "[3997]\tvalidation_0-rmse:1.73130\n",
+ "[3998]\tvalidation_0-rmse:1.73110\n",
+ "[3999]\tvalidation_0-rmse:1.73094\n",
+ "[4000]\tvalidation_0-rmse:1.73064\n",
+ "[4001]\tvalidation_0-rmse:1.73046\n",
+ "[4002]\tvalidation_0-rmse:1.73018\n",
+ "[4003]\tvalidation_0-rmse:1.72995\n",
+ "[4004]\tvalidation_0-rmse:1.72967\n",
+ "[4005]\tvalidation_0-rmse:1.72953\n",
+ "[4006]\tvalidation_0-rmse:1.72906\n",
+ "[4007]\tvalidation_0-rmse:1.72894\n",
+ "[4008]\tvalidation_0-rmse:1.72869\n",
+ "[4009]\tvalidation_0-rmse:1.72840\n",
+ "[4010]\tvalidation_0-rmse:1.72811\n",
+ "[4011]\tvalidation_0-rmse:1.72788\n",
+ "[4012]\tvalidation_0-rmse:1.72744\n",
+ "[4013]\tvalidation_0-rmse:1.72726\n",
+ "[4014]\tvalidation_0-rmse:1.72708\n",
+ "[4015]\tvalidation_0-rmse:1.72691\n",
+ "[4016]\tvalidation_0-rmse:1.72677\n",
+ "[4017]\tvalidation_0-rmse:1.72659\n",
+ "[4018]\tvalidation_0-rmse:1.72635\n",
+ "[4019]\tvalidation_0-rmse:1.72601\n",
+ "[4020]\tvalidation_0-rmse:1.72572\n",
+ "[4021]\tvalidation_0-rmse:1.72568\n",
+ "[4022]\tvalidation_0-rmse:1.72546\n",
+ "[4023]\tvalidation_0-rmse:1.72511\n",
+ "[4024]\tvalidation_0-rmse:1.72499\n",
+ "[4025]\tvalidation_0-rmse:1.72481\n",
+ "[4026]\tvalidation_0-rmse:1.72454\n",
+ "[4027]\tvalidation_0-rmse:1.72444\n",
+ "[4028]\tvalidation_0-rmse:1.72422\n",
+ "[4029]\tvalidation_0-rmse:1.72393\n",
+ "[4030]\tvalidation_0-rmse:1.72362\n",
+ "[4031]\tvalidation_0-rmse:1.72340\n",
+ "[4032]\tvalidation_0-rmse:1.72322\n",
+ "[4033]\tvalidation_0-rmse:1.72312\n",
+ "[4034]\tvalidation_0-rmse:1.72308\n",
+ "[4035]\tvalidation_0-rmse:1.72289\n",
+ "[4036]\tvalidation_0-rmse:1.72287\n",
+ "[4037]\tvalidation_0-rmse:1.72268\n",
+ "[4038]\tvalidation_0-rmse:1.72249\n",
+ "[4039]\tvalidation_0-rmse:1.72238\n",
+ "[4040]\tvalidation_0-rmse:1.72227\n",
+ "[4041]\tvalidation_0-rmse:1.72212\n",
+ "[4042]\tvalidation_0-rmse:1.72183\n",
+ "[4043]\tvalidation_0-rmse:1.72169\n",
+ "[4044]\tvalidation_0-rmse:1.72145\n",
+ "[4045]\tvalidation_0-rmse:1.72131\n",
+ "[4046]\tvalidation_0-rmse:1.72112\n",
+ "[4047]\tvalidation_0-rmse:1.72093\n",
+ "[4048]\tvalidation_0-rmse:1.72068\n",
+ "[4049]\tvalidation_0-rmse:1.72031\n",
+ "[4050]\tvalidation_0-rmse:1.71998\n",
+ "[4051]\tvalidation_0-rmse:1.71982\n",
+ "[4052]\tvalidation_0-rmse:1.71962\n",
+ "[4053]\tvalidation_0-rmse:1.71939\n",
+ "[4054]\tvalidation_0-rmse:1.71907\n",
+ "[4055]\tvalidation_0-rmse:1.71888\n",
+ "[4056]\tvalidation_0-rmse:1.71863\n",
+ "[4057]\tvalidation_0-rmse:1.71831\n",
+ "[4058]\tvalidation_0-rmse:1.71819\n",
+ "[4059]\tvalidation_0-rmse:1.71803\n",
+ "[4060]\tvalidation_0-rmse:1.71785\n",
+ "[4061]\tvalidation_0-rmse:1.71772\n",
+ "[4062]\tvalidation_0-rmse:1.71738\n",
+ "[4063]\tvalidation_0-rmse:1.71716\n",
+ "[4064]\tvalidation_0-rmse:1.71714\n",
+ "[4065]\tvalidation_0-rmse:1.71712\n",
+ "[4066]\tvalidation_0-rmse:1.71691\n",
+ "[4067]\tvalidation_0-rmse:1.71672\n",
+ "[4068]\tvalidation_0-rmse:1.71637\n",
+ "[4069]\tvalidation_0-rmse:1.71606\n",
+ "[4070]\tvalidation_0-rmse:1.71576\n",
+ "[4071]\tvalidation_0-rmse:1.71565\n",
+ "[4072]\tvalidation_0-rmse:1.71555\n",
+ "[4073]\tvalidation_0-rmse:1.71527\n",
+ "[4074]\tvalidation_0-rmse:1.71511\n",
+ "[4075]\tvalidation_0-rmse:1.71503\n",
+ "[4076]\tvalidation_0-rmse:1.71495\n",
+ "[4077]\tvalidation_0-rmse:1.71486\n",
+ "[4078]\tvalidation_0-rmse:1.71471\n",
+ "[4079]\tvalidation_0-rmse:1.71449\n",
+ "[4080]\tvalidation_0-rmse:1.71417\n",
+ "[4081]\tvalidation_0-rmse:1.71406\n",
+ "[4082]\tvalidation_0-rmse:1.71383\n",
+ "[4083]\tvalidation_0-rmse:1.71362\n",
+ "[4084]\tvalidation_0-rmse:1.71348\n",
+ "[4085]\tvalidation_0-rmse:1.71331\n",
+ "[4086]\tvalidation_0-rmse:1.71313\n",
+ "[4087]\tvalidation_0-rmse:1.71301\n",
+ "[4088]\tvalidation_0-rmse:1.71282\n",
+ "[4089]\tvalidation_0-rmse:1.71252\n",
+ "[4090]\tvalidation_0-rmse:1.71244\n",
+ "[4091]\tvalidation_0-rmse:1.71233\n",
+ "[4092]\tvalidation_0-rmse:1.71217\n",
+ "[4093]\tvalidation_0-rmse:1.71202\n",
+ "[4094]\tvalidation_0-rmse:1.71169\n",
+ "[4095]\tvalidation_0-rmse:1.71151\n",
+ "[4096]\tvalidation_0-rmse:1.71140\n",
+ "[4097]\tvalidation_0-rmse:1.71130\n",
+ "[4098]\tvalidation_0-rmse:1.71117\n",
+ "[4099]\tvalidation_0-rmse:1.71092\n",
+ "[4100]\tvalidation_0-rmse:1.71068\n",
+ "[4101]\tvalidation_0-rmse:1.71066\n",
+ "[4102]\tvalidation_0-rmse:1.71039\n",
+ "[4103]\tvalidation_0-rmse:1.71021\n",
+ "[4104]\tvalidation_0-rmse:1.71000\n",
+ "[4105]\tvalidation_0-rmse:1.70990\n",
+ "[4106]\tvalidation_0-rmse:1.70986\n",
+ "[4107]\tvalidation_0-rmse:1.70973\n",
+ "[4108]\tvalidation_0-rmse:1.70971\n",
+ "[4109]\tvalidation_0-rmse:1.70961\n",
+ "[4110]\tvalidation_0-rmse:1.70931\n",
+ "[4111]\tvalidation_0-rmse:1.70924\n",
+ "[4112]\tvalidation_0-rmse:1.70909\n",
+ "[4113]\tvalidation_0-rmse:1.70900\n",
+ "[4114]\tvalidation_0-rmse:1.70889\n",
+ "[4115]\tvalidation_0-rmse:1.70873\n",
+ "[4116]\tvalidation_0-rmse:1.70849\n",
+ "[4117]\tvalidation_0-rmse:1.70846\n",
+ "[4118]\tvalidation_0-rmse:1.70833\n",
+ "[4119]\tvalidation_0-rmse:1.70802\n",
+ "[4120]\tvalidation_0-rmse:1.70775\n",
+ "[4121]\tvalidation_0-rmse:1.70739\n",
+ "[4122]\tvalidation_0-rmse:1.70711\n",
+ "[4123]\tvalidation_0-rmse:1.70686\n",
+ "[4124]\tvalidation_0-rmse:1.70647\n",
+ "[4125]\tvalidation_0-rmse:1.70616\n",
+ "[4126]\tvalidation_0-rmse:1.70601\n",
+ "[4127]\tvalidation_0-rmse:1.70573\n",
+ "[4128]\tvalidation_0-rmse:1.70551\n",
+ "[4129]\tvalidation_0-rmse:1.70525\n",
+ "[4130]\tvalidation_0-rmse:1.70504\n",
+ "[4131]\tvalidation_0-rmse:1.70490\n",
+ "[4132]\tvalidation_0-rmse:1.70479\n",
+ "[4133]\tvalidation_0-rmse:1.70458\n",
+ "[4134]\tvalidation_0-rmse:1.70433\n",
+ "[4135]\tvalidation_0-rmse:1.70403\n",
+ "[4136]\tvalidation_0-rmse:1.70375\n",
+ "[4137]\tvalidation_0-rmse:1.70333\n",
+ "[4138]\tvalidation_0-rmse:1.70319\n",
+ "[4139]\tvalidation_0-rmse:1.70288\n",
+ "[4140]\tvalidation_0-rmse:1.70280\n",
+ "[4141]\tvalidation_0-rmse:1.70241\n",
+ "[4142]\tvalidation_0-rmse:1.70230\n",
+ "[4143]\tvalidation_0-rmse:1.70204\n",
+ "[4144]\tvalidation_0-rmse:1.70183\n",
+ "[4145]\tvalidation_0-rmse:1.70152\n",
+ "[4146]\tvalidation_0-rmse:1.70142\n",
+ "[4147]\tvalidation_0-rmse:1.70107\n",
+ "[4148]\tvalidation_0-rmse:1.70090\n",
+ "[4149]\tvalidation_0-rmse:1.70069\n",
+ "[4150]\tvalidation_0-rmse:1.70053\n",
+ "[4151]\tvalidation_0-rmse:1.70029\n",
+ "[4152]\tvalidation_0-rmse:1.70005\n",
+ "[4153]\tvalidation_0-rmse:1.69991\n",
+ "[4154]\tvalidation_0-rmse:1.69962\n",
+ "[4155]\tvalidation_0-rmse:1.69953\n",
+ "[4156]\tvalidation_0-rmse:1.69931\n",
+ "[4157]\tvalidation_0-rmse:1.69892\n",
+ "[4158]\tvalidation_0-rmse:1.69877\n",
+ "[4159]\tvalidation_0-rmse:1.69856\n",
+ "[4160]\tvalidation_0-rmse:1.69847\n",
+ "[4161]\tvalidation_0-rmse:1.69812\n",
+ "[4162]\tvalidation_0-rmse:1.69802\n",
+ "[4163]\tvalidation_0-rmse:1.69780\n",
+ "[4164]\tvalidation_0-rmse:1.69763\n",
+ "[4165]\tvalidation_0-rmse:1.69749\n",
+ "[4166]\tvalidation_0-rmse:1.69747\n",
+ "[4167]\tvalidation_0-rmse:1.69738\n",
+ "[4168]\tvalidation_0-rmse:1.69727\n",
+ "[4169]\tvalidation_0-rmse:1.69698\n",
+ "[4170]\tvalidation_0-rmse:1.69688\n",
+ "[4171]\tvalidation_0-rmse:1.69678\n",
+ "[4172]\tvalidation_0-rmse:1.69670\n",
+ "[4173]\tvalidation_0-rmse:1.69659\n",
+ "[4174]\tvalidation_0-rmse:1.69634\n",
+ "[4175]\tvalidation_0-rmse:1.69611\n",
+ "[4176]\tvalidation_0-rmse:1.69597\n",
+ "[4177]\tvalidation_0-rmse:1.69566\n",
+ "[4178]\tvalidation_0-rmse:1.69542\n",
+ "[4179]\tvalidation_0-rmse:1.69515\n",
+ "[4180]\tvalidation_0-rmse:1.69490\n",
+ "[4181]\tvalidation_0-rmse:1.69482\n",
+ "[4182]\tvalidation_0-rmse:1.69458\n",
+ "[4183]\tvalidation_0-rmse:1.69431\n",
+ "[4184]\tvalidation_0-rmse:1.69411\n",
+ "[4185]\tvalidation_0-rmse:1.69394\n",
+ "[4186]\tvalidation_0-rmse:1.69378\n",
+ "[4187]\tvalidation_0-rmse:1.69350\n",
+ "[4188]\tvalidation_0-rmse:1.69337\n",
+ "[4189]\tvalidation_0-rmse:1.69312\n",
+ "[4190]\tvalidation_0-rmse:1.69284\n",
+ "[4191]\tvalidation_0-rmse:1.69263\n",
+ "[4192]\tvalidation_0-rmse:1.69235\n",
+ "[4193]\tvalidation_0-rmse:1.69213\n",
+ "[4194]\tvalidation_0-rmse:1.69177\n",
+ "[4195]\tvalidation_0-rmse:1.69156\n",
+ "[4196]\tvalidation_0-rmse:1.69151\n",
+ "[4197]\tvalidation_0-rmse:1.69086\n",
+ "[4198]\tvalidation_0-rmse:1.69082\n",
+ "[4199]\tvalidation_0-rmse:1.69055\n",
+ "[4200]\tvalidation_0-rmse:1.69034\n",
+ "[4201]\tvalidation_0-rmse:1.69014\n",
+ "[4202]\tvalidation_0-rmse:1.68985\n",
+ "[4203]\tvalidation_0-rmse:1.68968\n",
+ "[4204]\tvalidation_0-rmse:1.68933\n",
+ "[4205]\tvalidation_0-rmse:1.68912\n",
+ "[4206]\tvalidation_0-rmse:1.68897\n",
+ "[4207]\tvalidation_0-rmse:1.68879\n",
+ "[4208]\tvalidation_0-rmse:1.68865\n",
+ "[4209]\tvalidation_0-rmse:1.68826\n",
+ "[4210]\tvalidation_0-rmse:1.68804\n",
+ "[4211]\tvalidation_0-rmse:1.68787\n",
+ "[4212]\tvalidation_0-rmse:1.68778\n",
+ "[4213]\tvalidation_0-rmse:1.68766\n",
+ "[4214]\tvalidation_0-rmse:1.68740\n",
+ "[4215]\tvalidation_0-rmse:1.68729\n",
+ "[4216]\tvalidation_0-rmse:1.68717\n",
+ "[4217]\tvalidation_0-rmse:1.68693\n",
+ "[4218]\tvalidation_0-rmse:1.68677\n",
+ "[4219]\tvalidation_0-rmse:1.68652\n",
+ "[4220]\tvalidation_0-rmse:1.68623\n",
+ "[4221]\tvalidation_0-rmse:1.68619\n",
+ "[4222]\tvalidation_0-rmse:1.68607\n",
+ "[4223]\tvalidation_0-rmse:1.68603\n",
+ "[4224]\tvalidation_0-rmse:1.68592\n",
+ "[4225]\tvalidation_0-rmse:1.68579\n",
+ "[4226]\tvalidation_0-rmse:1.68560\n",
+ "[4227]\tvalidation_0-rmse:1.68551\n",
+ "[4228]\tvalidation_0-rmse:1.68546\n",
+ "[4229]\tvalidation_0-rmse:1.68533\n",
+ "[4230]\tvalidation_0-rmse:1.68521\n",
+ "[4231]\tvalidation_0-rmse:1.68489\n",
+ "[4232]\tvalidation_0-rmse:1.68462\n",
+ "[4233]\tvalidation_0-rmse:1.68446\n",
+ "[4234]\tvalidation_0-rmse:1.68427\n",
+ "[4235]\tvalidation_0-rmse:1.68417\n",
+ "[4236]\tvalidation_0-rmse:1.68405\n",
+ "[4237]\tvalidation_0-rmse:1.68393\n",
+ "[4238]\tvalidation_0-rmse:1.68386\n",
+ "[4239]\tvalidation_0-rmse:1.68370\n",
+ "[4240]\tvalidation_0-rmse:1.68353\n",
+ "[4241]\tvalidation_0-rmse:1.68339\n",
+ "[4242]\tvalidation_0-rmse:1.68322\n",
+ "[4243]\tvalidation_0-rmse:1.68306\n",
+ "[4244]\tvalidation_0-rmse:1.68297\n",
+ "[4245]\tvalidation_0-rmse:1.68288\n",
+ "[4246]\tvalidation_0-rmse:1.68280\n",
+ "[4247]\tvalidation_0-rmse:1.68258\n",
+ "[4248]\tvalidation_0-rmse:1.68256\n",
+ "[4249]\tvalidation_0-rmse:1.68222\n",
+ "[4250]\tvalidation_0-rmse:1.68213\n",
+ "[4251]\tvalidation_0-rmse:1.68198\n",
+ "[4252]\tvalidation_0-rmse:1.68181\n",
+ "[4253]\tvalidation_0-rmse:1.68132\n",
+ "[4254]\tvalidation_0-rmse:1.68113\n",
+ "[4255]\tvalidation_0-rmse:1.68102\n",
+ "[4256]\tvalidation_0-rmse:1.68093\n",
+ "[4257]\tvalidation_0-rmse:1.68056\n",
+ "[4258]\tvalidation_0-rmse:1.68031\n",
+ "[4259]\tvalidation_0-rmse:1.67999\n",
+ "[4260]\tvalidation_0-rmse:1.67969\n",
+ "[4261]\tvalidation_0-rmse:1.67938\n",
+ "[4262]\tvalidation_0-rmse:1.67920\n",
+ "[4263]\tvalidation_0-rmse:1.67906\n",
+ "[4264]\tvalidation_0-rmse:1.67887\n",
+ "[4265]\tvalidation_0-rmse:1.67857\n",
+ "[4266]\tvalidation_0-rmse:1.67832\n",
+ "[4267]\tvalidation_0-rmse:1.67815\n",
+ "[4268]\tvalidation_0-rmse:1.67796\n",
+ "[4269]\tvalidation_0-rmse:1.67776\n",
+ "[4270]\tvalidation_0-rmse:1.67745\n",
+ "[4271]\tvalidation_0-rmse:1.67721\n",
+ "[4272]\tvalidation_0-rmse:1.67686\n",
+ "[4273]\tvalidation_0-rmse:1.67662\n",
+ "[4274]\tvalidation_0-rmse:1.67645\n",
+ "[4275]\tvalidation_0-rmse:1.67631\n",
+ "[4276]\tvalidation_0-rmse:1.67612\n",
+ "[4277]\tvalidation_0-rmse:1.67605\n",
+ "[4278]\tvalidation_0-rmse:1.67582\n",
+ "[4279]\tvalidation_0-rmse:1.67574\n",
+ "[4280]\tvalidation_0-rmse:1.67545\n",
+ "[4281]\tvalidation_0-rmse:1.67521\n",
+ "[4282]\tvalidation_0-rmse:1.67499\n",
+ "[4283]\tvalidation_0-rmse:1.67461\n",
+ "[4284]\tvalidation_0-rmse:1.67439\n",
+ "[4285]\tvalidation_0-rmse:1.67411\n",
+ "[4286]\tvalidation_0-rmse:1.67396\n",
+ "[4287]\tvalidation_0-rmse:1.67390\n",
+ "[4288]\tvalidation_0-rmse:1.67383\n",
+ "[4289]\tvalidation_0-rmse:1.67369\n",
+ "[4290]\tvalidation_0-rmse:1.67353\n",
+ "[4291]\tvalidation_0-rmse:1.67339\n",
+ "[4292]\tvalidation_0-rmse:1.67332\n",
+ "[4293]\tvalidation_0-rmse:1.67325\n",
+ "[4294]\tvalidation_0-rmse:1.67317\n",
+ "[4295]\tvalidation_0-rmse:1.67305\n",
+ "[4296]\tvalidation_0-rmse:1.67295\n",
+ "[4297]\tvalidation_0-rmse:1.67279\n",
+ "[4298]\tvalidation_0-rmse:1.67252\n",
+ "[4299]\tvalidation_0-rmse:1.67245\n",
+ "[4300]\tvalidation_0-rmse:1.67220\n",
+ "[4301]\tvalidation_0-rmse:1.67212\n",
+ "[4302]\tvalidation_0-rmse:1.67195\n",
+ "[4303]\tvalidation_0-rmse:1.67139\n",
+ "[4304]\tvalidation_0-rmse:1.67112\n",
+ "[4305]\tvalidation_0-rmse:1.67093\n",
+ "[4306]\tvalidation_0-rmse:1.67073\n",
+ "[4307]\tvalidation_0-rmse:1.67054\n",
+ "[4308]\tvalidation_0-rmse:1.67009\n",
+ "[4309]\tvalidation_0-rmse:1.66993\n",
+ "[4310]\tvalidation_0-rmse:1.66957\n",
+ "[4311]\tvalidation_0-rmse:1.66907\n",
+ "[4312]\tvalidation_0-rmse:1.66894\n",
+ "[4313]\tvalidation_0-rmse:1.66879\n",
+ "[4314]\tvalidation_0-rmse:1.66853\n",
+ "[4315]\tvalidation_0-rmse:1.66831\n",
+ "[4316]\tvalidation_0-rmse:1.66817\n",
+ "[4317]\tvalidation_0-rmse:1.66808\n",
+ "[4318]\tvalidation_0-rmse:1.66792\n",
+ "[4319]\tvalidation_0-rmse:1.66775\n",
+ "[4320]\tvalidation_0-rmse:1.66755\n",
+ "[4321]\tvalidation_0-rmse:1.66730\n",
+ "[4322]\tvalidation_0-rmse:1.66708\n",
+ "[4323]\tvalidation_0-rmse:1.66693\n",
+ "[4324]\tvalidation_0-rmse:1.66678\n",
+ "[4325]\tvalidation_0-rmse:1.66672\n",
+ "[4326]\tvalidation_0-rmse:1.66658\n",
+ "[4327]\tvalidation_0-rmse:1.66649\n",
+ "[4328]\tvalidation_0-rmse:1.66629\n",
+ "[4329]\tvalidation_0-rmse:1.66620\n",
+ "[4330]\tvalidation_0-rmse:1.66601\n",
+ "[4331]\tvalidation_0-rmse:1.66583\n",
+ "[4332]\tvalidation_0-rmse:1.66559\n",
+ "[4333]\tvalidation_0-rmse:1.66529\n",
+ "[4334]\tvalidation_0-rmse:1.66511\n",
+ "[4335]\tvalidation_0-rmse:1.66502\n",
+ "[4336]\tvalidation_0-rmse:1.66485\n",
+ "[4337]\tvalidation_0-rmse:1.66473\n",
+ "[4338]\tvalidation_0-rmse:1.66462\n",
+ "[4339]\tvalidation_0-rmse:1.66438\n",
+ "[4340]\tvalidation_0-rmse:1.66417\n",
+ "[4341]\tvalidation_0-rmse:1.66397\n",
+ "[4342]\tvalidation_0-rmse:1.66380\n",
+ "[4343]\tvalidation_0-rmse:1.66335\n",
+ "[4344]\tvalidation_0-rmse:1.66329\n",
+ "[4345]\tvalidation_0-rmse:1.66314\n",
+ "[4346]\tvalidation_0-rmse:1.66302\n",
+ "[4347]\tvalidation_0-rmse:1.66293\n",
+ "[4348]\tvalidation_0-rmse:1.66279\n",
+ "[4349]\tvalidation_0-rmse:1.66262\n",
+ "[4350]\tvalidation_0-rmse:1.66239\n",
+ "[4351]\tvalidation_0-rmse:1.66219\n",
+ "[4352]\tvalidation_0-rmse:1.66205\n",
+ "[4353]\tvalidation_0-rmse:1.66172\n",
+ "[4354]\tvalidation_0-rmse:1.66156\n",
+ "[4355]\tvalidation_0-rmse:1.66140\n",
+ "[4356]\tvalidation_0-rmse:1.66121\n",
+ "[4357]\tvalidation_0-rmse:1.66108\n",
+ "[4358]\tvalidation_0-rmse:1.66088\n",
+ "[4359]\tvalidation_0-rmse:1.66063\n",
+ "[4360]\tvalidation_0-rmse:1.66052\n",
+ "[4361]\tvalidation_0-rmse:1.66039\n",
+ "[4362]\tvalidation_0-rmse:1.66013\n",
+ "[4363]\tvalidation_0-rmse:1.66000\n",
+ "[4364]\tvalidation_0-rmse:1.65984\n",
+ "[4365]\tvalidation_0-rmse:1.65970\n",
+ "[4366]\tvalidation_0-rmse:1.65962\n",
+ "[4367]\tvalidation_0-rmse:1.65940\n",
+ "[4368]\tvalidation_0-rmse:1.65926\n",
+ "[4369]\tvalidation_0-rmse:1.65913\n",
+ "[4370]\tvalidation_0-rmse:1.65902\n",
+ "[4371]\tvalidation_0-rmse:1.65876\n",
+ "[4372]\tvalidation_0-rmse:1.65868\n",
+ "[4373]\tvalidation_0-rmse:1.65846\n",
+ "[4374]\tvalidation_0-rmse:1.65840\n",
+ "[4375]\tvalidation_0-rmse:1.65806\n",
+ "[4376]\tvalidation_0-rmse:1.65785\n",
+ "[4377]\tvalidation_0-rmse:1.65744\n",
+ "[4378]\tvalidation_0-rmse:1.65727\n",
+ "[4379]\tvalidation_0-rmse:1.65711\n",
+ "[4380]\tvalidation_0-rmse:1.65709\n",
+ "[4381]\tvalidation_0-rmse:1.65695\n",
+ "[4382]\tvalidation_0-rmse:1.65675\n",
+ "[4383]\tvalidation_0-rmse:1.65633\n",
+ "[4384]\tvalidation_0-rmse:1.65610\n",
+ "[4385]\tvalidation_0-rmse:1.65602\n",
+ "[4386]\tvalidation_0-rmse:1.65592\n",
+ "[4387]\tvalidation_0-rmse:1.65556\n",
+ "[4388]\tvalidation_0-rmse:1.65530\n",
+ "[4389]\tvalidation_0-rmse:1.65514\n",
+ "[4390]\tvalidation_0-rmse:1.65492\n",
+ "[4391]\tvalidation_0-rmse:1.65460\n",
+ "[4392]\tvalidation_0-rmse:1.65427\n",
+ "[4393]\tvalidation_0-rmse:1.65400\n",
+ "[4394]\tvalidation_0-rmse:1.65379\n",
+ "[4395]\tvalidation_0-rmse:1.65361\n",
+ "[4396]\tvalidation_0-rmse:1.65357\n",
+ "[4397]\tvalidation_0-rmse:1.65330\n",
+ "[4398]\tvalidation_0-rmse:1.65311\n",
+ "[4399]\tvalidation_0-rmse:1.65274\n",
+ "[4400]\tvalidation_0-rmse:1.65255\n",
+ "[4401]\tvalidation_0-rmse:1.65229\n",
+ "[4402]\tvalidation_0-rmse:1.65211\n",
+ "[4403]\tvalidation_0-rmse:1.65180\n",
+ "[4404]\tvalidation_0-rmse:1.65156\n",
+ "[4405]\tvalidation_0-rmse:1.65141\n",
+ "[4406]\tvalidation_0-rmse:1.65114\n",
+ "[4407]\tvalidation_0-rmse:1.65105\n",
+ "[4408]\tvalidation_0-rmse:1.65076\n",
+ "[4409]\tvalidation_0-rmse:1.65049\n",
+ "[4410]\tvalidation_0-rmse:1.65043\n",
+ "[4411]\tvalidation_0-rmse:1.65029\n",
+ "[4412]\tvalidation_0-rmse:1.65020\n",
+ "[4413]\tvalidation_0-rmse:1.65009\n",
+ "[4414]\tvalidation_0-rmse:1.64987\n",
+ "[4415]\tvalidation_0-rmse:1.64986\n",
+ "[4416]\tvalidation_0-rmse:1.64978\n",
+ "[4417]\tvalidation_0-rmse:1.64970\n",
+ "[4418]\tvalidation_0-rmse:1.64958\n",
+ "[4419]\tvalidation_0-rmse:1.64908\n",
+ "[4420]\tvalidation_0-rmse:1.64880\n",
+ "[4421]\tvalidation_0-rmse:1.64855\n",
+ "[4422]\tvalidation_0-rmse:1.64826\n",
+ "[4423]\tvalidation_0-rmse:1.64810\n",
+ "[4424]\tvalidation_0-rmse:1.64781\n",
+ "[4425]\tvalidation_0-rmse:1.64762\n",
+ "[4426]\tvalidation_0-rmse:1.64741\n",
+ "[4427]\tvalidation_0-rmse:1.64731\n",
+ "[4428]\tvalidation_0-rmse:1.64721\n",
+ "[4429]\tvalidation_0-rmse:1.64689\n",
+ "[4430]\tvalidation_0-rmse:1.64668\n",
+ "[4431]\tvalidation_0-rmse:1.64644\n",
+ "[4432]\tvalidation_0-rmse:1.64633\n",
+ "[4433]\tvalidation_0-rmse:1.64620\n",
+ "[4434]\tvalidation_0-rmse:1.64599\n",
+ "[4435]\tvalidation_0-rmse:1.64577\n",
+ "[4436]\tvalidation_0-rmse:1.64571\n",
+ "[4437]\tvalidation_0-rmse:1.64563\n",
+ "[4438]\tvalidation_0-rmse:1.64540\n",
+ "[4439]\tvalidation_0-rmse:1.64521\n",
+ "[4440]\tvalidation_0-rmse:1.64483\n",
+ "[4441]\tvalidation_0-rmse:1.64461\n",
+ "[4442]\tvalidation_0-rmse:1.64451\n",
+ "[4443]\tvalidation_0-rmse:1.64438\n",
+ "[4444]\tvalidation_0-rmse:1.64415\n",
+ "[4445]\tvalidation_0-rmse:1.64388\n",
+ "[4446]\tvalidation_0-rmse:1.64380\n",
+ "[4447]\tvalidation_0-rmse:1.64361\n",
+ "[4448]\tvalidation_0-rmse:1.64348\n",
+ "[4449]\tvalidation_0-rmse:1.64322\n",
+ "[4450]\tvalidation_0-rmse:1.64293\n",
+ "[4451]\tvalidation_0-rmse:1.64271\n",
+ "[4452]\tvalidation_0-rmse:1.64247\n",
+ "[4453]\tvalidation_0-rmse:1.64230\n",
+ "[4454]\tvalidation_0-rmse:1.64207\n",
+ "[4455]\tvalidation_0-rmse:1.64194\n",
+ "[4456]\tvalidation_0-rmse:1.64182\n",
+ "[4457]\tvalidation_0-rmse:1.64165\n",
+ "[4458]\tvalidation_0-rmse:1.64156\n",
+ "[4459]\tvalidation_0-rmse:1.64095\n",
+ "[4460]\tvalidation_0-rmse:1.64066\n",
+ "[4461]\tvalidation_0-rmse:1.64045\n",
+ "[4462]\tvalidation_0-rmse:1.64036\n",
+ "[4463]\tvalidation_0-rmse:1.64003\n",
+ "[4464]\tvalidation_0-rmse:1.63987\n",
+ "[4465]\tvalidation_0-rmse:1.63949\n",
+ "[4466]\tvalidation_0-rmse:1.63924\n",
+ "[4467]\tvalidation_0-rmse:1.63902\n",
+ "[4468]\tvalidation_0-rmse:1.63887\n",
+ "[4469]\tvalidation_0-rmse:1.63869\n",
+ "[4470]\tvalidation_0-rmse:1.63839\n",
+ "[4471]\tvalidation_0-rmse:1.63818\n",
+ "[4472]\tvalidation_0-rmse:1.63781\n",
+ "[4473]\tvalidation_0-rmse:1.63763\n",
+ "[4474]\tvalidation_0-rmse:1.63729\n",
+ "[4475]\tvalidation_0-rmse:1.63711\n",
+ "[4476]\tvalidation_0-rmse:1.63687\n",
+ "[4477]\tvalidation_0-rmse:1.63660\n",
+ "[4478]\tvalidation_0-rmse:1.63639\n",
+ "[4479]\tvalidation_0-rmse:1.63625\n",
+ "[4480]\tvalidation_0-rmse:1.63616\n",
+ "[4481]\tvalidation_0-rmse:1.63593\n",
+ "[4482]\tvalidation_0-rmse:1.63570\n",
+ "[4483]\tvalidation_0-rmse:1.63561\n",
+ "[4484]\tvalidation_0-rmse:1.63552\n",
+ "[4485]\tvalidation_0-rmse:1.63529\n",
+ "[4486]\tvalidation_0-rmse:1.63512\n",
+ "[4487]\tvalidation_0-rmse:1.63494\n",
+ "[4488]\tvalidation_0-rmse:1.63481\n",
+ "[4489]\tvalidation_0-rmse:1.63440\n",
+ "[4490]\tvalidation_0-rmse:1.63434\n",
+ "[4491]\tvalidation_0-rmse:1.63415\n",
+ "[4492]\tvalidation_0-rmse:1.63405\n",
+ "[4493]\tvalidation_0-rmse:1.63368\n",
+ "[4494]\tvalidation_0-rmse:1.63354\n",
+ "[4495]\tvalidation_0-rmse:1.63341\n",
+ "[4496]\tvalidation_0-rmse:1.63324\n",
+ "[4497]\tvalidation_0-rmse:1.63316\n",
+ "[4498]\tvalidation_0-rmse:1.63295\n",
+ "[4499]\tvalidation_0-rmse:1.63278\n",
+ "[4500]\tvalidation_0-rmse:1.63249\n",
+ "[4501]\tvalidation_0-rmse:1.63239\n",
+ "[4502]\tvalidation_0-rmse:1.63221\n",
+ "[4503]\tvalidation_0-rmse:1.63211\n",
+ "[4504]\tvalidation_0-rmse:1.63197\n",
+ "[4505]\tvalidation_0-rmse:1.63180\n",
+ "[4506]\tvalidation_0-rmse:1.63165\n",
+ "[4507]\tvalidation_0-rmse:1.63148\n",
+ "[4508]\tvalidation_0-rmse:1.63101\n",
+ "[4509]\tvalidation_0-rmse:1.63082\n",
+ "[4510]\tvalidation_0-rmse:1.63076\n",
+ "[4511]\tvalidation_0-rmse:1.63065\n",
+ "[4512]\tvalidation_0-rmse:1.63043\n",
+ "[4513]\tvalidation_0-rmse:1.63024\n",
+ "[4514]\tvalidation_0-rmse:1.63010\n",
+ "[4515]\tvalidation_0-rmse:1.62991\n",
+ "[4516]\tvalidation_0-rmse:1.62985\n",
+ "[4517]\tvalidation_0-rmse:1.62959\n",
+ "[4518]\tvalidation_0-rmse:1.62940\n",
+ "[4519]\tvalidation_0-rmse:1.62911\n",
+ "[4520]\tvalidation_0-rmse:1.62892\n",
+ "[4521]\tvalidation_0-rmse:1.62879\n",
+ "[4522]\tvalidation_0-rmse:1.62832\n",
+ "[4523]\tvalidation_0-rmse:1.62807\n",
+ "[4524]\tvalidation_0-rmse:1.62783\n",
+ "[4525]\tvalidation_0-rmse:1.62775\n",
+ "[4526]\tvalidation_0-rmse:1.62747\n",
+ "[4527]\tvalidation_0-rmse:1.62720\n",
+ "[4528]\tvalidation_0-rmse:1.62692\n",
+ "[4529]\tvalidation_0-rmse:1.62684\n",
+ "[4530]\tvalidation_0-rmse:1.62658\n",
+ "[4531]\tvalidation_0-rmse:1.62638\n",
+ "[4532]\tvalidation_0-rmse:1.62622\n",
+ "[4533]\tvalidation_0-rmse:1.62611\n",
+ "[4534]\tvalidation_0-rmse:1.62594\n",
+ "[4535]\tvalidation_0-rmse:1.62583\n",
+ "[4536]\tvalidation_0-rmse:1.62557\n",
+ "[4537]\tvalidation_0-rmse:1.62532\n",
+ "[4538]\tvalidation_0-rmse:1.62508\n",
+ "[4539]\tvalidation_0-rmse:1.62482\n",
+ "[4540]\tvalidation_0-rmse:1.62462\n",
+ "[4541]\tvalidation_0-rmse:1.62438\n",
+ "[4542]\tvalidation_0-rmse:1.62431\n",
+ "[4543]\tvalidation_0-rmse:1.62401\n",
+ "[4544]\tvalidation_0-rmse:1.62389\n",
+ "[4545]\tvalidation_0-rmse:1.62376\n",
+ "[4546]\tvalidation_0-rmse:1.62367\n",
+ "[4547]\tvalidation_0-rmse:1.62347\n",
+ "[4548]\tvalidation_0-rmse:1.62322\n",
+ "[4549]\tvalidation_0-rmse:1.62316\n",
+ "[4550]\tvalidation_0-rmse:1.62300\n",
+ "[4551]\tvalidation_0-rmse:1.62280\n",
+ "[4552]\tvalidation_0-rmse:1.62238\n",
+ "[4553]\tvalidation_0-rmse:1.62208\n",
+ "[4554]\tvalidation_0-rmse:1.62186\n",
+ "[4555]\tvalidation_0-rmse:1.62169\n",
+ "[4556]\tvalidation_0-rmse:1.62150\n",
+ "[4557]\tvalidation_0-rmse:1.62134\n",
+ "[4558]\tvalidation_0-rmse:1.62122\n",
+ "[4559]\tvalidation_0-rmse:1.62091\n",
+ "[4560]\tvalidation_0-rmse:1.62085\n",
+ "[4561]\tvalidation_0-rmse:1.62071\n",
+ "[4562]\tvalidation_0-rmse:1.62060\n",
+ "[4563]\tvalidation_0-rmse:1.62054\n",
+ "[4564]\tvalidation_0-rmse:1.62020\n",
+ "[4565]\tvalidation_0-rmse:1.61996\n",
+ "[4566]\tvalidation_0-rmse:1.61989\n",
+ "[4567]\tvalidation_0-rmse:1.61964\n",
+ "[4568]\tvalidation_0-rmse:1.61943\n",
+ "[4569]\tvalidation_0-rmse:1.61914\n",
+ "[4570]\tvalidation_0-rmse:1.61898\n",
+ "[4571]\tvalidation_0-rmse:1.61889\n",
+ "[4572]\tvalidation_0-rmse:1.61875\n",
+ "[4573]\tvalidation_0-rmse:1.61867\n",
+ "[4574]\tvalidation_0-rmse:1.61847\n",
+ "[4575]\tvalidation_0-rmse:1.61817\n",
+ "[4576]\tvalidation_0-rmse:1.61799\n",
+ "[4577]\tvalidation_0-rmse:1.61775\n",
+ "[4578]\tvalidation_0-rmse:1.61757\n",
+ "[4579]\tvalidation_0-rmse:1.61737\n",
+ "[4580]\tvalidation_0-rmse:1.61708\n",
+ "[4581]\tvalidation_0-rmse:1.61699\n",
+ "[4582]\tvalidation_0-rmse:1.61676\n",
+ "[4583]\tvalidation_0-rmse:1.61653\n",
+ "[4584]\tvalidation_0-rmse:1.61630\n",
+ "[4585]\tvalidation_0-rmse:1.61612\n",
+ "[4586]\tvalidation_0-rmse:1.61589\n",
+ "[4587]\tvalidation_0-rmse:1.61569\n",
+ "[4588]\tvalidation_0-rmse:1.61553\n",
+ "[4589]\tvalidation_0-rmse:1.61532\n",
+ "[4590]\tvalidation_0-rmse:1.61506\n",
+ "[4591]\tvalidation_0-rmse:1.61491\n",
+ "[4592]\tvalidation_0-rmse:1.61476\n",
+ "[4593]\tvalidation_0-rmse:1.61456\n",
+ "[4594]\tvalidation_0-rmse:1.61429\n",
+ "[4595]\tvalidation_0-rmse:1.61419\n",
+ "[4596]\tvalidation_0-rmse:1.61404\n",
+ "[4597]\tvalidation_0-rmse:1.61380\n",
+ "[4598]\tvalidation_0-rmse:1.61352\n",
+ "[4599]\tvalidation_0-rmse:1.61322\n",
+ "[4600]\tvalidation_0-rmse:1.61293\n",
+ "[4601]\tvalidation_0-rmse:1.61263\n",
+ "[4602]\tvalidation_0-rmse:1.61214\n",
+ "[4603]\tvalidation_0-rmse:1.61200\n",
+ "[4604]\tvalidation_0-rmse:1.61178\n",
+ "[4605]\tvalidation_0-rmse:1.61154\n",
+ "[4606]\tvalidation_0-rmse:1.61143\n",
+ "[4607]\tvalidation_0-rmse:1.61132\n",
+ "[4608]\tvalidation_0-rmse:1.61121\n",
+ "[4609]\tvalidation_0-rmse:1.61098\n",
+ "[4610]\tvalidation_0-rmse:1.61089\n",
+ "[4611]\tvalidation_0-rmse:1.61061\n",
+ "[4612]\tvalidation_0-rmse:1.61026\n",
+ "[4613]\tvalidation_0-rmse:1.61014\n",
+ "[4614]\tvalidation_0-rmse:1.60979\n",
+ "[4615]\tvalidation_0-rmse:1.60964\n",
+ "[4616]\tvalidation_0-rmse:1.60948\n",
+ "[4617]\tvalidation_0-rmse:1.60928\n",
+ "[4618]\tvalidation_0-rmse:1.60888\n",
+ "[4619]\tvalidation_0-rmse:1.60863\n",
+ "[4620]\tvalidation_0-rmse:1.60850\n",
+ "[4621]\tvalidation_0-rmse:1.60836\n",
+ "[4622]\tvalidation_0-rmse:1.60805\n",
+ "[4623]\tvalidation_0-rmse:1.60770\n",
+ "[4624]\tvalidation_0-rmse:1.60743\n",
+ "[4625]\tvalidation_0-rmse:1.60713\n",
+ "[4626]\tvalidation_0-rmse:1.60691\n",
+ "[4627]\tvalidation_0-rmse:1.60675\n",
+ "[4628]\tvalidation_0-rmse:1.60663\n",
+ "[4629]\tvalidation_0-rmse:1.60657\n",
+ "[4630]\tvalidation_0-rmse:1.60644\n",
+ "[4631]\tvalidation_0-rmse:1.60607\n",
+ "[4632]\tvalidation_0-rmse:1.60583\n",
+ "[4633]\tvalidation_0-rmse:1.60568\n",
+ "[4634]\tvalidation_0-rmse:1.60553\n",
+ "[4635]\tvalidation_0-rmse:1.60534\n",
+ "[4636]\tvalidation_0-rmse:1.60513\n",
+ "[4637]\tvalidation_0-rmse:1.60493\n",
+ "[4638]\tvalidation_0-rmse:1.60482\n",
+ "[4639]\tvalidation_0-rmse:1.60460\n",
+ "[4640]\tvalidation_0-rmse:1.60448\n",
+ "[4641]\tvalidation_0-rmse:1.60422\n",
+ "[4642]\tvalidation_0-rmse:1.60410\n",
+ "[4643]\tvalidation_0-rmse:1.60393\n",
+ "[4644]\tvalidation_0-rmse:1.60385\n",
+ "[4645]\tvalidation_0-rmse:1.60368\n",
+ "[4646]\tvalidation_0-rmse:1.60358\n",
+ "[4647]\tvalidation_0-rmse:1.60353\n",
+ "[4648]\tvalidation_0-rmse:1.60337\n",
+ "[4649]\tvalidation_0-rmse:1.60329\n",
+ "[4650]\tvalidation_0-rmse:1.60309\n",
+ "[4651]\tvalidation_0-rmse:1.60287\n",
+ "[4652]\tvalidation_0-rmse:1.60269\n",
+ "[4653]\tvalidation_0-rmse:1.60233\n",
+ "[4654]\tvalidation_0-rmse:1.60210\n",
+ "[4655]\tvalidation_0-rmse:1.60175\n",
+ "[4656]\tvalidation_0-rmse:1.60158\n",
+ "[4657]\tvalidation_0-rmse:1.60139\n",
+ "[4658]\tvalidation_0-rmse:1.60121\n",
+ "[4659]\tvalidation_0-rmse:1.60114\n",
+ "[4660]\tvalidation_0-rmse:1.60093\n",
+ "[4661]\tvalidation_0-rmse:1.60081\n",
+ "[4662]\tvalidation_0-rmse:1.60058\n",
+ "[4663]\tvalidation_0-rmse:1.60029\n",
+ "[4664]\tvalidation_0-rmse:1.60022\n",
+ "[4665]\tvalidation_0-rmse:1.59986\n",
+ "[4666]\tvalidation_0-rmse:1.59953\n",
+ "[4667]\tvalidation_0-rmse:1.59946\n",
+ "[4668]\tvalidation_0-rmse:1.59939\n",
+ "[4669]\tvalidation_0-rmse:1.59912\n",
+ "[4670]\tvalidation_0-rmse:1.59889\n",
+ "[4671]\tvalidation_0-rmse:1.59877\n",
+ "[4672]\tvalidation_0-rmse:1.59859\n",
+ "[4673]\tvalidation_0-rmse:1.59832\n",
+ "[4674]\tvalidation_0-rmse:1.59815\n",
+ "[4675]\tvalidation_0-rmse:1.59782\n",
+ "[4676]\tvalidation_0-rmse:1.59750\n",
+ "[4677]\tvalidation_0-rmse:1.59723\n",
+ "[4678]\tvalidation_0-rmse:1.59709\n",
+ "[4679]\tvalidation_0-rmse:1.59687\n",
+ "[4680]\tvalidation_0-rmse:1.59674\n",
+ "[4681]\tvalidation_0-rmse:1.59660\n",
+ "[4682]\tvalidation_0-rmse:1.59627\n",
+ "[4683]\tvalidation_0-rmse:1.59603\n",
+ "[4684]\tvalidation_0-rmse:1.59573\n",
+ "[4685]\tvalidation_0-rmse:1.59558\n",
+ "[4686]\tvalidation_0-rmse:1.59553\n",
+ "[4687]\tvalidation_0-rmse:1.59533\n",
+ "[4688]\tvalidation_0-rmse:1.59513\n",
+ "[4689]\tvalidation_0-rmse:1.59509\n",
+ "[4690]\tvalidation_0-rmse:1.59494\n",
+ "[4691]\tvalidation_0-rmse:1.59460\n",
+ "[4692]\tvalidation_0-rmse:1.59436\n",
+ "[4693]\tvalidation_0-rmse:1.59404\n",
+ "[4694]\tvalidation_0-rmse:1.59379\n",
+ "[4695]\tvalidation_0-rmse:1.59360\n",
+ "[4696]\tvalidation_0-rmse:1.59347\n",
+ "[4697]\tvalidation_0-rmse:1.59341\n",
+ "[4698]\tvalidation_0-rmse:1.59305\n",
+ "[4699]\tvalidation_0-rmse:1.59300\n",
+ "[4700]\tvalidation_0-rmse:1.59293\n",
+ "[4701]\tvalidation_0-rmse:1.59274\n",
+ "[4702]\tvalidation_0-rmse:1.59266\n",
+ "[4703]\tvalidation_0-rmse:1.59233\n",
+ "[4704]\tvalidation_0-rmse:1.59195\n",
+ "[4705]\tvalidation_0-rmse:1.59167\n",
+ "[4706]\tvalidation_0-rmse:1.59157\n",
+ "[4707]\tvalidation_0-rmse:1.59141\n",
+ "[4708]\tvalidation_0-rmse:1.59120\n",
+ "[4709]\tvalidation_0-rmse:1.59089\n",
+ "[4710]\tvalidation_0-rmse:1.59071\n",
+ "[4711]\tvalidation_0-rmse:1.59063\n",
+ "[4712]\tvalidation_0-rmse:1.59050\n",
+ "[4713]\tvalidation_0-rmse:1.59040\n",
+ "[4714]\tvalidation_0-rmse:1.59029\n",
+ "[4715]\tvalidation_0-rmse:1.58998\n",
+ "[4716]\tvalidation_0-rmse:1.58954\n",
+ "[4717]\tvalidation_0-rmse:1.58942\n",
+ "[4718]\tvalidation_0-rmse:1.58940\n",
+ "[4719]\tvalidation_0-rmse:1.58926\n",
+ "[4720]\tvalidation_0-rmse:1.58910\n",
+ "[4721]\tvalidation_0-rmse:1.58894\n",
+ "[4722]\tvalidation_0-rmse:1.58884\n",
+ "[4723]\tvalidation_0-rmse:1.58877\n",
+ "[4724]\tvalidation_0-rmse:1.58868\n",
+ "[4725]\tvalidation_0-rmse:1.58858\n",
+ "[4726]\tvalidation_0-rmse:1.58850\n",
+ "[4727]\tvalidation_0-rmse:1.58838\n",
+ "[4728]\tvalidation_0-rmse:1.58832\n",
+ "[4729]\tvalidation_0-rmse:1.58821\n",
+ "[4730]\tvalidation_0-rmse:1.58818\n",
+ "[4731]\tvalidation_0-rmse:1.58816\n",
+ "[4732]\tvalidation_0-rmse:1.58811\n",
+ "[4733]\tvalidation_0-rmse:1.58776\n",
+ "[4734]\tvalidation_0-rmse:1.58747\n",
+ "[4735]\tvalidation_0-rmse:1.58712\n",
+ "[4736]\tvalidation_0-rmse:1.58700\n",
+ "[4737]\tvalidation_0-rmse:1.58662\n",
+ "[4738]\tvalidation_0-rmse:1.58635\n",
+ "[4739]\tvalidation_0-rmse:1.58608\n",
+ "[4740]\tvalidation_0-rmse:1.58598\n",
+ "[4741]\tvalidation_0-rmse:1.58580\n",
+ "[4742]\tvalidation_0-rmse:1.58541\n",
+ "[4743]\tvalidation_0-rmse:1.58521\n",
+ "[4744]\tvalidation_0-rmse:1.58515\n",
+ "[4745]\tvalidation_0-rmse:1.58509\n",
+ "[4746]\tvalidation_0-rmse:1.58470\n",
+ "[4747]\tvalidation_0-rmse:1.58453\n",
+ "[4748]\tvalidation_0-rmse:1.58433\n",
+ "[4749]\tvalidation_0-rmse:1.58404\n",
+ "[4750]\tvalidation_0-rmse:1.58375\n",
+ "[4751]\tvalidation_0-rmse:1.58350\n",
+ "[4752]\tvalidation_0-rmse:1.58333\n",
+ "[4753]\tvalidation_0-rmse:1.58316\n",
+ "[4754]\tvalidation_0-rmse:1.58294\n",
+ "[4755]\tvalidation_0-rmse:1.58276\n",
+ "[4756]\tvalidation_0-rmse:1.58248\n",
+ "[4757]\tvalidation_0-rmse:1.58216\n",
+ "[4758]\tvalidation_0-rmse:1.58198\n",
+ "[4759]\tvalidation_0-rmse:1.58145\n",
+ "[4760]\tvalidation_0-rmse:1.58115\n",
+ "[4761]\tvalidation_0-rmse:1.58095\n",
+ "[4762]\tvalidation_0-rmse:1.58081\n",
+ "[4763]\tvalidation_0-rmse:1.58057\n",
+ "[4764]\tvalidation_0-rmse:1.58049\n",
+ "[4765]\tvalidation_0-rmse:1.58043\n",
+ "[4766]\tvalidation_0-rmse:1.58028\n",
+ "[4767]\tvalidation_0-rmse:1.58000\n",
+ "[4768]\tvalidation_0-rmse:1.57978\n",
+ "[4769]\tvalidation_0-rmse:1.57954\n",
+ "[4770]\tvalidation_0-rmse:1.57939\n",
+ "[4771]\tvalidation_0-rmse:1.57927\n",
+ "[4772]\tvalidation_0-rmse:1.57890\n",
+ "[4773]\tvalidation_0-rmse:1.57873\n",
+ "[4774]\tvalidation_0-rmse:1.57842\n",
+ "[4775]\tvalidation_0-rmse:1.57831\n",
+ "[4776]\tvalidation_0-rmse:1.57805\n",
+ "[4777]\tvalidation_0-rmse:1.57776\n",
+ "[4778]\tvalidation_0-rmse:1.57757\n",
+ "[4779]\tvalidation_0-rmse:1.57718\n",
+ "[4780]\tvalidation_0-rmse:1.57695\n",
+ "[4781]\tvalidation_0-rmse:1.57681\n",
+ "[4782]\tvalidation_0-rmse:1.57669\n",
+ "[4783]\tvalidation_0-rmse:1.57649\n",
+ "[4784]\tvalidation_0-rmse:1.57636\n",
+ "[4785]\tvalidation_0-rmse:1.57600\n",
+ "[4786]\tvalidation_0-rmse:1.57565\n",
+ "[4787]\tvalidation_0-rmse:1.57530\n",
+ "[4788]\tvalidation_0-rmse:1.57494\n",
+ "[4789]\tvalidation_0-rmse:1.57481\n",
+ "[4790]\tvalidation_0-rmse:1.57455\n",
+ "[4791]\tvalidation_0-rmse:1.57417\n",
+ "[4792]\tvalidation_0-rmse:1.57395\n",
+ "[4793]\tvalidation_0-rmse:1.57386\n",
+ "[4794]\tvalidation_0-rmse:1.57350\n",
+ "[4795]\tvalidation_0-rmse:1.57316\n",
+ "[4796]\tvalidation_0-rmse:1.57312\n",
+ "[4797]\tvalidation_0-rmse:1.57294\n",
+ "[4798]\tvalidation_0-rmse:1.57274\n",
+ "[4799]\tvalidation_0-rmse:1.57262\n",
+ "[4800]\tvalidation_0-rmse:1.57228\n",
+ "[4801]\tvalidation_0-rmse:1.57199\n",
+ "[4802]\tvalidation_0-rmse:1.57170\n",
+ "[4803]\tvalidation_0-rmse:1.57157\n",
+ "[4804]\tvalidation_0-rmse:1.57132\n",
+ "[4805]\tvalidation_0-rmse:1.57120\n",
+ "[4806]\tvalidation_0-rmse:1.57105\n",
+ "[4807]\tvalidation_0-rmse:1.57076\n",
+ "[4808]\tvalidation_0-rmse:1.57064\n",
+ "[4809]\tvalidation_0-rmse:1.57059\n",
+ "[4810]\tvalidation_0-rmse:1.57050\n",
+ "[4811]\tvalidation_0-rmse:1.57043\n",
+ "[4812]\tvalidation_0-rmse:1.57039\n",
+ "[4813]\tvalidation_0-rmse:1.57025\n",
+ "[4814]\tvalidation_0-rmse:1.56998\n",
+ "[4815]\tvalidation_0-rmse:1.56987\n",
+ "[4816]\tvalidation_0-rmse:1.56983\n",
+ "[4817]\tvalidation_0-rmse:1.56945\n",
+ "[4818]\tvalidation_0-rmse:1.56927\n",
+ "[4819]\tvalidation_0-rmse:1.56913\n",
+ "[4820]\tvalidation_0-rmse:1.56896\n",
+ "[4821]\tvalidation_0-rmse:1.56884\n",
+ "[4822]\tvalidation_0-rmse:1.56851\n",
+ "[4823]\tvalidation_0-rmse:1.56828\n",
+ "[4824]\tvalidation_0-rmse:1.56800\n",
+ "[4825]\tvalidation_0-rmse:1.56782\n",
+ "[4826]\tvalidation_0-rmse:1.56755\n",
+ "[4827]\tvalidation_0-rmse:1.56740\n",
+ "[4828]\tvalidation_0-rmse:1.56717\n",
+ "[4829]\tvalidation_0-rmse:1.56695\n",
+ "[4830]\tvalidation_0-rmse:1.56674\n",
+ "[4831]\tvalidation_0-rmse:1.56665\n",
+ "[4832]\tvalidation_0-rmse:1.56656\n",
+ "[4833]\tvalidation_0-rmse:1.56653\n",
+ "[4834]\tvalidation_0-rmse:1.56622\n",
+ "[4835]\tvalidation_0-rmse:1.56607\n",
+ "[4836]\tvalidation_0-rmse:1.56594\n",
+ "[4837]\tvalidation_0-rmse:1.56575\n",
+ "[4838]\tvalidation_0-rmse:1.56555\n",
+ "[4839]\tvalidation_0-rmse:1.56534\n",
+ "[4840]\tvalidation_0-rmse:1.56515\n",
+ "[4841]\tvalidation_0-rmse:1.56502\n",
+ "[4842]\tvalidation_0-rmse:1.56474\n",
+ "[4843]\tvalidation_0-rmse:1.56450\n",
+ "[4844]\tvalidation_0-rmse:1.56430\n",
+ "[4845]\tvalidation_0-rmse:1.56419\n",
+ "[4846]\tvalidation_0-rmse:1.56404\n",
+ "[4847]\tvalidation_0-rmse:1.56383\n",
+ "[4848]\tvalidation_0-rmse:1.56358\n",
+ "[4849]\tvalidation_0-rmse:1.56338\n",
+ "[4850]\tvalidation_0-rmse:1.56323\n",
+ "[4851]\tvalidation_0-rmse:1.56297\n",
+ "[4852]\tvalidation_0-rmse:1.56267\n",
+ "[4853]\tvalidation_0-rmse:1.56221\n",
+ "[4854]\tvalidation_0-rmse:1.56194\n",
+ "[4855]\tvalidation_0-rmse:1.56149\n",
+ "[4856]\tvalidation_0-rmse:1.56144\n",
+ "[4857]\tvalidation_0-rmse:1.56120\n",
+ "[4858]\tvalidation_0-rmse:1.56101\n",
+ "[4859]\tvalidation_0-rmse:1.56065\n",
+ "[4860]\tvalidation_0-rmse:1.56028\n",
+ "[4861]\tvalidation_0-rmse:1.56019\n",
+ "[4862]\tvalidation_0-rmse:1.55983\n",
+ "[4863]\tvalidation_0-rmse:1.55972\n",
+ "[4864]\tvalidation_0-rmse:1.55951\n",
+ "[4865]\tvalidation_0-rmse:1.55917\n",
+ "[4866]\tvalidation_0-rmse:1.55890\n",
+ "[4867]\tvalidation_0-rmse:1.55868\n",
+ "[4868]\tvalidation_0-rmse:1.55860\n",
+ "[4869]\tvalidation_0-rmse:1.55836\n",
+ "[4870]\tvalidation_0-rmse:1.55822\n",
+ "[4871]\tvalidation_0-rmse:1.55814\n",
+ "[4872]\tvalidation_0-rmse:1.55800\n",
+ "[4873]\tvalidation_0-rmse:1.55772\n",
+ "[4874]\tvalidation_0-rmse:1.55768\n",
+ "[4875]\tvalidation_0-rmse:1.55752\n",
+ "[4876]\tvalidation_0-rmse:1.55749\n",
+ "[4877]\tvalidation_0-rmse:1.55743\n",
+ "[4878]\tvalidation_0-rmse:1.55742\n",
+ "[4879]\tvalidation_0-rmse:1.55724\n",
+ "[4880]\tvalidation_0-rmse:1.55715\n",
+ "[4881]\tvalidation_0-rmse:1.55709\n",
+ "[4882]\tvalidation_0-rmse:1.55706\n",
+ "[4883]\tvalidation_0-rmse:1.55701\n",
+ "[4884]\tvalidation_0-rmse:1.55699\n",
+ "[4885]\tvalidation_0-rmse:1.55697\n",
+ "[4886]\tvalidation_0-rmse:1.55678\n",
+ "[4887]\tvalidation_0-rmse:1.55656\n",
+ "[4888]\tvalidation_0-rmse:1.55639\n",
+ "[4889]\tvalidation_0-rmse:1.55625\n",
+ "[4890]\tvalidation_0-rmse:1.55610\n",
+ "[4891]\tvalidation_0-rmse:1.55599\n",
+ "[4892]\tvalidation_0-rmse:1.55591\n",
+ "[4893]\tvalidation_0-rmse:1.55572\n",
+ "[4894]\tvalidation_0-rmse:1.55564\n",
+ "[4895]\tvalidation_0-rmse:1.55560\n",
+ "[4896]\tvalidation_0-rmse:1.55556\n",
+ "[4897]\tvalidation_0-rmse:1.55548\n",
+ "[4898]\tvalidation_0-rmse:1.55544\n",
+ "[4899]\tvalidation_0-rmse:1.55534\n",
+ "[4900]\tvalidation_0-rmse:1.55518\n",
+ "[4901]\tvalidation_0-rmse:1.55496\n",
+ "[4902]\tvalidation_0-rmse:1.55483\n",
+ "[4903]\tvalidation_0-rmse:1.55474\n",
+ "[4904]\tvalidation_0-rmse:1.55465\n",
+ "[4905]\tvalidation_0-rmse:1.55444\n",
+ "[4906]\tvalidation_0-rmse:1.55435\n",
+ "[4907]\tvalidation_0-rmse:1.55416\n",
+ "[4908]\tvalidation_0-rmse:1.55396\n",
+ "[4909]\tvalidation_0-rmse:1.55383\n",
+ "[4910]\tvalidation_0-rmse:1.55370\n",
+ "[4911]\tvalidation_0-rmse:1.55340\n",
+ "[4912]\tvalidation_0-rmse:1.55333\n",
+ "[4913]\tvalidation_0-rmse:1.55306\n",
+ "[4914]\tvalidation_0-rmse:1.55301\n",
+ "[4915]\tvalidation_0-rmse:1.55301\n",
+ "[4916]\tvalidation_0-rmse:1.55271\n",
+ "[4917]\tvalidation_0-rmse:1.55248\n",
+ "[4918]\tvalidation_0-rmse:1.55216\n",
+ "[4919]\tvalidation_0-rmse:1.55197\n",
+ "[4920]\tvalidation_0-rmse:1.55163\n",
+ "[4921]\tvalidation_0-rmse:1.55133\n",
+ "[4922]\tvalidation_0-rmse:1.55130\n",
+ "[4923]\tvalidation_0-rmse:1.55107\n",
+ "[4924]\tvalidation_0-rmse:1.55067\n",
+ "[4925]\tvalidation_0-rmse:1.55055\n",
+ "[4926]\tvalidation_0-rmse:1.55039\n",
+ "[4927]\tvalidation_0-rmse:1.55020\n",
+ "[4928]\tvalidation_0-rmse:1.55010\n",
+ "[4929]\tvalidation_0-rmse:1.54996\n",
+ "[4930]\tvalidation_0-rmse:1.54975\n",
+ "[4931]\tvalidation_0-rmse:1.54947\n",
+ "[4932]\tvalidation_0-rmse:1.54927\n",
+ "[4933]\tvalidation_0-rmse:1.54884\n",
+ "[4934]\tvalidation_0-rmse:1.54870\n",
+ "[4935]\tvalidation_0-rmse:1.54856\n",
+ "[4936]\tvalidation_0-rmse:1.54840\n",
+ "[4937]\tvalidation_0-rmse:1.54829\n",
+ "[4938]\tvalidation_0-rmse:1.54804\n",
+ "[4939]\tvalidation_0-rmse:1.54785\n",
+ "[4940]\tvalidation_0-rmse:1.54769\n",
+ "[4941]\tvalidation_0-rmse:1.54760\n",
+ "[4942]\tvalidation_0-rmse:1.54736\n",
+ "[4943]\tvalidation_0-rmse:1.54729\n",
+ "[4944]\tvalidation_0-rmse:1.54716\n",
+ "[4945]\tvalidation_0-rmse:1.54700\n",
+ "[4946]\tvalidation_0-rmse:1.54693\n",
+ "[4947]\tvalidation_0-rmse:1.54674\n",
+ "[4948]\tvalidation_0-rmse:1.54650\n",
+ "[4949]\tvalidation_0-rmse:1.54618\n",
+ "[4950]\tvalidation_0-rmse:1.54610\n",
+ "[4951]\tvalidation_0-rmse:1.54603\n",
+ "[4952]\tvalidation_0-rmse:1.54591\n",
+ "[4953]\tvalidation_0-rmse:1.54563\n",
+ "[4954]\tvalidation_0-rmse:1.54547\n",
+ "[4955]\tvalidation_0-rmse:1.54525\n",
+ "[4956]\tvalidation_0-rmse:1.54520\n",
+ "[4957]\tvalidation_0-rmse:1.54516\n",
+ "[4958]\tvalidation_0-rmse:1.54498\n",
+ "[4959]\tvalidation_0-rmse:1.54473\n",
+ "[4960]\tvalidation_0-rmse:1.54455\n",
+ "[4961]\tvalidation_0-rmse:1.54428\n",
+ "[4962]\tvalidation_0-rmse:1.54410\n",
+ "[4963]\tvalidation_0-rmse:1.54389\n",
+ "[4964]\tvalidation_0-rmse:1.54359\n",
+ "[4965]\tvalidation_0-rmse:1.54341\n",
+ "[4966]\tvalidation_0-rmse:1.54302\n",
+ "[4967]\tvalidation_0-rmse:1.54270\n",
+ "[4968]\tvalidation_0-rmse:1.54249\n",
+ "[4969]\tvalidation_0-rmse:1.54231\n",
+ "[4970]\tvalidation_0-rmse:1.54205\n",
+ "[4971]\tvalidation_0-rmse:1.54192\n",
+ "[4972]\tvalidation_0-rmse:1.54169\n",
+ "[4973]\tvalidation_0-rmse:1.54155\n",
+ "[4974]\tvalidation_0-rmse:1.54132\n",
+ "[4975]\tvalidation_0-rmse:1.54112\n",
+ "[4976]\tvalidation_0-rmse:1.54104\n",
+ "[4977]\tvalidation_0-rmse:1.54079\n",
+ "[4978]\tvalidation_0-rmse:1.54056\n",
+ "[4979]\tvalidation_0-rmse:1.54025\n",
+ "[4980]\tvalidation_0-rmse:1.54014\n",
+ "[4981]\tvalidation_0-rmse:1.54011\n",
+ "[4982]\tvalidation_0-rmse:1.53999\n",
+ "[4983]\tvalidation_0-rmse:1.53970\n",
+ "[4984]\tvalidation_0-rmse:1.53958\n",
+ "[4985]\tvalidation_0-rmse:1.53935\n",
+ "[4986]\tvalidation_0-rmse:1.53921\n",
+ "[4987]\tvalidation_0-rmse:1.53918\n",
+ "[4988]\tvalidation_0-rmse:1.53885\n",
+ "[4989]\tvalidation_0-rmse:1.53878\n",
+ "[4990]\tvalidation_0-rmse:1.53851\n",
+ "[4991]\tvalidation_0-rmse:1.53829\n",
+ "[4992]\tvalidation_0-rmse:1.53805\n",
+ "[4993]\tvalidation_0-rmse:1.53777\n",
+ "[4994]\tvalidation_0-rmse:1.53756\n",
+ "[4995]\tvalidation_0-rmse:1.53733\n",
+ "[4996]\tvalidation_0-rmse:1.53724\n",
+ "[4997]\tvalidation_0-rmse:1.53701\n",
+ "[4998]\tvalidation_0-rmse:1.53676\n",
+ "[4999]\tvalidation_0-rmse:1.53647\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-2 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: #000;\n",
+ " --sklearn-color-text-muted: #666;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-2 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: flex;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ " align-items: start;\n",
+ " justify-content: space-between;\n",
+ " gap: 0.5em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 label.sk-toggleable__label .caption {\n",
+ " font-size: 0.6rem;\n",
+ " font-weight: lighter;\n",
+ " color: var(--sklearn-color-text-muted);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-2 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-2 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-2 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-2 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 0.5em;\n",
+ " text-align: center;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-2 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>XGBRegressor</div></div><div><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.07, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=5000, n_jobs=-1,\n",
+ " num_parallel_tree=None, random_state=None, ...)"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "model2=XGBRegressor(n_estimators=5000, learning_rate=0.07, n_jobs=-1)\n",
+ "model2.fit(X_clean, y_train, eval_set=[(X_clean, y_train)], verbose=True) \n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ameltebboune/.pyenv/versions/3.10.12/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+ " from .autonotebook import tqdm as notebook_tqdm\n",
+ "[I 2025-03-30 19:30:17,246] A new study created in memory with name: no-name-1c3dc80e-24c5-42af-b161-8f2476486481\n",
+ "[I 2025-03-30 19:30:21,681] Trial 0 finished with value: -21.010909593158196 and parameters: {'n_estimators': 2185, 'learning_rate': 0.28570714885887566, 'max_depth': 8, 'subsample': 0.7993292420985183, 'colsample_bytree': 0.5780093202212182, 'gamma': 0.15599452033620265}. Best is trial 0 with value: -21.010909593158196.\n",
+ "[I 2025-03-30 19:30:23,005] Trial 1 finished with value: -19.239828283811015 and parameters: {'n_estimators': 761, 'learning_rate': 0.2611910822747312, 'max_depth': 7, 'subsample': 0.8540362888980227, 'colsample_bytree': 0.5102922471479012, 'gamma': 0.9699098521619943}. Best is trial 1 with value: -19.239828283811015.\n",
+ "[I 2025-03-30 19:30:26,675] Trial 2 finished with value: -16.562373695164588 and parameters: {'n_estimators': 4246, 'learning_rate': 0.07157834209670008, 'max_depth': 4, 'subsample': 0.5917022549267169, 'colsample_bytree': 0.6521211214797689, 'gamma': 0.5247564316322378}. Best is trial 2 with value: -16.562373695164588.\n",
+ "[I 2025-03-30 19:30:30,534] Trial 3 finished with value: -18.66993321598087 and parameters: {'n_estimators': 2444, 'learning_rate': 0.09445645065743215, 'max_depth': 7, 'subsample': 0.569746930326021, 'colsample_bytree': 0.6460723242676091, 'gamma': 0.3663618432936917}. Best is trial 2 with value: -16.562373695164588.\n",
+ "[I 2025-03-30 19:30:32,743] Trial 4 finished with value: -18.10395488606618 and parameters: {'n_estimators': 2552, 'learning_rate': 0.23770102880397392, 'max_depth': 4, 'subsample': 0.7571172192068059, 'colsample_bytree': 0.7962072844310213, 'gamma': 0.046450412719997725}. Best is trial 2 with value: -16.562373695164588.\n",
+ "[I 2025-03-30 19:30:34,571] Trial 5 finished with value: -15.879253375258605 and parameters: {'n_estimators': 3234, 'learning_rate': 0.059451995869314544, 'max_depth': 3, 'subsample': 0.9744427686266666, 'colsample_bytree': 0.9828160165372797, 'gamma': 0.8083973481164611}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:38,100] Trial 6 finished with value: -17.20437346545946 and parameters: {'n_estimators': 1871, 'learning_rate': 0.03832491306185132, 'max_depth': 8, 'subsample': 0.7200762468698007, 'colsample_bytree': 0.5610191174223894, 'gamma': 0.4951769101112702}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:39,034] Trial 7 finished with value: -17.45687723032278 and parameters: {'n_estimators': 654, 'learning_rate': 0.2737029166028468, 'max_depth': 5, 'subsample': 0.831261142176991, 'colsample_bytree': 0.6558555380447055, 'gamma': 0.5200680211778108}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:42,581] Trial 8 finished with value: -17.599495800275413 and parameters: {'n_estimators': 2960, 'learning_rate': 0.06360779210240283, 'max_depth': 10, 'subsample': 0.8875664116805573, 'colsample_bytree': 0.9697494707820946, 'gamma': 0.8948273504276488}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:45,260] Trial 9 finished with value: -17.1792896119419 and parameters: {'n_estimators': 3191, 'learning_rate': 0.2773435281567039, 'max_depth': 3, 'subsample': 0.5979914312095727, 'colsample_bytree': 0.522613644455269, 'gamma': 0.32533033076326434}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:48,149] Trial 10 finished with value: -18.44939585351828 and parameters: {'n_estimators': 4798, 'learning_rate': 0.1472649232218539, 'max_depth': 5, 'subsample': 0.9775724145208066, 'colsample_bytree': 0.991948117710163, 'gamma': 0.7823772698868177}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:51,601] Trial 11 finished with value: -15.931280012019624 and parameters: {'n_estimators': 4306, 'learning_rate': 0.013773839621049166, 'max_depth': 3, 'subsample': 0.5065883662316701, 'colsample_bytree': 0.8317806927449907, 'gamma': 0.6971558983400944}. Best is trial 5 with value: -15.879253375258605.\n",
+ "[I 2025-03-30 19:30:54,553] Trial 12 finished with value: -15.778360042325511 and parameters: {'n_estimators': 3928, 'learning_rate': 0.01822979580932628, 'max_depth': 3, 'subsample': 0.510015238742354, 'colsample_bytree': 0.8791406858049345, 'gamma': 0.7239260351173952}. Best is trial 12 with value: -15.778360042325511.\n",
+ "[I 2025-03-30 19:30:56,476] Trial 13 finished with value: -16.924228908031033 and parameters: {'n_estimators': 3768, 'learning_rate': 0.12587794323724624, 'max_depth': 5, 'subsample': 0.9993823546841585, 'colsample_bytree': 0.8892016965842913, 'gamma': 0.7323011406528656}. Best is trial 12 with value: -15.778360042325511.\n",
+ "[I 2025-03-30 19:30:58,904] Trial 14 finished with value: -16.79189691467546 and parameters: {'n_estimators': 3483, 'learning_rate': 0.19038447495245797, 'max_depth': 3, 'subsample': 0.688732614593298, 'colsample_bytree': 0.9073757812633082, 'gamma': 0.8389426599618366}. Best is trial 12 with value: -15.778360042325511.\n",
+ "[I 2025-03-30 19:31:02,505] Trial 15 finished with value: -15.685176363491104 and parameters: {'n_estimators': 4998, 'learning_rate': 0.010753651843373006, 'max_depth': 4, 'subsample': 0.9271566188833311, 'colsample_bytree': 0.9121993823243162, 'gamma': 0.6446736852680854}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:07,770] Trial 16 finished with value: -16.019292917884854 and parameters: {'n_estimators': 4943, 'learning_rate': 0.011918892347107017, 'max_depth': 6, 'subsample': 0.9175766057116287, 'colsample_bytree': 0.7604014727911059, 'gamma': 0.6321841669530673}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:11,266] Trial 17 finished with value: -17.299708241493928 and parameters: {'n_estimators': 4172, 'learning_rate': 0.10618831477729414, 'max_depth': 4, 'subsample': 0.675315270863944, 'colsample_bytree': 0.8792024361054287, 'gamma': 0.6291816288960175}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:16,598] Trial 18 finished with value: -20.498233268228525 and parameters: {'n_estimators': 4546, 'learning_rate': 0.19572407895822103, 'max_depth': 6, 'subsample': 0.7743300284100342, 'colsample_bytree': 0.9317014333681496, 'gamma': 0.3480702839892055}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:24,643] Trial 19 finished with value: -17.779754193536775 and parameters: {'n_estimators': 3759, 'learning_rate': 0.03688540203654369, 'max_depth': 10, 'subsample': 0.6481321396200751, 'colsample_bytree': 0.8360594415574141, 'gamma': 0.9518536548097474}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:26,553] Trial 20 finished with value: -16.109652447913604 and parameters: {'n_estimators': 1434, 'learning_rate': 0.09161013527789827, 'max_depth': 4, 'subsample': 0.5045115012031428, 'colsample_bytree': 0.7181030855185175, 'gamma': 0.6253453045257586}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:29,019] Trial 21 finished with value: -15.859102126511289 and parameters: {'n_estimators': 3786, 'learning_rate': 0.04624904756643894, 'max_depth': 3, 'subsample': 0.9382777773056039, 'colsample_bytree': 0.9566534343376979, 'gamma': 0.8000219554354063}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:31,449] Trial 22 finished with value: -15.80248664005283 and parameters: {'n_estimators': 3874, 'learning_rate': 0.03812921087576409, 'max_depth': 3, 'subsample': 0.9513285743576703, 'colsample_bytree': 0.9396495602916162, 'gamma': 0.7027851802466951}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:35,109] Trial 23 finished with value: -15.894348272498803 and parameters: {'n_estimators': 4974, 'learning_rate': 0.02551228949302048, 'max_depth': 4, 'subsample': 0.8904648836897633, 'colsample_bytree': 0.8644033804720407, 'gamma': 0.673346704654435}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:38,870] Trial 24 finished with value: -17.733983951956713 and parameters: {'n_estimators': 4550, 'learning_rate': 0.07234919846086718, 'max_depth': 5, 'subsample': 0.9446555964703545, 'colsample_bytree': 0.9342288810162639, 'gamma': 0.4341484886463425}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:41,293] Trial 25 finished with value: -16.245807905272365 and parameters: {'n_estimators': 3954, 'learning_rate': 0.010342026838197498, 'max_depth': 3, 'subsample': 0.8419489568614742, 'colsample_bytree': 0.8304095758970247, 'gamma': 0.5480641111479758}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:43,697] Trial 26 finished with value: -16.03745222841961 and parameters: {'n_estimators': 3437, 'learning_rate': 0.04411712120289912, 'max_depth': 4, 'subsample': 0.8876141395838021, 'colsample_bytree': 0.9315847180544795, 'gamma': 0.7326289903141601}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:46,636] Trial 27 finished with value: -16.46440929874206 and parameters: {'n_estimators': 4642, 'learning_rate': 0.11865460178502046, 'max_depth': 3, 'subsample': 0.7947121811754493, 'colsample_bytree': 0.7865011057859432, 'gamma': 0.8786270065830333}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:50,859] Trial 28 finished with value: -17.67608173893071 and parameters: {'n_estimators': 4087, 'learning_rate': 0.08250938152695331, 'max_depth': 5, 'subsample': 0.5506750561234522, 'colsample_bytree': 0.707289201615861, 'gamma': 0.5929930141865837}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:54,328] Trial 29 finished with value: -19.311036801807774 and parameters: {'n_estimators': 1961, 'learning_rate': 0.18230866807213564, 'max_depth': 9, 'subsample': 0.7285811542420699, 'colsample_bytree': 0.8604941919890781, 'gamma': 0.2735722787864486}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:57,626] Trial 30 finished with value: -17.06046673092864 and parameters: {'n_estimators': 2841, 'learning_rate': 0.049958361945033475, 'max_depth': 6, 'subsample': 0.8140937028808048, 'colsample_bytree': 0.9074136202529428, 'gamma': 0.4279524870056814}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:31:59,628] Trial 31 finished with value: -15.77797891238895 and parameters: {'n_estimators': 3507, 'learning_rate': 0.02972324363727483, 'max_depth': 3, 'subsample': 0.9375257350821563, 'colsample_bytree': 0.9530242532800298, 'gamma': 0.7900575596910049}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:02,201] Trial 32 finished with value: -15.812181601594649 and parameters: {'n_estimators': 3636, 'learning_rate': 0.02856718757686806, 'max_depth': 4, 'subsample': 0.9190517496462927, 'colsample_bytree': 0.9482456953190592, 'gamma': 0.7400788186945833}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:04,804] Trial 33 finished with value: -15.755520069900527 and parameters: {'n_estimators': 4366, 'learning_rate': 0.024413190312569215, 'max_depth': 3, 'subsample': 0.8594747004561148, 'colsample_bytree': 0.9146095919982477, 'gamma': 0.9120296048116969}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:08,220] Trial 34 finished with value: -15.803150116723947 and parameters: {'n_estimators': 4371, 'learning_rate': 0.02440329147241411, 'max_depth': 4, 'subsample': 0.8621879823165911, 'colsample_bytree': 0.9100796857432292, 'gamma': 0.9909776637868206}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:11,125] Trial 35 finished with value: -15.986206874008525 and parameters: {'n_estimators': 4620, 'learning_rate': 0.058317300404975764, 'max_depth': 3, 'subsample': 0.8735579204223085, 'colsample_bytree': 0.8564198646106612, 'gamma': 0.9118685528197352}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:13,527] Trial 36 finished with value: -18.482121450411768 and parameters: {'n_estimators': 3208, 'learning_rate': 0.22521692934583604, 'max_depth': 4, 'subsample': 0.9175521747293633, 'colsample_bytree': 0.9957788555321875, 'gamma': 0.8517287271429922}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:16,632] Trial 37 finished with value: -17.669757705638936 and parameters: {'n_estimators': 4384, 'learning_rate': 0.07937052287751206, 'max_depth': 7, 'subsample': 0.9732709746222248, 'colsample_bytree': 0.7981489495274486, 'gamma': 0.7780133870977612}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:19,425] Trial 38 finished with value: -15.771135298823964 and parameters: {'n_estimators': 4038, 'learning_rate': 0.023764534689038358, 'max_depth': 3, 'subsample': 0.793667174435506, 'colsample_bytree': 0.9682512082795518, 'gamma': 0.9328829652377452}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:25,172] Trial 39 finished with value: -18.110789314256614 and parameters: {'n_estimators': 4766, 'learning_rate': 0.0624453274132781, 'max_depth': 8, 'subsample': 0.821545740642084, 'colsample_bytree': 0.9821901451605324, 'gamma': 0.9567417728632167}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:27,285] Trial 40 finished with value: -16.6703693694362 and parameters: {'n_estimators': 2538, 'learning_rate': 0.10273555381183813, 'max_depth': 4, 'subsample': 0.7874651330223416, 'colsample_bytree': 0.9597977223447893, 'gamma': 0.9197814547686757}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:29,994] Trial 41 finished with value: -15.749580532441566 and parameters: {'n_estimators': 4066, 'learning_rate': 0.02355199454427007, 'max_depth': 3, 'subsample': 0.7479093001274075, 'colsample_bytree': 0.9037368885585251, 'gamma': 0.8470245086506399}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:32,974] Trial 42 finished with value: -15.708322442930704 and parameters: {'n_estimators': 4207, 'learning_rate': 0.033146931138649575, 'max_depth': 3, 'subsample': 0.7545269172473295, 'colsample_bytree': 0.9069046960523239, 'gamma': 0.8511976065660148}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:34,057] Trial 43 finished with value: -16.058615207322052 and parameters: {'n_estimators': 1050, 'learning_rate': 0.049102358179022254, 'max_depth': 3, 'subsample': 0.7492372125622327, 'colsample_bytree': 0.9105024717001154, 'gamma': 0.9974848953207296}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:37,226] Trial 44 finished with value: -15.81922866658538 and parameters: {'n_estimators': 4119, 'learning_rate': 0.027424583492352654, 'max_depth': 4, 'subsample': 0.7513195485576731, 'colsample_bytree': 0.8163295215836371, 'gamma': 0.858379133892198}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:40,168] Trial 45 finished with value: -16.0120376068437 and parameters: {'n_estimators': 4417, 'learning_rate': 0.06574207422787434, 'max_depth': 3, 'subsample': 0.7070154887387011, 'colsample_bytree': 0.5993636108361037, 'gamma': 0.08353295830121954}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:45,226] Trial 46 finished with value: -21.254389914492887 and parameters: {'n_estimators': 4832, 'learning_rate': 0.2980392190520865, 'max_depth': 5, 'subsample': 0.7683195039922904, 'colsample_bytree': 0.9732646534899104, 'gamma': 0.9322460148013696}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:48,006] Trial 47 finished with value: -16.054869587976846 and parameters: {'n_estimators': 4204, 'learning_rate': 0.01105821664602272, 'max_depth': 3, 'subsample': 0.8420180926370283, 'colsample_bytree': 0.8815056151764031, 'gamma': 0.8378336639539896}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:50,574] Trial 48 finished with value: -15.869731763935263 and parameters: {'n_estimators': 3050, 'learning_rate': 0.040749693947280986, 'max_depth': 4, 'subsample': 0.8085964856120036, 'colsample_bytree': 0.9000782680492228, 'gamma': 0.8925163920914974}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:53,915] Trial 49 finished with value: -15.87310753277317 and parameters: {'n_estimators': 4675, 'learning_rate': 0.051678156681540494, 'max_depth': 3, 'subsample': 0.7252980218499163, 'colsample_bytree': 0.9241174923730154, 'gamma': 0.8264874623025321}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:32:58,295] Trial 50 finished with value: -20.58448836031342 and parameters: {'n_estimators': 4019, 'learning_rate': 0.250350006869436, 'max_depth': 5, 'subsample': 0.6590828634793958, 'colsample_bytree': 0.8500173993788557, 'gamma': 0.7725830307531555}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:00,646] Trial 51 finished with value: -15.792584830124715 and parameters: {'n_estimators': 3490, 'learning_rate': 0.029138908069015153, 'max_depth': 3, 'subsample': 0.8994235448889321, 'colsample_bytree': 0.9655960573172921, 'gamma': 0.8858318600762773}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:03,089] Trial 52 finished with value: -15.808306898778696 and parameters: {'n_estimators': 3650, 'learning_rate': 0.02306908906214271, 'max_depth': 3, 'subsample': 0.8558384323312782, 'colsample_bytree': 0.9922172299870718, 'gamma': 0.8031098310549027}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:05,526] Trial 53 finished with value: -15.74487524443552 and parameters: {'n_estimators': 3366, 'learning_rate': 0.037769504589901096, 'max_depth': 3, 'subsample': 0.7958738817249686, 'colsample_bytree': 0.8893504111220938, 'gamma': 0.7609264959573665}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:08,008] Trial 54 finished with value: -15.892960752078716 and parameters: {'n_estimators': 3302, 'learning_rate': 0.036535001964517394, 'max_depth': 4, 'subsample': 0.7844088499340728, 'colsample_bytree': 0.8827331246796651, 'gamma': 0.6896155050005528}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:11,084] Trial 55 finished with value: -16.586690222896497 and parameters: {'n_estimators': 4292, 'learning_rate': 0.139410141656755, 'max_depth': 3, 'subsample': 0.7024790583176281, 'colsample_bytree': 0.8995102473942858, 'gamma': 0.9529174643910082}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:13,842] Trial 56 finished with value: -15.784624778971605 and parameters: {'n_estimators': 3984, 'learning_rate': 0.021026829580282593, 'max_depth': 3, 'subsample': 0.7377782963523327, 'colsample_bytree': 0.9155982999861016, 'gamma': 0.6606231534179179}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:16,751] Trial 57 finished with value: -16.090798122524312 and parameters: {'n_estimators': 4433, 'learning_rate': 0.07713443616189296, 'max_depth': 3, 'subsample': 0.8286328325274601, 'colsample_bytree': 0.8679176536527582, 'gamma': 0.753941421146614}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:20,817] Trial 58 finished with value: -16.559139002895172 and parameters: {'n_estimators': 4989, 'learning_rate': 0.05409832686168788, 'max_depth': 4, 'subsample': 0.7795256778846188, 'colsample_bytree': 0.8448407717148357, 'gamma': 0.5602863779920042}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:23,389] Trial 59 finished with value: -16.525657275952653 and parameters: {'n_estimators': 2685, 'learning_rate': 0.08897890048214599, 'max_depth': 4, 'subsample': 0.6303226437137611, 'colsample_bytree': 0.9384843024812084, 'gamma': 0.8708246472987378}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:24,934] Trial 60 finished with value: -16.361002936066193 and parameters: {'n_estimators': 2188, 'learning_rate': 0.015324989524628338, 'max_depth': 3, 'subsample': 0.7622893257448525, 'colsample_bytree': 0.8167748262847839, 'gamma': 0.9258870172902512}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:27,275] Trial 61 finished with value: -15.739047348572134 and parameters: {'n_estimators': 3658, 'learning_rate': 0.03577891083397244, 'max_depth': 3, 'subsample': 0.8001953415425607, 'colsample_bytree': 0.9517497560006127, 'gamma': 0.8107728080206729}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:29,819] Trial 62 finished with value: -15.747824167242829 and parameters: {'n_estimators': 3664, 'learning_rate': 0.03427896613031848, 'max_depth': 3, 'subsample': 0.7991567298012487, 'colsample_bytree': 0.891856391338859, 'gamma': 0.8000920381375524}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:32,322] Trial 63 finished with value: -15.739167067043633 and parameters: {'n_estimators': 3682, 'learning_rate': 0.03735484500616336, 'max_depth': 3, 'subsample': 0.8051265727983098, 'colsample_bytree': 0.8934395940137452, 'gamma': 0.8119095265764107}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:34,981] Trial 64 finished with value: -15.859687912032417 and parameters: {'n_estimators': 3046, 'learning_rate': 0.0384326234335824, 'max_depth': 4, 'subsample': 0.7093808401221267, 'colsample_bytree': 0.8915827896433758, 'gamma': 0.7147357665699562}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:37,334] Trial 65 finished with value: -15.841102590645509 and parameters: {'n_estimators': 3332, 'learning_rate': 0.06857093867781143, 'max_depth': 3, 'subsample': 0.8032555652329675, 'colsample_bytree': 0.8711681629161379, 'gamma': 0.8108029732711752}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:41,209] Trial 66 finished with value: -19.08397028502918 and parameters: {'n_estimators': 3721, 'learning_rate': 0.16119447885362292, 'max_depth': 9, 'subsample': 0.7381345300658165, 'colsample_bytree': 0.7606980965628775, 'gamma': 0.7530991349308002}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:44,054] Trial 67 finished with value: -15.736706597888746 and parameters: {'n_estimators': 3886, 'learning_rate': 0.03683168805942622, 'max_depth': 3, 'subsample': 0.6847502782887034, 'colsample_bytree': 0.9256671368912539, 'gamma': 0.6690090981137}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:47,387] Trial 68 finished with value: -16.336809843958065 and parameters: {'n_estimators': 3856, 'learning_rate': 0.058321776772236045, 'max_depth': 4, 'subsample': 0.6766618864044931, 'colsample_bytree': 0.9297357452649798, 'gamma': 0.6089339398456839}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:49,863] Trial 69 finished with value: -15.744459553108467 and parameters: {'n_estimators': 3587, 'learning_rate': 0.034256410642261675, 'max_depth': 3, 'subsample': 0.8364677265726806, 'colsample_bytree': 0.9460123130112177, 'gamma': 0.6676821075423827}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:52,700] Trial 70 finished with value: -16.008155158291384 and parameters: {'n_estimators': 3555, 'learning_rate': 0.042517673378853676, 'max_depth': 4, 'subsample': 0.8758536243301461, 'colsample_bytree': 0.9501156721576788, 'gamma': 0.6658474903946493}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:55,185] Trial 71 finished with value: -15.74788304456472 and parameters: {'n_estimators': 3854, 'learning_rate': 0.0342722056907596, 'max_depth': 3, 'subsample': 0.8176640429258832, 'colsample_bytree': 0.8872884647499761, 'gamma': 0.6496511646113503}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:57,521] Trial 72 finished with value: -15.752819510522178 and parameters: {'n_estimators': 3416, 'learning_rate': 0.04651986176103956, 'max_depth': 3, 'subsample': 0.8314146353832903, 'colsample_bytree': 0.9244912591038285, 'gamma': 0.5939193492702375}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:33:59,972] Trial 73 finished with value: -15.728124285893296 and parameters: {'n_estimators': 3629, 'learning_rate': 0.03539096538966274, 'max_depth': 3, 'subsample': 0.842891039978815, 'colsample_bytree': 0.9808308306805785, 'gamma': 0.483180291302878}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:34:02,323] Trial 74 finished with value: -15.908564536878373 and parameters: {'n_estimators': 3133, 'learning_rate': 0.017406055005561086, 'max_depth': 3, 'subsample': 0.6139511404477955, 'colsample_bytree': 0.9766151977884776, 'gamma': 0.43942417601926115}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:34:04,451] Trial 75 finished with value: -15.817516521200933 and parameters: {'n_estimators': 2933, 'learning_rate': 0.05759194166835574, 'max_depth': 3, 'subsample': 0.8423461024584159, 'colsample_bytree': 0.9441061216696303, 'gamma': 0.46930009315263777}. Best is trial 15 with value: -15.685176363491104.\n",
+ "[I 2025-03-30 19:34:07,987] Trial 76 finished with value: -15.60866434302228 and parameters: {'n_estimators': 3373, 'learning_rate': 0.011362733546249535, 'max_depth': 5, 'subsample': 0.7671132751212617, 'colsample_bytree': 0.997863383611026, 'gamma': 0.5451039959595075}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:11,791] Trial 77 finished with value: -15.676479663936197 and parameters: {'n_estimators': 3768, 'learning_rate': 0.012956583205158623, 'max_depth': 5, 'subsample': 0.7685639526417912, 'colsample_bytree': 0.9997539736980543, 'gamma': 0.5411409190257719}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:16,294] Trial 78 finished with value: -15.740358966772806 and parameters: {'n_estimators': 3779, 'learning_rate': 0.010589637336435372, 'max_depth': 6, 'subsample': 0.7776865505323218, 'colsample_bytree': 0.9977027042298436, 'gamma': 0.5095492161604697}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:20,691] Trial 79 finished with value: -15.848445938868583 and parameters: {'n_estimators': 4233, 'learning_rate': 0.0176530072635105, 'max_depth': 5, 'subsample': 0.7636606110765323, 'colsample_bytree': 0.9831128615466418, 'gamma': 0.5569590930746097}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:24,035] Trial 80 finished with value: -15.762598046941246 and parameters: {'n_estimators': 3928, 'learning_rate': 0.010530885883749872, 'max_depth': 5, 'subsample': 0.9927273930826359, 'colsample_bytree': 0.9685546031288009, 'gamma': 0.3861029332604173}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:28,547] Trial 81 finished with value: -15.723204062208055 and parameters: {'n_estimators': 3717, 'learning_rate': 0.010612721635660717, 'max_depth': 6, 'subsample': 0.7763719163242253, 'colsample_bytree': 0.9909862372914297, 'gamma': 0.5045456456695125}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:33,234] Trial 82 finished with value: -16.11163796730517 and parameters: {'n_estimators': 3757, 'learning_rate': 0.017574760870892166, 'max_depth': 6, 'subsample': 0.7687734825569928, 'colsample_bytree': 0.9866156619570718, 'gamma': 0.5374131670396712}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:37,432] Trial 83 finished with value: -16.578538361467935 and parameters: {'n_estimators': 3226, 'learning_rate': 0.030483520864567765, 'max_depth': 6, 'subsample': 0.7183793182698592, 'colsample_bytree': 0.9591825926631506, 'gamma': 0.48403340480262574}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:41,038] Trial 84 finished with value: -16.6449803418191 and parameters: {'n_estimators': 3558, 'learning_rate': 0.04708779611674324, 'max_depth': 5, 'subsample': 0.7381141541638667, 'colsample_bytree': 0.9735829145355916, 'gamma': 0.5794553605524664}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:47,923] Trial 85 finished with value: -16.777317201849492 and parameters: {'n_estimators': 4155, 'learning_rate': 0.020201789273359715, 'max_depth': 7, 'subsample': 0.7571558865821846, 'colsample_bytree': 0.9999411733177012, 'gamma': 0.5193812596647811}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:54,772] Trial 86 finished with value: -17.119517624372016 and parameters: {'n_estimators': 3866, 'learning_rate': 0.027005704158183284, 'max_depth': 7, 'subsample': 0.6936831934119942, 'colsample_bytree': 0.9584891573578985, 'gamma': 0.4072851950836089}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:34:58,306] Trial 87 finished with value: -16.567550449670367 and parameters: {'n_estimators': 3435, 'learning_rate': 0.04410667188820573, 'max_depth': 5, 'subsample': 0.8078287871485134, 'colsample_bytree': 0.9875702590318182, 'gamma': 0.46638524338298326}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:02,493] Trial 88 finished with value: -15.73566752408376 and parameters: {'n_estimators': 3626, 'learning_rate': 0.010366734205956515, 'max_depth': 6, 'subsample': 0.8229525679576276, 'colsample_bytree': 0.6718829153636385, 'gamma': 0.3088349867268276}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:06,163] Trial 89 finished with value: -15.978326897002045 and parameters: {'n_estimators': 3309, 'learning_rate': 0.016607008653775537, 'max_depth': 6, 'subsample': 0.9058825206091997, 'colsample_bytree': 0.6921424299197209, 'gamma': 0.2793338883791274}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:11,140] Trial 90 finished with value: -15.992537412767504 and parameters: {'n_estimators': 4492, 'learning_rate': 0.010433480152051314, 'max_depth': 6, 'subsample': 0.7896811461257676, 'colsample_bytree': 0.6021718394838373, 'gamma': 0.1569458130621559}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:14,930] Trial 91 finished with value: -16.570368015170224 and parameters: {'n_estimators': 3674, 'learning_rate': 0.029550106860548823, 'max_depth': 6, 'subsample': 0.8205245072579261, 'colsample_bytree': 0.660448512376666, 'gamma': 0.21524073795493082}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:18,702] Trial 92 finished with value: -20.742362263610783 and parameters: {'n_estimators': 3512, 'learning_rate': 0.22168622475779384, 'max_depth': 6, 'subsample': 0.7771063191634263, 'colsample_bytree': 0.639455484056703, 'gamma': 0.6406939556044671}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:22,213] Trial 93 finished with value: -15.934624507703258 and parameters: {'n_estimators': 3958, 'learning_rate': 0.020885725298801283, 'max_depth': 5, 'subsample': 0.8707717504434759, 'colsample_bytree': 0.7270326642611674, 'gamma': 0.34679651085968277}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:25,163] Trial 94 finished with value: -16.215719796410553 and parameters: {'n_estimators': 3706, 'learning_rate': 0.05228622016776288, 'max_depth': 4, 'subsample': 0.8458758909011125, 'colsample_bytree': 0.9754427553429819, 'gamma': 0.6168037574172571}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:28,634] Trial 95 finished with value: -16.262640928552738 and parameters: {'n_estimators': 3805, 'learning_rate': 0.03149807415894269, 'max_depth': 5, 'subsample': 0.7463103801345825, 'colsample_bytree': 0.918537078094165, 'gamma': 0.5699122916031633}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:33,722] Trial 96 finished with value: -17.718145450752594 and parameters: {'n_estimators': 4088, 'learning_rate': 0.04225368482877592, 'max_depth': 7, 'subsample': 0.9605596791327816, 'colsample_bytree': 0.9403750322214806, 'gamma': 0.499259244115145}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:36,889] Trial 97 finished with value: -15.695701552644186 and parameters: {'n_estimators': 3617, 'learning_rate': 0.025788052721899823, 'max_depth': 4, 'subsample': 0.5505064091803205, 'colsample_bytree': 0.9589196449447663, 'gamma': 0.5356881934459553}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:39,426] Trial 98 finished with value: -15.666049549485962 and parameters: {'n_estimators': 3120, 'learning_rate': 0.024370771708129325, 'max_depth': 4, 'subsample': 0.7199656410427937, 'colsample_bytree': 0.9593649752398007, 'gamma': 0.5279979712515451}. Best is trial 76 with value: -15.60866434302228.\n",
+ "[I 2025-03-30 19:35:42,181] Trial 99 finished with value: -15.643315660373418 and parameters: {'n_estimators': 3113, 'learning_rate': 0.02423722415992556, 'max_depth': 4, 'subsample': 0.5595838830200461, 'colsample_bytree': 0.9643224176486229, 'gamma': 0.534664988102398}. Best is trial 76 with value: -15.60866434302228.\n"
]
}
],
"source": [
- "X = pd.read_csv('data/X_train_6ZIKlTY.csv')\n",
- "y = pd.read_csv('data/y_train_lXj6X5y.csv')\n",
- "data = PreprocessData(X, y)"
+ "import optuna\n",
+ "from optuna import Trial\n",
+ "from optuna.samplers import TPESampler\n",
+ "from sklearn.model_selection import cross_val_score\n",
+ "\n",
+ "def objective(trial: Trial) -> float:\n",
+ " params = {\n",
+ " 'n_estimators': trial.suggest_int('n_estimators', 500, 5000),\n",
+ " 'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3),\n",
+ " 'max_depth': trial.suggest_int('max_depth', 3, 10),\n",
+ " 'subsample': trial.suggest_float('subsample', 0.5, 1),\n",
+ " 'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1),\n",
+ " 'gamma': trial.suggest_float('gamma', 0, 1),\n",
+ " 'random_state': 42,\n",
+ " 'n_jobs': -1\n",
+ " }\n",
+ " model = XGBRegressor(**params)\n",
+ " return cross_val_score(model, X_clean, y_train, n_jobs=-1, cv=5, scoring='neg_mean_squared_error').mean()\n",
+ "\n",
+ "sampler = TPESampler(seed=42)\n",
+ "study = optuna.create_study(direction='maximize', sampler=sampler)\n",
+ "study.optimize(objective, n_trials=100) \n"
]
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>cohort</th>\n",
- " <th>sexM</th>\n",
- " <th>age_at_diagnosis</th>\n",
- " <th>age</th>\n",
- " <th>ledd</th>\n",
- " <th>time_since_intake_on</th>\n",
- " <th>time_since_intake_off</th>\n",
- " <th>on</th>\n",
- " <th>off</th>\n",
- " <th>est_LRRK2+</th>\n",
- " <th>...</th>\n",
- " <th>zzdt1581</th>\n",
- " <th>zzdt1708</th>\n",
- " <th>zzhd4675</th>\n",
- " <th>zzie1203</th>\n",
- " <th>zzih2520</th>\n",
- " <th>zzlf7854</th>\n",
- " <th>zzmr9316</th>\n",
- " <th>zznx1511</th>\n",
- " <th>zzpu4420</th>\n",
- " <th>zztp1426</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>52.1</td>\n",
- " <td>607.0</td>\n",
- " <td>1.9</td>\n",
- " <td>NaN</td>\n",
- " <td>7.0</td>\n",
- " <td>NaN</td>\n",
- " <td>1.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>53.0</td>\n",
- " <td>666.0</td>\n",
- " <td>1.9</td>\n",
- " <td>17.6</td>\n",
- " <td>12.0</td>\n",
- " <td>44.0</td>\n",
- " <td>1.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>53.9</td>\n",
- " <td>717.0</td>\n",
- " <td>1.2</td>\n",
- " <td>NaN</td>\n",
- " <td>6.0</td>\n",
- " <td>NaN</td>\n",
- " <td>1.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>54.8</td>\n",
- " <td>770.0</td>\n",
- " <td>1.5</td>\n",
- " <td>NaN</td>\n",
- " <td>11.0</td>\n",
- " <td>NaN</td>\n",
- " <td>1.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>56.9</td>\n",
- " <td>885.0</td>\n",
- " <td>0.3</td>\n",
- " <td>NaN</td>\n",
- " <td>24.0</td>\n",
- " <td>NaN</td>\n",
- " <td>1.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "<p>5 rows × 6984 columns</p>\n",
- "</div>"
- ],
"text/plain": [
- " cohort sexM age_at_diagnosis age ledd time_since_intake_on \\\n",
- "0 1 0 48.5 52.1 607.0 1.9 \n",
- "1 1 0 48.5 53.0 666.0 1.9 \n",
- "2 1 0 48.5 53.9 717.0 1.2 \n",
- "3 1 0 48.5 54.8 770.0 1.5 \n",
- "4 1 0 48.5 56.9 885.0 0.3 \n",
- "\n",
- " time_since_intake_off on off est_LRRK2+ ... zzdt1581 zzdt1708 \\\n",
- "0 NaN 7.0 NaN 1.0 ... 0 0 \n",
- "1 17.6 12.0 44.0 1.0 ... 0 0 \n",
- "2 NaN 6.0 NaN 1.0 ... 0 0 \n",
- "3 NaN 11.0 NaN 1.0 ... 0 0 \n",
- "4 NaN 24.0 NaN 1.0 ... 0 0 \n",
- "\n",
- " zzhd4675 zzie1203 zzih2520 zzlf7854 zzmr9316 zznx1511 zzpu4420 \\\n",
- "0 0 0 0 0 0 0 0 \n",
- "1 0 0 0 0 0 0 0 \n",
- "2 0 0 0 0 0 0 0 \n",
- "3 0 0 0 0 0 0 0 \n",
- "4 0 0 0 0 0 0 0 \n",
- "\n",
- " zztp1426 \n",
- "0 0 \n",
- "1 0 \n",
- "2 0 \n",
- "3 0 \n",
- "4 0 \n",
- "\n",
- "[5 rows x 6984 columns]"
+ "{'n_estimators': 3373,\n",
+ " 'learning_rate': 0.011362733546249535,\n",
+ " 'max_depth': 5,\n",
+ " 'subsample': 0.7671132751212617,\n",
+ " 'colsample_bytree': 0.997863383611026,\n",
+ " 'gamma': 0.5451039959595075,\n",
+ " 'random_state': 42,\n",
+ " 'n_jobs': -1}"
]
},
- "execution_count": 3,
+ "execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "X1 = data.get_X()\n",
- "y1 = data.get_y()\n",
- "X1.head()\n"
+ "# on recup le meilleur parametre\n",
+ "best_params = study.best_params\n",
+ "best_params['random_state'] = 42\n",
+ "best_params['n_jobs'] = -1\n",
+ "# entrainement avec best_params\n",
+ "best_params\n"
]
},
{
@@ -626,304 +11743,6414 @@
"metadata": {},
"outputs": [],
"source": [
- "X1_clean = X1.drop(['ledd','off','time_since_intake_on','time_since_intake_off'],axis=1)"
+ "\n",
+ "X_clean_train, X_clean_val, y_clean_train, y_clean_val = train_test_split(X_clean, y_train, test_size=0.2, random_state=42)\n"
]
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 35,
"metadata": {},
"outputs": [
{
"data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>cohort</th>\n",
- " <th>sexM</th>\n",
- " <th>age_at_diagnosis</th>\n",
- " <th>age</th>\n",
- " <th>time_since_intake_on</th>\n",
- " <th>time_since_intake_off</th>\n",
- " <th>on</th>\n",
- " <th>est_LRRK2+</th>\n",
- " <th>est_GBA+</th>\n",
- " <th>est_OTHER+</th>\n",
- " <th>...</th>\n",
- " <th>zzdt1581</th>\n",
- " <th>zzdt1708</th>\n",
- " <th>zzhd4675</th>\n",
- " <th>zzie1203</th>\n",
- " <th>zzih2520</th>\n",
- " <th>zzlf7854</th>\n",
- " <th>zzmr9316</th>\n",
- " <th>zznx1511</th>\n",
- " <th>zzpu4420</th>\n",
- " <th>zztp1426</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>52.1</td>\n",
- " <td>1.9</td>\n",
- " <td>NaN</td>\n",
- " <td>7.0</td>\n",
- " <td>1.0</td>\n",
- " <td>0.0</td>\n",
- " <td>0.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>53.0</td>\n",
- " <td>1.9</td>\n",
- " <td>17.6</td>\n",
- " <td>12.0</td>\n",
- " <td>1.0</td>\n",
- " <td>0.0</td>\n",
- " <td>0.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>53.9</td>\n",
- " <td>1.2</td>\n",
- " <td>NaN</td>\n",
- " <td>6.0</td>\n",
- " <td>1.0</td>\n",
- " <td>0.0</td>\n",
- " <td>0.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>54.8</td>\n",
- " <td>1.5</td>\n",
- " <td>NaN</td>\n",
- " <td>11.0</td>\n",
- " <td>1.0</td>\n",
- " <td>0.0</td>\n",
- " <td>0.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>48.5</td>\n",
- " <td>56.9</td>\n",
- " <td>0.3</td>\n",
- " <td>NaN</td>\n",
- " <td>24.0</td>\n",
- " <td>1.0</td>\n",
- " <td>0.0</td>\n",
- " <td>0.0</td>\n",
- " <td>...</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "<p>5 rows × 6982 columns</p>\n",
- "</div>"
- ],
"text/plain": [
- " cohort sexM age_at_diagnosis age time_since_intake_on \\\n",
- "0 1 0 48.5 52.1 1.9 \n",
- "1 1 0 48.5 53.0 1.9 \n",
- "2 1 0 48.5 53.9 1.2 \n",
- "3 1 0 48.5 54.8 1.5 \n",
- "4 1 0 48.5 56.9 0.3 \n",
- "\n",
- " time_since_intake_off on est_LRRK2+ est_GBA+ est_OTHER+ ... \\\n",
- "0 NaN 7.0 1.0 0.0 0.0 ... \n",
- "1 17.6 12.0 1.0 0.0 0.0 ... \n",
- "2 NaN 6.0 1.0 0.0 0.0 ... \n",
- "3 NaN 11.0 1.0 0.0 0.0 ... \n",
- "4 NaN 24.0 1.0 0.0 0.0 ... \n",
- "\n",
- " zzdt1581 zzdt1708 zzhd4675 zzie1203 zzih2520 zzlf7854 zzmr9316 \\\n",
- "0 0 0 0 0 0 0 0 \n",
- "1 0 0 0 0 0 0 0 \n",
- "2 0 0 0 0 0 0 0 \n",
- "3 0 0 0 0 0 0 0 \n",
- "4 0 0 0 0 0 0 0 \n",
- "\n",
- " zznx1511 zzpu4420 zztp1426 \n",
- "0 0 0 0 \n",
- "1 0 0 0 \n",
- "2 0 0 0 \n",
- "3 0 0 0 \n",
- "4 0 0 0 \n",
- "\n",
- "[5 rows x 6982 columns]"
+ "3.6993290040017266"
]
},
- "execution_count": 7,
+ "execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "X1_clean.head()"
+ "y_pred = model3.predict(X_clean_val)\n",
+ "# rmse\n",
+ "np.sqrt(mean_squared_error(y_clean_val, y_pred))"
]
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_X_train=X.iloc[index_closest.values.flatten()]\n",
+ "new_y_train=y.iloc[index_closest.values.flatten()]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "cohort 0\n",
- "sexM 0\n",
- "age_at_diagnosis 0\n",
- "age 0\n",
- "on 0\n",
- " ..\n",
- "zzlf7854 0\n",
- "zzmr9316 0\n",
- "zznx1511 0\n",
- "zzpu4420 0\n",
- "zztp1426 0\n",
- "Length: 6980, dtype: int64"
+ "array([[<Axes: title={'center': 'cohort'}>,\n",
+ " <Axes: title={'center': 'sexM'}>,\n",
+ " <Axes: title={'center': 'age_at_diagnosis'}>,\n",
+ " <Axes: title={'center': 'age'}>,\n",
+ " <Axes: title={'center': 'ledd'}>],\n",
+ " [<Axes: title={'center': 'on'}>, <Axes: title={'center': 'off'}>,\n",
+ " <Axes: title={'center': 'est_LRRK2+'}>,\n",
+ " <Axes: title={'center': 'est_GBA+'}>,\n",
+ " <Axes: title={'center': 'est_OTHER+'}>],\n",
+ " [<Axes: title={'center': 'time_since_diagnosis'}>,\n",
+ " <Axes: title={'center': 'ledd_missing'}>,\n",
+ " <Axes: title={'center': 'off_missing'}>,\n",
+ " <Axes: title={'center': 'num_visite'}>,\n",
+ " <Axes: title={'center': 'nb_visites'}>],\n",
+ " [<Axes: title={'center': 'diff_on'}>,\n",
+ " <Axes: title={'center': 'diff_off'}>,\n",
+ " <Axes: title={'center': 'diff_on_first'}>,\n",
+ " <Axes: title={'center': 'diff_off_first'}>,\n",
+ " <Axes: title={'center': 'mean_on'}>],\n",
+ " [<Axes: title={'center': 'mean_off'}>,\n",
+ " <Axes: title={'center': 'std_on'}>,\n",
+ " <Axes: title={'center': 'std_off'}>,\n",
+ " <Axes: title={'center': 'time_since_last_visit'}>, <Axes: >]],\n",
+ " dtype=object)"
]
},
- "execution_count": 12,
+ "execution_count": 45,
"metadata": {},
"output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 2000x1500 with 25 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
}
],
"source": [
- "# recuperer les lignes ou il y a un NaN sur la colonne 'on'\n",
- "X1_a_imputer = X1_clean[X1_clean['on'].isnull()]\n",
+ "new_X_train.hist(bins=50, figsize=(20,15))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[<Axes: title={'center': 'cohort'}>,\n",
+ " <Axes: title={'center': 'sexM'}>,\n",
+ " <Axes: title={'center': 'age_at_diagnosis'}>,\n",
+ " <Axes: title={'center': 'age'}>,\n",
+ " <Axes: title={'center': 'ledd'}>],\n",
+ " [<Axes: title={'center': 'on'}>, <Axes: title={'center': 'off'}>,\n",
+ " <Axes: title={'center': 'time_since_diagnosis'}>,\n",
+ " <Axes: title={'center': 'est_LRRK2+'}>,\n",
+ " <Axes: title={'center': 'est_GBA+'}>],\n",
+ " [<Axes: title={'center': 'est_OTHER+'}>,\n",
+ " <Axes: title={'center': 'ledd_missing'}>,\n",
+ " <Axes: title={'center': 'off_missing'}>,\n",
+ " <Axes: title={'center': 'num_visite'}>,\n",
+ " <Axes: title={'center': 'nb_visites'}>],\n",
+ " [<Axes: title={'center': 'diff_on'}>,\n",
+ " <Axes: title={'center': 'diff_off'}>,\n",
+ " <Axes: title={'center': 'diff_on_first'}>,\n",
+ " <Axes: title={'center': 'diff_off_first'}>,\n",
+ " <Axes: title={'center': 'mean_on'}>],\n",
+ " [<Axes: title={'center': 'mean_off'}>,\n",
+ " <Axes: title={'center': 'std_on'}>,\n",
+ " <Axes: title={'center': 'std_off'}>,\n",
+ " <Axes: title={'center': 'time_since_last_visit'}>, <Axes: >]],\n",
+ " dtype=object)"
+ ]
+ },
+ "execution_count": 46,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 2000x1500 with 25 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "X_test.hist(bins=50, figsize=(20,15))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fitting 5 folds for each of 50 candidates, totalling 250 fits\n",
+ "[CV] END activation=logistic, alpha=0.0015352246941973493, beta_1=0.9832513550762977, beta_2=1.679613031172742, early_stopping=True, epsilon=1.562069367563986e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.0001994916615063395, max_iter=1000, solver=sgd, validation_fraction=0.16674172222780437; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0015352246941973493, beta_1=0.9832513550762977, beta_2=1.679613031172742, early_stopping=True, epsilon=1.562069367563986e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.0001994916615063395, max_iter=1000, solver=sgd, validation_fraction=0.16674172222780437; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0015352246941973493, beta_1=0.9832513550762977, beta_2=1.679613031172742, early_stopping=True, epsilon=1.562069367563986e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.0001994916615063395, max_iter=1000, solver=sgd, validation_fraction=0.16674172222780437; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0015352246941973493, beta_1=0.9832513550762977, beta_2=1.679613031172742, early_stopping=True, epsilon=1.562069367563986e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.0001994916615063395, max_iter=1000, solver=sgd, validation_fraction=0.16674172222780437; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.461896279370496e-05, beta_1=1.411241041827657, beta_2=1.0394799112659767, early_stopping=True, epsilon=3.839629299804172e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0226739865237804, max_iter=1000, solver=sgd, validation_fraction=0.20284688768272233; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.461896279370496e-05, beta_1=1.411241041827657, beta_2=1.0394799112659767, early_stopping=True, epsilon=3.839629299804172e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0226739865237804, max_iter=1000, solver=sgd, validation_fraction=0.20284688768272233; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.461896279370496e-05, beta_1=1.411241041827657, beta_2=1.0394799112659767, early_stopping=True, epsilon=3.839629299804172e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0226739865237804, max_iter=1000, solver=sgd, validation_fraction=0.20284688768272233; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.5339162591163623e-06, beta_1=1.406937307049537, beta_2=1.0705070712749227, early_stopping=True, epsilon=1.349283426801327e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.07886714129990492, max_iter=2000, solver=sgd, validation_fraction=0.16092275383467414; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.5339162591163623e-06, beta_1=1.406937307049537, beta_2=1.0705070712749227, early_stopping=True, epsilon=1.349283426801327e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.07886714129990492, max_iter=2000, solver=sgd, validation_fraction=0.16092275383467414; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.5339162591163623e-06, beta_1=1.406937307049537, beta_2=1.0705070712749227, early_stopping=True, epsilon=1.349283426801327e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.07886714129990492, max_iter=2000, solver=sgd, validation_fraction=0.16092275383467414; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.5339162591163623e-06, beta_1=1.406937307049537, beta_2=1.0705070712749227, early_stopping=True, epsilon=1.349283426801327e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.07886714129990492, max_iter=2000, solver=sgd, validation_fraction=0.16092275383467414; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.5339162591163623e-06, beta_1=1.406937307049537, beta_2=1.0705070712749227, early_stopping=True, epsilon=1.349283426801327e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.07886714129990492, max_iter=2000, solver=sgd, validation_fraction=0.16092275383467414; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=8.386394780402564e-06, beta_1=1.0407844405599858, beta_2=1.5831951924735757, early_stopping=True, epsilon=1.6595613641357215e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0014899847475658245, max_iter=2000, solver=sgd, validation_fraction=0.2510722820635305; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0015352246941973493, beta_1=0.9832513550762977, beta_2=1.679613031172742, early_stopping=True, epsilon=1.562069367563986e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.0001994916615063395, max_iter=1000, solver=sgd, validation_fraction=0.16674172222780437; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=8.386394780402564e-06, beta_1=1.0407844405599858, beta_2=1.5831951924735757, early_stopping=True, epsilon=1.6595613641357215e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0014899847475658245, max_iter=2000, solver=sgd, validation_fraction=0.2510722820635305; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=8.386394780402564e-06, beta_1=1.0407844405599858, beta_2=1.5831951924735757, early_stopping=True, epsilon=1.6595613641357215e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0014899847475658245, max_iter=2000, solver=sgd, validation_fraction=0.2510722820635305; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=8.386394780402564e-06, beta_1=1.0407844405599858, beta_2=1.5831951924735757, early_stopping=True, epsilon=1.6595613641357215e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0014899847475658245, max_iter=2000, solver=sgd, validation_fraction=0.2510722820635305; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=8.386394780402564e-06, beta_1=1.0407844405599858, beta_2=1.5831951924735757, early_stopping=True, epsilon=1.6595613641357215e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0014899847475658245, max_iter=2000, solver=sgd, validation_fraction=0.2510722820635305; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00012030178871154674, beta_1=1.3461635690639364, beta_2=1.0848359700799746, early_stopping=True, epsilon=8.69299151113954e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.06584106160121614, max_iter=2000, solver=sgd, validation_fraction=0.21957999576221704; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00012030178871154674, beta_1=1.3461635690639364, beta_2=1.0848359700799746, early_stopping=True, epsilon=8.69299151113954e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.06584106160121614, max_iter=2000, solver=sgd, validation_fraction=0.21957999576221704; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00012030178871154674, beta_1=1.3461635690639364, beta_2=1.0848359700799746, early_stopping=True, epsilon=8.69299151113954e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.06584106160121614, max_iter=2000, solver=sgd, validation_fraction=0.21957999576221704; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00012030178871154674, beta_1=1.3461635690639364, beta_2=1.0848359700799746, early_stopping=True, epsilon=8.69299151113954e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.06584106160121614, max_iter=2000, solver=sgd, validation_fraction=0.21957999576221704; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00012030178871154674, beta_1=1.3461635690639364, beta_2=1.0848359700799746, early_stopping=True, epsilon=8.69299151113954e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.06584106160121614, max_iter=2000, solver=sgd, validation_fraction=0.21957999576221704; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.2087541473056965e-06, beta_1=1.7689399423098324, beta_2=1.7323593965363417, early_stopping=True, epsilon=2.658754398327272e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.007119418600172993, max_iter=2000, solver=sgd, validation_fraction=0.10141326104394349; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.2087541473056965e-06, beta_1=1.7689399423098324, beta_2=1.7323593965363417, early_stopping=True, epsilon=2.658754398327272e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.007119418600172993, max_iter=2000, solver=sgd, validation_fraction=0.10141326104394349; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.2087541473056965e-06, beta_1=1.7689399423098324, beta_2=1.7323593965363417, early_stopping=True, epsilon=2.658754398327272e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.007119418600172993, max_iter=2000, solver=sgd, validation_fraction=0.10141326104394349; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=3.6618192203924288e-06, beta_1=1.6013947837732858, beta_2=0.9745431886154029, early_stopping=True, epsilon=9.413993046829942e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007593893885357799, max_iter=1000, solver=adam, validation_fraction=0.13976848081776105; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.2087541473056965e-06, beta_1=1.7689399423098324, beta_2=1.7323593965363417, early_stopping=True, epsilon=2.658754398327272e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.007119418600172993, max_iter=2000, solver=sgd, validation_fraction=0.10141326104394349; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.2087541473056965e-06, beta_1=1.7689399423098324, beta_2=1.7323593965363417, early_stopping=True, epsilon=2.658754398327272e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.007119418600172993, max_iter=2000, solver=sgd, validation_fraction=0.10141326104394349; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.461896279370496e-05, beta_1=1.411241041827657, beta_2=1.0394799112659767, early_stopping=True, epsilon=3.839629299804172e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0226739865237804, max_iter=1000, solver=sgd, validation_fraction=0.20284688768272233; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=3.6618192203924288e-06, beta_1=1.6013947837732858, beta_2=0.9745431886154029, early_stopping=True, epsilon=9.413993046829942e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007593893885357799, max_iter=1000, solver=adam, validation_fraction=0.13976848081776105; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=3.6618192203924288e-06, beta_1=1.6013947837732858, beta_2=0.9745431886154029, early_stopping=True, epsilon=9.413993046829942e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007593893885357799, max_iter=1000, solver=adam, validation_fraction=0.13976848081776105; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=3.6618192203924288e-06, beta_1=1.6013947837732858, beta_2=0.9745431886154029, early_stopping=True, epsilon=9.413993046829942e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007593893885357799, max_iter=1000, solver=adam, validation_fraction=0.13976848081776105; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=3.6618192203924288e-06, beta_1=1.6013947837732858, beta_2=0.9745431886154029, early_stopping=True, epsilon=9.413993046829942e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007593893885357799, max_iter=1000, solver=adam, validation_fraction=0.13976848081776105; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0014477786306928671, beta_1=1.4053540148062305, beta_2=1.8262082484254978, early_stopping=True, epsilon=2.005183170872387e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.03549079546095973, max_iter=2000, solver=sgd, validation_fraction=0.11908202329808226; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0014477786306928671, beta_1=1.4053540148062305, beta_2=1.8262082484254978, early_stopping=True, epsilon=2.005183170872387e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.03549079546095973, max_iter=2000, solver=sgd, validation_fraction=0.11908202329808226; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0014477786306928671, beta_1=1.4053540148062305, beta_2=1.8262082484254978, early_stopping=True, epsilon=2.005183170872387e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.03549079546095973, max_iter=2000, solver=sgd, validation_fraction=0.11908202329808226; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0014477786306928671, beta_1=1.4053540148062305, beta_2=1.8262082484254978, early_stopping=True, epsilon=2.005183170872387e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.03549079546095973, max_iter=2000, solver=sgd, validation_fraction=0.11908202329808226; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0014477786306928671, beta_1=1.4053540148062305, beta_2=1.8262082484254978, early_stopping=True, epsilon=2.005183170872387e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.03549079546095973, max_iter=2000, solver=sgd, validation_fraction=0.11908202329808226; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.753594952976443e-05, beta_1=1.1248581387047203, beta_2=1.6295332177202302, early_stopping=True, epsilon=1.8841476921545105e-08, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0026100256506134765, max_iter=1000, solver=adam, validation_fraction=0.24264895744459902; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.753594952976443e-05, beta_1=1.1248581387047203, beta_2=1.6295332177202302, early_stopping=True, epsilon=1.8841476921545105e-08, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0026100256506134765, max_iter=1000, solver=adam, validation_fraction=0.24264895744459902; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.753594952976443e-05, beta_1=1.1248581387047203, beta_2=1.6295332177202302, early_stopping=True, epsilon=1.8841476921545105e-08, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0026100256506134765, max_iter=1000, solver=adam, validation_fraction=0.24264895744459902; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.753594952976443e-05, beta_1=1.1248581387047203, beta_2=1.6295332177202302, early_stopping=True, epsilon=1.8841476921545105e-08, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0026100256506134765, max_iter=1000, solver=adam, validation_fraction=0.24264895744459902; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.753594952976443e-05, beta_1=1.1248581387047203, beta_2=1.6295332177202302, early_stopping=True, epsilon=1.8841476921545105e-08, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0026100256506134765, max_iter=1000, solver=adam, validation_fraction=0.24264895744459902; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0007707580772445939, beta_1=1.0357489348292068, beta_2=1.1560427159290478, early_stopping=True, epsilon=1.2046674587990324e-09, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.0020797422068521733, max_iter=1000, solver=adam, validation_fraction=0.27915271913470385; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0007707580772445939, beta_1=1.0357489348292068, beta_2=1.1560427159290478, early_stopping=True, epsilon=1.2046674587990324e-09, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.0020797422068521733, max_iter=1000, solver=adam, validation_fraction=0.27915271913470385; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0007707580772445939, beta_1=1.0357489348292068, beta_2=1.1560427159290478, early_stopping=True, epsilon=1.2046674587990324e-09, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.0020797422068521733, max_iter=1000, solver=adam, validation_fraction=0.27915271913470385; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0007707580772445939, beta_1=1.0357489348292068, beta_2=1.1560427159290478, early_stopping=True, epsilon=1.2046674587990324e-09, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.0020797422068521733, max_iter=1000, solver=adam, validation_fraction=0.27915271913470385; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.461896279370496e-05, beta_1=1.411241041827657, beta_2=1.0394799112659767, early_stopping=True, epsilon=3.839629299804172e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0226739865237804, max_iter=1000, solver=sgd, validation_fraction=0.20284688768272233; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0007707580772445939, beta_1=1.0357489348292068, beta_2=1.1560427159290478, early_stopping=True, epsilon=1.2046674587990324e-09, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.0020797422068521733, max_iter=1000, solver=adam, validation_fraction=0.27915271913470385; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.808939009276714e-05, beta_1=1.308062120473538, beta_2=1.8074757172787006, early_stopping=True, epsilon=3.151987295193894e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.01847793417351926, max_iter=2000, solver=adam, validation_fraction=0.1153959819657586; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.808939009276714e-05, beta_1=1.308062120473538, beta_2=1.8074757172787006, early_stopping=True, epsilon=3.151987295193894e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.01847793417351926, max_iter=2000, solver=adam, validation_fraction=0.1153959819657586; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.808939009276714e-05, beta_1=1.308062120473538, beta_2=1.8074757172787006, early_stopping=True, epsilon=3.151987295193894e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.01847793417351926, max_iter=2000, solver=adam, validation_fraction=0.1153959819657586; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.808939009276714e-05, beta_1=1.308062120473538, beta_2=1.8074757172787006, early_stopping=True, epsilon=3.151987295193894e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.01847793417351926, max_iter=2000, solver=adam, validation_fraction=0.1153959819657586; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.808939009276714e-05, beta_1=1.308062120473538, beta_2=1.8074757172787006, early_stopping=True, epsilon=3.151987295193894e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.01847793417351926, max_iter=2000, solver=adam, validation_fraction=0.1153959819657586; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0006013671933592871, beta_1=1.6795873711762423, beta_2=1.5242916127289798, early_stopping=True, epsilon=3.901821268272626e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0023420907100434145, max_iter=2000, solver=sgd, validation_fraction=0.18330198957407326; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0006013671933592871, beta_1=1.6795873711762423, beta_2=1.5242916127289798, early_stopping=True, epsilon=3.901821268272626e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0023420907100434145, max_iter=2000, solver=sgd, validation_fraction=0.18330198957407326; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0006013671933592871, beta_1=1.6795873711762423, beta_2=1.5242916127289798, early_stopping=True, epsilon=3.901821268272626e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0023420907100434145, max_iter=2000, solver=sgd, validation_fraction=0.18330198957407326; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0006013671933592871, beta_1=1.6795873711762423, beta_2=1.5242916127289798, early_stopping=True, epsilon=3.901821268272626e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0023420907100434145, max_iter=2000, solver=sgd, validation_fraction=0.18330198957407326; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0006013671933592871, beta_1=1.6795873711762423, beta_2=1.5242916127289798, early_stopping=True, epsilon=3.901821268272626e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0023420907100434145, max_iter=2000, solver=sgd, validation_fraction=0.18330198957407326; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00014367095138664247, beta_1=1.6066327150088986, beta_2=1.796001690793501, early_stopping=True, epsilon=4.325207525386531e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00048284249748183273, max_iter=2000, solver=adam, validation_fraction=0.26360295318449867; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00014367095138664247, beta_1=1.6066327150088986, beta_2=1.796001690793501, early_stopping=True, epsilon=4.325207525386531e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00048284249748183273, max_iter=2000, solver=adam, validation_fraction=0.26360295318449867; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00014367095138664247, beta_1=1.6066327150088986, beta_2=1.796001690793501, early_stopping=True, epsilon=4.325207525386531e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00048284249748183273, max_iter=2000, solver=adam, validation_fraction=0.26360295318449867; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00014367095138664247, beta_1=1.6066327150088986, beta_2=1.796001690793501, early_stopping=True, epsilon=4.325207525386531e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00048284249748183273, max_iter=2000, solver=adam, validation_fraction=0.26360295318449867; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00014367095138664247, beta_1=1.6066327150088986, beta_2=1.796001690793501, early_stopping=True, epsilon=4.325207525386531e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00048284249748183273, max_iter=2000, solver=adam, validation_fraction=0.26360295318449867; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.656246725411735e-05, beta_1=0.9644911972897988, beta_2=1.4340360104335046, early_stopping=True, epsilon=9.32523838591071e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0006430385379260096, max_iter=2000, solver=adam, validation_fraction=0.13365820843458612; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.656246725411735e-05, beta_1=0.9644911972897988, beta_2=1.4340360104335046, early_stopping=True, epsilon=9.32523838591071e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0006430385379260096, max_iter=2000, solver=adam, validation_fraction=0.13365820843458612; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.656246725411735e-05, beta_1=0.9644911972897988, beta_2=1.4340360104335046, early_stopping=True, epsilon=9.32523838591071e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0006430385379260096, max_iter=2000, solver=adam, validation_fraction=0.13365820843458612; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.656246725411735e-05, beta_1=0.9644911972897988, beta_2=1.4340360104335046, early_stopping=True, epsilon=9.32523838591071e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0006430385379260096, max_iter=2000, solver=adam, validation_fraction=0.13365820843458612; total time= 0.0s\n",
+ "Iteration 1, loss = 107.34435404\n",
+ "[CV] END activation=relu, alpha=1.656246725411735e-05, beta_1=0.9644911972897988, beta_2=1.4340360104335046, early_stopping=True, epsilon=9.32523838591071e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0006430385379260096, max_iter=2000, solver=adam, validation_fraction=0.13365820843458612; total time= 0.0s\n",
+ "Iteration 1, loss = 106.17526909\n",
+ "[CV] END activation=relu, alpha=4.124247162072427e-05, beta_1=0.8648273548618726, beta_2=1.1538900223929514, early_stopping=True, epsilon=3.1171099804016666e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000799162192038436, max_iter=1000, solver=sgd, validation_fraction=0.10737738947090657; total time= 0.0s\n",
+ "Iteration 1, loss = 105.07778066\n",
+ "[CV] END activation=relu, alpha=4.124247162072427e-05, beta_1=0.8648273548618726, beta_2=1.1538900223929514, early_stopping=True, epsilon=3.1171099804016666e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000799162192038436, max_iter=1000, solver=sgd, validation_fraction=0.10737738947090657; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=4.124247162072427e-05, beta_1=0.8648273548618726, beta_2=1.1538900223929514, early_stopping=True, epsilon=3.1171099804016666e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000799162192038436, max_iter=1000, solver=sgd, validation_fraction=0.10737738947090657; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=4.124247162072427e-05, beta_1=0.8648273548618726, beta_2=1.1538900223929514, early_stopping=True, epsilon=3.1171099804016666e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000799162192038436, max_iter=1000, solver=sgd, validation_fraction=0.10737738947090657; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=4.124247162072427e-05, beta_1=0.8648273548618726, beta_2=1.1538900223929514, early_stopping=True, epsilon=3.1171099804016666e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000799162192038436, max_iter=1000, solver=sgd, validation_fraction=0.10737738947090657; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.008062316132568977, beta_1=1.2106259763049132, beta_2=0.9330474278272584, early_stopping=True, epsilon=4.89939546714915e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.011018344696523035, max_iter=1000, solver=sgd, validation_fraction=0.18955663291461833; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.008062316132568977, beta_1=1.2106259763049132, beta_2=0.9330474278272584, early_stopping=True, epsilon=4.89939546714915e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.011018344696523035, max_iter=1000, solver=sgd, validation_fraction=0.18955663291461833; total time= 0.0s\n",
+ "Iteration 1, loss = 105.63723363\n",
+ "[CV] END activation=relu, alpha=0.008062316132568977, beta_1=1.2106259763049132, beta_2=0.9330474278272584, early_stopping=True, epsilon=4.89939546714915e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.011018344696523035, max_iter=1000, solver=sgd, validation_fraction=0.18955663291461833; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.008062316132568977, beta_1=1.2106259763049132, beta_2=0.9330474278272584, early_stopping=True, epsilon=4.89939546714915e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.011018344696523035, max_iter=1000, solver=sgd, validation_fraction=0.18955663291461833; total time= 0.0s\n",
+ "Iteration 1, loss = 105.98245413\n",
+ "[CV] END activation=relu, alpha=0.008062316132568977, beta_1=1.2106259763049132, beta_2=0.9330474278272584, early_stopping=True, epsilon=4.89939546714915e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.011018344696523035, max_iter=1000, solver=sgd, validation_fraction=0.18955663291461833; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=9.294394155644998e-06, beta_1=1.4714634118584726, beta_2=1.6615434533671847, early_stopping=True, epsilon=2.987274199563844e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0025757392938302766, max_iter=2000, solver=sgd, validation_fraction=0.17976488848891062; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=9.294394155644998e-06, beta_1=1.4714634118584726, beta_2=1.6615434533671847, early_stopping=True, epsilon=2.987274199563844e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0025757392938302766, max_iter=2000, solver=sgd, validation_fraction=0.17976488848891062; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=9.294394155644998e-06, beta_1=1.4714634118584726, beta_2=1.6615434533671847, early_stopping=True, epsilon=2.987274199563844e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0025757392938302766, max_iter=2000, solver=sgd, validation_fraction=0.17976488848891062; total time= 0.0s\n",
+ "Validation score: 0.503234\n",
+ "Validation score: 0.487596\n",
+ "Validation score: 0.365956\n",
+ "[CV] END activation=tanh, alpha=9.294394155644998e-06, beta_1=1.4714634118584726, beta_2=1.6615434533671847, early_stopping=True, epsilon=2.987274199563844e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0025757392938302766, max_iter=2000, solver=sgd, validation_fraction=0.17976488848891062; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=9.294394155644998e-06, beta_1=1.4714634118584726, beta_2=1.6615434533671847, early_stopping=True, epsilon=2.987274199563844e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.0025757392938302766, max_iter=2000, solver=sgd, validation_fraction=0.17976488848891062; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=2.2969898716342096e-06, beta_1=1.6344671930936487, beta_2=1.2207479869652387, early_stopping=True, epsilon=2.3606794572813078e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.00592487005199432, max_iter=1000, solver=sgd, validation_fraction=0.10331756578557123; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=2.2969898716342096e-06, beta_1=1.6344671930936487, beta_2=1.2207479869652387, early_stopping=True, epsilon=2.3606794572813078e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.00592487005199432, max_iter=1000, solver=sgd, validation_fraction=0.10331756578557123; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=2.2969898716342096e-06, beta_1=1.6344671930936487, beta_2=1.2207479869652387, early_stopping=True, epsilon=2.3606794572813078e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.00592487005199432, max_iter=1000, solver=sgd, validation_fraction=0.10331756578557123; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=2.2969898716342096e-06, beta_1=1.6344671930936487, beta_2=1.2207479869652387, early_stopping=True, epsilon=2.3606794572813078e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.00592487005199432, max_iter=1000, solver=sgd, validation_fraction=0.10331756578557123; total time= 0.0s\n",
+ "Validation score: 0.392928\n",
+ "[CV] END activation=logistic, alpha=2.2969898716342096e-06, beta_1=1.6344671930936487, beta_2=1.2207479869652387, early_stopping=True, epsilon=2.3606794572813078e-09, hidden_layer_sizes=(200, 150, 100), learning_rate=constant, learning_rate_init=0.00592487005199432, max_iter=1000, solver=sgd, validation_fraction=0.10331756578557123; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.001729833026599907, beta_1=1.1483173213044378, beta_2=0.9961669334363117, early_stopping=True, epsilon=7.604077403300586e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.000258560889073134, max_iter=2000, solver=adam, validation_fraction=0.12269470424811782; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.001729833026599907, beta_1=1.1483173213044378, beta_2=0.9961669334363117, early_stopping=True, epsilon=7.604077403300586e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.000258560889073134, max_iter=2000, solver=adam, validation_fraction=0.12269470424811782; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.001729833026599907, beta_1=1.1483173213044378, beta_2=0.9961669334363117, early_stopping=True, epsilon=7.604077403300586e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.000258560889073134, max_iter=2000, solver=adam, validation_fraction=0.12269470424811782; total time= 0.0s\n",
+ "Validation score: 0.494786\n",
+ "[CV] END activation=logistic, alpha=0.001729833026599907, beta_1=1.1483173213044378, beta_2=0.9961669334363117, early_stopping=True, epsilon=7.604077403300586e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.000258560889073134, max_iter=2000, solver=adam, validation_fraction=0.12269470424811782; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.001729833026599907, beta_1=1.1483173213044378, beta_2=0.9961669334363117, early_stopping=True, epsilon=7.604077403300586e-08, hidden_layer_sizes=(100, 100), learning_rate=adaptive, learning_rate_init=0.000258560889073134, max_iter=2000, solver=adam, validation_fraction=0.12269470424811782; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00014648457497911012, beta_1=1.4950886149457372, beta_2=1.12852716679512, early_stopping=True, epsilon=2.23825649904092e-09, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0038810723164094817, max_iter=2000, solver=adam, validation_fraction=0.11862055356117984; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00014648457497911012, beta_1=1.4950886149457372, beta_2=1.12852716679512, early_stopping=True, epsilon=2.23825649904092e-09, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0038810723164094817, max_iter=2000, solver=adam, validation_fraction=0.11862055356117984; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00014648457497911012, beta_1=1.4950886149457372, beta_2=1.12852716679512, early_stopping=True, epsilon=2.23825649904092e-09, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0038810723164094817, max_iter=2000, solver=adam, validation_fraction=0.11862055356117984; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00014648457497911012, beta_1=1.4950886149457372, beta_2=1.12852716679512, early_stopping=True, epsilon=2.23825649904092e-09, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0038810723164094817, max_iter=2000, solver=adam, validation_fraction=0.11862055356117984; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00014648457497911012, beta_1=1.4950886149457372, beta_2=1.12852716679512, early_stopping=True, epsilon=2.23825649904092e-09, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0038810723164094817, max_iter=2000, solver=adam, validation_fraction=0.11862055356117984; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.003996430167694255, beta_1=1.4324683558159947, beta_2=1.2389958880695957, early_stopping=True, epsilon=4.9936620665064145e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.04584154780136381, max_iter=2000, solver=adam, validation_fraction=0.22840632923085757; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.003996430167694255, beta_1=1.4324683558159947, beta_2=1.2389958880695957, early_stopping=True, epsilon=4.9936620665064145e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.04584154780136381, max_iter=2000, solver=adam, validation_fraction=0.22840632923085757; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.003996430167694255, beta_1=1.4324683558159947, beta_2=1.2389958880695957, early_stopping=True, epsilon=4.9936620665064145e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.04584154780136381, max_iter=2000, solver=adam, validation_fraction=0.22840632923085757; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.003996430167694255, beta_1=1.4324683558159947, beta_2=1.2389958880695957, early_stopping=True, epsilon=4.9936620665064145e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.04584154780136381, max_iter=2000, solver=adam, validation_fraction=0.22840632923085757; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.003996430167694255, beta_1=1.4324683558159947, beta_2=1.2389958880695957, early_stopping=True, epsilon=4.9936620665064145e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.04584154780136381, max_iter=2000, solver=adam, validation_fraction=0.22840632923085757; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.005527642876529975, beta_1=1.5845553104628296, beta_2=1.5689213558887571, early_stopping=True, epsilon=1.4500174972770093e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.009783749110062351, max_iter=1000, solver=sgd, validation_fraction=0.13216161028349974; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.005527642876529975, beta_1=1.5845553104628296, beta_2=1.5689213558887571, early_stopping=True, epsilon=1.4500174972770093e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.009783749110062351, max_iter=1000, solver=sgd, validation_fraction=0.13216161028349974; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.005527642876529975, beta_1=1.5845553104628296, beta_2=1.5689213558887571, early_stopping=True, epsilon=1.4500174972770093e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.009783749110062351, max_iter=1000, solver=sgd, validation_fraction=0.13216161028349974; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.005527642876529975, beta_1=1.5845553104628296, beta_2=1.5689213558887571, early_stopping=True, epsilon=1.4500174972770093e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.009783749110062351, max_iter=1000, solver=sgd, validation_fraction=0.13216161028349974; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.005527642876529975, beta_1=1.5845553104628296, beta_2=1.5689213558887571, early_stopping=True, epsilon=1.4500174972770093e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.009783749110062351, max_iter=1000, solver=sgd, validation_fraction=0.13216161028349974; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=8.759009842205827e-05, beta_1=1.2479757188432612, beta_2=1.8943580168645595, early_stopping=True, epsilon=2.248280560174535e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030316645506200065, max_iter=2000, solver=sgd, validation_fraction=0.173293756916572; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=8.759009842205827e-05, beta_1=1.2479757188432612, beta_2=1.8943580168645595, early_stopping=True, epsilon=2.248280560174535e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030316645506200065, max_iter=2000, solver=sgd, validation_fraction=0.173293756916572; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=8.759009842205827e-05, beta_1=1.2479757188432612, beta_2=1.8943580168645595, early_stopping=True, epsilon=2.248280560174535e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030316645506200065, max_iter=2000, solver=sgd, validation_fraction=0.173293756916572; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=8.759009842205827e-05, beta_1=1.2479757188432612, beta_2=1.8943580168645595, early_stopping=True, epsilon=2.248280560174535e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030316645506200065, max_iter=2000, solver=sgd, validation_fraction=0.173293756916572; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=8.759009842205827e-05, beta_1=1.2479757188432612, beta_2=1.8943580168645595, early_stopping=True, epsilon=2.248280560174535e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030316645506200065, max_iter=2000, solver=sgd, validation_fraction=0.173293756916572; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0007651731056383424, beta_1=1.1077527310605368, beta_2=1.4424859765318438, early_stopping=True, epsilon=1.0414253710293554e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0005641381315708959, max_iter=2000, solver=sgd, validation_fraction=0.2957785716550018; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0007651731056383424, beta_1=1.1077527310605368, beta_2=1.4424859765318438, early_stopping=True, epsilon=1.0414253710293554e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0005641381315708959, max_iter=2000, solver=sgd, validation_fraction=0.2957785716550018; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0007651731056383424, beta_1=1.1077527310605368, beta_2=1.4424859765318438, early_stopping=True, epsilon=1.0414253710293554e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0005641381315708959, max_iter=2000, solver=sgd, validation_fraction=0.2957785716550018; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0007651731056383424, beta_1=1.1077527310605368, beta_2=1.4424859765318438, early_stopping=True, epsilon=1.0414253710293554e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0005641381315708959, max_iter=2000, solver=sgd, validation_fraction=0.2957785716550018; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0007651731056383424, beta_1=1.1077527310605368, beta_2=1.4424859765318438, early_stopping=True, epsilon=1.0414253710293554e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0005641381315708959, max_iter=2000, solver=sgd, validation_fraction=0.2957785716550018; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0036998679204890915, beta_1=1.4305074873712655, beta_2=1.6947318224112942, early_stopping=True, epsilon=1.0122183035228772e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030029844369151297, max_iter=1000, solver=sgd, validation_fraction=0.24449042305230106; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0036998679204890915, beta_1=1.4305074873712655, beta_2=1.6947318224112942, early_stopping=True, epsilon=1.0122183035228772e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030029844369151297, max_iter=1000, solver=sgd, validation_fraction=0.24449042305230106; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0036998679204890915, beta_1=1.4305074873712655, beta_2=1.6947318224112942, early_stopping=True, epsilon=1.0122183035228772e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030029844369151297, max_iter=1000, solver=sgd, validation_fraction=0.24449042305230106; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0036998679204890915, beta_1=1.4305074873712655, beta_2=1.6947318224112942, early_stopping=True, epsilon=1.0122183035228772e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030029844369151297, max_iter=1000, solver=sgd, validation_fraction=0.24449042305230106; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0036998679204890915, beta_1=1.4305074873712655, beta_2=1.6947318224112942, early_stopping=True, epsilon=1.0122183035228772e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0030029844369151297, max_iter=1000, solver=sgd, validation_fraction=0.24449042305230106; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00019409609450297477, beta_1=1.5677854602920027, beta_2=0.9435994113772583, early_stopping=True, epsilon=9.75216457233856e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0006897330321733757, max_iter=2000, solver=adam, validation_fraction=0.2495437547794828; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00019409609450297477, beta_1=1.5677854602920027, beta_2=0.9435994113772583, early_stopping=True, epsilon=9.75216457233856e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0006897330321733757, max_iter=2000, solver=adam, validation_fraction=0.2495437547794828; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00019409609450297477, beta_1=1.5677854602920027, beta_2=0.9435994113772583, early_stopping=True, epsilon=9.75216457233856e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0006897330321733757, max_iter=2000, solver=adam, validation_fraction=0.2495437547794828; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00019409609450297477, beta_1=1.5677854602920027, beta_2=0.9435994113772583, early_stopping=True, epsilon=9.75216457233856e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0006897330321733757, max_iter=2000, solver=adam, validation_fraction=0.2495437547794828; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00019409609450297477, beta_1=1.5677854602920027, beta_2=0.9435994113772583, early_stopping=True, epsilon=9.75216457233856e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.0006897330321733757, max_iter=2000, solver=adam, validation_fraction=0.2495437547794828; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.005167425813322415, beta_1=1.227755964168997, beta_2=1.8665581535617652, early_stopping=True, epsilon=8.457460033731488e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007644457600399744, max_iter=1000, solver=sgd, validation_fraction=0.2702273343033714; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.005167425813322415, beta_1=1.227755964168997, beta_2=1.8665581535617652, early_stopping=True, epsilon=8.457460033731488e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007644457600399744, max_iter=1000, solver=sgd, validation_fraction=0.2702273343033714; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.005167425813322415, beta_1=1.227755964168997, beta_2=1.8665581535617652, early_stopping=True, epsilon=8.457460033731488e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007644457600399744, max_iter=1000, solver=sgd, validation_fraction=0.2702273343033714; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.005167425813322415, beta_1=1.227755964168997, beta_2=1.8665581535617652, early_stopping=True, epsilon=8.457460033731488e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007644457600399744, max_iter=1000, solver=sgd, validation_fraction=0.2702273343033714; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.005167425813322415, beta_1=1.227755964168997, beta_2=1.8665581535617652, early_stopping=True, epsilon=8.457460033731488e-08, hidden_layer_sizes=(100,), learning_rate=adaptive, learning_rate_init=0.0007644457600399744, max_iter=1000, solver=sgd, validation_fraction=0.2702273343033714; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=4.763991596630587e-06, beta_1=1.356244461195892, beta_2=1.836061158683365, early_stopping=True, epsilon=2.4663777473099754e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00042340516626221137, max_iter=1000, solver=sgd, validation_fraction=0.1717293562592328; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=4.763991596630587e-06, beta_1=1.356244461195892, beta_2=1.836061158683365, early_stopping=True, epsilon=2.4663777473099754e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00042340516626221137, max_iter=1000, solver=sgd, validation_fraction=0.1717293562592328; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=4.763991596630587e-06, beta_1=1.356244461195892, beta_2=1.836061158683365, early_stopping=True, epsilon=2.4663777473099754e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00042340516626221137, max_iter=1000, solver=sgd, validation_fraction=0.1717293562592328; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=4.763991596630587e-06, beta_1=1.356244461195892, beta_2=1.836061158683365, early_stopping=True, epsilon=2.4663777473099754e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00042340516626221137, max_iter=1000, solver=sgd, validation_fraction=0.1717293562592328; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=4.763991596630587e-06, beta_1=1.356244461195892, beta_2=1.836061158683365, early_stopping=True, epsilon=2.4663777473099754e-08, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00042340516626221137, max_iter=1000, solver=sgd, validation_fraction=0.1717293562592328; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00011839097834757703, beta_1=1.6764956988560276, beta_2=1.640694540892429, early_stopping=True, epsilon=2.4776016523736907e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0011980458901470984, max_iter=1000, solver=sgd, validation_fraction=0.26187223109570273; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00011839097834757703, beta_1=1.6764956988560276, beta_2=1.640694540892429, early_stopping=True, epsilon=2.4776016523736907e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0011980458901470984, max_iter=1000, solver=sgd, validation_fraction=0.26187223109570273; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00011839097834757703, beta_1=1.6764956988560276, beta_2=1.640694540892429, early_stopping=True, epsilon=2.4776016523736907e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0011980458901470984, max_iter=1000, solver=sgd, validation_fraction=0.26187223109570273; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00011839097834757703, beta_1=1.6764956988560276, beta_2=1.640694540892429, early_stopping=True, epsilon=2.4776016523736907e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0011980458901470984, max_iter=1000, solver=sgd, validation_fraction=0.26187223109570273; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.00011839097834757703, beta_1=1.6764956988560276, beta_2=1.640694540892429, early_stopping=True, epsilon=2.4776016523736907e-08, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0011980458901470984, max_iter=1000, solver=sgd, validation_fraction=0.26187223109570273; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.0588337464036476e-05, beta_1=1.4109021971548148, beta_2=0.9815860209822004, early_stopping=True, epsilon=1.0241645176346665e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0003826677479763707, max_iter=2000, solver=sgd, validation_fraction=0.17935676544277768; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.0588337464036476e-05, beta_1=1.4109021971548148, beta_2=0.9815860209822004, early_stopping=True, epsilon=1.0241645176346665e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0003826677479763707, max_iter=2000, solver=sgd, validation_fraction=0.17935676544277768; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.0588337464036476e-05, beta_1=1.4109021971548148, beta_2=0.9815860209822004, early_stopping=True, epsilon=1.0241645176346665e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0003826677479763707, max_iter=2000, solver=sgd, validation_fraction=0.17935676544277768; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.0588337464036476e-05, beta_1=1.4109021971548148, beta_2=0.9815860209822004, early_stopping=True, epsilon=1.0241645176346665e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0003826677479763707, max_iter=2000, solver=sgd, validation_fraction=0.17935676544277768; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=1.0588337464036476e-05, beta_1=1.4109021971548148, beta_2=0.9815860209822004, early_stopping=True, epsilon=1.0241645176346665e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.0003826677479763707, max_iter=2000, solver=sgd, validation_fraction=0.17935676544277768; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0036309591863459105, beta_1=1.1376571616946842, beta_2=1.2755453943446802, early_stopping=True, epsilon=1.5415722348909027e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.002493412052414958, max_iter=1000, solver=sgd, validation_fraction=0.15730825042565688; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0036309591863459105, beta_1=1.1376571616946842, beta_2=1.2755453943446802, early_stopping=True, epsilon=1.5415722348909027e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.002493412052414958, max_iter=1000, solver=sgd, validation_fraction=0.15730825042565688; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0036309591863459105, beta_1=1.1376571616946842, beta_2=1.2755453943446802, early_stopping=True, epsilon=1.5415722348909027e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.002493412052414958, max_iter=1000, solver=sgd, validation_fraction=0.15730825042565688; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0036309591863459105, beta_1=1.1376571616946842, beta_2=1.2755453943446802, early_stopping=True, epsilon=1.5415722348909027e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.002493412052414958, max_iter=1000, solver=sgd, validation_fraction=0.15730825042565688; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0036309591863459105, beta_1=1.1376571616946842, beta_2=1.2755453943446802, early_stopping=True, epsilon=1.5415722348909027e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=constant, learning_rate_init=0.002493412052414958, max_iter=1000, solver=sgd, validation_fraction=0.15730825042565688; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0027645119606152023, beta_1=1.0500011091553483, beta_2=0.9388308509559803, early_stopping=True, epsilon=4.041392483060387e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0009548908358062307, max_iter=2000, solver=adam, validation_fraction=0.15430858316394838; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0027645119606152023, beta_1=1.0500011091553483, beta_2=0.9388308509559803, early_stopping=True, epsilon=4.041392483060387e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0009548908358062307, max_iter=2000, solver=adam, validation_fraction=0.15430858316394838; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0027645119606152023, beta_1=1.0500011091553483, beta_2=0.9388308509559803, early_stopping=True, epsilon=4.041392483060387e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0009548908358062307, max_iter=2000, solver=adam, validation_fraction=0.15430858316394838; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0027645119606152023, beta_1=1.0500011091553483, beta_2=0.9388308509559803, early_stopping=True, epsilon=4.041392483060387e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0009548908358062307, max_iter=2000, solver=adam, validation_fraction=0.15430858316394838; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.0027645119606152023, beta_1=1.0500011091553483, beta_2=0.9388308509559803, early_stopping=True, epsilon=4.041392483060387e-09, hidden_layer_sizes=(200, 100), learning_rate=adaptive, learning_rate_init=0.0009548908358062307, max_iter=2000, solver=adam, validation_fraction=0.15430858316394838; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=6.746222278126141e-05, beta_1=1.6411810519369694, beta_2=1.0943605959914735, early_stopping=True, epsilon=6.648257162269159e-09, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0002600514485557596, max_iter=2000, solver=adam, validation_fraction=0.2939073734228318; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=6.746222278126141e-05, beta_1=1.6411810519369694, beta_2=1.0943605959914735, early_stopping=True, epsilon=6.648257162269159e-09, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0002600514485557596, max_iter=2000, solver=adam, validation_fraction=0.2939073734228318; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=6.746222278126141e-05, beta_1=1.6411810519369694, beta_2=1.0943605959914735, early_stopping=True, epsilon=6.648257162269159e-09, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0002600514485557596, max_iter=2000, solver=adam, validation_fraction=0.2939073734228318; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=6.746222278126141e-05, beta_1=1.6411810519369694, beta_2=1.0943605959914735, early_stopping=True, epsilon=6.648257162269159e-09, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0002600514485557596, max_iter=2000, solver=adam, validation_fraction=0.2939073734228318; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=6.746222278126141e-05, beta_1=1.6411810519369694, beta_2=1.0943605959914735, early_stopping=True, epsilon=6.648257162269159e-09, hidden_layer_sizes=(200, 100), learning_rate=constant, learning_rate_init=0.0002600514485557596, max_iter=2000, solver=adam, validation_fraction=0.2939073734228318; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=1.9580595319750418e-05, beta_1=1.594391008573935, beta_2=1.170805168036948, early_stopping=True, epsilon=7.549928546183044e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000357273679720162, max_iter=2000, solver=adam, validation_fraction=0.18566289498802158; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=1.9580595319750418e-05, beta_1=1.594391008573935, beta_2=1.170805168036948, early_stopping=True, epsilon=7.549928546183044e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000357273679720162, max_iter=2000, solver=adam, validation_fraction=0.18566289498802158; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=1.9580595319750418e-05, beta_1=1.594391008573935, beta_2=1.170805168036948, early_stopping=True, epsilon=7.549928546183044e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000357273679720162, max_iter=2000, solver=adam, validation_fraction=0.18566289498802158; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=1.9580595319750418e-05, beta_1=1.594391008573935, beta_2=1.170805168036948, early_stopping=True, epsilon=7.549928546183044e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000357273679720162, max_iter=2000, solver=adam, validation_fraction=0.18566289498802158; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=1.9580595319750418e-05, beta_1=1.594391008573935, beta_2=1.170805168036948, early_stopping=True, epsilon=7.549928546183044e-09, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.000357273679720162, max_iter=2000, solver=adam, validation_fraction=0.18566289498802158; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.7091271850403913e-06, beta_1=1.714298513898854, beta_2=1.3423079945081313, early_stopping=True, epsilon=3.0169958884097634e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00035366981180526904, max_iter=1000, solver=adam, validation_fraction=0.2276541187686701; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.7091271850403913e-06, beta_1=1.714298513898854, beta_2=1.3423079945081313, early_stopping=True, epsilon=3.0169958884097634e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00035366981180526904, max_iter=1000, solver=adam, validation_fraction=0.2276541187686701; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.7091271850403913e-06, beta_1=1.714298513898854, beta_2=1.3423079945081313, early_stopping=True, epsilon=3.0169958884097634e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00035366981180526904, max_iter=1000, solver=adam, validation_fraction=0.2276541187686701; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.7091271850403913e-06, beta_1=1.714298513898854, beta_2=1.3423079945081313, early_stopping=True, epsilon=3.0169958884097634e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00035366981180526904, max_iter=1000, solver=adam, validation_fraction=0.2276541187686701; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.7091271850403913e-06, beta_1=1.714298513898854, beta_2=1.3423079945081313, early_stopping=True, epsilon=3.0169958884097634e-09, hidden_layer_sizes=(300, 200, 100), learning_rate=adaptive, learning_rate_init=0.00035366981180526904, max_iter=1000, solver=adam, validation_fraction=0.2276541187686701; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0008945150807271533, beta_1=1.3537996984588894, beta_2=1.511659574159729, early_stopping=True, epsilon=6.9055794274856946e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0011692786931726754, max_iter=1000, solver=sgd, validation_fraction=0.10287869772595118; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0008945150807271533, beta_1=1.3537996984588894, beta_2=1.511659574159729, early_stopping=True, epsilon=6.9055794274856946e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0011692786931726754, max_iter=1000, solver=sgd, validation_fraction=0.10287869772595118; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0008945150807271533, beta_1=1.3537996984588894, beta_2=1.511659574159729, early_stopping=True, epsilon=6.9055794274856946e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0011692786931726754, max_iter=1000, solver=sgd, validation_fraction=0.10287869772595118; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0008945150807271533, beta_1=1.3537996984588894, beta_2=1.511659574159729, early_stopping=True, epsilon=6.9055794274856946e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0011692786931726754, max_iter=1000, solver=sgd, validation_fraction=0.10287869772595118; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.0008945150807271533, beta_1=1.3537996984588894, beta_2=1.511659574159729, early_stopping=True, epsilon=6.9055794274856946e-09, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0011692786931726754, max_iter=1000, solver=sgd, validation_fraction=0.10287869772595118; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.329143589765976e-06, beta_1=0.8940628312802916, beta_2=1.2113821680603551, early_stopping=True, epsilon=9.09957391842177e-08, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0001125857189529804, max_iter=2000, solver=sgd, validation_fraction=0.2613825954101559; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.329143589765976e-06, beta_1=0.8940628312802916, beta_2=1.2113821680603551, early_stopping=True, epsilon=9.09957391842177e-08, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0001125857189529804, max_iter=2000, solver=sgd, validation_fraction=0.2613825954101559; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.329143589765976e-06, beta_1=0.8940628312802916, beta_2=1.2113821680603551, early_stopping=True, epsilon=9.09957391842177e-08, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0001125857189529804, max_iter=2000, solver=sgd, validation_fraction=0.2613825954101559; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.329143589765976e-06, beta_1=0.8940628312802916, beta_2=1.2113821680603551, early_stopping=True, epsilon=9.09957391842177e-08, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0001125857189529804, max_iter=2000, solver=sgd, validation_fraction=0.2613825954101559; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.329143589765976e-06, beta_1=0.8940628312802916, beta_2=1.2113821680603551, early_stopping=True, epsilon=9.09957391842177e-08, hidden_layer_sizes=(200, 150, 100), learning_rate=adaptive, learning_rate_init=0.0001125857189529804, max_iter=2000, solver=sgd, validation_fraction=0.2613825954101559; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=7.222628076034489e-05, beta_1=1.4491239089601207, beta_2=0.9480541183046141, early_stopping=True, epsilon=7.912094453767008e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0006062906489871087, max_iter=2000, solver=sgd, validation_fraction=0.28668726161589664; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=7.222628076034489e-05, beta_1=1.4491239089601207, beta_2=0.9480541183046141, early_stopping=True, epsilon=7.912094453767008e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0006062906489871087, max_iter=2000, solver=sgd, validation_fraction=0.28668726161589664; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=7.222628076034489e-05, beta_1=1.4491239089601207, beta_2=0.9480541183046141, early_stopping=True, epsilon=7.912094453767008e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0006062906489871087, max_iter=2000, solver=sgd, validation_fraction=0.28668726161589664; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=7.222628076034489e-05, beta_1=1.4491239089601207, beta_2=0.9480541183046141, early_stopping=True, epsilon=7.912094453767008e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0006062906489871087, max_iter=2000, solver=sgd, validation_fraction=0.28668726161589664; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=7.222628076034489e-05, beta_1=1.4491239089601207, beta_2=0.9480541183046141, early_stopping=True, epsilon=7.912094453767008e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=adaptive, learning_rate_init=0.0006062906489871087, max_iter=2000, solver=sgd, validation_fraction=0.28668726161589664; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.00014371754621569935, beta_1=1.4832798056287428, beta_2=1.5157895792734748, early_stopping=True, epsilon=7.722949750823e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.039957361305262486, max_iter=2000, solver=adam, validation_fraction=0.26018985893647995; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.00014371754621569935, beta_1=1.4832798056287428, beta_2=1.5157895792734748, early_stopping=True, epsilon=7.722949750823e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.039957361305262486, max_iter=2000, solver=adam, validation_fraction=0.26018985893647995; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.00014371754621569935, beta_1=1.4832798056287428, beta_2=1.5157895792734748, early_stopping=True, epsilon=7.722949750823e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.039957361305262486, max_iter=2000, solver=adam, validation_fraction=0.26018985893647995; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.00014371754621569935, beta_1=1.4832798056287428, beta_2=1.5157895792734748, early_stopping=True, epsilon=7.722949750823e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.039957361305262486, max_iter=2000, solver=adam, validation_fraction=0.26018985893647995; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=0.00014371754621569935, beta_1=1.4832798056287428, beta_2=1.5157895792734748, early_stopping=True, epsilon=7.722949750823e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.039957361305262486, max_iter=2000, solver=adam, validation_fraction=0.26018985893647995; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00019654779079114097, beta_1=0.9283718528806764, beta_2=1.7111230563183293, early_stopping=True, epsilon=4.378032200510872e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.028925477121979116, max_iter=2000, solver=sgd, validation_fraction=0.14133687197534908; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00019654779079114097, beta_1=0.9283718528806764, beta_2=1.7111230563183293, early_stopping=True, epsilon=4.378032200510872e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.028925477121979116, max_iter=2000, solver=sgd, validation_fraction=0.14133687197534908; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00019654779079114097, beta_1=0.9283718528806764, beta_2=1.7111230563183293, early_stopping=True, epsilon=4.378032200510872e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.028925477121979116, max_iter=2000, solver=sgd, validation_fraction=0.14133687197534908; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00019654779079114097, beta_1=0.9283718528806764, beta_2=1.7111230563183293, early_stopping=True, epsilon=4.378032200510872e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.028925477121979116, max_iter=2000, solver=sgd, validation_fraction=0.14133687197534908; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=0.00019654779079114097, beta_1=0.9283718528806764, beta_2=1.7111230563183293, early_stopping=True, epsilon=4.378032200510872e-08, hidden_layer_sizes=(100, 100, 100), learning_rate=constant, learning_rate_init=0.028925477121979116, max_iter=2000, solver=sgd, validation_fraction=0.14133687197534908; total time= 0.0s\n",
+ "Iteration 2, loss = 80.36622753\n",
+ "Iteration 2, loss = 75.59576247\n",
+ "Iteration 2, loss = 76.99806913\n",
+ "[CV] END activation=tanh, alpha=2.3040838394677016e-05, beta_1=1.0604338337076673, beta_2=1.3959878505479768, early_stopping=True, epsilon=2.4309762581888137e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.06455716578617579, max_iter=2000, solver=sgd, validation_fraction=0.18358920634311576; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.3040838394677016e-05, beta_1=1.0604338337076673, beta_2=1.3959878505479768, early_stopping=True, epsilon=2.4309762581888137e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.06455716578617579, max_iter=2000, solver=sgd, validation_fraction=0.18358920634311576; total time= 0.0s\n",
+ "[CV] END activation=tanh, alpha=2.3040838394677016e-05, beta_1=1.0604338337076673, beta_2=1.3959878505479768, early_stopping=True, epsilon=2.4309762581888137e-08, hidden_layer_sizes=(100, 100), learning_rate=constant, learning_rate_init=0.06455716578617579, max_iter=2000, solver=sgd, validation_fraction=0.18358920634311576; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.3431925993528133e-05, beta_1=0.9772621042359432, beta_2=1.6505396901656941, early_stopping=True, epsilon=4.1083693308654244e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0017292310724138062, max_iter=2000, solver=adam, validation_fraction=0.2552825921483994; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.3431925993528133e-05, beta_1=0.9772621042359432, beta_2=1.6505396901656941, early_stopping=True, epsilon=4.1083693308654244e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0017292310724138062, max_iter=2000, solver=adam, validation_fraction=0.2552825921483994; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.3431925993528133e-05, beta_1=0.9772621042359432, beta_2=1.6505396901656941, early_stopping=True, epsilon=4.1083693308654244e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0017292310724138062, max_iter=2000, solver=adam, validation_fraction=0.2552825921483994; total time= 0.0s\n",
+ "Iteration 2, loss = 77.18043556\n",
+ "[CV] END activation=relu, alpha=1.3431925993528133e-05, beta_1=0.9772621042359432, beta_2=1.6505396901656941, early_stopping=True, epsilon=4.1083693308654244e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0017292310724138062, max_iter=2000, solver=adam, validation_fraction=0.2552825921483994; total time= 0.0s\n",
+ "Iteration 2, loss = 78.44012626\n",
+ "Validation score: 0.504119\n",
+ "[CV] END activation=relu, alpha=1.3431925993528133e-05, beta_1=0.9772621042359432, beta_2=1.6505396901656941, early_stopping=True, epsilon=4.1083693308654244e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0017292310724138062, max_iter=2000, solver=adam, validation_fraction=0.2552825921483994; total time= 0.0s\n",
+ "Validation score: 0.455376\n",
+ "[CV] END activation=logistic, alpha=0.0052848090786736055, beta_1=1.6575543390911687, beta_2=1.3289511279722808, early_stopping=True, epsilon=3.1749883464243805e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0002038785830097136, max_iter=1000, solver=adam, validation_fraction=0.20105047448957145; total time= 0.0s\n",
+ "Validation score: 0.494324\n",
+ "[CV] END activation=logistic, alpha=0.0052848090786736055, beta_1=1.6575543390911687, beta_2=1.3289511279722808, early_stopping=True, epsilon=3.1749883464243805e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0002038785830097136, max_iter=1000, solver=adam, validation_fraction=0.20105047448957145; total time= 0.0s\n",
+ "[CV] END activation=logistic, alpha=0.0052848090786736055, beta_1=1.6575543390911687, beta_2=1.3289511279722808, early_stopping=True, epsilon=3.1749883464243805e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0002038785830097136, max_iter=1000, solver=adam, validation_fraction=0.20105047448957145; total time= 0.0s\n",
+ "Validation score: 0.489163\n",
+ "[CV] END activation=logistic, alpha=0.0052848090786736055, beta_1=1.6575543390911687, beta_2=1.3289511279722808, early_stopping=True, epsilon=3.1749883464243805e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0002038785830097136, max_iter=1000, solver=adam, validation_fraction=0.20105047448957145; total time= 0.0s\n",
+ "Validation score: 0.465574\n",
+ "[CV] END activation=logistic, alpha=0.0052848090786736055, beta_1=1.6575543390911687, beta_2=1.3289511279722808, early_stopping=True, epsilon=3.1749883464243805e-08, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.0002038785830097136, max_iter=1000, solver=adam, validation_fraction=0.20105047448957145; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.9063314120324373e-05, beta_1=1.6946277052677043, beta_2=1.2891627585662897, early_stopping=True, epsilon=1.051175676286039e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00018787112256023889, max_iter=1000, solver=sgd, validation_fraction=0.290012393410161; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.9063314120324373e-05, beta_1=1.6946277052677043, beta_2=1.2891627585662897, early_stopping=True, epsilon=1.051175676286039e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00018787112256023889, max_iter=1000, solver=sgd, validation_fraction=0.290012393410161; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.9063314120324373e-05, beta_1=1.6946277052677043, beta_2=1.2891627585662897, early_stopping=True, epsilon=1.051175676286039e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00018787112256023889, max_iter=1000, solver=sgd, validation_fraction=0.290012393410161; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.9063314120324373e-05, beta_1=1.6946277052677043, beta_2=1.2891627585662897, early_stopping=True, epsilon=1.051175676286039e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00018787112256023889, max_iter=1000, solver=sgd, validation_fraction=0.290012393410161; total time= 0.0s\n",
+ "[CV] END activation=relu, alpha=1.9063314120324373e-05, beta_1=1.6946277052677043, beta_2=1.2891627585662897, early_stopping=True, epsilon=1.051175676286039e-09, hidden_layer_sizes=(100,), learning_rate=constant, learning_rate_init=0.00018787112256023889, max_iter=1000, solver=sgd, validation_fraction=0.290012393410161; total time= 0.0s\n",
+ "Iteration 1, loss = 177.18208109\n",
+ "Iteration 1, loss = 178.23709545\n",
+ "Validation score: 0.880378\n",
+ "Validation score: 0.877876\n",
+ "Iteration 1, loss = 668.89193609\n",
+ "Iteration 1, loss = 666.13631196\n",
+ "Validation score: -3.167553\n",
+ "Iteration 1, loss = 670.87739044\n",
+ "Validation score: -3.192504\n",
+ "Iteration 1, loss = 667.84883733\n",
+ "Iteration 2, loss = 13.44947528\n",
+ "Iteration 3, loss = 75.86196503\n",
+ "Validation score: 0.913358\n",
+ "Iteration 2, loss = 13.43630245\n",
+ "Validation score: -3.181701\n",
+ "Iteration 3, loss = 75.51261056\n",
+ "Iteration 3, loss = 74.52637635\n",
+ "Validation score: -3.185294\n",
+ "Iteration 3, loss = 77.35328299\n",
+ "Validation score: 0.913878\n",
+ "Iteration 3, loss = 76.62252298\n",
+ "Validation score: 0.425657\n",
+ "Iteration 1, loss = 665.11113745\n",
+ "Validation score: 0.488143\n",
+ "Validation score: 0.504911\n",
+ "Validation score: 0.493350\n",
+ "Validation score: 0.477334\n",
+ "Iteration 2, loss = 510.36582450\n"
+ ]
+ },
+ {
+ "ename": "KeyboardInterrupt",
+ "evalue": "",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[11], line 30\u001b[0m\n\u001b[1;32m 24\u001b[0m random_search \u001b[38;5;241m=\u001b[39m RandomizedSearchCV(\n\u001b[1;32m 25\u001b[0m mlp, param_distributions, n_iter\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m50\u001b[39m, cv\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m, \n\u001b[1;32m 26\u001b[0m scoring\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mneg_root_mean_squared_error\u001b[39m\u001b[38;5;124m'\u001b[39m, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m, n_jobs\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m\n\u001b[1;32m 27\u001b[0m )\n\u001b[1;32m 29\u001b[0m \u001b[38;5;66;03m# Entraînement\u001b[39;00m\n\u001b[0;32m---> 30\u001b[0m \u001b[43mrandom_search\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_clean_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_clean_train\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;66;03m# Récupérer le meilleur modèle\u001b[39;00m\n\u001b[1;32m 33\u001b[0m best_mlp \u001b[38;5;241m=\u001b[39m random_search\u001b[38;5;241m.\u001b[39mbest_estimator_\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/sklearn/base.py:1389\u001b[0m, in \u001b[0;36m_fit_context.<locals>.decorator.<locals>.wrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1382\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[1;32m 1384\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[1;32m 1385\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[1;32m 1386\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[1;32m 1387\u001b[0m )\n\u001b[1;32m 1388\u001b[0m ):\n\u001b[0;32m-> 1389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfit_method\u001b[49m\u001b[43m(\u001b[49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/sklearn/model_selection/_search.py:1024\u001b[0m, in \u001b[0;36mBaseSearchCV.fit\u001b[0;34m(self, X, y, **params)\u001b[0m\n\u001b[1;32m 1018\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_results(\n\u001b[1;32m 1019\u001b[0m all_candidate_params, n_splits, all_out, all_more_results\n\u001b[1;32m 1020\u001b[0m )\n\u001b[1;32m 1022\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m results\n\u001b[0;32m-> 1024\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_run_search\u001b[49m\u001b[43m(\u001b[49m\u001b[43mevaluate_candidates\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1026\u001b[0m \u001b[38;5;66;03m# multimetric is determined here because in the case of a callable\u001b[39;00m\n\u001b[1;32m 1027\u001b[0m \u001b[38;5;66;03m# self.scoring the return type is only known after calling\u001b[39;00m\n\u001b[1;32m 1028\u001b[0m first_test_score \u001b[38;5;241m=\u001b[39m all_out[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest_scores\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/sklearn/model_selection/_search.py:1951\u001b[0m, in \u001b[0;36mRandomizedSearchCV._run_search\u001b[0;34m(self, evaluate_candidates)\u001b[0m\n\u001b[1;32m 1949\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21m_run_search\u001b[39m(\u001b[38;5;28mself\u001b[39m, evaluate_candidates):\n\u001b[1;32m 1950\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Search n_iter candidates from param_distributions\"\"\"\u001b[39;00m\n\u001b[0;32m-> 1951\u001b[0m \u001b[43mevaluate_candidates\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1952\u001b[0m \u001b[43m \u001b[49m\u001b[43mParameterSampler\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1953\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparam_distributions\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mn_iter\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrandom_state\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrandom_state\u001b[49m\n\u001b[1;32m 1954\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1955\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/sklearn/model_selection/_search.py:970\u001b[0m, in \u001b[0;36mBaseSearchCV.fit.<locals>.evaluate_candidates\u001b[0;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[1;32m 962\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 963\u001b[0m \u001b[38;5;28mprint\u001b[39m(\n\u001b[1;32m 964\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFitting \u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;124m folds for each of \u001b[39m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;124m candidates,\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 965\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m totalling \u001b[39m\u001b[38;5;132;01m{2}\u001b[39;00m\u001b[38;5;124m fits\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\n\u001b[1;32m 966\u001b[0m n_splits, n_candidates, n_candidates \u001b[38;5;241m*\u001b[39m n_splits\n\u001b[1;32m 967\u001b[0m )\n\u001b[1;32m 968\u001b[0m )\n\u001b[0;32m--> 970\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[43mparallel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 971\u001b[0m \u001b[43m \u001b[49m\u001b[43mdelayed\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_fit_and_score\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 972\u001b[0m \u001b[43m \u001b[49m\u001b[43mclone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbase_estimator\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 973\u001b[0m \u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 974\u001b[0m \u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 975\u001b[0m \u001b[43m \u001b[49m\u001b[43mtrain\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 976\u001b[0m \u001b[43m \u001b[49m\u001b[43mtest\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 977\u001b[0m \u001b[43m \u001b[49m\u001b[43mparameters\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparameters\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 978\u001b[0m \u001b[43m \u001b[49m\u001b[43msplit_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msplit_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_splits\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 979\u001b[0m \u001b[43m \u001b[49m\u001b[43mcandidate_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcand_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_candidates\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 980\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfit_and_score_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 981\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 982\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mcand_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mparameters\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43msplit_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtest\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mproduct\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 983\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43menumerate\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcandidate_params\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 984\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43menumerate\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcv\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mrouted_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplitter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 985\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 986\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 988\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(out) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 989\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 990\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo fits were performed. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 991\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWas the CV iterator empty? \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 992\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWere there no candidates?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 993\u001b[0m )\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/sklearn/utils/parallel.py:77\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m 72\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[1;32m 73\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 74\u001b[0m (_with_config(delayed_func, config), args, kwargs)\n\u001b[1;32m 75\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[1;32m 76\u001b[0m )\n\u001b[0;32m---> 77\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43miterable_with_config\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/joblib/parallel.py:2007\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m 2001\u001b[0m \u001b[38;5;66;03m# The first item from the output is blank, but it makes the interpreter\u001b[39;00m\n\u001b[1;32m 2002\u001b[0m \u001b[38;5;66;03m# progress until it enters the Try/Except block of the generator and\u001b[39;00m\n\u001b[1;32m 2003\u001b[0m \u001b[38;5;66;03m# reaches the first `yield` statement. This starts the asynchronous\u001b[39;00m\n\u001b[1;32m 2004\u001b[0m \u001b[38;5;66;03m# dispatch of the tasks to the workers.\u001b[39;00m\n\u001b[1;32m 2005\u001b[0m \u001b[38;5;28mnext\u001b[39m(output)\n\u001b[0;32m-> 2007\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreturn_generator \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43moutput\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/joblib/parallel.py:1650\u001b[0m, in \u001b[0;36mParallel._get_outputs\u001b[0;34m(self, iterator, pre_dispatch)\u001b[0m\n\u001b[1;32m 1647\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m\n\u001b[1;32m 1649\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend\u001b[38;5;241m.\u001b[39mretrieval_context():\n\u001b[0;32m-> 1650\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_retrieve()\n\u001b[1;32m 1652\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mGeneratorExit\u001b[39;00m:\n\u001b[1;32m 1653\u001b[0m \u001b[38;5;66;03m# The generator has been garbage collected before being fully\u001b[39;00m\n\u001b[1;32m 1654\u001b[0m \u001b[38;5;66;03m# consumed. This aborts the remaining tasks if possible and warn\u001b[39;00m\n\u001b[1;32m 1655\u001b[0m \u001b[38;5;66;03m# the user if necessary.\u001b[39;00m\n\u001b[1;32m 1656\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/joblib/parallel.py:1762\u001b[0m, in \u001b[0;36mParallel._retrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1757\u001b[0m \u001b[38;5;66;03m# If the next job is not ready for retrieval yet, we just wait for\u001b[39;00m\n\u001b[1;32m 1758\u001b[0m \u001b[38;5;66;03m# async callbacks to progress.\u001b[39;00m\n\u001b[1;32m 1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ((\u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[1;32m 1760\u001b[0m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mget_status(\n\u001b[1;32m 1761\u001b[0m timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtimeout) \u001b[38;5;241m==\u001b[39m TASK_PENDING)):\n\u001b[0;32m-> 1762\u001b[0m \u001b[43mtime\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msleep\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m0.01\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1763\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m\n\u001b[1;32m 1765\u001b[0m \u001b[38;5;66;03m# We need to be careful: the job list can be filling up as\u001b[39;00m\n\u001b[1;32m 1766\u001b[0m \u001b[38;5;66;03m# we empty it and Python list are not thread-safe by\u001b[39;00m\n\u001b[1;32m 1767\u001b[0m \u001b[38;5;66;03m# default hence the use of the lock\u001b[39;00m\n",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+ ]
+ }
+ ],
+ "source": [
+ "from sklearn.neural_network import MLPRegressor\n",
+ "from sklearn.model_selection import RandomizedSearchCV\n",
+ "from scipy.stats import loguniform, uniform\n",
+ "import numpy as np\n",
"\n",
- "X1_sans_nan = X1_clean.dropna()\n",
- "X1_sans_nan.isna().sum()"
+ "# Définir un espace de recherche large\n",
+ "param_distributions = {\n",
+ " 'hidden_layer_sizes': [(100,), (100, 100), (200, 100), (100, 100, 100), (200, 150, 100), (300, 200, 100)],\n",
+ " 'activation': ['relu', 'tanh', 'logistic'],\n",
+ " 'solver': ['adam', 'sgd'],\n",
+ " 'alpha': loguniform(1e-6, 1e-2),\n",
+ " 'learning_rate': ['constant', 'adaptive'],\n",
+ " 'learning_rate_init': loguniform(1e-4, 1e-1),\n",
+ " 'max_iter': [1000, 2000],\n",
+ " 'early_stopping': [True],\n",
+ " 'validation_fraction': uniform(0.1, 0.2),\n",
+ " 'beta_1': uniform(0.8, 0.999),\n",
+ " 'beta_2': uniform(0.9, 0.9999),\n",
+ " 'epsilon': loguniform(1e-9, 1e-7)\n",
+ "}\n",
+ "\n",
+ "# Recherche aléatoire avec validation croisée\n",
+ "mlp = MLPRegressor(random_state=42, verbose=True)\n",
+ "random_search = RandomizedSearchCV(\n",
+ " mlp, param_distributions, n_iter=50, cv=5, \n",
+ " scoring='neg_root_mean_squared_error', random_state=42, n_jobs=-1, verbose=2\n",
+ ")\n",
+ "\n",
+ "# Entraînement\n",
+ "random_search.fit(X_clean_train, y_clean_train)\n",
+ "\n",
+ "# Récupérer le meilleur modèle\n",
+ "best_mlp = random_search.best_estimator_\n",
+ "print(f\"Meilleurs paramètres: {random_search.best_params_}\")"
]
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 12,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Iteration 1, loss = 143.30715504\n",
+ "Validation score: 0.893588\n",
+ "Iteration 2, loss = 12.04859539\n",
+ "Validation score: 0.918013\n",
+ "Iteration 3, loss = 10.40679944\n",
+ "Validation score: 0.923223\n",
+ "Iteration 4, loss = 10.00400146\n",
+ "Validation score: 0.925454\n",
+ "Iteration 5, loss = 9.75601589\n",
+ "Validation score: 0.926138\n",
+ "Iteration 6, loss = 9.66049169\n",
+ "Validation score: 0.926123\n",
+ "Iteration 7, loss = 9.59790303\n",
+ "Validation score: 0.927131\n",
+ "Iteration 8, loss = 9.52550678\n",
+ "Validation score: 0.927055\n",
+ "Iteration 9, loss = 9.47659040\n",
+ "Validation score: 0.927481\n",
+ "Iteration 10, loss = 9.45962981\n",
+ "Validation score: 0.927283\n",
+ "Iteration 11, loss = 9.42718820\n",
+ "Validation score: 0.927706\n",
+ "Iteration 12, loss = 9.45353437\n",
+ "Validation score: 0.927962\n",
+ "Iteration 13, loss = 9.36331977\n",
+ "Validation score: 0.927139\n",
+ "Iteration 14, loss = 9.35572100\n",
+ "Validation score: 0.927847\n",
+ "Iteration 15, loss = 9.32927541\n",
+ "Validation score: 0.928583\n",
+ "Iteration 16, loss = 9.31623676\n",
+ "Validation score: 0.928188\n",
+ "Iteration 17, loss = 9.30424229\n",
+ "Validation score: 0.928813\n",
+ "Iteration 18, loss = 9.29649915\n",
+ "Validation score: 0.927649\n",
+ "Iteration 19, loss = 9.27627270\n",
+ "Validation score: 0.928085\n",
+ "Iteration 20, loss = 9.26014365\n",
+ "Validation score: 0.928793\n",
+ "Iteration 21, loss = 9.25612244\n",
+ "Validation score: 0.929101\n",
+ "Iteration 22, loss = 9.21590115\n",
+ "Validation score: 0.928841\n",
+ "Iteration 23, loss = 9.23541928\n",
+ "Validation score: 0.929295\n",
+ "Iteration 24, loss = 9.20635183\n",
+ "Validation score: 0.928978\n",
+ "Iteration 25, loss = 9.21133534\n",
+ "Validation score: 0.929316\n",
+ "Iteration 26, loss = 9.21041275\n",
+ "Validation score: 0.928085\n",
+ "Iteration 27, loss = 9.18713185\n",
+ "Validation score: 0.929055\n",
+ "Iteration 28, loss = 9.20083967\n",
+ "Validation score: 0.929457\n",
+ "Iteration 29, loss = 9.15471323\n",
+ "Validation score: 0.929487\n",
+ "Iteration 30, loss = 9.18119637\n",
+ "Validation score: 0.927539\n",
+ "Iteration 31, loss = 9.19465843\n",
+ "Validation score: 0.929721\n",
+ "Iteration 32, loss = 9.15366764\n",
+ "Validation score: 0.928791\n",
+ "Iteration 33, loss = 9.16103848\n",
+ "Validation score: 0.928487\n",
+ "Iteration 34, loss = 9.14901952\n",
+ "Validation score: 0.929939\n",
+ "Iteration 35, loss = 9.12524664\n",
+ "Validation score: 0.929456\n",
+ "Iteration 36, loss = 9.13056174\n",
+ "Validation score: 0.928917\n",
+ "Iteration 37, loss = 9.15431307\n",
+ "Validation score: 0.929995\n",
+ "Iteration 38, loss = 9.14172421\n",
+ "Validation score: 0.929786\n",
+ "Iteration 39, loss = 9.12615450\n",
+ "Validation score: 0.929840\n",
+ "Iteration 40, loss = 9.11613879\n",
+ "Validation score: 0.928722\n",
+ "Iteration 41, loss = 9.10165984\n",
+ "Validation score: 0.929968\n",
+ "Iteration 42, loss = 9.11627955\n",
+ "Validation score: 0.930129\n",
+ "Iteration 43, loss = 9.10381564\n",
+ "Validation score: 0.928496\n",
+ "Iteration 44, loss = 9.08965429\n",
+ "Validation score: 0.929888\n",
+ "Iteration 45, loss = 9.12496471\n",
+ "Validation score: 0.929442\n",
+ "Iteration 46, loss = 9.09357978\n",
+ "Validation score: 0.929192\n",
+ "Iteration 47, loss = 9.08762689\n",
+ "Validation score: 0.929801\n",
+ "Iteration 48, loss = 9.09515311\n",
+ "Validation score: 0.930304\n",
+ "Iteration 49, loss = 9.08211592\n",
+ "Validation score: 0.930191\n",
+ "Iteration 50, loss = 9.06059152\n",
+ "Validation score: 0.930358\n",
+ "Iteration 51, loss = 9.09138309\n",
+ "Validation score: 0.929583\n",
+ "Iteration 52, loss = 9.09277860\n",
+ "Validation score: 0.928219\n",
+ "Iteration 53, loss = 9.09165517\n",
+ "Validation score: 0.930296\n",
+ "Iteration 54, loss = 9.12960319\n",
+ "Validation score: 0.930347\n",
+ "Iteration 55, loss = 9.07192090\n",
+ "Validation score: 0.929925\n",
+ "Iteration 56, loss = 9.05590194\n",
+ "Validation score: 0.930301\n",
+ "Iteration 57, loss = 9.06736315\n",
+ "Validation score: 0.929569\n",
+ "Iteration 58, loss = 9.05163568\n",
+ "Validation score: 0.929873\n",
+ "Iteration 59, loss = 9.08451749\n",
+ "Validation score: 0.930347\n",
+ "Validation score did not improve more than tol=0.000100 for 10 consecutive epochs. Stopping.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "4.269006004869188"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "from sklearn.model_selection import train_test_split\n",
- "X_train, X_test, y_train, y_test = train_test_split(X1_sans_nan.drop(['on'],axis=1), X1_sans_nan['on'], test_size=0.2, random_state=42)\n"
+ "# refaire la distance du cosinus\n",
+ "best_param= {'activation': 'relu', 'alpha': 1.8942844905792806e-06, 'beta_1': 0.9006772233760493, 'beta_2': 0.9182200034689846, 'early_stopping': True, 'epsilon': 1.5448485924752334e-09, 'hidden_layer_sizes': (200, 100), 'learning_rate': 'constant', 'learning_rate_init': 0.0001635181426158941, 'max_iter': 2000, 'solver': 'adam', 'validation_fraction': 0.2689750621938909}\n",
+ "best_mlp = MLPRegressor(random_state=42, verbose=True, **best_param)\n",
+ "best_mlp.fit(X_clean_train, y_clean_train)\n",
+ "# regarder val avec le rmse\n",
+ "\n",
+ "y_pred = best_mlp.predict(X_clean_val)\n",
+ "# rmse\n",
+ "np.sqrt(mean_squared_error(y_clean_val, y_pred)) "
]
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": 37,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "[0]\tvalidation_0-rmse:10.32333\tvalidation_1-rmse:10.39185\n",
- "[1]\tvalidation_0-rmse:10.29032\tvalidation_1-rmse:10.36258\n",
- "[2]\tvalidation_0-rmse:10.25915\tvalidation_1-rmse:10.33404\n",
- "[3]\tvalidation_0-rmse:10.22992\tvalidation_1-rmse:10.30862\n",
- "[4]\tvalidation_0-rmse:10.20204\tvalidation_1-rmse:10.28366\n",
- "[5]\tvalidation_0-rmse:10.17581\tvalidation_1-rmse:10.26081\n",
- "[6]\tvalidation_0-rmse:10.15070\tvalidation_1-rmse:10.23894\n",
- "[7]\tvalidation_0-rmse:10.12647\tvalidation_1-rmse:10.21733\n",
- "[8]\tvalidation_0-rmse:10.10337\tvalidation_1-rmse:10.19649\n",
- "[9]\tvalidation_0-rmse:10.08087\tvalidation_1-rmse:10.17622\n",
- "[10]\tvalidation_0-rmse:10.05985\tvalidation_1-rmse:10.15847\n",
- "[11]\tvalidation_0-rmse:10.03988\tvalidation_1-rmse:10.14029\n",
- "[12]\tvalidation_0-rmse:10.02084\tvalidation_1-rmse:10.12460\n",
- "[13]\tvalidation_0-rmse:10.00285\tvalidation_1-rmse:10.10855\n",
- "[14]\tvalidation_0-rmse:9.98567\tvalidation_1-rmse:10.09444\n",
- "[15]\tvalidation_0-rmse:9.96909\tvalidation_1-rmse:10.07967\n",
- "[16]\tvalidation_0-rmse:9.95318\tvalidation_1-rmse:10.06704\n",
- "[17]\tvalidation_0-rmse:9.93839\tvalidation_1-rmse:10.05572\n",
- "[18]\tvalidation_0-rmse:9.92505\tvalidation_1-rmse:10.04452\n",
- "[19]\tvalidation_0-rmse:9.91030\tvalidation_1-rmse:10.03279\n",
- "[20]\tvalidation_0-rmse:9.89815\tvalidation_1-rmse:10.02348\n",
- "[21]\tvalidation_0-rmse:9.88585\tvalidation_1-rmse:10.01303\n",
- "[22]\tvalidation_0-rmse:9.87483\tvalidation_1-rmse:10.00465\n",
- "[23]\tvalidation_0-rmse:9.86289\tvalidation_1-rmse:9.99492\n",
- "[24]\tvalidation_0-rmse:9.85220\tvalidation_1-rmse:9.98699\n",
+ "[LightGBM] [Debug] Dataset::GetMultiBinFromSparseFeatures: sparse rate 0.761971\n",
+ "[LightGBM] [Debug] Dataset::GetMultiBinFromAllFeatures: sparse rate 0.130294\n",
+ "[LightGBM] [Debug] init for col-wise cost 0.000430 seconds, init for row-wise cost 0.001020 seconds\n",
+ "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001036 seconds.\n",
+ "You can set `force_row_wise=true` to remove the overhead.\n",
+ "And if memory is not enough, you can set `force_col_wise=true`.\n",
+ "[LightGBM] [Debug] Using Dense Multi-Val Bin\n",
+ "[LightGBM] [Info] Total Bins 6340\n",
+ "[LightGBM] [Info] Number of data points in the train set: 44482, number of used features: 33\n",
+ "[LightGBM] [Info] Start training from score 37.336864\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 6\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 22 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 30 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 19 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 24 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 23 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 30 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 18 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 18 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 30 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 26 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 16 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 30 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 23 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 14 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 22 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 14 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 30 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 19 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 20 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 24 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 24 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 26 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 25 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 27 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 26 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 28 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 24 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 29 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n",
+ "[LightGBM] [Debug] Trained a tree with leaves = 31 and depth = 7\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-8 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: #000;\n",
+ " --sklearn-color-text-muted: #666;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-8 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: flex;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ " align-items: start;\n",
+ " justify-content: space-between;\n",
+ " gap: 0.5em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 label.sk-toggleable__label .caption {\n",
+ " font-size: 0.6rem;\n",
+ " font-weight: lighter;\n",
+ " color: var(--sklearn-color-text-muted);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-8 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-8 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-8 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-8 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 0.5em;\n",
+ " text-align: center;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-8 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-8 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LGBMRegressor(learning_rate=0.05, max_depth=7, n_estimators=4000, n_jobs=-1,\n",
+ " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LGBMRegressor</div></div><div><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>LGBMRegressor(learning_rate=0.05, max_depth=7, n_estimators=4000, n_jobs=-1,\n",
+ " verbose=2)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "LGBMRegressor(learning_rate=0.05, max_depth=7, n_estimators=4000, n_jobs=-1,\n",
+ " verbose=2)"
+ ]
+ },
+ "execution_count": 37,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import lightgbm\n",
+ "import optuna\n",
+ "from optuna import Trial\n",
+ "from optuna.samplers import TPESampler\n",
+ "from sklearn.model_selection import cross_val_score\n",
+ "\n",
+ "\n",
+ "model4=lightgbm.LGBMRegressor(n_estimators=4000, learning_rate=0.05, n_jobs=-1,verbose=2,max_depth=7)\n",
+ "model4.fit(X_tr,y_tr)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2.7249980592707375"
+ ]
+ },
+ "execution_count": 38,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pred=model4.predict(X_val)\n",
+ "np.sqrt(mean_squared_error(pred,y_val))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(array([1.3000e+01, 1.0900e+02, 6.5600e+02, 2.7830e+03, 8.1220e+03,\n",
+ " 1.5674e+04, 2.2441e+04, 5.2040e+03, 5.5100e+02, 5.0000e+01]),\n",
+ " array([-54.4 , -46.2836322 , -38.1672644 , -30.05089661,\n",
+ " -21.93452881, -13.81816101, -5.70179321, 2.41457458,\n",
+ " 10.53094238, 18.64731018, 26.76367798]),\n",
+ " <BarContainer object of 10 artists>)"
+ ]
+ },
+ "execution_count": 39,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 640x480 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "y_false=X_train['off']\n",
+ "import matplotlib.pyplot as plt\n",
+ "diff = y_false-y_train\n",
+ "plt.hist(diff)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 17.497033\n",
+ "1 -5.900000\n",
+ "2 26.357908\n",
+ "3 16.753651\n",
+ "4 5.408791\n",
+ " ... \n",
+ "55598 1.900000\n",
+ "55599 -0.600000\n",
+ "55600 4.300000\n",
+ "55601 3.300000\n",
+ "55602 -0.200000\n",
+ "Name: target, Length: 55603, dtype: float64"
+ ]
+ },
+ "execution_count": 56,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# on decompose le signal comme composante principae + bruit on va essayer d'estimer le bruit. La composante principale etant 'off'\n",
+ "\n",
+ "y_a_pred = y_train - X_train['off'].to_numpy()\n",
+ "y_a_pred"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "44464 -5.099191\n",
+ "38133 7.000000\n",
+ "30901 -3.988948\n",
+ "53334 9.528405\n",
+ "32070 13.267738\n",
+ " ... \n",
+ "44732 25.600000\n",
+ "54343 13.952093\n",
+ "38158 14.005115\n",
+ "860 10.700000\n",
+ "15795 1.430612\n",
+ "Name: target, Length: 44482, dtype: float64"
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "\n",
+ "X_tr,X_v,y_tr,y_v=train_test_split(X_train,y_a_pred,random_state=42,test_size=0.2)\n",
+ "\n",
+ "y_tr"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "44464 -5.099191\n",
+ "38133 7.000000\n",
+ "30901 -3.988948\n",
+ "53334 9.528405\n",
+ "32070 13.267738\n",
+ " ... \n",
+ "44732 25.600000\n",
+ "54343 13.952093\n",
+ "38158 14.005115\n",
+ "860 10.700000\n",
+ "15795 1.430612\n",
+ "Name: target, Length: 44482, dtype: float64"
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_tr"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "model_bruit="
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ameltebboune/.pyenv/versions/3.10.12/lib/python3.10/site-packages/xgboost/core.py:158: UserWarning: [20:55:38] WARNING: /Users/runner/work/xgboost/xgboost/src/learner.cc:740: \n",
+ "Parameters: { \"verbose\" } are not used.\n",
+ "\n",
+ " warnings.warn(smsg, UserWarning)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-9 {\n",
+ " /* Definition of color scheme common for light and dark mode */\n",
+ " --sklearn-color-text: #000;\n",
+ " --sklearn-color-text-muted: #666;\n",
+ " --sklearn-color-line: gray;\n",
+ " /* Definition of color scheme for unfitted estimators */\n",
+ " --sklearn-color-unfitted-level-0: #fff5e6;\n",
+ " --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+ " --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+ " --sklearn-color-unfitted-level-3: chocolate;\n",
+ " /* Definition of color scheme for fitted estimators */\n",
+ " --sklearn-color-fitted-level-0: #f0f8ff;\n",
+ " --sklearn-color-fitted-level-1: #d4ebff;\n",
+ " --sklearn-color-fitted-level-2: #b3dbfd;\n",
+ " --sklearn-color-fitted-level-3: cornflowerblue;\n",
+ "\n",
+ " /* Specific color for light theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+ " --sklearn-color-icon: #696969;\n",
+ "\n",
+ " @media (prefers-color-scheme: dark) {\n",
+ " /* Redefinition of color scheme for dark theme */\n",
+ " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+ " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+ " --sklearn-color-icon: #878787;\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 pre {\n",
+ " padding: 0;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 input.sk-hidden--visually {\n",
+ " border: 0;\n",
+ " clip: rect(1px 1px 1px 1px);\n",
+ " clip: rect(1px, 1px, 1px, 1px);\n",
+ " height: 1px;\n",
+ " margin: -1px;\n",
+ " overflow: hidden;\n",
+ " padding: 0;\n",
+ " position: absolute;\n",
+ " width: 1px;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-dashed-wrapped {\n",
+ " border: 1px dashed var(--sklearn-color-line);\n",
+ " margin: 0 0.4em 0.5em 0.4em;\n",
+ " box-sizing: border-box;\n",
+ " padding-bottom: 0.4em;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-container {\n",
+ " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+ " but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+ " so we also need the `!important` here to be able to override the\n",
+ " default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+ " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+ " display: inline-block !important;\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-text-repr-fallback {\n",
+ " display: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-parallel-item,\n",
+ "div.sk-serial,\n",
+ "div.sk-item {\n",
+ " /* draw centered vertical line to link estimators */\n",
+ " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+ " background-size: 2px 100%;\n",
+ " background-repeat: no-repeat;\n",
+ " background-position: center center;\n",
+ "}\n",
+ "\n",
+ "/* Parallel-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel-item::after {\n",
+ " content: \"\";\n",
+ " width: 100%;\n",
+ " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+ " flex-grow: 1;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel {\n",
+ " display: flex;\n",
+ " align-items: stretch;\n",
+ " justify-content: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " position: relative;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel-item {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel-item:first-child::after {\n",
+ " align-self: flex-end;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel-item:last-child::after {\n",
+ " align-self: flex-start;\n",
+ " width: 50%;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-parallel-item:only-child::after {\n",
+ " width: 0;\n",
+ "}\n",
+ "\n",
+ "/* Serial-specific style estimator block */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-serial {\n",
+ " display: flex;\n",
+ " flex-direction: column;\n",
+ " align-items: center;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " padding-right: 1em;\n",
+ " padding-left: 1em;\n",
+ "}\n",
+ "\n",
+ "\n",
+ "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+ "clickable and can be expanded/collapsed.\n",
+ "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+ "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+ "*/\n",
+ "\n",
+ "/* Pipeline and ColumnTransformer style (default) */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-toggleable {\n",
+ " /* Default theme specific background. It is overwritten whether we have a\n",
+ " specific estimator or a Pipeline/ColumnTransformer */\n",
+ " background-color: var(--sklearn-color-background);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable label */\n",
+ "#sk-container-id-9 label.sk-toggleable__label {\n",
+ " cursor: pointer;\n",
+ " display: flex;\n",
+ " width: 100%;\n",
+ " margin-bottom: 0;\n",
+ " padding: 0.5em;\n",
+ " box-sizing: border-box;\n",
+ " text-align: center;\n",
+ " align-items: start;\n",
+ " justify-content: space-between;\n",
+ " gap: 0.5em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 label.sk-toggleable__label .caption {\n",
+ " font-size: 0.6rem;\n",
+ " font-weight: lighter;\n",
+ " color: var(--sklearn-color-text-muted);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 label.sk-toggleable__label-arrow:before {\n",
+ " /* Arrow on the left of the label */\n",
+ " content: \"▸\";\n",
+ " float: left;\n",
+ " margin-right: 0.25em;\n",
+ " color: var(--sklearn-color-icon);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {\n",
+ " color: var(--sklearn-color-text);\n",
+ "}\n",
+ "\n",
+ "/* Toggleable content - dropdown */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-toggleable__content {\n",
+ " max-height: 0;\n",
+ " max-width: 0;\n",
+ " overflow: hidden;\n",
+ " text-align: left;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-toggleable__content.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-toggleable__content pre {\n",
+ " margin: 0.2em;\n",
+ " border-radius: 0.25em;\n",
+ " color: var(--sklearn-color-text);\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-toggleable__content.fitted pre {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+ " /* Expand drop-down */\n",
+ " max-height: 200px;\n",
+ " max-width: 100%;\n",
+ " overflow: auto;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+ " content: \"▾\";\n",
+ "}\n",
+ "\n",
+ "/* Pipeline/ColumnTransformer-specific style */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific style */\n",
+ "\n",
+ "/* Colorize estimator box */\n",
+ "#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-label label.sk-toggleable__label,\n",
+ "#sk-container-id-9 div.sk-label label {\n",
+ " /* The background is the default theme color */\n",
+ " color: var(--sklearn-color-text-on-default-background);\n",
+ "}\n",
+ "\n",
+ "/* On hover, darken the color of the background */\n",
+ "#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Label box, darken color on hover, fitted */\n",
+ "#sk-container-id-9 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+ " color: var(--sklearn-color-text);\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Estimator label */\n",
+ "\n",
+ "#sk-container-id-9 div.sk-label label {\n",
+ " font-family: monospace;\n",
+ " font-weight: bold;\n",
+ " display: inline-block;\n",
+ " line-height: 1.2em;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-label-container {\n",
+ " text-align: center;\n",
+ "}\n",
+ "\n",
+ "/* Estimator-specific */\n",
+ "#sk-container-id-9 div.sk-estimator {\n",
+ " font-family: monospace;\n",
+ " border: 1px dotted var(--sklearn-color-border-box);\n",
+ " border-radius: 0.25em;\n",
+ " box-sizing: border-box;\n",
+ " margin-bottom: 0.5em;\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-0);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-estimator.fitted {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-0);\n",
+ "}\n",
+ "\n",
+ "/* on hover */\n",
+ "#sk-container-id-9 div.sk-estimator:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-2);\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 div.sk-estimator.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-2);\n",
+ "}\n",
+ "\n",
+ "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+ "\n",
+ "/* Common style for \"i\" and \"?\" */\n",
+ "\n",
+ ".sk-estimator-doc-link,\n",
+ "a:link.sk-estimator-doc-link,\n",
+ "a:visited.sk-estimator-doc-link {\n",
+ " float: right;\n",
+ " font-size: smaller;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1em;\n",
+ " height: 1em;\n",
+ " width: 1em;\n",
+ " text-decoration: none !important;\n",
+ " margin-left: 0.5em;\n",
+ " text-align: center;\n",
+ " /* unfitted */\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted,\n",
+ "a:link.sk-estimator-doc-link.fitted,\n",
+ "a:visited.sk-estimator-doc-link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+ ".sk-estimator-doc-link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover,\n",
+ "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+ ".sk-estimator-doc-link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "/* Span, style for the box shown on hovering the info icon */\n",
+ ".sk-estimator-doc-link span {\n",
+ " display: none;\n",
+ " z-index: 9999;\n",
+ " position: relative;\n",
+ " font-weight: normal;\n",
+ " right: .2ex;\n",
+ " padding: .5ex;\n",
+ " margin: .5ex;\n",
+ " width: min-content;\n",
+ " min-width: 20ex;\n",
+ " max-width: 50ex;\n",
+ " color: var(--sklearn-color-text);\n",
+ " box-shadow: 2pt 2pt 4pt #999;\n",
+ " /* unfitted */\n",
+ " background: var(--sklearn-color-unfitted-level-0);\n",
+ " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link.fitted span {\n",
+ " /* fitted */\n",
+ " background: var(--sklearn-color-fitted-level-0);\n",
+ " border: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "\n",
+ ".sk-estimator-doc-link:hover span {\n",
+ " display: block;\n",
+ "}\n",
+ "\n",
+ "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+ "\n",
+ "#sk-container-id-9 a.estimator_doc_link {\n",
+ " float: right;\n",
+ " font-size: 1rem;\n",
+ " line-height: 1em;\n",
+ " font-family: monospace;\n",
+ " background-color: var(--sklearn-color-background);\n",
+ " border-radius: 1rem;\n",
+ " height: 1rem;\n",
+ " width: 1rem;\n",
+ " text-decoration: none;\n",
+ " /* unfitted */\n",
+ " color: var(--sklearn-color-unfitted-level-1);\n",
+ " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 a.estimator_doc_link.fitted {\n",
+ " /* fitted */\n",
+ " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+ " color: var(--sklearn-color-fitted-level-1);\n",
+ "}\n",
+ "\n",
+ "/* On hover */\n",
+ "#sk-container-id-9 a.estimator_doc_link:hover {\n",
+ " /* unfitted */\n",
+ " background-color: var(--sklearn-color-unfitted-level-3);\n",
+ " color: var(--sklearn-color-background);\n",
+ " text-decoration: none;\n",
+ "}\n",
+ "\n",
+ "#sk-container-id-9 a.estimator_doc_link.fitted:hover {\n",
+ " /* fitted */\n",
+ " background-color: var(--sklearn-color-fitted-level-3);\n",
+ "}\n",
+ "</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" checked><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>XGBRegressor</div></div><div><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+ ],
+ "text/plain": [
+ "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+ " num_parallel_tree=None, random_state=None, ...)"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "model_bruit=XGBRegressor(verbose=True)\n",
+ "model_bruit.fit(X_tr,y_tr)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([ 3.9438012 , 14.851429 , -0.03574099, ..., 13.556425 ,\n",
+ " 19.116198 , 8.866528 ], dtype=float32)"
+ ]
+ },
+ "execution_count": 62,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pred=model_bruit.predict(X_v)\n",
+ "pred"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "y_f=X_v['off']+pred"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "y_autre=X_v['off']+y_v"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3.312973790552476"
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "np.sqrt(mean_squared_error(y_f,y_autre))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Performance du modèle d'imputation linéaire - MAE: 1.33, R²: 0.97\n",
+ "Pourcentage de valeurs manquantes après imputation: 0.00%\n",
+ "Variable 'disease_duration' ajoutée avec succès.\n"
+ ]
+ }
+ ],
+ "source": [
+ "X = pd.read_csv('data/X_train_6ZIKlTY.csv')\n",
+ "y = pd.read_csv('data/y_train_lXj6X5y.csv')\n",
+ "data = PreprocessData(X, y)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>cohort</th>\n",
+ " <th>sexM</th>\n",
+ " <th>age_at_diagnosis</th>\n",
+ " <th>age</th>\n",
+ " <th>ledd</th>\n",
+ " <th>time_since_intake_on</th>\n",
+ " <th>time_since_intake_off</th>\n",
+ " <th>on</th>\n",
+ " <th>off</th>\n",
+ " <th>est_LRRK2+</th>\n",
+ " <th>...</th>\n",
+ " <th>zzdt1581</th>\n",
+ " <th>zzdt1708</th>\n",
+ " <th>zzhd4675</th>\n",
+ " <th>zzie1203</th>\n",
+ " <th>zzih2520</th>\n",
+ " <th>zzlf7854</th>\n",
+ " <th>zzmr9316</th>\n",
+ " <th>zznx1511</th>\n",
+ " <th>zzpu4420</th>\n",
+ " <th>zztp1426</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>52.1</td>\n",
+ " <td>607.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>7.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.0</td>\n",
+ " <td>666.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>17.6</td>\n",
+ " <td>12.0</td>\n",
+ " <td>44.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.9</td>\n",
+ " <td>717.0</td>\n",
+ " <td>1.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>54.8</td>\n",
+ " <td>770.0</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>11.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>56.9</td>\n",
+ " <td>885.0</td>\n",
+ " <td>0.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>5 rows × 6984 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " cohort sexM age_at_diagnosis age ledd time_since_intake_on \\\n",
+ "0 1 0 48.5 52.1 607.0 1.9 \n",
+ "1 1 0 48.5 53.0 666.0 1.9 \n",
+ "2 1 0 48.5 53.9 717.0 1.2 \n",
+ "3 1 0 48.5 54.8 770.0 1.5 \n",
+ "4 1 0 48.5 56.9 885.0 0.3 \n",
+ "\n",
+ " time_since_intake_off on off est_LRRK2+ ... zzdt1581 zzdt1708 \\\n",
+ "0 NaN 7.0 NaN 1.0 ... 0 0 \n",
+ "1 17.6 12.0 44.0 1.0 ... 0 0 \n",
+ "2 NaN 6.0 NaN 1.0 ... 0 0 \n",
+ "3 NaN 11.0 NaN 1.0 ... 0 0 \n",
+ "4 NaN 24.0 NaN 1.0 ... 0 0 \n",
+ "\n",
+ " zzhd4675 zzie1203 zzih2520 zzlf7854 zzmr9316 zznx1511 zzpu4420 \\\n",
+ "0 0 0 0 0 0 0 0 \n",
+ "1 0 0 0 0 0 0 0 \n",
+ "2 0 0 0 0 0 0 0 \n",
+ "3 0 0 0 0 0 0 0 \n",
+ "4 0 0 0 0 0 0 0 \n",
+ "\n",
+ " zztp1426 \n",
+ "0 0 \n",
+ "1 0 \n",
+ "2 0 \n",
+ "3 0 \n",
+ "4 0 \n",
+ "\n",
+ "[5 rows x 6984 columns]"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X1 = data.get_X()\n",
+ "y1 = data.get_y()\n",
+ "X1.head()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X1_clean = X1.drop(['ledd','off','time_since_intake_on','time_since_intake_off'],axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>cohort</th>\n",
+ " <th>sexM</th>\n",
+ " <th>age_at_diagnosis</th>\n",
+ " <th>age</th>\n",
+ " <th>time_since_intake_on</th>\n",
+ " <th>time_since_intake_off</th>\n",
+ " <th>on</th>\n",
+ " <th>est_LRRK2+</th>\n",
+ " <th>est_GBA+</th>\n",
+ " <th>est_OTHER+</th>\n",
+ " <th>...</th>\n",
+ " <th>zzdt1581</th>\n",
+ " <th>zzdt1708</th>\n",
+ " <th>zzhd4675</th>\n",
+ " <th>zzie1203</th>\n",
+ " <th>zzih2520</th>\n",
+ " <th>zzlf7854</th>\n",
+ " <th>zzmr9316</th>\n",
+ " <th>zznx1511</th>\n",
+ " <th>zzpu4420</th>\n",
+ " <th>zztp1426</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>52.1</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>7.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>17.6</td>\n",
+ " <td>12.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.9</td>\n",
+ " <td>1.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>54.8</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>11.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>56.9</td>\n",
+ " <td>0.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>24.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>5 rows × 6982 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " cohort sexM age_at_diagnosis age time_since_intake_on \\\n",
+ "0 1 0 48.5 52.1 1.9 \n",
+ "1 1 0 48.5 53.0 1.9 \n",
+ "2 1 0 48.5 53.9 1.2 \n",
+ "3 1 0 48.5 54.8 1.5 \n",
+ "4 1 0 48.5 56.9 0.3 \n",
+ "\n",
+ " time_since_intake_off on est_LRRK2+ est_GBA+ est_OTHER+ ... \\\n",
+ "0 NaN 7.0 1.0 0.0 0.0 ... \n",
+ "1 17.6 12.0 1.0 0.0 0.0 ... \n",
+ "2 NaN 6.0 1.0 0.0 0.0 ... \n",
+ "3 NaN 11.0 1.0 0.0 0.0 ... \n",
+ "4 NaN 24.0 1.0 0.0 0.0 ... \n",
+ "\n",
+ " zzdt1581 zzdt1708 zzhd4675 zzie1203 zzih2520 zzlf7854 zzmr9316 \\\n",
+ "0 0 0 0 0 0 0 0 \n",
+ "1 0 0 0 0 0 0 0 \n",
+ "2 0 0 0 0 0 0 0 \n",
+ "3 0 0 0 0 0 0 0 \n",
+ "4 0 0 0 0 0 0 0 \n",
+ "\n",
+ " zznx1511 zzpu4420 zztp1426 \n",
+ "0 0 0 0 \n",
+ "1 0 0 0 \n",
+ "2 0 0 0 \n",
+ "3 0 0 0 \n",
+ "4 0 0 0 \n",
+ "\n",
+ "[5 rows x 6982 columns]"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X1_clean.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "cohort 0\n",
+ "sexM 0\n",
+ "age_at_diagnosis 0\n",
+ "age 0\n",
+ "on 0\n",
+ " ..\n",
+ "zzlf7854 0\n",
+ "zzmr9316 0\n",
+ "zznx1511 0\n",
+ "zzpu4420 0\n",
+ "zztp1426 0\n",
+ "Length: 6980, dtype: int64"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# recuperer les lignes ou il y a un NaN sur la colonne 'on'\n",
+ "X1_a_imputer = X1_clean[X1_clean['on'].isnull()]\n",
+ "\n",
+ "X1_sans_nan = X1_clean.dropna()\n",
+ "X1_sans_nan.isna().sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.model_selection import train_test_split\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X1_sans_nan.drop(['on'],axis=1), X1_sans_nan['on'], test_size=0.2, random_state=42)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[0]\tvalidation_0-rmse:10.32333\tvalidation_1-rmse:10.39185\n",
+ "[1]\tvalidation_0-rmse:10.29032\tvalidation_1-rmse:10.36258\n",
+ "[2]\tvalidation_0-rmse:10.25915\tvalidation_1-rmse:10.33404\n",
+ "[3]\tvalidation_0-rmse:10.22992\tvalidation_1-rmse:10.30862\n",
+ "[4]\tvalidation_0-rmse:10.20204\tvalidation_1-rmse:10.28366\n",
+ "[5]\tvalidation_0-rmse:10.17581\tvalidation_1-rmse:10.26081\n",
+ "[6]\tvalidation_0-rmse:10.15070\tvalidation_1-rmse:10.23894\n",
+ "[7]\tvalidation_0-rmse:10.12647\tvalidation_1-rmse:10.21733\n",
+ "[8]\tvalidation_0-rmse:10.10337\tvalidation_1-rmse:10.19649\n",
+ "[9]\tvalidation_0-rmse:10.08087\tvalidation_1-rmse:10.17622\n",
+ "[10]\tvalidation_0-rmse:10.05985\tvalidation_1-rmse:10.15847\n",
+ "[11]\tvalidation_0-rmse:10.03988\tvalidation_1-rmse:10.14029\n",
+ "[12]\tvalidation_0-rmse:10.02084\tvalidation_1-rmse:10.12460\n",
+ "[13]\tvalidation_0-rmse:10.00285\tvalidation_1-rmse:10.10855\n",
+ "[14]\tvalidation_0-rmse:9.98567\tvalidation_1-rmse:10.09444\n",
+ "[15]\tvalidation_0-rmse:9.96909\tvalidation_1-rmse:10.07967\n",
+ "[16]\tvalidation_0-rmse:9.95318\tvalidation_1-rmse:10.06704\n",
+ "[17]\tvalidation_0-rmse:9.93839\tvalidation_1-rmse:10.05572\n",
+ "[18]\tvalidation_0-rmse:9.92505\tvalidation_1-rmse:10.04452\n",
+ "[19]\tvalidation_0-rmse:9.91030\tvalidation_1-rmse:10.03279\n",
+ "[20]\tvalidation_0-rmse:9.89815\tvalidation_1-rmse:10.02348\n",
+ "[21]\tvalidation_0-rmse:9.88585\tvalidation_1-rmse:10.01303\n",
+ "[22]\tvalidation_0-rmse:9.87483\tvalidation_1-rmse:10.00465\n",
+ "[23]\tvalidation_0-rmse:9.86289\tvalidation_1-rmse:9.99492\n",
+ "[24]\tvalidation_0-rmse:9.85220\tvalidation_1-rmse:9.98699\n",
"[25]\tvalidation_0-rmse:9.84252\tvalidation_1-rmse:9.97932\n",
"[26]\tvalidation_0-rmse:9.83166\tvalidation_1-rmse:9.97021\n",
"[27]\tvalidation_0-rmse:9.82181\tvalidation_1-rmse:9.96371\n",
@@ -4202,32 +21429,798 @@
"data": {
"image/png": "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",
"text/plain": [
- "<Figure size 1000x600 with 1 Axes>"
+ "<Figure size 1000x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# distribution des résidus\n",
+ "residuals_test = y_test - y_pred_test\n",
+ "plt.figure(figsize=(10, 6)) \n",
+ "plt.hist(residuals_test, bins=30, alpha=0.7, color='blue')\n",
+ "plt.axvline(0, color='red', linestyle='--')\n",
+ "plt.xlabel('Résidus')\n",
+ "plt.ylabel('Fréquence')\n",
+ "plt.title('Distribution des résidus (Test)')\n",
+ "plt.grid(True)\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "liste_features = X_train.columns.tolist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "['cohort', 'sexM', 'age_at_diagnosis', 'age', 'est_LRRK2+', 'est_GBA+', 'est_OTHER+', 'disease_duration', 'aadg7112', 'aajs7617', 'aalb3070', 'aalz2188', 'aamf6938', 'aamg4569', 'aaqz0968', 'aauc0739', 'aays3682', 'aban3890', 'abaq6463', 'abew7519', 'abgv8337', 'abgz3701', 'abid8152', 'abke2862', 'aboj9895', 'abpu1638', 'abrb2093', 'abya9876', 'acdu4832', 'aclg6928', 'acps4514', 'acts7885', 'actu7591', 'acvs2278', 'adbf2383', 'adcy3285', 'addz5435', 'adho4742', 'adjv3378', 'adld2185', 'adry8906', 'adxx9232', 'adzj1311', 'adzz2628', 'aedd6317', 'aeku3324', 'aelx6157', 'aeoy2168', 'aery0570', 'aexp4060', 'aeyw2859', 'afce4434', 'afcy0672', 'affq9241', 'afin9002', 'afld1218', 'aflw5990', 'afnv8830', 'afuc8911', 'afyu7589', 'afze3065', 'aghh9935', 'agok9547', 'agsk2476', 'agtv9185', 'ahcj2728', 'ahnr6218', 'ahnt9258', 'ahsi7448', 'ahwy8974', 'aidp2729', 'aige1393', 'aigr7588', 'aihi2572', 'ailn7385', 'aimb1534', 'aipu0934', 'aipz8644', 'airv4858', 'aisw2579', 'aisx0714', 'aitb3036', 'aiwb5393', 'ajau0326', 'ajde3498', 'ajep0249', 'ajfl8256', 'ajja7615', 'ajow1322', 'ajpn9625', 'ajqf9254', 'ajtv8089', 'ajuc7318', 'ajuu4804', 'ajwr7869', 'ajzh7238', 'ajzk2629', 'ajzt1280', 'ajzz0139', 'akcq7289', 'akcr5103', 'akka4282', 'akkm3720', 'akkx8229', 'akoe6491', 'akoh6497', 'akts8306', 'akue9904', 'akvh1456', 'akvq3234', 'akvz4834', 'akyu6046', 'alaw1949', 'aldj9983', 'aldz0316', 'aliv9936', 'alji9023', 'aljz0477', 'alnh7966', 'alrc3686', 'alsf3278', 'alsu8122', 'altt2386', 'alzc7430', 'ambm3314', 'amcl0641', 'amfv2928', 'amia0967', 'amnc8878', 'ampi7286', 'amqx0221', 'amsl7259', 'anbi6777', 'aneo3308', 'anfh3746', 'anil5179', 'anlx8263', 'anmx1899', 'anno9928', 'anro1806', 'anrp3238', 'anrw5804', 'anug9115', 'anve0893', 'anyx2977', 'anzg8533', 'aobp2930', 'aoiq6589', 'aojz0077', 'aoon9592', 'aoxs7615', 'apbg3123', 'apew9898', 'aphg1943', 'aplx0379', 'apnu3846', 'apqt1224', 'apwf5268', 'apwt4633', 'apya5285', 'aqab2260', 'aqaf4410', 'aqer7834', 'aqfi6535', 'aqfo6562', 'aqjb5523', 'aqnr6820', 'aqnt4969', 'aqpb8528', 'aqqn0715', 'aqug6320', 'arab5680', 'ardp9465', 'argk4907', 'arhi4614', 'arkz1753', 'arod5023', 'arqb5876', 'arvk0919', 'arvw6642', 'aryg0827', 'asho9420', 'asko1204', 'asmr3745', 'asqm7989', 'asto6597', 'aswe8319', 'atae1115', 'atgj9630', 'athu6470', 'atje1438', 'atjr8021', 'atne0159', 'atoq9955', 'atpg7331', 'atpj3632', 'attb6528', 'atvb0136', 'atve2593', 'atvl4675', 'aual9944', 'augb5305', 'auhy8082', 'aukv1595', 'aulw7588', 'aunj4955', 'aunt2627', 'auqh9910', 'autq4015', 'auwg9324', 'auyf7244', 'avad8925', 'avej6475', 'avev2076', 'avfy5334', 'avgb3465', 'avne8017', 'avof9600', 'avoi6096', 'avqp0497', 'avrs3257', 'avzc4051', 'awdt4598', 'awdx8648', 'awdz5427', 'awem3679', 'awhe3823', 'awlu1367', 'awzv4394', 'axcy4652', 'axew6006', 'axig6884', 'axik8806', 'axjp8227', 'axld7017', 'axqd2173', 'axqv8827', 'axzc6991', 'ayje9069', 'ayjg6733', 'ayld3911', 'aylw8968', 'ayoh0618', 'ayoo7715', 'aysn9956', 'ayto8738', 'ayuu7438', 'aywg6818', 'azas8069', 'azcd8098', 'azgc3062', 'azjz2299', 'azmz3355', 'azom6890', 'azrk4901', 'azuq0307', 'azyl2755', 'azzg8975', 'baah6506', 'babg6537', 'bagc6354', 'baps6387', 'barq4375', 'batl9658', 'bbea3224', 'bbfu7509', 'bbgm6543', 'bbja4737', 'bblk4594', 'bbmw8931', 'bbqb3000', 'bbrl8632', 'bbst2059', 'bbuj8260', 'bbvn0236', 'bchx1202', 'bcie4987', 'bcix6158', 'bckp1724', 'bctp6294', 'bctw9269', 'bcwg4397', 'bdae0510', 'bdah2846', 'bddt1714', 'bdgx7288', 'bdhr5494', 'bdjn2094', 'bdno0505', 'bdqs8340', 'bdtg5605', 'bduf2349', 'beft4782', 'beiv3319', 'besz5843', 'beyh6466', 'bezl3958', 'bfaz5558', 'bfgt6766', 'bfic8816', 'bfif2860', 'bfjr5128', 'bfmr0319', 'bfom7355', 'bfto0884', 'bfuq5450', 'bfvk5401', 'bfzr5305', 'bgcv8486', 'bghg3828', 'bgkc2591', 'bgnd7156', 'bgnh2631', 'bgrz2145', 'bgsr8791', 'bguv8687', 'bgux4415', 'bgzr5920', 'bhje1519', 'bhon9506', 'bhpu1917', 'bhrn8954', 'bhtm4618', 'bhvh9312', 'bhya4642', 'biaa9397', 'bidl2485', 'bidq0373', 'bied5995', 'bifi9421', 'biia7350', 'biir2786', 'biji1456', 'bikd5090', 'bild5221', 'bimc0776', 'bipu3501', 'birw2120', 'bisf1672', 'biup8385', 'biym6307', 'bizc1335', 'bjah9840', 'bjao7913', 'bjgq4583', 'bjir8162', 'bjja7509', 'bjjy8273', 'bjmo4796', 'bjrf5965', 'bjup7763', 'bjxx3288', 'bjxy0582', 'bjys4771', 'bkcq1750', 'bkgu7107', 'bkiw3388', 'bkkh1835', 'bkki0095', 'bknx6816', 'bkxn7369', 'bkyi5719', 'blci0252', 'blef3741', 'blgq9469', 'blid1941', 'bllg2483', 'blss1850', 'blsz8539', 'bltl8384', 'blve1874', 'blvq7416', 'blys3025', 'blyz5998', 'bmfg4068', 'bmfx6140', 'bmgp5618', 'bmhf4127', 'bmia5026', 'bmix0480', 'bmkw7358', 'bmmu8921', 'bmsi8278', 'bmua8934', 'bmyf7579', 'bnao5660', 'bncu3357', 'bncw1943', 'bnes1435', 'bnex3263', 'bnig5334', 'bnmw9495', 'bnpf9069', 'bntb9065', 'bnus7633', 'bnwa4324', 'boby5635', 'bocc7826', 'boct0887', 'bodf9382', 'bomo0210', 'bopx6310', 'bots0409', 'bouc2403', 'bowu3920', 'bozi3505', 'bpac1435', 'bpkj0608', 'bpsa5971', 'bpti2989', 'bptl7084', 'bpuv8516', 'bpyr0913', 'bqaw7492', 'bqdq3121', 'bqdx7357', 'bqeg2773', 'bqij8474', 'bqov0005', 'bqwz3671', 'bqxr6541', 'bqyr2348', 'brck7169', 'brfd4880', 'brgw0617', 'brls6237', 'brnb2190', 'brod0992', 'bron0329', 'brsl8986', 'bruz3734', 'brvb3836', 'brxw4875', 'bsad8265', 'bsbg5141', 'bsfw1287', 'bslp8368', 'bsnc5223', 'bsnz1436', 'bstn8242', 'bsui7786', 'bsum0799', 'bsvb1793', 'bswa0807', 'btbc3748', 'btbk6949', 'btdp6511', 'btgt1502', 'btld0498', 'btlg4218', 'btlm2221', 'btpg9738', 'btqx3748', 'btrd6751', 'btru1448', 'bttj2360', 'btud3471', 'btwu4877', 'btyd3720', 'btzu8342', 'bugd8879', 'bukl8224', 'bukq3862', 'buoz5186', 'buro2706', 'busy6997', 'buuz2140', 'buxs0586', 'buzw7680', 'bvcg5851', 'bvcu8104', 'bvef3680', 'bvhf7686', 'bvio6239', 'bvku8694', 'bvno4691', 'bvom8094', 'bvqf3949', 'bvtg8978', 'bvtu1696', 'bvvy6389', 'bvwu9857', 'bwbt3555', 'bwek3069', 'bwob0847', 'bwtk8444', 'bwut8572', 'bwxn1412', 'bwyq5010', 'bxdf5185', 'bxez4454', 'bxfx4510', 'bxii7579', 'bxiv0134', 'bxiv9218', 'bxjc9963', 'bxks8951', 'bxog2866', 'bxsb3503', 'bxth7303', 'byih0115', 'bynr5939', 'byyk4156', 'bzgh9170', 'bzia1589', 'bzlc9706', 'bzno1712', 'bzqy1157', 'cafc6888', 'cait3626', 'caog8443', 'capo0407', 'cauv1912', 'cavh2438', 'caxb3395', 'caxz6957', 'cbgg5920', 'cblo0623', 'cbns4995', 'cbqg7992', 'cbrh6083', 'cbxc1317', 'ccds3900', 'ccek4115', 'ccfd0750', 'ccft1054', 'ccjb2878', 'ccjk7538', 'cclo6851', 'ccns1521', 'ccpz5722', 'ccua1483', 'cdcx9112', 'cdex8460', 'cdgh2806', 'cdiv7669', 'cdjp3901', 'cdjz0038', 'cdkq1190', 'cdlh1085', 'cdoq8976', 'cdrr6501', 'cdsx4649', 'ceav2855', 'cecd8047', 'cedg4198', 'ceeg3841', 'cefm7261', 'cegk2194', 'ceit5785', 'cekr2758', 'ceoi2182', 'cerh6293', 'cert4488', 'ceso9151', 'cete2679', 'cety8258', 'ceua1110', 'cevo6351', 'ceyo6755', 'cfbj3314', 'cfet1189', 'cfis5491', 'cfjj4224', 'cfki4480', 'cfky7095', 'cfoa4441', 'cfqg5254', 'cfrw5864', 'cfrz8083', 'cfsx7411', 'cfty6893', 'cfzm0950', 'cfzu0856', 'cgay2581', 'cgaz5825', 'cgba7972', 'cgeh1231', 'cgfz9856', 'cgia0765', 'cgil4646', 'cgmo6324', 'cgny3056', 'cgpc3601', 'cgux9973', 'chbn2420', 'chda0974', 'chjr7100', 'chnt6161', 'chos9291', 'chqn4414', 'chxu4696', 'ciae6731', 'cidz7486', 'cied1248', 'cieq4013', 'cigb5985', 'cigk2253', 'cija6991', 'cijl6863', 'ciku3135', 'cimc0425', 'cimj6021', 'cios3673', 'ciou0253', 'cipm3294', 'ciuo8822', 'ciwp5755', 'cjbd5723', 'cjbw9749', 'cjda4340', 'cjeg6169', 'cjka6334', 'cjkr3665', 'cjol6453', 'cjva6176', 'ckfb7346', 'ckjw7144', 'ckpd5262', 'ckpt2825', 'ckpt5164', 'cksu9051', 'clai4564', 'clcp1210', 'cliy6444', 'cljq3549', 'cllm7591', 'cllu9299', 'cloh8621', 'clom8257', 'clos0537', 'clpt6852', 'clsn7236', 'clte6265', 'clur6612', 'clvy8702', 'clxn0520', 'clzw7803', 'cmaj8790', 'cmbt4393', 'cmcx9771', 'cmgg9010', 'cmmc9620', 'cmnc5562', 'cmph3638', 'cmqm1584', 'cmub1332', 'cmvn9856', 'cmyw5535', 'cmyy4876', 'cmzc0323', 'cnab5654', 'cnel6547', 'cnia9891', 'cnny7210', 'cnou9683', 'cnti9475', 'cnvq0892', 'cnwo7815', 'cnyc7844', 'cnzm2974', 'codl0636', 'cods3619', 'cotn0151', 'couz6787', 'covl4554', 'covr5547', 'coxh6952', 'coze4437', 'cozg7070', 'cpbx0977', 'cpfi2338', 'cpho7909', 'cple7563', 'cpli3540', 'cpmf4065', 'cpqs6386', 'cprw6154', 'cpst6624', 'cpvi8230', 'cpye1962', 'cqcs5029', 'cqdc4369', 'cqfz5019', 'cqhh7994', 'cqmi0074', 'cqnk6335', 'cqon8632', 'cqoq6644', 'cqpw0457', 'cqrq9364', 'cqub9960', 'cqxm5852', 'cqxv0572', 'crah0769', 'crcj2668', 'crdq4611', 'crei6154', 'creq0120', 'crft9883', 'crgd8998', 'crpi5306', 'crss7546', 'csbz3084', 'cscz7431', 'cshs3949', 'cskn9607', 'cslh5415', 'csmc1741', 'csmy3033', 'csnc1328', 'cspi4397', 'csqu1398', 'cssu3137', 'csuy7178', 'csvr4131', 'csxd6270', 'ctdw1359', 'ctev6576', 'ctgr3137', 'ctgs3967', 'ctki3668', 'ctln8871', 'ctlt0559', 'ctnx9606', 'ctrm4834', 'ctrr0678', 'ctta1927', 'cuad8299', 'cuav5259', 'cuba4586', 'cueh1019', 'cufw7664', 'cugj5306', 'cuhz1505', 'cuju6977', 'cumq7445', 'cumr3309', 'cuyf1764', 'cuzf3491', 'cvaf4286', 'cvba5551', 'cvcg5152', 'cvcn1491', 'cvdt0969', 'cvhc9623', 'cvmb5536', 'cvmj9256', 'cvvr4393', 'cvwe5213', 'cvwi8585', 'cvxf4500', 'cvyw4747', 'cwfb2287', 'cwgb8310', 'cwgu9519', 'cwhu1708', 'cwkj5564', 'cwmm7181', 'cwqn0646', 'cwrw0736', 'cwwf0696', 'cwys2538', 'cxen7720', 'cxgg3326', 'cxgi0238', 'cxhd2348', 'cxlh0746', 'cxlu2709', 'cxol8250', 'cxov7211', 'cxow7884', 'cxqc1957', 'cxql9430', 'cxrk7107', 'cxsg5342', 'cxvm0895', 'cxvr9741', 'cxzs0307', 'cyat6398', 'cybc7504', 'cybd7984', 'cybv0823', 'cyfj4407', 'cygt1897', 'cyku6756', 'cynz6202', 'cyti9501', 'cywb0017', 'cyzg6760', 'czfu6546', 'czkd3929', 'czlz3166', 'czna4423', 'cztx7061', 'czut9688', 'czxl6517', 'daej9055', 'daeo5543', 'dafa7146', 'dahf4615', 'daim3278', 'dalr8769', 'dals2717', 'dalv9044', 'dany8581', 'daql6628', 'dayb4850', 'dbcf4805', 'dbdw4043', 'dbec6048', 'dbgo7458', 'dbqc0192', 'dbqz1817', 'dbrc0746', 'dbtc6946', 'dbwr1515', 'dbyc7191', 'dcah3450', 'dcat2917', 'dcgb8645', 'dcgq4902', 'dcii4598', 'dcmt3176', 'dcmz7067', 'dcpr6342', 'dcqa9012', 'dcqd2334', 'dctd7416', 'dcwm4015', 'dcyi5992', 'dcyp3819', 'dczt7918', 'ddac4595', 'ddcb6111', 'ddea9835', 'ddjb8862', 'ddmm4547', 'ddsi6930', 'ddxr8131', 'ddxz9740', 'deap7560', 'decc5058', 'degl2008', 'dehe1659', 'dekq6489', 'deks4957', 'deld9271', 'deug0678', 'dexo3280', 'deyp7593', 'dezd6134', 'dfeb4784', 'dfef7914', 'dfes1574', 'dfhh1119', 'dflg7057', 'dfmy4688', 'dfoj5348', 'dfpt8355', 'dfvt9567', 'dfyj7773', 'dfyq3842', 'dfyt5319', 'dfzz3358', 'dgal9981', 'dgfj6087', 'dgng1031', 'dgnq4478', 'dgof8081', 'dgoi0666', 'dgoj7819', 'dgpx6330', 'dgsg1177', 'dgwg9683', 'dgwv8187', 'dgyj9470', 'dgyk3090', 'dgzl7837', 'dhau8542', 'dhfa9344', 'dhqv3033', 'dhre3510', 'dhtz6468', 'diaq1456', 'dibh3764', 'digb6280', 'digl9665', 'dihq3558', 'diin8617', 'dikw1630', 'dinc5816', 'dipv3418', 'dise4207', 'dist7178', 'disu0197', 'diuh8103', 'dixq3120', 'dizj4472', 'djam0145', 'djbw5737', 'djdb0369', 'djed7905', 'djhq2267', 'djir1790', 'djom1351', 'djvt6968', 'djxk6148', 'djyv0072', 'dkbu3235', 'dkdw5040', 'dkdz9554', 'dkik5517', 'dkom3172', 'dkqw4826', 'dkxz6661', 'dlaa5314', 'dlaz5632', 'dlby4852', 'dlcq6619', 'dlem8915', 'dljj8346', 'dlke6091', 'dlmv5443', 'dlnv0758', 'dltj7142', 'dlxv7435', 'dlyu3541', 'dmbm5736', 'dmer1310', 'dmkm8839', 'dmmc4091', 'dmme3609', 'dmnx3526', 'dmps1111', 'dmud5862', 'dmud9616', 'dmue1367', 'dmva8656', 'dmwu0764', 'dnbn1464', 'dnei8873', 'dngg2484', 'dnon9230', 'dnox8857', 'dnpa5007', 'dnpq8590', 'dnsn9114', 'dntp5296', 'dntv4474', 'dnuw2801', 'dnyk9954', 'dnzv9451', 'dnzw2292', 'dokz2975', 'donu6118', 'dorg9269', 'dowf7855', 'dozl1408', 'dpas4376', 'dpau8438', 'dpcn9815', 'dpda0184', 'dpdz4398', 'dpeg3702', 'dpnv9699', 'dpsf0906', 'dpvx8521', 'dpys0011', 'dqcn2509', 'dqes1138', 'dqkr8532', 'dqny4827', 'dqpv4262', 'dqtb3870', 'dqwn6074', 'dqws1834', 'dqxn7981', 'dqyt7196', 'drbh3433', 'drcy0170', 'drgu9533', 'drgy5735', 'drlh4943', 'drly9239', 'drtj0310', 'drws5925', 'dryh2813', 'dsag5291', 'dsaj3286', 'dscx0872', 'dsdn9557', 'dsiv9234', 'dsjl3035', 'dspo5254', 'dssd3268', 'dsso0904', 'dssv9274', 'dsth5280', 'dstq6357', 'dsvf0533', 'dsxd4187', 'dsye3797', 'dtds9042', 'dtko9972', 'dtnc8698', 'dtog2416', 'dtpx2615', 'dtrv3586', 'dttc5826', 'dtwf9092', 'dtyw2419', 'ducv0931', 'duhj2012', 'duhv1675', 'duit2772', 'duod9294', 'duqq9350', 'durg5285', 'dutm5066', 'duzk6812', 'dvai4543', 'dvef0974', 'dvij1080', 'dvir8675', 'dvtj6701', 'dwbw8066', 'dwdm4001', 'dwii6666', 'dwlv7922', 'dwnn8673', 'dwpg2135', 'dwpn0660', 'dwrz6900', 'dwth3472', 'dwyh6451', 'dwyt5004', 'dxaj7505', 'dxay4679', 'dxbg4145', 'dxbm2385', 'dxbn0402', 'dxck3223', 'dxee3298', 'dxef8153', 'dxfd4544', 'dxgw9796', 'dxpv7111', 'dxqg0119', 'dxxr8990', 'dxya3335', 'dydd2780', 'dyea2375', 'dyfc7629', 'dyft1640', 'dyif0030', 'dyjm8442', 'dyoy6860', 'dyrr3267', 'dyrr9500', 'dysg0588', 'dyvh1314', 'dywc4924', 'dywy0529', 'dyxe7320', 'dyzd7648', 'dzbm5853', 'dzek6715', 'dzhl3594', 'dzhw9809', 'dzmb3119', 'dzss8544', 'eabi6820', 'eacy9976', 'eadd2180', 'eafz5923', 'eank6780', 'earu6990', 'eash7047', 'eawb0262', 'eawl2327', 'eawo7418', 'eayf1725', 'ebbq8040', 'ebct6605', 'ebcu3752', 'ebfo1530', 'ebfw0100', 'ebii5134', 'ebkn5433', 'ebmx8204', 'ebrg1798', 'ebsb1036', 'ebtc0845', 'ebtp5276', 'ebzd6304', 'ecaf6045', 'ecdh4808', 'ecdj2382', 'eces1249', 'ecgi9967', 'ecqs1367', 'ecug1730', 'ecxm6761', 'ecxp8733', 'edgz1393', 'edlr3496', 'edmi2882', 'ednl4562', 'edpd7910', 'edrk4889', 'edtb2045', 'edtd0098', 'edxh9475', 'edze2672', 'eeet9890', 'eefo0429', 'eehk3032', 'eekj6038', 'eekw4723', 'eeoe7524', 'eepb9624', 'eepn8928', 'eeqt7372', 'eerc8628', 'eexf6841', 'efbn5781', 'efcc4913', 'efdb6604', 'efhm7947', 'efvu2417', 'egat1673', 'egcg4715', 'egfn4143', 'eggc9564', 'egmu5123', 'egoe2512', 'egrh6535', 'egri5290', 'egut6402', 'egvy5450', 'egwv9461', 'egzf6611', 'ehek4738', 'ehge1487', 'ehjt6875', 'ehkr7914', 'ehoy2317', 'ehpe6598', 'ehrv0752', 'ehxq4725', 'ehyh3938', 'eicx6573', 'eidb2420', 'eidx0480', 'eign5627', 'eigr5544', 'eiho1494', 'eioz4273', 'eirq7598', 'ejbf2936', 'ejej3828', 'ejgt3489', 'ejgy8995', 'ejmf4978', 'ejmp9274', 'ejoc6530', 'ejpu8132', 'ejsm0710', 'ejth9015', 'ejug7033', 'ejvu2329', 'ejwb9709', 'ejzd0624', 'ekbe4608', 'ekbh1447', 'ekbl3505', 'ekiy2053', 'ekko6908', 'elad8377', 'elce5266', 'eleo3009', 'elgj4165', 'eljx7008', 'elqp1430', 'eltw1007', 'elzx2877', 'embo1713', 'embv1294', 'emdi7139', 'emgc0905', 'emgu7506', 'emik9100', 'emjr8374', 'emky3462', 'emqh3640', 'emwf1235', 'enbp6932', 'enbt7380', 'endj8866', 'eniv8331', 'enjd6938', 'enjn3876', 'ensg1710', 'entm0798', 'enug4143', 'enuk5144', 'envl0469', 'enys7135', 'eobv3686', 'eocw8532', 'eoml2226', 'eone6525', 'eorb3854', 'eotq8340', 'eoty4130', 'eouw2226', 'eowo8681', 'epbf9260', 'ephh0428', 'epkb0105', 'epof0888', 'epqb2964', 'eptf8284', 'eptl9158', 'epua1501', 'epux8386', 'epyq5767', 'eqbb4306', 'eqdj6704', 'eqed1662', 'eqet5496', 'eqgc9466', 'eqgi4668', 'eqhg4982', 'eqhi8121', 'eqhx6123', 'erdv8320', 'erej5620', 'erem4145', 'erfr4966', 'ergc7764', 'erhc6080', 'erhz6899', 'erji5562', 'eroa1663', 'errj8395', 'errn8096', 'errs6442', 'ertf3568', 'erzc3026', 'erzi8744', 'esbv2466', 'esfb9267', 'esfw9290', 'eshs6657', 'esia1597', 'esib5017', 'esio0753', 'esqe0095', 'esql7225', 'esrk1486', 'esvi6165', 'esvt9369', 'eswb9728', 'esxe9952', 'eszf7895', 'eszq3019', 'etaj6679', 'etbp8388', 'etff9360', 'etji0217', 'etmi4279', 'etnu0107', 'etpx6752', 'ettq1235', 'etuf2075', 'etuu3474', 'etvc5524', 'etvm4112', 'etzx3534', 'eucb9793', 'eucu9795', 'euel9412', 'euho8794', 'euiz7648', 'eumr0447', 'eumv2538', 'euox1746', 'euoy3265', 'eupu5015', 'euxw5710', 'euzc0186', 'evcc5409', 'evdw0607', 'evfg9241', 'evgh2023', 'evhu9651', 'evlv5592', 'evms1054', 'evni6750', 'evnq3670', 'evoz7639', 'evtj4873', 'evtu0235', 'evuq7710', 'evvb6950', 'evxk0769', 'evxu8228', 'evyo0859', 'ewbk2252', 'ewch9553', 'ewdl7865', 'eweb9339', 'ewfn6652', 'ewgv5579', 'ewhj3784', 'ewor4698', 'ewtv1012', 'ewvv0005', 'ewzk4974', 'ewzr1614', 'exdr5203', 'exdt2923', 'exdt7850', 'exev0541', 'exfm7519', 'exio2882', 'exjk3886', 'exob4675', 'exoi2923', 'exoq7568', 'exqz6485', 'exta3054', 'extm3472', 'exyw4971', 'eybs3318', 'eybw2664', 'eycd4653', 'eydg9479', 'eygq3921', 'eyjd1114', 'eykm4692', 'eyld3439', 'eynh7972', 'eyoh7024', 'eyqv7529', 'eyrr6276', 'eyvq7044', 'ezfz3298', 'ezgh4907', 'ezgu9272', 'ezhp8758', 'ezjf3536', 'ezkr4721', 'ezoc1746', 'ezom3114', 'ezpy9621', 'ezqw9549', 'eztt2481', 'ezui2082', 'ezwh4899', 'ezwp8105', 'fabs5162', 'fabt3366', 'faem0258', 'fahk8695', 'fajv7816', 'fakt8809', 'faku2184', 'falq1560', 'famx2902', 'faqn6387', 'fask9743', 'faza4742', 'fazv8916', 'fbav7296', 'fbbw3530', 'fbdg6141', 'fbff3298', 'fbic0134', 'fbmf7975', 'fbqp9773', 'fbsb7798', 'fbuu6584', 'fbvr7175', 'fbyd1910', 'fbyl7086', 'fcaz3326', 'fcep2353', 'fckq3705', 'fclx5070', 'fcno9153', 'fcri7547', 'fctm6723', 'fcvu4980', 'fcxe6528', 'fdbp3900', 'fdck0940', 'fddv8844', 'fdgh2888', 'fdin9821', 'fdmf4958', 'fdou2218', 'fdrv5770', 'fdun3133', 'fdvw0661', 'fdwn9688', 'fdxt8718', 'feal0298', 'febv1254', 'fedp7997', 'fegi0996', 'fehq2391', 'feic4268', 'feiw6587', 'fejq2270', 'feqq9213', 'fezq5075', 'ffar6982', 'ffbd6707', 'fffq6737', 'ffih8323', 'ffjq6186', 'ffjt5250', 'ffle2721', 'ffqj5498', 'ffub0279', 'fgep4973', 'fght6090', 'fgkk6359', 'fgne2441', 'fgob4912', 'fgpt7040', 'fgsf1649', 'fgsj6951', 'fgua9156', 'fhgz4045', 'fhro2496', 'fibk1362', 'fids1261', 'fieo5884', 'fijh7888', 'fiob7172', 'fiqr1416', 'firo0828', 'fisx1072', 'fiti0297', 'fiuq4320', 'fivf5482', 'fjak5441', 'fjdj6640', 'fjdt3182', 'fjdw1107', 'fjtb1344', 'fjwt0070', 'fkcg2486', 'fker7650', 'fkfp5208', 'fkfv6506', 'fkhc9527', 'fknv0806', 'fkts9187', 'fkuk6243', 'flfk0650', 'fljp4677', 'flub9930', 'flvq8228', 'flwm4909', 'flxe3892', 'flzw8240', 'fmbf8415', 'fmbh9380', 'fmgn3255', 'fmgu3227', 'fmja7928', 'fmmr6568', 'fmnr3337', 'fmpi4866', 'fmsg2156', 'fmtg6118', 'fmym6397', 'fmzj1893', 'fnds6890', 'fnft2454', 'fnfv8262', 'fngi2813', 'fnjm5726', 'fnnn9973', 'fnty3895', 'fnud8981', 'fnuz7877', 'fnvt3266', 'fnya1341', 'fobb8541', 'fofm3503', 'foft7419', 'foiz0613', 'folp8598', 'fomq0195', 'foqz6625', 'foui2795', 'foyh8834', 'fpao5862', 'fpbu9193', 'fpex8931', 'fpjn5458', 'fpmp1197', 'fptm1139', 'fqam1246', 'fqca5064', 'fqch9539', 'fqeg4945', 'fqfe2328', 'fqik7542', 'fqji5097', 'fqkq9363', 'fqoa7730', 'fqph2496', 'fqqq1026', 'fqsr6725', 'fqwu0276', 'fqxc4381', 'fret4883', 'frjm6283', 'frlf3195', 'frrf9658', 'fruz2570', 'frvd9558', 'frwt4467', 'frxn2512', 'fryt6946', 'fryx1758', 'frzc9797', 'fsbk5818', 'fskl4336', 'fsol2149', 'fsxz5233', 'fszp7223', 'ftex1398', 'ftfg4068', 'ftgw5246', 'ftkq6780', 'ftku1658', 'ftlq4013', 'ftlr7233', 'ftnz1789', 'ftyu8231', 'fudq2790', 'fujh9208', 'fuky1581', 'fuln4224', 'fums1835', 'fumx8362', 'furc5189', 'fusf3952', 'futt0574', 'fuwi5341', 'fuwu6297', 'fuyy7441', 'fvci0636', 'fvdk3306', 'fvwn7829', 'fwbc6134', 'fwdh9035', 'fwei2929', 'fwfa6718', 'fwhm8472', 'fwix2925', 'fwjs0822', 'fwmt2638', 'fwmt2842', 'fwng3327', 'fwtt8757', 'fwui7857', 'fwwy0612', 'fwyv2973', 'fxbv9271', 'fxby4700', 'fxdr9082', 'fxjc2533', 'fxkf7735', 'fxlm2322', 'fxvi1049', 'fxyj8364', 'fyab2608', 'fyaw9889', 'fycl1700', 'fyfj0181', 'fygi0602', 'fykj2522', 'fylc3458', 'fyoi2058', 'fypz4802', 'fyqn5341', 'fyrw4551', 'fytf6007', 'fyvn3915', 'fyxt9682', 'fyzg4710', 'fzbn8819', 'fzfj7097', 'fzja4038', 'fzmw1143', 'fzmw4438', 'fzmx1314', 'fznl0284', 'fzod6953', 'fzon8581', 'fzpf6060', 'fztx0163', 'fzuy6742', 'fzxr8032', 'fzzq5253', 'gaai9902', 'gadn4996', 'gadx2337', 'gaet4173', 'gaje9578', 'gajk2960', 'gakp0805', 'galp2579', 'ganm7537', 'gapg8249', 'gapr8494', 'gaps0171', 'gaqa9812', 'gazn7169', 'gbez9057', 'gblq6831', 'gbmi7841', 'gboe8726', 'gbos1801', 'gbrj1638', 'gbrl6717', 'gbsc8347', 'gbsx3729', 'gbsz3506', 'gbvl7290', 'gbws4106', 'gcbk0398', 'gceg5980', 'gcfj7621', 'gcfz4148', 'gcgl9800', 'gcjc4803', 'gckb3998', 'gcks9410', 'gcoa2009', 'gcoo4159', 'gcpp1976', 'gcsx7308', 'gcta4395', 'gcuo4258', 'gcvd6700', 'gcvn5161', 'gcwz5870', 'gcyi9692', 'gcyv8909', 'gczo6416', 'gddt1005', 'gded2093', 'gdeo2276', 'gdfh8825', 'gdrk0966', 'gdro6899', 'gdsw0780', 'gdwh7489', 'geee3452', 'gees2840', 'geex9511', 'geje7448', 'gema6918', 'geri1619', 'gevu7432', 'gexo5710', 'gezf3855', 'gezg8778', 'gezh3119', 'gezm6761', 'gezp1297', 'gezq9431', 'gfah4648', 'gfcd6188', 'gfce7980', 'gfdm5452', 'gffz6404', 'gfgw2013', 'gfhs4805', 'gfiz8695', 'gfjz2403', 'gfnq5028', 'gfrz2219', 'gfts7899', 'gfue2315', 'gfvm0932', 'gfya9297', 'gfyx9460', 'ggeq7844', 'ggno1956', 'ggsw5870', 'ggwb0999', 'ggwm9700', 'ggwq6295', 'ghdr9357', 'ghkv0600', 'ghkx1620', 'ghlb5850', 'ghlg4555', 'ghsa4508', 'ghxq6906', 'ghyj8069', 'ghzt8436', 'gias8153', 'giaz6587', 'gibg8507', 'gibu1991', 'gikl8840', 'gikt5795', 'giqj7976', 'gish6891', 'giws7788', 'gixd5575', 'gizf3561', 'gizs3569', 'gjaf9495', 'gjet0400', 'gjfk0533', 'gjkd8123', 'gjla1780', 'gjln7861', 'gjma9021', 'gjnw8664', 'gjpt8090', 'gjta5135', 'gjuo0201', 'gjuw6469', 'gjwa7465', 'gjyo9759', 'gkaf5202', 'gkhc5266', 'gkjl3306', 'gkjs3550', 'gkph9652', 'gkuk8611', 'gkuz2847', 'gkvf0630', 'gkxe0477', 'gkys1876', 'gkzw9307', 'glay7640', 'glec4562', 'glfw1933', 'gloq4353', 'glpf2142', 'glpn7904', 'glur2209', 'gluz9927', 'glys0134', 'glyy1634', 'gmam4562', 'gmay2586', 'gmbu8906', 'gmdp2794', 'gmfc6500', 'gmka5007', 'gmma5528', 'gmmr4130', 'gmoc6530', 'gmtd3922', 'gmwi2423', 'gmyf0722', 'gmzb1103', 'gmzv6534', 'gnap6403', 'gncx1020', 'gnfe4594', 'gnfo8411', 'gnnk5453', 'gnnv3298', 'gnox1772', 'godt5861', 'goeh3483', 'gogc0101', 'gogd5434', 'gohi7298', 'gohy7843', 'goit9823', 'gola9015', 'gonb0543', 'goom3351', 'goql6594', 'gorz7232', 'govb4424', 'gozv9082', 'gpeg4782', 'gpes4163', 'gphb1966', 'gpmw3781', 'gpol4170', 'gpos6204', 'gpuk1971', 'gpzb0655', 'gqad7347', 'gqcc5046', 'gqdt1384', 'gqef4626', 'gqff4887', 'gqhy8644', 'gqhz0982', 'gqmw2940', 'gqnl7247', 'gquv7049', 'gqxc3464', 'gqzv2789', 'grfj4701', 'grfs0327', 'grhk7329', 'grng3060', 'groz9759', 'grxx9880', 'gsat0447', 'gsho2852', 'gshr4769', 'gsjo6264', 'gsmf9870', 'gspa8435', 'gspr3782', 'gsqk7543', 'gsug4762', 'gszm9429', 'gtfc5795', 'gtgl0954', 'gthw4741', 'gtik7519', 'gtks6578', 'gtmi8850', 'gtmo9313', 'gtoy7296', 'gtsw2198', 'guaz8184', 'gubn1337', 'guck4063', 'gukv6728', 'gula8413', 'guvb0624', 'guvl6154', 'guvw8705', 'guxk7013', 'gvap4026', 'gvap4355', 'gvcs1622', 'gvdv5214', 'gved1918', 'gvfl4993', 'gvil0828', 'gvka1336', 'gvso0811', 'gvtg5447', 'gvzg9071', 'gwag1146', 'gwbm9501', 'gwbt8627', 'gwhj8167', 'gwhw2059', 'gwtp4601', 'gwtr6993', 'gwyy4534', 'gxkf8622', 'gxoj9087', 'gxsj5736', 'gxty7179', 'gygp9997', 'gyhb1009', 'gyjq6785', 'gylc9507', 'gylj9235', 'gyln0671', 'gyol4406', 'gyql9131', 'gyrv7570', 'gyry8106', 'gysd2132', 'gysi6609', 'gytz3915', 'gywl6494', 'gzah7628', 'gzck9444', 'gzkf0053', 'gzll8680', 'gzrg2710', 'gzui1462', 'gzur0686', 'hacw9783', 'halr4339', 'hamk5191', 'hans8583', 'haov2245', 'haul4805', 'hawb1904', 'haws5715', 'hays5182', 'hbbp7722', 'hbeh7416', 'hbfe6679', 'hbfp3851', 'hbjr0129', 'hbmm2148', 'hbnr8721', 'hbpk9248', 'hbpy9868', 'hbvw9318', 'hbyf9283', 'hccv0258', 'hccx4380', 'hchk2705', 'hcjn3312', 'hcjn3924', 'hcmg5382', 'hcpc5538', 'hcrv8826', 'hcsv6588', 'hcwj3391', 'hcxh1698', 'hdaz3148', 'hdeg1927', 'hdfk0650', 'hdkx7219', 'hdlc9431', 'hdoj1057', 'hdqf2241', 'hdru0748', 'hdsm8387', 'hdvn5618', 'hdze9597', 'hehf7447', 'helx4419', 'herr2191', 'hesq0309', 'hetw6280', 'hevc3432', 'hezy5692', 'hfct3739', 'hfeo3696', 'hfgz2764', 'hfha5423', 'hfiw2656', 'hfiw8925', 'hflf5830', 'hfmi2579', 'hfsg2839', 'hftb6922', 'hftj1143', 'hgby1507', 'hgdi3146', 'hger2878', 'hgkc9041', 'hgkj5733', 'hgma8042', 'hgpp6189', 'hgqn6894', 'hgrq6878', 'hgvi3839', 'hhaz1831', 'hhbm5015', 'hhgg3332', 'hhka3339', 'hhms6704', 'hhpo2526', 'hhpv5882', 'hhqx4826', 'hhuf3226', 'hhwx4098', 'hhzp3205', 'hici7653', 'hied4256', 'hiff0790', 'higl8758', 'hiht7340', 'hill9387', 'himp6459', 'hinz9113', 'hiqi8656', 'hirs7673', 'hium2628', 'hiwt1959', 'hiyd0569', 'hiyf4975', 'hiyy1959', 'hizj7498', 'hjab7763', 'hjbx5995', 'hjcp6863', 'hjdy8843', 'hjhv7162', 'hjiv5589', 'hjmi5180', 'hjwz5935', 'hjyq4916', 'hkfj2258', 'hkjs5559', 'hkms3624', 'hknx3094', 'hkof7556', 'hktp4418', 'hkts6133', 'hkvz3054', 'hldl9116', 'hlgx9891', 'hlnd4887', 'hlnl0886', 'hlog3125', 'hloj6527', 'hlom2631', 'hlse1124', 'hltc6187', 'hlut8615', 'hlvm1864', 'hlws6546', 'hlxt3727', 'hlyy0098', 'hmdr5457', 'hmes5746', 'hmgr9278', 'hmgy7199', 'hmsz6358', 'hmwo5665', 'hmwp0437', 'hnap4434', 'hnbq5721', 'hndu0819', 'hngm3971', 'hnhd6525', 'hniv1080', 'hnke5841', 'hnlw7050', 'hnmz7475', 'hnqh6152', 'hnqq7076', 'hnvy2655', 'hnws9850', 'hnyr2211', 'hoak8005', 'hoap2927', 'hobm4722', 'hocy0058', 'hogy0039', 'holx6553', 'homn7372', 'hoob0492', 'hopd6918', 'hoqg6363', 'hoxd8066', 'hpau1393', 'hpde6500', 'hpgt3114', 'hpip5593', 'hpiw0773', 'hpkh3873', 'hpsw7172', 'hpwm9484', 'hpyk8407', 'hqip0757', 'hqix9445', 'hqjc5610', 'hqlr6971', 'hqma3852', 'hqoa6468', 'hqqw5360', 'hqre2200', 'hqxa7908', 'hqxg8004', 'hrap1116', 'hrdn7594', 'hree4632', 'hrfo8464', 'hrgh1771', 'hriy2860', 'hrks9089', 'hrpj9322', 'hrpw2426', 'hrpx3884', 'hrrl5844', 'hrut1237', 'hruu8170', 'hryf1274', 'hsag9255', 'hsav9286', 'hsba1696', 'hsgy6454', 'hshz5064', 'hskc1934', 'hslw7403', 'hsms0980', 'hsqu3590', 'hsup9668', 'htbe3332', 'htcz4461', 'htgz4165', 'hthk2225', 'htiy9222', 'htuu8239', 'htvb2415', 'htzl6396', 'hubv6694', 'hudu8923', 'hufn1391', 'hujy8764', 'hukb2538', 'huqg9918', 'huyg1170', 'huyr7950', 'huzk9639', 'hvgy1359', 'hvko0318', 'hvlt2395', 'hvrj1725', 'hvvo3180', 'hwax3617', 'hwfj9206', 'hwsx2077', 'hwuq5171', 'hxkl7862', 'hxks1045', 'hxkv7195', 'hxlh9653', 'hxwz9192', 'hyas7936', 'hyaz3611', 'hybr4018', 'hycb4855', 'hyhn9085', 'hyje0871', 'hymw1607', 'hysj3798', 'hysm5010', 'hysv3661', 'hyvk0044', 'hyxh6059', 'hzbe1968', 'hzdd6309', 'hzkg7907', 'hzpj8471', 'hzri1208', 'hztm0885', 'hzxh9892', 'hzxt8579', 'iaby6092', 'iado9493', 'iadu1008', 'iahu6522', 'iakg8029', 'ialr0928', 'iaws4750', 'iaxd4355', 'ibbb9560', 'ibcl0765', 'ibhk0251', 'ibik4146', 'ibjh4141', 'ibng1958', 'ibyz2615', 'icci3118', 'icea9173', 'icem0051', 'ichp0865', 'icjp3831', 'ickl9031', 'icle2097', 'iclm2443', 'icsk2465', 'icxl3708', 'iczq4226', 'idjc9186', 'idou8718', 'idxm7083', 'idym9953', 'idzz9648', 'iebk5902', 'iegu9236', 'ielf4862', 'iemj6376', 'ienp3228', 'iepv0659', 'ieqa3074', 'ieqi2017', 'ierr1142', 'iery6916', 'ietd1312', 'ieve3141', 'ifda8938', 'ifen7194', 'ifhj7303', 'ifhx6630', 'ifib8029', 'ifkh2123', 'ifma4580', 'ifmq2759', 'ifnh3245', 'ifqh7340', 'ifwi2510', 'ifyh3204', 'igcp5298', 'igft4679', 'iggv7897', 'igib8993', 'igiy7831', 'igjr8952', 'igjz8381', 'igqv1519', 'igwq6257', 'igwv8211', 'igxx3164', 'igzo6484', 'ihal1949', 'ihax9815', 'ihcs1232', 'iheo6049', 'ihwp8562', 'ihza9130', 'ihzp8641', 'iibu4474', 'iicn4035', 'iidc2183', 'iidd4869', 'iifc7855', 'iihb0226', 'iilq6764', 'iimb6022', 'iimg1398', 'iimo3680', 'iiqc0750', 'iisz9688', 'iiug6631', 'iiur9984', 'iivt1441', 'iiwm2696', 'iiyc4347', 'iizc9696', 'ijbf5660', 'ijhs3547', 'ijkt0355', 'ijmn0355', 'ijrk9639', 'ijrr4542', 'ijuj5853', 'ijwg7764', 'ijwt1103', 'ikdp8590', 'ikeg7290', 'ikeq0815', 'iker1747', 'ikgc3437', 'ikhi3695', 'ikhr8000', 'ikig9523', 'ikil7891', 'ikio4712', 'ikjz1687', 'iklv9752', 'ikos2686', 'ikra9301', 'ikrq5522', 'ikvd6096', 'iljz0072', 'illa1573', 'ilmr4230', 'ilns1359', 'ilns2615', 'ilon4701', 'ilqj8504', 'ilsk1624', 'ilsr6873', 'ilsz3234', 'ilus2378', 'ilwa4789', 'ilxe9816', 'ilzn4437', 'imad9387', 'imee5044', 'imgq9500', 'imkf7589', 'imlq4487', 'imti6802', 'imuf5700', 'imvp0292', 'imyc1720', 'inbs0408', 'inbw3381', 'inff1668', 'infg8610', 'ingp7934', 'inje8653', 'inkw7082', 'inpg4456', 'inpn5461', 'inxp2884', 'inyb4828', 'ioao6071', 'ioiz2978', 'iols7011', 'iopy7636', 'iosw4023', 'iotl0582', 'ipcw9877', 'ipfi8994', 'iphi7119', 'ipks1307', 'iplp5212', 'ipsk3174', 'ipsq4546', 'iptj9884', 'ipvv8622', 'ipyq0982', 'ipyx1830', 'iqbi9102', 'iqbo9934', 'iqij6408', 'iqmu6831', 'iqnv5479', 'iqpp7744', 'iqxi5564', 'irff2473', 'irlg3639', 'irlw4901', 'irnv5317', 'irnx7841', 'iroi2552', 'irqm3485', 'irrr9599', 'iruy4335', 'irwe3478', 'irze7155', 'irzw9017', 'isaa1817', 'isan5412', 'isbn0034', 'isbu2758', 'ishy0440', 'isju4026', 'isjx6011', 'iskr5150', 'isph0871', 'istd3415', 'iszb2222', 'itan7511', 'itbp5949', 'itdj6172', 'itfu0812', 'itfu6732', 'itgk8334', 'ithc6323', 'itrh4575', 'itsy3959', 'itup8254', 'iucc8170', 'iudm7746', 'iufu7208', 'iupr9919', 'iusz8570', 'iuvr5896', 'iuzy2298', 'ivcg1112', 'ivem5274', 'ivgp2835', 'ivix0314', 'ivlt3173', 'ivnv3426', 'ivpf8114', 'ivqf2786', 'ivuu5691', 'ivwc9407', 'ivxp2605', 'ivyn1991', 'iwel2130', 'iwhb8421', 'iwhe8151', 'iwij6752', 'iwmk4742', 'iwmz9095', 'iwnm5888', 'iwsj3661', 'iwtc3484', 'iwua2560', 'iwzs7798', 'ixcq0275', 'ixes9250', 'ixjn2637', 'ixkc7548', 'ixml1528', 'ixmq1284', 'ixoi2416', 'ixsi4394', 'ixtc8833', 'ixtr0595', 'ixum7049', 'ixxs4206', 'iykl5929', 'iyqz0908', 'iysa3490', 'iyzo4057', 'izea2520', 'izky2868', 'izmn9777', 'izqw7098', 'izrn5326', 'izsf8888', 'izsw5398', 'izth1726', 'iztr9602', 'izvc9978', 'izvf8946', 'jafu3504', 'jafy6412', 'jane3226', 'jaqe8437', 'jarl6065', 'jatd1457', 'jauq3190', 'jaxi5700', 'jaxk6195', 'jazo4703', 'jbfx9114', 'jbgc7451', 'jbkd6516', 'jbkm8278', 'jbpo0371', 'jbsl9203', 'jbtw8596', 'jbwh3569', 'jcaa7365', 'jcah4814', 'jcdh2706', 'jcdu5354', 'jcew0685', 'jcff0597', 'jcfm8452', 'jchy4654', 'jclm5994', 'jcmc6955', 'jcoi6479', 'jcoo8592', 'jcri4184', 'jcwt2733', 'jdau3099', 'jdcy7826', 'jdgn3548', 'jdid2569', 'jdmn3528', 'jdqy1986', 'jdst8697', 'jdwx6906', 'jepn5855', 'jesg8916', 'jesk3087', 'jesq6678', 'jewg2042', 'jfcb4480', 'jfcd6416', 'jfhl2821', 'jfhl3522', 'jfkn7998', 'jfkq7841', 'jfmd7607', 'jfmf0509', 'jfmz2270', 'jfnx9547', 'jfor5471', 'jfpj7153', 'jfrj8141', 'jfuw2723', 'jfzn0090', 'jfzr3603', 'jgbu2063', 'jght0329', 'jgkc9615', 'jgkg6949', 'jgot4950', 'jgvy9078', 'jgwl1568', 'jgwv2734', 'jgxm2771', 'jgzq3274', 'jhgc6994', 'jhgo3241', 'jhhh7048', 'jhho7222', 'jhkf0539', 'jhko8015', 'jhmg2189', 'jhmk3498', 'jhoa9173', 'jhpi7440', 'jhpx2922', 'jhsc9256', 'jhyk9541', 'jiaz2760', 'jidk7174', 'jieb8398', 'jihi7444', 'jijs9805', 'jikh4493', 'jiko7540', 'jilf9590', 'jimh9295', 'jinw8888', 'jisq4499', 'jitq8081', 'jitw6482', 'jivi3251', 'jizz3609', 'jjai9349', 'jjbg8536', 'jjdw0436', 'jjfu4578', 'jjgo6859', 'jjoi1134', 'jjqd9289', 'jjyd9545', 'jkco6671', 'jkcu1705', 'jkdb4289', 'jkhp3229', 'jkkb5411', 'jklh8398', 'jknc2849', 'jkom9057', 'jkuy2758', 'jkvw0419', 'jkxz9580', 'jlfa8262', 'jlfi3800', 'jlga1357', 'jlig4204', 'jljc2756', 'jlsk9760', 'jlyn1967', 'jlyy5990', 'jlzc0072', 'jmar0313', 'jmiw3401', 'jmjs0378', 'jmlk4155', 'jmlp1195', 'jmnk4220', 'jmta7659', 'jmxk7817', 'jmym0786', 'jncd8735', 'jnfp4836', 'jngs5634', 'jngv6168', 'jnhb5791', 'jnjt6565', 'jnqo5188', 'jnra3373', 'jnua0043', 'jnyh1652', 'jnyq6254', 'joak5437', 'jocg1646', 'jogb9564', 'jowc8665', 'joyc6858', 'jozd2359', 'jpaa6173', 'jpal5163', 'jpbk1049', 'jpbs5595', 'jpcm0608', 'jphz9712', 'jpia8108', 'jpkk4371', 'jpkk8142', 'jppn4908', 'jpwr6567', 'jpwx3089', 'jqep5472', 'jqey7228', 'jqfo5420', 'jqim2419', 'jqjw9450', 'jqkj7816', 'jqnt0402', 'jqod6026', 'jqpr2042', 'jqrh1744', 'jqsl6530', 'jqtm7760', 'jqxc5424', 'jqxf6356', 'jqxi4397', 'jqxz7853', 'jqyu4110', 'jreg6561', 'jrgl1382', 'jrgn9283', 'jriw9168', 'jrnr1993', 'jrqp8906', 'jrqy6160', 'jrtj9359', 'jryz5803', 'jscx1460', 'jscx5613', 'jsed0519', 'jsfk1280', 'jshk0229', 'jsia0022', 'jsmw2829', 'jste6872', 'jstf1572', 'jsuo2913', 'jsvs6488', 'jswh7613', 'jtas6320', 'jtdo3904', 'jtfr8345', 'jthg8302', 'jthg8875', 'jtir3832', 'jtpp0137', 'jtsk0969', 'jtsq6774', 'jttx2414', 'jubb7617', 'judb5795', 'jufe4545', 'jufh5626', 'juqb5601', 'juud1104', 'juyj5935', 'jvao6358', 'jvev0623', 'jvis4587', 'jvko4541', 'jvkp9286', 'jvnc5636', 'jvpd1423', 'jvpm6892', 'jvrt4565', 'jvrx5904', 'jvsh3389', 'jvyl8410', 'jwfz6540', 'jwgo3216', 'jwhd6616', 'jwis0317', 'jwjo3607', 'jwkh6337', 'jwmj5912', 'jwmu2053', 'jwnx0803', 'jwpy0566', 'jwrl8097', 'jwry6476', 'jwsv8197', 'jwsw4004', 'jwus2012', 'jwyz8954', 'jwzp3670', 'jxaj2501', 'jxfl4866', 'jxhe7890', 'jxhz8800', 'jxir2116', 'jxkf8233', 'jxvk6684', 'jxxk1069', 'jyal8558', 'jybz6086', 'jygu2846', 'jyjn1317', 'jyvt4800', 'jyvu5552', 'jzae5316', 'jzam7544', 'jzat0899', 'jzda2015', 'jzfy8294', 'jzjg2307', 'jzlg3625', 'jzpe6624', 'jzpz9071', 'jzre7140', 'jzyn7131', 'kaao0697', 'kacd4378', 'kaed1820', 'kafl0883', 'kahk8868', 'kahy1224', 'kaja6002', 'kajc0002', 'kajk2661', 'kajr1401', 'kamu4047', 'kaol7211', 'kato6942', 'kaud0195', 'kauf2444', 'kave3914', 'kbao5260', 'kbef1942', 'kbgd4328', 'kbhj7469', 'kbjn8919', 'kbjo6067', 'kbjy9404', 'kbke2186', 'kboe9525', 'kbpe0088', 'kbql7054', 'kcaf0494', 'kcbh0011', 'kceq4393', 'kcex5945', 'kcjl0333', 'kcne5825', 'kcnn3765', 'kcpu5884', 'kczw2006', 'kdde3677', 'kdgk5066', 'kdmi5224', 'kdmy1223', 'kdsk1904', 'kdtk0531', 'kdtn7683', 'kduy2106', 'keca2906', 'kecc6814', 'kefu3041', 'keho9059', 'kekv8201', 'kepe5405', 'kepo9071', 'kepr3474', 'kewl2546', 'keww7071', 'kewz8875', 'kexp8326', 'keyj8916', 'kfet2337', 'kfmj4311', 'kfnh8419', 'kfnk9808', 'kfop4167', 'kfoy1303', 'kfqc7976', 'kfqn9865', 'kfsd7094', 'kfuq2619', 'kfyu4049', 'kgcd2334', 'kgdc2737', 'kgia3855', 'kgiq1033', 'kgrf8033', 'kgrz2149', 'kgun8790', 'kgwl4660', 'kgyq5324', 'kgzh9081', 'khba4824', 'khev4713', 'khjn3892', 'khkf3266', 'khvk6994', 'khwr3000', 'khzx6913', 'kiam0497', 'kias9425', 'kicc8588', 'kifd0333', 'kifu8263', 'kihi6142', 'kilq4560', 'kilx9074', 'kira1976', 'kish3973', 'kitv3498', 'kiuc4316', 'kius9293', 'kiyp6785', 'kizy0673', 'kjet4064', 'kjhk7863', 'kjiu3640', 'kjoe3719', 'kjqx1148', 'kjun4923', 'kjvy9073', 'kjzg8972', 'kkgh7316', 'kkhs8860', 'kkjm9016', 'kksk2650', 'kkvh1228', 'kkwz4642', 'klfg3704', 'klgj8809', 'klmp4380', 'klna1171', 'klot7972', 'klpt8935', 'klqo1529', 'klqt8199', 'klss3332', 'kltr8461', 'kmbx9172', 'kmcg9806', 'kmdn7533', 'kmhp2947', 'kmpe2685', 'kmpi9146', 'kmrj1248', 'kmvq1070', 'kncc5641', 'knfy8815', 'knkh1256', 'knmf0665', 'knpi9987', 'knpq0755', 'knwq3153', 'knzt3468', 'koar1977', 'kohh2733', 'koja3388', 'kopy2946', 'kotn9233', 'koxk7539', 'kozm0995', 'kpbj2916', 'kpcw1992', 'kppi2840', 'kpra8061', 'kprp6894', 'kpxq2617', 'kqjo5495', 'kqmw4304', 'kqsb4343', 'kqvr8044', 'kqwv6794', 'kqzs1984', 'kraj2051', 'krfh1877', 'krfj7178', 'krjz3520', 'krlj0932', 'krpw2634', 'krrs1077', 'krsm5264', 'krst3743', 'krui0105', 'krum1307', 'kryg0769', 'kshq6789', 'ksit7421', 'ksmc9221', 'ksrh5318', 'ksrv9860', 'ksuf6528', 'kszg4077', 'kszy3985', 'kten4097', 'ktet2100', 'ktge4463', 'ktld6283', 'ktnn7483', 'ktpa7420', 'kttd5863', 'ktvb1097', 'ktwj6182', 'kuei2080', 'kufj7163', 'kuhu2971', 'kulu3378', 'kuoj1542', 'kurr2897', 'kusb3088', 'kuxk6111', 'kvdp8507', 'kved0045', 'kvjn9814', 'kvkb5939', 'kvla8086', 'kvlx2420', 'kvui9599', 'kvyt9609', 'kwbt8656', 'kwbw7098', 'kwhk1730', 'kwjc0102', 'kwlw2539', 'kwmf2808', 'kwof4185', 'kwpx5081', 'kwtk9213', 'kwxz6535', 'kwyd5832', 'kwyh1663', 'kwzc5300', 'kxfu6461', 'kxip7820', 'kxls1787', 'kxnu6595', 'kxrp4055', 'kxry6882', 'kxsb9753', 'kyac5861', 'kyao6681', 'kyfd2491', 'kyfp2504', 'kygf0538', 'kyxs8260', 'kzcw4607', 'kzfr8427', 'kzin8563', 'kzkm6073', 'kzlp5248', 'kzqm5081', 'kzre7827', 'kzvu1059', 'kzzs4772', 'laai2599', 'ladf6625', 'lalv1210', 'lamm4861', 'laov8157', 'lapm9281', 'laqk3187', 'latr9597', 'laup8782', 'lauy0288', 'lavv9354', 'lawl2157', 'laws8051', 'laxp7855', 'layy1683', 'lbcc3402', 'lbkv0185', 'lblq8911', 'lbsn9421', 'lbsx2092', 'lbsz8055', 'lbwp6185', 'lbwr8277', 'lbwr9563', 'lcbc6033', 'lcbw1155', 'lcbw1506', 'lceo9569', 'lcfj5922', 'lciu3906', 'lcjf4868', 'lcnr4928', 'lcny2891', 'lcod1220', 'lcpg9027', 'lcrk6649', 'lcru7151', 'lctd7733', 'lcuu6756', 'lcuu8482', 'lcvs2131', 'lcyi5533', 'lczq0306', 'ldid2454', 'ldll3477', 'ldoo1116', 'ldoo4225', 'ldse6903', 'lduw6685', 'ldwi8984', 'ldwx8800', 'leab1774', 'leeo3766', 'lefw3388', 'lekv0813', 'lemf3011', 'lenr6757', 'lenw5638', 'lepd2011', 'lepn6767', 'lerc9947', 'leuy4866', 'levw2327', 'lezz7368', 'lfbc3424', 'lfbl5076', 'lfdg5647', 'lfiq7254', 'lfwm3360', 'lfyj5063', 'lfzo7598', 'lgcl3268', 'lgeq5594', 'lgiw8924', 'lglm1839', 'lgqo2294', 'lguu2252', 'lgyh5615', 'lgyn1511', 'lhah6357', 'lhcl3266', 'lhcn2989', 'lhdy1072', 'lher7578', 'lhhu2375', 'lhkk3298', 'lhmo4535', 'libz1251', 'lihh9050', 'liql8901', 'liuy1355', 'livw9297', 'liwj7053', 'lizd0884', 'ljch5466', 'ljep8680', 'ljid6628', 'ljus7490', 'ljwh9769', 'ljyh7578', 'lkfx1123', 'lkhl2227', 'lkho0104', 'lkjx1992', 'lkng9528', 'lknv4330', 'lkos4395', 'lksx0163', 'lkvr5865', 'llcx5215', 'llse5470', 'lltd8818', 'llus4540', 'lmau0272', 'lmgr7959', 'lmgx5767', 'lmon5630', 'lmsa2273', 'lmvr7887', 'lmwk5773', 'lndx3634', 'lnhd0316', 'lnjo4686', 'lnpp9522', 'lnpx9974', 'lnsr4482', 'lntj9769', 'lnuz4750', 'load0873', 'locn9696', 'lodm5200', 'lofv1499', 'lofw9707', 'lojs1275', 'loks2432', 'lomw8856', 'loox1530', 'lope9873', 'loqt1087', 'lpmf8735', 'lpnz2865', 'lpqz8187', 'lpte6176', 'lptq5384', 'lqar1408', 'lqax0778', 'lqce9646', 'lqct0685', 'lqje5518', 'lqob6660', 'lqqg7687', 'lqqj8633', 'lqti1278', 'lqwr1745', 'lqwr9634', 'lqxj5960', 'lrap6873', 'lrie9155', 'lrmw5304', 'lrsn4616', 'lsep4991', 'lsgw8887', 'lslr7112', 'lslu0002', 'lsor0501', 'lspt8063', 'lsss1001', 'lsvo6287', 'lswo0938', 'lsxa2161', 'ltcz8215', 'ltgx2743', 'ltko1046', 'ltlq1913', 'ltmv6231', 'ltpp3777', 'lttp6222', 'ltts6311', 'ltux0293', 'ltzs2934', 'lucr5648', 'lufd3188', 'luhk7708', 'luij2195', 'luil3442', 'luiv6235', 'lujc1706', 'lums4674', 'lupn5755', 'luqj8815', 'lusn0974', 'luso0860', 'lust3215', 'luup6030', 'luux6475', 'luwt9801', 'luxg9966', 'lvbo6637', 'lvgn1459', 'lvid4995', 'lvmh7467', 'lvnk0326', 'lvra2199', 'lvwl0262', 'lvwn1750', 'lvyt7039', 'lwfr1850', 'lwgi0531', 'lwif1861', 'lwis4321', 'lwiv3215', 'lwjq4696', 'lwkz5890', 'lwmd6725', 'lwmi9414', 'lwpc8144', 'lwtm8211', 'lwxv1967', 'lwyj2983', 'lwyy0567', 'lxec2959', 'lxeu1624', 'lxhd9617', 'lxji5573', 'lxjk6052', 'lxmi5429', 'lxot1841', 'lxqp6619', 'lxtl2935', 'lxub4284', 'lxvs4070', 'lxwq5815', 'lyat3987', 'lyfb1044', 'lyob2169', 'lyoj8152', 'lypg5873', 'lyqa6268', 'lytu7103', 'lyww6667', 'lzdh7062', 'lzdj2065', 'lzdv8397', 'lzgd2983', 'lzkx0508', 'lzlg0982', 'lzmn5410', 'lzne5081', 'lznx7287', 'lzpd8781', 'lzub2929', 'mabp7663', 'magz2742', 'mail0722', 'maqz8781', 'math1295', 'matn4467', 'mavn6478', 'maxx5017', 'mayy5240', 'mazi2683', 'mbih6415', 'mbjy5169', 'mbpp2424', 'mbrb0869', 'mbvp5502', 'mcbj0543', 'mcdz0863', 'mcmq3219', 'mcrw2515', 'mdcb6304', 'mdna2790', 'mdnm9688', 'mdwg1526', 'mdzk3634', 'meas8391', 'meca2107', 'meeb0156', 'mefk5369', 'meii8847', 'memn9762', 'meou4235', 'meqh2770', 'merl5232', 'meyn7205', 'mfis8312', 'mfix1838', 'mfjp7021', 'mfog3267', 'mfpy7637', 'mfqx5485', 'mfrl9544', 'mfsk5829', 'mftp1023', 'mfue2701', 'mfvv6215', 'mgas8060', 'mgbm3335', 'mgco1382', 'mgep8889', 'mghd1231', 'mghj7398', 'mghx9609', 'mgnc9295', 'mgno2961', 'mgpo2400', 'mgqu0980', 'mgsj5724', 'mgtb6884', 'mgwr8293', 'mgxw6224', 'mgyx4769', 'mhfg3538', 'mhln2096', 'mhmo7097', 'mhng2032', 'mhtq2980', 'mhua2310', 'mhvz2504', 'mhwn7664', 'mhza3459', 'micu5459', 'miee2578', 'miem3260', 'miev4439', 'miew5562', 'mifb8106', 'milt3784', 'mimd0122', 'minr1989', 'miou3088', 'mivw0763', 'miwk9585', 'mjcd0121', 'mjcy0248', 'mjdl8623', 'mjfw1002', 'mjjh9802', 'mjjz9470', 'mjlo8417', 'mjsn6817', 'mkmm0380', 'mksa1349', 'mkua3990', 'mldx1128', 'mlfl3732', 'mlgp5312', 'mlih1349', 'mljr2391', 'mljt5838', 'mlno8799', 'mloq2340', 'mlra8349', 'mlrl6531', 'mmfg2024', 'mmfx6031', 'mmjw0829', 'mmpb7871', 'mmpc4614', 'mmpi1490', 'mmpw2987', 'mmuf1104', 'mmwe8119', 'mmww3703', 'mnbf5564', 'mncy2800', 'mnde6499', 'mnio0111', 'mnjz9837', 'mnlx1055', 'mnnu0672', 'mnnu6390', 'mnrg4627', 'mnrj6228', 'mnsn9674', 'mntu6907', 'moaa7304', 'moct4100', 'mods8392', 'modt6974', 'mofq3678', 'moht9511', 'moml9087', 'momm8424', 'moqx4288', 'morv8744', 'motn7065', 'moui2525', 'move9930', 'mozd9414', 'mpbx6681', 'mpdq5086', 'mpew9584', 'mpht1583', 'mpiw0531', 'mpld2031', 'mppl2624', 'mpsx5474', 'mpvq9484', 'mpxl4432', 'mpyn1610', 'mqdf5057', 'mqdq8047', 'mqjv7193', 'mqne4908', 'mqoq0712', 'mqyw7913', 'mrka8081', 'mrkk2294', 'mrku8805', 'mrly4309', 'mrpb7994', 'mrso1591', 'mrwh8289', 'mrwj4183', 'msat2874', 'msex1720', 'msfc7861', 'msyv1420', 'mtbd8107', 'mtif7978', 'mtlb2468', 'mtpz4542', 'mtqf4567', 'mtto3615', 'mtwd2975', 'mtwr5736', 'mtxd5871', 'mtzd6005', 'mubs3534', 'muhd6110', 'muhq0035', 'mukz7090', 'mulf0014', 'mumx5877', 'muvl0441', 'muxr3180', 'mvmg1272', 'mvmq2804', 'mvoj6933', 'mvou8111', 'mvqe0087', 'mvvr0575', 'mwae9033', 'mwcb8106', 'mwfv5546', 'mwgq3469', 'mwig7755', 'mwiz7164', 'mwla6800', 'mwlc4610', 'mwmu8732', 'mwoc2111', 'mwpg3116', 'mwre0554', 'mwsu9870', 'mwvc1303', 'mwxr2760', 'mxac1244', 'mxdx1863', 'mxek2629', 'mxfd8359', 'mxjx9465', 'mxos5470', 'mxsc0388', 'mxsi9600', 'mxvq7451', 'myew0071', 'myha3906', 'mypw6333', 'mytm7464', 'myzk0916', 'myzm9860', 'mzaq9519', 'mzba7604', 'mzkf2561', 'mzlj1794', 'mznw3445', 'mzqb0109', 'mzqe1859', 'mzqy4314', 'mzuu7390', 'nafl2952', 'naie8987', 'najo0729', 'najp3977', 'nakc7103', 'nake1189', 'nalb8919', 'naok1529', 'nata0815', 'naxr1952', 'nbaq1899', 'nbdn0211', 'nbie8293', 'nbjx6467', 'nbpp7391', 'nbqf1470', 'nbse3594', 'nbsy0644', 'nbtu5280', 'nbus4771', 'nbuz8241', 'nbxj1829', 'nbya2980', 'nccd6929', 'ncjo3858', 'ncpl5877', 'ncps9032', 'ncrx6201', 'ncsl0439', 'ncyk7481', 'nczp8945', 'ndai1909', 'ndaq3685', 'ndaz7478', 'nddl2049', 'ndev9581', 'ndfl0913', 'ndjb1894', 'ndmb2106', 'ndnb9464', 'ndqx0690', 'ndwe7373', 'ndwg5186', 'ndwh8773', 'ndwj1135', 'ndwx7388', 'ndyy9614', 'nebj9461', 'necf3972', 'necp2968', 'negc4233', 'nejm0230', 'nelz3179', 'nenk7739', 'neov8553', 'nety0825', 'nfay5390', 'nfbd5891', 'nfha6709', 'nfiv4285', 'nfjl0605', 'nfjt0193', 'nfng0879', 'nfqt8969', 'nfwd8219', 'ngeg8565', 'nghz3736', 'ngrt1409', 'ngsb9443', 'ngte8760', 'ngwl4518', 'ngys1963', 'ngze1334', 'nhdd9673', 'nhdu1436', 'nhef0684', 'nhfd1137', 'nhgu8519', 'nhig2537', 'nhir3024', 'nhlr8671', 'nhmj2393', 'nhod1610', 'nhog5251', 'nhoy7454', 'nhqi2632', 'nhsp1114', 'nhtb2653', 'nhtb4219', 'nhvn1838', 'nhwc2661', 'nhwq0304', 'nhwq5301', 'niak2436', 'nigc7355', 'nihn1443', 'nijl3279', 'nijo9787', 'nikz7010', 'nilh8819', 'nipd2115', 'niqr6353', 'niri7123', 'niru6634', 'nisa7745', 'njbn2345', 'njdm1302', 'njgf3220', 'njnr3102', 'njra7501', 'njry7584', 'nkbq0168', 'nkff5996', 'nkhz5980', 'nkib5603', 'nkit2122', 'nklo7889', 'nkmy2558', 'nkot7423', 'nkqt0608', 'nkrq3891', 'nkrv2149', 'nkte7281', 'nkub6010', 'nldf8659', 'nldr3405', 'nldy4670', 'nlfe3809', 'nlgs5640', 'nlgv4495', 'nlio2627', 'nlli2691', 'nloe7660', 'nlpb5302', 'nlpb9190', 'nlqk7833', 'nltk6764', 'nlxb4016', 'nlzm1081', 'nlzs6202', 'nmac7382', 'nmbh8959', 'nmfa9794', 'nmgo9306', 'nmla3826', 'nmnr8268', 'nmza7088', 'nncb5043', 'nndr4748', 'nnge7232', 'nngr8916', 'nngw5000', 'nnon2756', 'nnph4639', 'nnpn5969', 'nnve0760', 'noby1972', 'nofs8413', 'nogl3098', 'nohp4759', 'nokz3881', 'noni0568', 'nonx3049', 'norx9667', 'notx3656', 'nour4803', 'nous6055', 'nozf9947', 'npbu1030', 'npgc9757', 'npia5222', 'npkf4937', 'npnv1181', 'npok1057', 'npow2052', 'nprj0503', 'nprq6676', 'nptl5569', 'npvd8751', 'npwu4424', 'npwy7343', 'nqag9787', 'nqel0642', 'nqev4156', 'nqft1216', 'nqhq4040', 'nqpn5964', 'nqqk8147', 'nqrz6347', 'nqvp4748', 'nqxo2974', 'nrad0234', 'nray0985', 'nrdb5584', 'nrec9604', 'nrfr0998', 'nrgv7457', 'nrgz9428', 'nrka5661', 'nrmc2340', 'nrmr9290', 'nrtc1751', 'nrvt9411', 'nsad8258', 'nsaj9267', 'nsan8821', 'nsau2592', 'nsaw6005', 'nscs6147', 'nsfy7991', 'nsgw9306', 'nsjp4365', 'nsmf6304', 'nsos8666', 'nsqw4997', 'nsuk6939', 'nsun3761', 'nswo3140', 'nsxa3650', 'ntcb7922', 'ntft4951', 'ntht6991', 'ntjr2251', 'ntkk4219', 'ntme0255', 'ntoa5413', 'ntpu2941', 'ntqd4587', 'ntth7892', 'ntud3509', 'ntuw0235', 'ntxw5310', 'ntza8376', 'nuct3180', 'nugh6389', 'nugo3672', 'nugx3875', 'nuje7695', 'nukb3412', 'nuln0711', 'nunm4659', 'nuov3862', 'nuqx4783', 'nuvo4166', 'nuxr6020', 'nuzv7974', 'nvah0713', 'nvbd1076', 'nvbz1583', 'nvca7682', 'nvcq0705', 'nves2959', 'nvko7254', 'nvmh4939', 'nvnj4859', 'nvrc2618', 'nvth8985', 'nvtq9864', 'nvvc7884', 'nvvv6774', 'nvyo6625', 'nvzt6658', 'nvzx2713', 'nweb0408', 'nwpr5625', 'nwqe9848', 'nwrj3549', 'nwzw6782', 'nxfw6544', 'nxms0918', 'nxnq5462', 'nxoq2580', 'nxvs2752', 'nxyk3357', 'nxzt0222', 'nydm4348', 'nyfu0019', 'nynl6630', 'nynw0715', 'nypm8648', 'nyti2349', 'nyuy3198', 'nzat9186', 'nzcq5015', 'nzed7991', 'nzgr9392', 'nzgx4064', 'nzha2802', 'nzim6554', 'nzlj3932', 'nzmf9949', 'nzpq3945', 'nzqx0065', 'nzrj0380', 'nzsp4700', 'nzsy6303', 'nzxb1839', 'nzxe9463', 'nzxi8648', 'oaab1677', 'oaeo6556', 'oagr5311', 'oahj7975', 'oale8949', 'oalq2578', 'oaou9712', 'oawp3927', 'oaxc2882', 'oaxc7901', 'obeg6048', 'obex0437', 'obgv5921', 'obht2115', 'obou0878', 'obxi7694', 'obxo8063', 'obyv4148', 'occs1715', 'ocdz6031', 'ocfn5730', 'ocgw8573', 'ocjb6170', 'ocjv7918', 'ocru0752', 'octi9223', 'ocxj1390', 'ocxs2022', 'odal2423', 'odcr3564', 'odfj9390', 'odhc1154', 'odhs5208', 'odie1570', 'odkz1524', 'odoc9567', 'oduu7146', 'odyf6652', 'odyy1520', 'oeae8786', 'oecm7952', 'oefm8808', 'oekd6301', 'oelc1085', 'oelm7038', 'oeni1744', 'oerm8084', 'oeyk8474', 'oeyx0610', 'ofai2016', 'ofap0850', 'ofbu3134', 'ofhm0407', 'ofhr6541', 'ofkf7118', 'ofld6790', 'oflt0410', 'ofoq9733', 'ofsu5621', 'ofvd4555', 'ofvt0180', 'ofyx4673', 'ogan3744', 'ogfy0474', 'ogkc8560', 'ogmt3450', 'ogpv8580', 'ogsz1807', 'ogtw8610', 'ogxm0047', 'ohdh8294', 'ohev2965', 'ohjq9889', 'ohjx4706', 'ohmg8732', 'ohox2053', 'ohpo5936', 'ohqu4764', 'ohud8369', 'ohwn9611', 'ohxw3941', 'oibi8629', 'oibp4438', 'oice9572', 'oifh2093', 'oifw1829', 'oipr4431', 'oipv4371', 'oisn6780', 'ojbg0657', 'ojbg2336', 'ojdq4376', 'ojeu7955', 'ojgr5739', 'ojhy3941', 'ojjr1874', 'ojjt8642', 'ojmu8110', 'ojpl7920', 'okla7030', 'okoq0494', 'okpd0454', 'okpl9153', 'okpv6733', 'okpx4962', 'okqu3433', 'okrg3018', 'oksl4667', 'okvm7903', 'okxl1910', 'okxo5971', 'okyt5702', 'okzu2647', 'olav4860', 'olcz0390', 'oldl3183', 'oliy4010', 'oljs5762', 'olob3004', 'olqi7626', 'olry6526', 'olsa9825', 'oltr1320', 'olvf1010', 'olwt0723', 'oman3571', 'ombp0146', 'omds3852', 'omef4637', 'omeh8539', 'omfc8947', 'omfg1734', 'omfr8700', 'omft2017', 'omjy7389', 'omky4765', 'omnw6686', 'omqs7964', 'omta0643', 'omta6234', 'omtb7378', 'omub3966', 'omuc0269', 'omwf3507', 'omwv0612', 'omxd3109', 'omyb6159', 'omzy1801', 'onad0970', 'once9578', 'ondk7534', 'onfg2871', 'onft0539', 'onib8552', 'onkw5945', 'onms0115', 'onse8907', 'onxz0612', 'ooag4442', 'ooca4526', 'oofo0933', 'oogm6948', 'oohr6058', 'ooht9523', 'ooiz5026', 'ookf3944', 'oolk1097', 'oomc1784', 'oorf2136', 'oori4450', 'ooys1528', 'opet5219', 'opik3533', 'opjl7431', 'opjs5888', 'opkz4710', 'opld9899', 'opsx1719', 'optm6906', 'opxk1358', 'oqbh3590', 'oqma8085', 'oqpi5150', 'oqxk1578', 'oqxp9963', 'oqzm0429', 'orar4608', 'orcu7140', 'orgt0313', 'orjr4906', 'orln7240', 'oroa8791', 'oroi9396', 'orpq6876', 'orty9612', 'oruv0779', 'orzy6156', 'osar7728', 'osat1891', 'osay3420', 'osbo5614', 'osei9558', 'oshg5508', 'oshq1955', 'osio6900', 'osiv2659', 'oskq9329', 'oskv9259', 'oslw2296', 'osnt6376', 'osqr7888', 'osrs3919', 'osuc1859', 'osvv3215', 'osxj5952', 'oszl7088', 'otbo3043', 'otcd6857', 'otdj0256', 'otjm9368', 'otmu0809', 'otov0674', 'otst3925', 'otvk3455', 'otvk7450', 'otxp9006', 'otzn8605', 'oudk2839', 'ougz5234', 'oujp2057', 'oulp5364', 'ouns3370', 'ouqz4586', 'ouse3535', 'outy0089', 'ouxo4723', 'ouxy7074', 'ouzs7908', 'ouzz9761', 'oveg9449', 'ovhd6864', 'ovhz8659', 'ovjm5013', 'ovkd2412', 'ovol8427', 'ovoo3180', 'ovrw7258', 'ovsc3165', 'ovtc9191', 'ovwl1805', 'ovyv0964', 'ovzk6187', 'owbr6938', 'owld6277', 'owlu6294', 'owng3445', 'owop5150', 'owqc8325', 'owqi8601', 'oxcl7282', 'oxmk6572', 'oxmw4948', 'oxrn5093', 'oxun0405', 'oxux0215', 'oxwn7926', 'oxxl4256', 'oxyp7333', 'oyce9739', 'oycp8296', 'oydp2673', 'oyes1872', 'oyfn6076', 'oyhx7628', 'oykf8998', 'oyml5950', 'oymn7715', 'oyts0598', 'oyty6233', 'oyva6259', 'oywt3480', 'oyxd2742', 'oyyp8123', 'oyzx7057', 'ozcs7389', 'ozdg8495', 'ozjq4824', 'ozkd5093', 'ozrt8421', 'ozsu5489', 'oztm2403', 'ozug1135', 'paci7452', 'pafg4618', 'pafq5628', 'pahr9561', 'pamx1252', 'pann9047', 'pawr8899', 'paxd8550', 'pbap4395', 'pbcg0676', 'pbcv1266', 'pbda0452', 'pbfz5889', 'pbkz5755', 'pbmg5406', 'pbnn0591', 'pbpk9578', 'pbrj0631', 'pbwp6064', 'pbwv3112', 'pbww7866', 'pbwy2542', 'pcaw9171', 'pcbh4083', 'pcdb3011', 'pcfd9482', 'pcfq0441', 'pcfv3563', 'pcgm1104', 'pcih2676', 'pckm7597', 'pcma3176', 'pcsg3051', 'pcwp7272', 'pcxw5634', 'pddk5373', 'pdkj6278', 'pdks8555', 'pdln3091', 'pdlu4041', 'pdrn0976', 'pdvn6527', 'pefu2116', 'pehh9166', 'peky4876', 'pemu6262', 'perb5922', 'pesb0348', 'pewr1644', 'pfcf7947', 'pffb5863', 'pfff2870', 'pffu3444', 'pfgl3437', 'pfie2768', 'pfma3446', 'pfzu8042', 'pgbe9408', 'pgir9673', 'pgis5072', 'pglb5180', 'pgme6939', 'pgos9732', 'pgpp1934', 'pgqw8065', 'pgqy4959', 'pgwy1866', 'pgxw0586', 'pgze3395', 'phbb6091', 'phcd2353', 'phcj8194', 'phet2387', 'phfp2836', 'phhw0713', 'phkz7390', 'phpi8206', 'phwv4138', 'phzd4178', 'piab8465', 'pidl9225', 'pidn4335', 'piee8343', 'pihe6294', 'piix4756', 'pilk4274', 'piru3849', 'pita5889', 'pity1432', 'piur6001', 'pixq4076', 'pjcj6740', 'pjcu0390', 'pjee6333', 'pjgk7785', 'pjgx0544', 'pjhn8201', 'pjho6329', 'pjhz2241', 'pjlt4070', 'pjrc9644', 'pjre8150', 'pjrw6607', 'pjrw7837', 'pjry7761', 'pjsb8900', 'pjte5643', 'pjtn9951', 'pjun3381', 'pjzy0314', 'pkal4061', 'pkdd9864', 'pkjb4151', 'pkll4106', 'pkls4877', 'pknk1998', 'pkop2032', 'pkrr9126', 'pksi4666', 'pksk5507', 'pkxn8130', 'plbb4730', 'plbt6688', 'plbv3285', 'plcw2587', 'plde8966', 'pldg7326', 'pldv6001', 'pler9762', 'plfp9959', 'plfs3625', 'plik2983', 'pljm6212', 'plnn8834', 'plsk4730', 'pltk6825', 'plug2422', 'pmiu1361', 'pmqd8480', 'pmxx5993', 'pnaw9487', 'pncj7096', 'pnde3619', 'pned2326', 'pnfu0332', 'pnhi1850', 'pnhp2105', 'pnku9578', 'pnpm8166', 'pnrh1727', 'pnsn3636', 'pnsu7967', 'pntd5053', 'pnve9362', 'pnwc4600', 'pnwp2332', 'pnzj8892', 'pobb8219', 'pobr2137', 'podz9764', 'pogu5133', 'poie1590', 'poio5449', 'pokh5544', 'pomq8191', 'poqf7228', 'porm6022', 'porp8426', 'pouk0497', 'poww7802', 'poxj1631', 'poyv9224', 'ppcc2950', 'ppds1538', 'ppiu0150', 'ppku3832', 'ppop6904', 'pprm0838', 'ppvt9545', 'ppxt8159', 'ppym9574', 'ppyo9166', 'ppzz3854', 'pqas0395', 'pqgl7506', 'pqny2432', 'pqoi8665', 'pqqt3153', 'pqre1663', 'pquf0809', 'pqye3518', 'pqyq6233', 'prba4559', 'prcy7099', 'prgf4032', 'prik1400', 'prkq6409', 'prny6478', 'prqs9356', 'prrs9906', 'przx8474', 'psbs0767', 'psgg3006', 'pshm2912', 'psmh8616', 'psqf6715', 'pssw3411', 'psta4589', 'psuy0948', 'ptab1928', 'ptft2928', 'ptgb6564', 'ptgj9308', 'ptjj7640', 'ptjz8924', 'ptke4824', 'ptlf4606', 'ptln0914', 'ptmn4891', 'ptov1376', 'ptoz0719', 'ptpa0899', 'ptsp3266', 'ptvi4541', 'ptwe7784', 'ptxi4368', 'puku8720', 'pusz6383', 'putx4414', 'pvec4883', 'pver5294', 'pvmg5702', 'pvnm9096', 'pvnp3239', 'pvoe0301', 'pvtj4780', 'pvvp5932', 'pvww8394', 'pwbp6189', 'pwdf2303', 'pwdk9858', 'pwhw1942', 'pwis5704', 'pwit5308', 'pwjq8119', 'pwkm6559', 'pwmm8416', 'pwmn2872', 'pwol8972', 'pwry4803', 'pwvs3864', 'pxfi6558', 'pxhx4012', 'pxje2536', 'pxkr7262', 'pxsh0207', 'pxsn6600', 'pxuw7004', 'pxvd0683', 'pxxi9834', 'pxzb1884', 'pycv5121', 'pygv9789', 'pymx7633', 'pyna3314', 'pynm5578', 'pynx2890', 'pyqz1549', 'pyui2602', 'pyui8309', 'pyux8591', 'pyza8453', 'pyzi4745', 'pzbo5222', 'pzdh2288', 'pzft7152', 'pziq9019', 'pzlg2016', 'pznn4852', 'pzns5898', 'pzvb8484', 'pzzf4854', 'pzzn9356', 'qaac2732', 'qacr2203', 'qagc3503', 'qahi4765', 'qajm5728', 'qamk4125', 'qanr6442', 'qans7500', 'qanu9931', 'qavd1917', 'qbbi1683', 'qbcb1367', 'qbfd7201', 'qbiy5015', 'qbpb7965', 'qbrq0123', 'qbty2233', 'qbvw3629', 'qbwb5012', 'qbwc5421', 'qbwq3277', 'qbwv9286', 'qcem6365', 'qcjj1262', 'qcls3397', 'qcnt9593', 'qcuz8046', 'qcvv7863', 'qdal8519', 'qdfd7433', 'qdfs2452', 'qdhk0650', 'qdrq6109', 'qduo5924', 'qduy3451', 'qdvx6899', 'qdvz8522', 'qdyf1027', 'qead7016', 'qedc0555', 'qedq4978', 'qefd8049', 'qegr4124', 'qejd4257', 'qepr8626', 'qesm9845', 'qexp3204', 'qexu0485', 'qeyp1028', 'qfas1551', 'qfcq6015', 'qfcr3870', 'qfed8232', 'qfft8264', 'qfiv7223', 'qfjm0236', 'qflf3628', 'qfqb1261', 'qfsx3543', 'qfwh2142', 'qfxh6012', 'qfxp0491', 'qfzh8413', 'qgbm7331', 'qgce0751', 'qgdc4372', 'qgde5463', 'qgdf4907', 'qgdn7287', 'qghk1802', 'qgrs4112', 'qgus6098', 'qgwb2759', 'qgxd0607', 'qhbo1754', 'qhmj4626', 'qhrt7460', 'qhsd8116', 'qhyn7823', 'qhyw0417', 'qhyy7266', 'qiae5476', 'qihi0973', 'qikh9587', 'qiwe0253', 'qiwk3293', 'qiwo4704', 'qjdv0501', 'qjer2592', 'qjfl4112', 'qjnf1272', 'qjsh5185', 'qjuv9929', 'qjvd8650', 'qjwu4810', 'qkcu2935', 'qkcy4718', 'qkem5272', 'qkfv5349', 'qkhu4473', 'qkkv0749', 'qkmd3909', 'qknn7623', 'qkto1287', 'qkup1174', 'qkva2394', 'qkvo3593', 'qkxj9291', 'qlaj0972', 'qldd5899', 'qlfb6435', 'qlih6776', 'qlll5677', 'qlma0823', 'qlmv5608', 'qlod1804', 'qlpt8620', 'qlwc3829', 'qmap5690', 'qmav6193', 'qmfa7285', 'qmgb3607', 'qmgg6661', 'qmjq9788', 'qmkl4558', 'qmle7529', 'qmmt8149', 'qmrh0449', 'qmso4059', 'qmvo5837', 'qmzi1898', 'qnam4777', 'qncy1613', 'qndm2861', 'qnio1925', 'qnle3571', 'qnrv6563', 'qnsk5415', 'qnxu3088', 'qnyi7819', 'qobp2661', 'qodq8798', 'qole3321', 'qori9777', 'qosh6561', 'qovo6541', 'qovu0168', 'qown7074', 'qoxz0773', 'qoyc8947', 'qpao9337', 'qpbs9258', 'qpbt8058', 'qpcr8738', 'qpdd0791', 'qpdl9875', 'qpmn9310', 'qpon9557', 'qpym3381', 'qqbp1755', 'qqcq1610', 'qqeh4618', 'qqmr3453', 'qqpt8342', 'qqqi7002', 'qqry5039', 'qqsz0713', 'qqxj9825', 'qqyq2904', 'qqze5702', 'qreh4516', 'qrev7506', 'qrkr3721', 'qrqr6397', 'qsbl6971', 'qsji7522', 'qsjn2813', 'qspy2177', 'qssq8058', 'qsvi4975', 'qsxg0927', 'qtcv1053', 'qtdp5531', 'qtiw2413', 'qtjg5377', 'qtmn1915', 'qttm0655', 'qtzc6717', 'qtzu4770', 'quaz2156', 'quhf8360', 'quhq6997', 'quir2169', 'qupa4075', 'qupu4615', 'quqo2405', 'qusd1987', 'qutz1228', 'quvp2390', 'quyt4760', 'qvam7835', 'qvdu4935', 'qvfc1824', 'qvhs2160', 'qvhs5249', 'qvit5393', 'qviv9505', 'qvjh2282', 'qvjs5943', 'qvlw3822', 'qvme9513', 'qvpg6605', 'qvrb7980', 'qvsf1861', 'qweg5695', 'qweu6023', 'qwme4113', 'qwnj0947', 'qwoh1846', 'qwqg4898', 'qwvc1999', 'qwyn1219', 'qxac9835', 'qxir6616', 'qxjp0417', 'qxjv6802', 'qxkk7832', 'qxlw1822', 'qxtl7250', 'qxvp0494', 'qxwq9617', 'qymy1642', 'qynr0705', 'qysr9124', 'qyvj1827', 'qyzp1635', 'qzau6792', 'qzdr4102', 'qzdr9883', 'qzej8935', 'qzii9765', 'qzja8069', 'qzji4718', 'qzrl0032', 'qzye3078', 'raai9495', 'rabv7024', 'radx8246', 'rael1667', 'raev0436', 'ragg7303', 'rahc3753', 'rahi4544', 'rakv5455', 'ramb5669', 'ramr1490', 'raoe3244', 'rasq7492', 'raui0882', 'raum2193', 'ravt1851', 'rbao7328', 'rbcw9736', 'rbgj7219', 'rbqa4017', 'rbsl3102', 'rbyi3963', 'rbzy8070', 'rcet8984', 'rcjp2394', 'rcks1166', 'rclp2091', 'rcos1619', 'rcsl6743', 'rctm3596', 'rcur1934', 'rcux4487', 'rcxe6457', 'rcxg2816', 'rcxn6618', 'rdmx9326', 'rdof4979', 'rdrn7698', 'rduz6064', 'rdxl4347', 'rdxv0465', 'rdzc0085', 'rdzw1188', 'rebn7825', 'redc0964', 'redy1159', 'reet1944', 'refr4807', 'regc6756', 'rege2509', 'regv9771', 'reho7937', 'rejw6330', 'relj1152', 'reop7707', 'reqn8349', 'resl7919', 'retb4596', 'rewv6928', 'reyb3789', 'reyv8213', 'rezb3628', 'rfja7840', 'rfjf0736', 'rfkm1104', 'rflw4312', 'rfmy3899', 'rfry0633', 'rftb1449', 'rfuz0315', 'rfzv7978', 'rgev9080', 'rggv4448', 'rgje5273', 'rgmk2209', 'rgnv5698', 'rgqt7865', 'rhbn9463', 'rhec6412', 'rhfa0455', 'rhfu6782', 'rhgn2838', 'rhib5615', 'rhip9687', 'rhot5398', 'rhrd6813', 'rhtt4632', 'rhtw5747', 'rhuf2226', 'rhvb4186', 'rhzc2104', 'riaa1471', 'riec7940', 'rifp6065', 'riku5299', 'rimg6650', 'rinf2434', 'ripg4684', 'rivr3757', 'rizm4233', 'rizp0679', 'rjby7733', 'rjdd1960', 'rjex4102', 'rjhq9306', 'rjjn5422', 'rjjy1897', 'rjmh3316', 'rjnd1086', 'rjob4102', 'rjrw5233', 'rjvh4521', 'rjvs2514', 'rjzb7258', 'rkag1969', 'rkey9638', 'rkis2561', 'rkjq3384', 'rkkx6467', 'rknq0110', 'rknq5477', 'rkzr5041', 'rlak0645', 'rlew3624', 'rlfl2880', 'rlir7977', 'rlld9407', 'rlpc9757', 'rlqu1501', 'rlsx1348', 'rlyi2548', 'rmas9562', 'rmda3008', 'rmfn3520', 'rmib3023', 'rmkc5047', 'rmuw3776', 'rmuz1452', 'rnaf9014', 'rnan8218', 'rnft8119', 'rngo3423', 'rnhh5466', 'rnhz8608', 'rnkh7028', 'rnlp1766', 'rnmn1305', 'rnpq5574', 'rnqd9817', 'rnvq3872', 'rnyj1228', 'rnzi9223', 'rnzp4875', 'roax3273', 'robq0618', 'roen6865', 'rofr5746', 'romc2732', 'roon9305', 'rotd3323', 'rotm9564', 'rpcf0849', 'rpeu9966', 'rpig2414', 'rpkc9694', 'rplz2170', 'rpoj2210', 'rpoz8666', 'rppt8177', 'rpsk7896', 'rpsw2678', 'rpxp1097', 'rqah1626', 'rqcj5970', 'rqcr6619', 'rqdn3088', 'rqep6892', 'rqhp6054', 'rqhy6879', 'rqjs7432', 'rqkx9989', 'rqlx2764', 'rquj4054', 'rquu5658', 'rqxa9402', 'rrae6762', 'rrfa5400', 'rrgy9811', 'rriz8778', 'rrkx0012', 'rrly0194', 'rrqx7433', 'rrsp1975', 'rrtc7005', 'rrvq3651', 'rrvt0451', 'rryq1605', 'rryr6153', 'rrzh2324', 'rsaq3234', 'rsbp3039', 'rsbs0193', 'rsqs8753', 'rssm6208', 'rstf1719', 'rsui7941', 'rsup4093', 'rsvj1337', 'rsvu8696', 'rtee8412', 'rtej9612', 'rtey3720', 'rtjy0222', 'rtnc8194', 'rtns4116', 'rtre0236', 'rtrl0534', 'rtvn1573', 'rtyz9397', 'rtzb0334', 'rtzs4333', 'rtzt8668', 'rucn3942', 'ruea9305', 'ruft8260', 'rukb7428', 'ruoy7139', 'rupm0895', 'ruqj1637', 'ruqz6156', 'ruti7800', 'ruvk5820', 'ruzw6886', 'rvch8364', 'rvcm1264', 'rvff7403', 'rvgk6986', 'rvhw1368', 'rvhw8425', 'rvkh2146', 'rvpp0147', 'rvtx1869', 'rwex8984', 'rwhj7889', 'rwij7452', 'rwme8155', 'rwvj6375', 'rwzv3130', 'rxdc4878', 'rxgf3754', 'rxnk0948', 'rxnp9008', 'rxyl2256', 'ryal8476', 'rybq7000', 'ryfh3702', 'ryip6792', 'ryjd1256', 'rymk8215', 'rysd1098', 'rysd4826', 'rysw2644', 'ryxv5651', 'rzbx9120', 'rzdq6240', 'rzdx9841', 'rzgv3842', 'rzgz1756', 'rzhk0937', 'rzhk2385', 'rzjf6759', 'rzlf3729', 'rzne9027', 'rznu6407', 'rzqj5111', 'rzrl7099', 'rzwk4336', 'rzyt1278', 'sabk3328', 'sacl4964', 'sadh9377', 'sadk9754', 'sads7126', 'saep8218', 'salf4734', 'sant7421', 'sapz6815', 'savo2477', 'sawl5359', 'sbce6481', 'sbev9134', 'sbfi2562', 'sbig3923', 'sbvx8145', 'sbwu2191', 'sbwy3843', 'sbyq4160', 'scbq1714', 'sccm6311', 'scdk6708', 'scfs7924', 'schl4770', 'sckn9352', 'scmh6443', 'scni7051', 'scrs7711', 'scxs9045', 'sdas8537', 'sdbe3531', 'sdcg6432', 'sdct2055', 'sddu2480', 'sdjq6605', 'sdmj0894', 'sdmj4064', 'sdqq1970', 'sdtb6487', 'sdts1188', 'sdwp9043', 'sdyg8488', 'sebf6213', 'seca2504', 'sefc0523', 'sefp7571', 'sehv7257', 'sejg1082', 'sesx5679', 'setn6648', 'sevp7015', 'sezn9319', 'sffh1188', 'sfhy8785', 'sfiy3851', 'sfjg1540', 'sfkw1870', 'sflo1341', 'sfnd3043', 'sfoy4864', 'sfpt3109', 'sfqh6610', 'sfrd0168', 'sfvr1345', 'sfxn6017', 'sfzi3713', 'sgce0363', 'sgdy2333', 'sggb6415', 'sgjd6606', 'sgjd9244', 'sgjv3950', 'sgmc5590', 'sgnh2710', 'sgpv4281', 'sgsq6238', 'sgtu9903', 'sguz2939', 'sgwp3724', 'shaq9550', 'shci9636', 'shed5023', 'sheu6445', 'shev6921', 'shfd2431', 'shfr9149', 'shgb5387', 'shkm2867', 'shmy1407', 'shno1150', 'shsj3694', 'shtc3943', 'shxo4402', 'shxt1144', 'siaj1878', 'sifc8252', 'sifc8758', 'sifn2710', 'sigr4368', 'sigt2586', 'siiz9754', 'sikh9447', 'sioo2663', 'siue3421', 'sivo1965', 'siwz1058', 'siyc5713', 'sjaf2569', 'sjbk0438', 'sjbr9866', 'sjcm3607', 'sjfh5808', 'sjhz8143', 'sjjg1793', 'sjjw5241', 'sjvs3483', 'skck7057', 'skic5054', 'sklv1592', 'skna3360', 'sksi5444', 'skwk4870', 'skwz9232', 'skxw2304', 'slag3205', 'slcb6717', 'sljy7039', 'slkc1486', 'slmm9907', 'slne0088', 'slrp8845', 'sltd2089', 'slvt2536', 'slxb8602', 'slyf0860', 'slzm3905', 'smas0045', 'smeo5944', 'smfs2368', 'smjg1818', 'smon9359', 'smra1821', 'smsm9713', 'smuh9824', 'smzd8069', 'smzs3198', 'sndn0156', 'snhy8812', 'snjp9595', 'snkg6872', 'snou8744', 'snpa3284', 'snpg0503', 'snxk7758', 'soat2836', 'soef5404', 'soji0483', 'sojr1776', 'solh3356', 'soli2781', 'sonv7504', 'sopo7062', 'soqj7153', 'sorz8564', 'sosj7796', 'sosp9061', 'soud1331', 'soug7534', 'sova2986', 'spar4895', 'sper0160', 'spiy1094', 'spjb6672', 'spoz1825', 'spth3095', 'spvk9377', 'sqca0332', 'sqeh2410', 'sqes5990', 'sqfu3026', 'sqgp3147', 'sqhr5444', 'sqir7819', 'sqmt7634', 'sqrd4461', 'sqrk8866', 'sqrz1465', 'squh6824', 'squr9078', 'sqvb5389', 'sqvz2086', 'sqwg7547', 'sqyb7403', 'srbp1670', 'srbq5890', 'srdg6361', 'srea6989', 'srfc9965', 'srgp1899', 'srjq3168', 'srkj4262', 'srkn8912', 'srnt5309', 'srpz0869', 'srqe6565', 'srtp4343', 'srxa7390', 'srzq9764', 'sshh0351', 'ssiv8561', 'sskn6619', 'ssls7275', 'ssrx5986', 'sstl9335', 'ssxh3472', 'staq3693', 'steb4859', 'sted6586', 'sthi2568', 'stkn7169', 'stnk4792', 'stpx1980', 'stpy0238', 'stso3975', 'sttu0488', 'stvy1474', 'stxt6595', 'stxw2306', 'suak6680', 'suho3272', 'suid5391', 'suif6525', 'sukx2970', 'sunw0427', 'suog1431', 'suta7205', 'suwu1742', 'suzc4625', 'svci9376', 'svfz7325', 'svgm3452', 'svhk9733', 'svky5147', 'svod7715', 'svor0167', 'svqh6497', 'svqu4970', 'svqy0869', 'svvq1644', 'svwj3968', 'svwx8538', 'svxu9998', 'svzz6824', 'swdk4620', 'swjm4922', 'swjr9230', 'swkj2595', 'swmv0619', 'swnu4874', 'swpx9364', 'swsx9729', 'swtv9954', 'sxas5933', 'sxer2185', 'sxev5510', 'sxew1151', 'sxfr0700', 'sxhx1070', 'sxkv2613', 'sxkz2251', 'sxnc5859', 'sxpc8838', 'sxra7666', 'sxwa1019', 'sxyo2720', 'sxzd0166', 'syfj4911', 'syic5094', 'sypt5571', 'syqt2258', 'syrz9644', 'syto9729', 'syur7151', 'sywv5701', 'syxd5289', 'szbc3649', 'szgs3303', 'szvf3988', 'szxr4084', 'szyg4334', 'taac1565', 'tagm2994', 'tahe2857', 'tahp8559', 'tans9284', 'tara1172', 'taxq0008', 'tbei3120', 'tbgb9253', 'tbix2459', 'tbjs9524', 'tbke0959', 'tbpr6452', 'tbps3661', 'tbqf1675', 'tbrq5124', 'tbwo5015', 'tcbq3000', 'tcdx7351', 'tcer6671', 'tcif6730', 'tcig8865', 'tcio6371', 'tcqd5202', 'tcrj3650', 'tcrj5890', 'tcro7616', 'tcrv1104', 'tcvi8002', 'tcyx5186', 'tdkl0422', 'tdlw7820', 'tdmb9214', 'tdom4168', 'tdpt4295', 'tebb2205', 'teci5360', 'tecm7430', 'teft1933', 'tegk6545', 'tegl5674', 'tegt9156', 'temb6579', 'teny6360', 'tepx0567', 'terr9685', 'tesg2824', 'tetx0641', 'teve2318', 'teyd5651', 'teyu5212', 'tezh1439', 'tezq4108', 'tffg6626', 'tfgk2849', 'tfhc9353', 'tfjx7212', 'tfko4218', 'tfkv2874', 'tfof5433', 'tfre2863', 'tfsw6960', 'tfww4091', 'tges0511', 'tgkv0477', 'tgly2116', 'tgnw5693', 'tgpw4111', 'tgri7355', 'tgvg2426', 'tgws6867', 'tgzr4384', 'thap1806', 'thbg4055', 'thbt5878', 'thcs3226', 'thdl4254', 'thgu2244', 'thha0164', 'thhh6422', 'thkq3455', 'thnb3735', 'thqe9437', 'thqu9198', 'thse8633', 'thve1621', 'tiaj2171', 'tiec6541', 'tiha6174', 'tihy4018', 'tiix0956', 'tijx1264', 'timk6006', 'tird8860', 'tisy7231', 'tivk9795', 'tiwi9523', 'tjac1485', 'tjai9661', 'tjap3749', 'tjcn8281', 'tjet4210', 'tjgd7280', 'tjhd6522', 'tjir1365', 'tjkj3539', 'tjmi7920', 'tjml3178', 'tjpu7939', 'tjsa4083', 'tjtu9295', 'tjwf8965', 'tjxq1868', 'tjyc7459', 'tjza2559', 'tkaa9424', 'tkcp7779', 'tkhd6371', 'tkla1084', 'tkli3022', 'tklt4197', 'tkoa2932', 'tkpb7604', 'tkus3053', 'tkvn2173', 'tkwq8389', 'tlbx3617', 'tldp6371', 'tlqw8014', 'tlsh7026', 'tlsx4461', 'tlxe7745', 'tlzc6827', 'tmen5517', 'tmjk3598', 'tmju9042', 'tmka4076', 'tmmo4103', 'tmnl9181', 'tmop3118', 'tmtf3104', 'tmtn0758', 'tmup5329', 'tmwm4009', 'tmzf0624', 'tmzx9281', 'tnbh3925', 'tndh9849', 'tngf6412', 'tngw8340', 'tnmq8579', 'tnqf2628', 'tnqi2204', 'tnrf6363', 'tnrq9476', 'tnrt8756', 'tntm4996', 'tnxi5883', 'tnzj4242', 'tocj9818', 'todv1018', 'tolz8874', 'torr0434', 'touo2535', 'tows4296', 'toxb0859', 'tpdg7056', 'tpdo6510', 'tpfu1105', 'tphp1634', 'tpll4393', 'tplw3659', 'tplx4353', 'tpnd9436', 'tpoj7725', 'tpox5486', 'tpsq1426', 'tpws9139', 'tpxd8070', 'tqbl8828', 'tqcm3475', 'tqde8599', 'tqgo0379', 'tqnn6589', 'tqob7613', 'tqsm0060', 'tqwy4008', 'traq0439', 'traz0805', 'trbj8902', 'trcq3771', 'trcz2450', 'trff3062', 'trgt4204', 'trlc3868', 'troi6041', 'trtf4606', 'trtw4475', 'tryy2239', 'tsbi4720', 'tsel7980', 'tspz9473', 'tsrn6398', 'tsrz3944', 'tstq8470', 'tsum3982', 'tsvm8486', 'tsvr0688', 'tsvx3549', 'tsyk6504', 'tsyn8107', 'tszq8410', 'ttdr3928', 'ttfd6918', 'ttfh0930', 'ttfq3353', 'ttha7655', 'ttiv3166', 'ttnh5705', 'ttvn0879', 'ttwk5222', 'ttyl8378', 'tuak5960', 'tuaw1559', 'tuiz5355', 'tuln3328', 'tumc8574', 'tumf5344', 'tuqy2643', 'tuss6623', 'tuud6964', 'tuux5638', 'tuvp3985', 'tuzb4911', 'tvbt8631', 'tvfr9086', 'tvhr5765', 'tvnu1612', 'tvwt9315', 'tvwy8906', 'tvxq1682', 'tvyp8531', 'tvyz1928', 'twdk5059', 'twle0847', 'twmq4536', 'twmr5141', 'twmv9963', 'twos5459', 'twry0219', 'twzq3707', 'twzt6625', 'txgc1768', 'txhl9610', 'txiy0259', 'txmo4551', 'txoq2123', 'txqp5174', 'txuh0114', 'tycg2568', 'tycj6999', 'tycq0074', 'tydf8499', 'tyef2392', 'tyfd3168', 'tykl4261', 'tylq4336', 'tyoc4734', 'tyok3198', 'tyvg8412', 'tywz0860', 'tyyd1226', 'tzbh5170', 'tzbh7660', 'tzce2829', 'tzhk2174', 'tzii4386', 'tzkb6407', 'tzlb3810', 'tzmf8858', 'tzmn2970', 'tzph2271', 'tztq0232', 'tzzk3773', 'uadw3656', 'uafk6491', 'uagg4521', 'uagi3759', 'ualn8859', 'uary4335', 'uarz7792', 'uasn9932', 'uauv1493', 'uaxr4290', 'uaxt9096', 'ubai7792', 'ubdn5133', 'ubdv5803', 'ubhv3564', 'ubmq2334', 'ubnc7030', 'ubqr1674', 'ubul8489', 'ubwa6737', 'ubxl4485', 'ubyc8568', 'ucem8910', 'uchz0262', 'ucjw3753', 'ucnb1427', 'ucos4012', 'ucqi4556', 'ucxh1046', 'ucxm8399', 'udba5720', 'uddd3766', 'udfc1857', 'udgb8656', 'udhf3849', 'udid5461', 'udke6661', 'udnq5922', 'udpr0954', 'udqi4267', 'udra4383', 'udyw9337', 'uebc3514', 'uebo9330', 'uedm8600', 'ueev8105', 'uego1098', 'uejh2085', 'uevs6482', 'uewt2264', 'uewx0113', 'ueyr7979', 'ueyw8876', 'uezl7336', 'ufcm8764', 'ufda8748', 'ufdm2516', 'ufex5615', 'ufhe4020', 'ufmg8514', 'ufmw6654', 'ufno1652', 'ufqv0679', 'ufse5537', 'ufur2695', 'ufuu0837', 'ugai7193', 'ugby5408', 'ugec2362', 'uged4101', 'ugeu4744', 'ugie2531', 'ugig1253', 'ugje0407', 'ugke1527', 'ugkv6573', 'ugnl2467', 'ugsn4552', 'ugtk2435', 'uhbe6543', 'uhbt5261', 'uhbx0549', 'uhct0829', 'uhdn7745', 'uhgn1092', 'uhhq8906', 'uhhw1913', 'uhjj9587', 'uhnc2103', 'uhnq8472', 'uhor2776', 'uhtk5291', 'uhtz8573', 'uhxd5517', 'uhzv1540', 'uhzz6319', 'uicp6269', 'uidw5460', 'uifh9428', 'uifv6879', 'uiim5956', 'uiin7801', 'uijb3989', 'uilu4979', 'uipp5717', 'uipp7938', 'uixl1362', 'ujbk1978', 'ujea7089', 'ujij4807', 'ujjo1962', 'ujrs9526', 'ujsz1947', 'ujzk7795', 'ukdz3462', 'ukel1952', 'ukfo6309', 'ukfq6138', 'ukhr7162', 'ukjs7763', 'ukot2774', 'ukpx8947', 'ukqf9402', 'ukvh1228', 'ukzc2532', 'ukzl3145', 'ulcj5287', 'ulcq5231', 'ulej2538', 'uler8180', 'ulkj9171', 'ulkx6634', 'ulok7762', 'ulqy7466', 'ulwg5535', 'umaa8720', 'umag0514', 'umbd5851', 'umdd5522', 'umhp7423', 'umkw5575', 'umnn4025', 'umoj4984', 'umqo6752', 'umsd8840', 'umtj9188', 'unee3404', 'unel6949', 'ungs1816', 'uniq2176', 'unjh9660', 'unke2915', 'unov5948', 'unrv4563', 'unxf6692', 'unxy6232', 'unyg6981', 'uobn5861', 'uocc6700', 'uocv0230', 'uodo1558', 'uoel6228', 'uogo6599', 'uoji7678', 'uolc7924', 'uonz1964', 'uoum2505', 'uoxr0341', 'upgf6376', 'uphu9794', 'upih0461', 'upkm1147', 'upne7778', 'upnh9242', 'upof6445', 'upoi3367', 'upuq8291', 'upwk1625', 'upxg9365', 'uqfs0024', 'uqgt8691', 'uqjh6120', 'uquo2235', 'uqyf2480', 'urbj2893', 'urbp6239', 'ured8434', 'urmo2387', 'urnv9034', 'ursw0532', 'urua6368', 'urwk5255', 'urwm0372', 'urww3588', 'uryo2004', 'usbj9812', 'useo2939', 'usft3862', 'usmj2867', 'ussw0459', 'ussw2170', 'ustj5073', 'usvd0895', 'usxn3395', 'utaq0461', 'utbv3775', 'uthr2741', 'utjb7137', 'utko3599', 'utly6521', 'utmj4368', 'utrw8585', 'uttv5875', 'utud2456', 'utvm4737', 'utwg7687', 'uubl1312', 'uuep8634', 'uugh2820', 'uuik2955', 'uull2452', 'uupf7407', 'uuro0244', 'uutu5184', 'uvbp4401', 'uvcj7594', 'uveg3045', 'uvgn0547', 'uvie5676', 'uvjs3006', 'uvjs9173', 'uvnp6496', 'uvqm3206', 'uvqo5181', 'uvri0915', 'uvrl0669', 'uvrt1726', 'uvwk7717', 'uvwo6123', 'uwcc7902', 'uwib6052', 'uwjz6097', 'uwkf2537', 'uwoo0945', 'uwra3307', 'uwww5068', 'uwxz0582', 'uwyt5237', 'uxab7178', 'uxcu7778', 'uxji8558', 'uxlr5710', 'uxqz6506', 'uxve2074', 'uxvv5862', 'uxys1438', 'uybi5635', 'uycl3853', 'uygc3653', 'uyhz1403', 'uymk9720', 'uyna5986', 'uyor9296', 'uyrs2572', 'uyyg2099', 'uyyt1431', 'uzbf3059', 'uzbp4872', 'uzbt5299', 'uzbu4726', 'uzch4913', 'uzck3587', 'uzfb7424', 'uzhx7255', 'uzkj4252', 'uzmh4531', 'uzmv8481', 'uzpf2652', 'uzro1720', 'uzud3195', 'uzwg9314', 'uzwx8225', 'vafx1837', 'vagm1000', 'vaiw2038', 'vaiy5696', 'vajy9320', 'vakg0473', 'valc5518', 'valu3586', 'vams4008', 'vaod4714', 'vawd3185', 'vaxp3314', 'vayc1727', 'vbgh6063', 'vbgp1371', 'vbjs6917', 'vblt7474', 'vbnt0728', 'vbok0485', 'vbqc2395', 'vbsy0746', 'vbwv5463', 'vbxy1481', 'vbzn9661', 'vbzw6342', 'vbzz7677', 'vchk3477', 'vcin2154', 'vciy8815', 'vcje9305', 'vckd3495', 'vcxz8967', 'vcyv5023', 'vdgg1743', 'vdhk7350', 'vdiy8903', 'vdlm1446', 'vdlw8646', 'vdmc6711', 'vdop7186', 'vdrj7651', 'vdup6950', 'vdwc5052', 'vdwp2414', 'vdyb1303', 'vdyg2709', 'veac5690', 'vekq3300', 'vele3631', 'veon0377', 'vepm5561', 'veta1901', 'veus3087', 'veyl6274', 'vfic8574', 'vfjf0160', 'vflj8770', 'vfmr7032', 'vfnl8593', 'vfof6002', 'vfto8822', 'vfty4840', 'vfws1821', 'vgcv5955', 'vgeg3141', 'vghu9820', 'vgki9038', 'vgna8052', 'vgpu6715', 'vgyn3589', 'vgzj7551', 'vhdj4614', 'vhej3653', 'vhgz3382', 'vhkw4943', 'vhmd5642', 'vhnx5897', 'vhop9569', 'vhpu0723', 'vhpu4506', 'vhsw0193', 'vhtd9717', 'vhth2709', 'viac5103', 'vici8740', 'viil8264', 'vili0929', 'vion7034', 'viqz8102', 'vixt5145', 'viyk2068', 'vizc7165', 'vjfn6151', 'vjhd5101', 'vjhl2406', 'vjid2859', 'vjkm8909', 'vjpi8375', 'vjpr6085', 'vjpw8338', 'vjsu0450', 'vjtd5399', 'vjts1426', 'vjxc1900', 'vkal5242', 'vkbi8019', 'vkdx9082', 'vkit8409', 'vkkl3681', 'vklk8338', 'vkly0124', 'vkmv9575', 'vknl0987', 'vkoa5930', 'vkpb7025', 'vkre5337', 'vkuo2550', 'vkup8377', 'vkyp8042', 'vleo4333', 'vleo7008', 'vljl9944', 'vljp0202', 'vlks8533', 'vlkx6986', 'vlly1327', 'vlnw8224', 'vlrv4056', 'vlsw6556', 'vluk4826', 'vlvs2842', 'vlwd4528', 'vmcb4770', 'vmcc4123', 'vmjc4858', 'vmlo9104', 'vmnd2268', 'vmng6399', 'vmnk2904', 'vmog6282', 'vmpa7709', 'vmqi3337', 'vmrg7604', 'vmsl1239', 'vmtc6979', 'vmtd9741', 'vmxx8421', 'vmzl3710', 'vnfl6605', 'vngt2193', 'vngx5946', 'vnho3283', 'vniu0448', 'vnlr5593', 'vnss9713', 'vnyl5180', 'vnzf8799', 'vobo4601', 'vocv4254', 'voda9436', 'vodi9916', 'vohi8014', 'vokr4884', 'vone7342', 'vooj8413', 'voqi3850', 'votc0985', 'vowg0672', 'vpap9028', 'vpat2490', 'vpax0615', 'vpdt9691', 'vper4005', 'vpgl7029', 'vpho6082', 'vpmk2473', 'vpox0431', 'vppq5043', 'vpqw8325', 'vptn9653', 'vpvl0305', 'vpzd3911', 'vpzo4962', 'vqbn7186', 'vqbx5912', 'vqgm7583', 'vqjc9395', 'vqjh5592', 'vqof7029', 'vqqv8870', 'vqsa5045', 'vqtc5472', 'vqti3826', 'vqvc9529', 'vqvf9684', 'vrkl5315', 'vrlr4587', 'vrls3976', 'vrmm1930', 'vrmq2408', 'vrmw8876', 'vrpy8430', 'vrzi3817', 'vsbj9804', 'vsbx1134', 'vsfn5203', 'vsgy9787', 'vshv4613', 'vsio4751', 'vsnj7923', 'vspb4899', 'vspw5357', 'vsrg3225', 'vsrs8732', 'vsvo3966', 'vtch6402', 'vtct4318', 'vtdy8063', 'vtfs6001', 'vtir4832', 'vtjo6804', 'vtuc1548', 'vtwj8381', 'vucx2563', 'vugg0977', 'vugm7524', 'vugz1279', 'vuhl5145', 'vukn0761', 'vulj4569', 'vulk7259', 'vulm7336', 'vusd5366', 'vuvl4222', 'vuwa6313', 'vuwf6386', 'vvab3462', 'vvao0528', 'vvgj4281', 'vvlz7109', 'vvpz3607', 'vvvu4738', 'vvxc5453', 'vvzf9541', 'vwau7225', 'vwfm6847', 'vwfu9126', 'vwvg0109', 'vwwj9859', 'vxdm6039', 'vxdy5051', 'vxhz8723', 'vxis9166', 'vxjj2723', 'vxko4641', 'vxmc2725', 'vxqx0990', 'vxrn9334', 'vxrr7068', 'vxrw8903', 'vxvn1192', 'vxyf9902', 'vxzr0860', 'vyek4166', 'vyhf8166', 'vyim3902', 'vylc4360', 'vylo8568', 'vylx4035', 'vymd1074', 'vyrf4122', 'vyuf8130', 'vywq0643', 'vyxk9125', 'vzac9016', 'vzen1793', 'vzfx1826', 'vzhq2537', 'vzip9573', 'vzjc5211', 'vzmi1048', 'vzon5461', 'vzov8705', 'vzpq1839', 'vzvy0054', 'wado7700', 'waeo3827', 'wagd4920', 'waot5047', 'wark9801', 'wasi4525', 'wawl2364', 'wbbt0015', 'wbes8537', 'wbev5235', 'wbgr9461', 'wbkb0991', 'wbnb9119', 'wbnw0781', 'wcak3371', 'wcau9985', 'wcdn4268', 'wcea8006', 'wcgm8776', 'wckm0101', 'wcml0347', 'wcnr3828', 'wcnu4218', 'wcpc7088', 'wctd0091', 'wcun3663', 'wcwe2797', 'wczt8911', 'wdcb7474', 'wdcn4084', 'wded7275', 'wdks2480', 'wdlq5436', 'wdls1896', 'wdnh7104', 'wdwr3830', 'weaw6420', 'weay3119', 'wefk1055', 'weke1933', 'wemf9801', 'wetg2362', 'weto2901', 'wevn8521', 'wexy6172', 'wfde6564', 'wfdx1824', 'wfii6391', 'wfis4682', 'wfiv3709', 'wfom6161', 'wfsv4753', 'wfub1738', 'wfur5172', 'wfxq9926', 'wgai8582', 'wgfd3541', 'wgfl2550', 'wghp8229', 'wghw9830', 'wgpi7849', 'wgrn7803', 'whaj6284', 'whha0444', 'whhm6232', 'whjg4587', 'whkl8021', 'whou3959', 'whrt3653', 'whtj9759', 'whxf4349', 'wian3261', 'wiar1929', 'wicf5235', 'wimq2316', 'wims8374', 'wimz6798', 'wiqu2476', 'wirb4224', 'wirz8765', 'witl3113', 'wiwj6244', 'wjaz6782', 'wjbi1597', 'wjdy0201', 'wjfu6226', 'wjhv4240', 'wjis3283', 'wjll2590', 'wjmk5655', 'wjoo3090', 'wjtk8646', 'wjux9292', 'wjxj8031', 'wjxx9315', 'wkau7254', 'wkqa3849', 'wkqa6441', 'wkrf2169', 'wkwi3761', 'wkxh0607', 'wkya8294', 'wlcx7110', 'wlda8610', 'wldv8192', 'wlic2269', 'wlnm5825', 'wltk8017', 'wlvv1195', 'wlwm3505', 'wmbx0534', 'wmda4411', 'wmfu1055', 'wmju4637', 'wmkl0675', 'wmmm9985', 'wmqo9633', 'wmsd3167', 'wmtf9401', 'wmxe4936', 'wmyl9107', 'wnba6328', 'wncd0438', 'wndg6904', 'wndz6750', 'wnfs4191', 'wnfw6197', 'wnlt9069', 'wnme7747', 'wnou5435', 'wnwi9539', 'wnwq6559', 'wnxn6833', 'wnyd5589', 'wocy9008', 'woen3825', 'woft3801', 'wofz3708', 'wogf3291', 'woim8684', 'womd0690', 'wopo3613', 'wopw0725', 'wowy1715', 'wozr6015', 'wpaj2552', 'wpao5582', 'wpcn9853', 'wpeq2103', 'wper2057', 'wpgl8346', 'wpjv2042', 'wplk9249', 'wpnr4774', 'wppd8049', 'wpsl6707', 'wpst3363', 'wptt9909', 'wpwn8497', 'wpws1954', 'wpwx7040', 'wpxu1901', 'wpzy9900', 'wqes4154', 'wqfw2542', 'wqkh0583', 'wqmy9065', 'wqoc5474', 'wquu3591', 'wqve6998', 'wrda4130', 'wrjm5561', 'wrkz4662', 'wrny4421', 'wrpi6077', 'wrsu1096', 'wrwg0319', 'wrxi6471', 'wryc2819', 'wrzq0838', 'wsjh9785', 'wsjr5905', 'wskf9463', 'wslt3068', 'wsow1006', 'wsqs9644', 'wsrb6614', 'wsrn1792', 'wssn3812', 'wstl6155', 'wsxm6765', 'wsyg3324', 'wtas6966', 'wtav3989', 'wtay9877', 'wtco1607', 'wtgs4328', 'wtit3176', 'wtkf8709', 'wtlp7264', 'wtpg3989', 'wuef6375', 'wufy7036', 'wuga4265', 'wuht0890', 'wuim8823', 'wumm1282', 'wumn9145', 'wutz1207', 'wuuc5748', 'wuzu4244', 'wveh6813', 'wvet3721', 'wvfj9745', 'wvpm9510', 'wvqe2528', 'wvub8582', 'wvuq2904', 'wvvc3277', 'wvye7836', 'wwba6707', 'wwbf8739', 'wwbw3823', 'wwdw0250', 'wwex1822', 'wwgn0944', 'wwhj5939', 'wwkx9489', 'wwme6719', 'wwmi6252', 'wwnh3324', 'wwte8747', 'wwzv0924', 'wxaw2112', 'wxbv6888', 'wxjk8094', 'wxof0749', 'wxuy9680', 'wxvs0408', 'wxzx1282', 'wyac8598', 'wyal5065', 'wycu0830', 'wygb6466', 'wygq8577', 'wyhi3155', 'wykh7236', 'wykz6450', 'wynp8547', 'wyoa1434', 'wyth0270', 'wyvb7305', 'wyvg8470', 'wyzn4316', 'wzbu7084', 'wzfv3667', 'wzhc4352', 'wzio4115', 'wzir6344', 'wzkl4570', 'wzps0878', 'wzri8747', 'wzyi4196', 'xakp6908', 'xanm6873', 'xans8930', 'xaog4753', 'xaom0209', 'xaqs4210', 'xbab5689', 'xbbd4771', 'xbbg5675', 'xbgs6846', 'xbgt6426', 'xbie2704', 'xbkk6593', 'xbop9471', 'xbrj8904', 'xbsz1221', 'xcmx5417', 'xcmy7005', 'xcoe5160', 'xcot6139', 'xcte8133', 'xcwj9136', 'xcwp7203', 'xdad1056', 'xdav2461', 'xdbd0503', 'xdcx0924', 'xddm1043', 'xdhv4840', 'xdue1468', 'xdvs5301', 'xdzc1998', 'xeae1790', 'xedm7602', 'xedn0480', 'xeep6830', 'xejt5417', 'xemd3176', 'xeyx2845', 'xfcr6281', 'xfcy5394', 'xfdl8147', 'xfiw2537', 'xfjy3572', 'xfoy9018', 'xfqz2127', 'xfsj2596', 'xfuu5805', 'xfxv1774', 'xgdr8149', 'xget7659', 'xgkb9582', 'xgmx1279', 'xgpb6884', 'xgpz2379', 'xgqj9573', 'xgrg0444', 'xgsr4838', 'xgue5543', 'xgys0227', 'xgzs7946', 'xhai7026', 'xhal4088', 'xhds9267', 'xhfu4794', 'xhgy1805', 'xhgy7154', 'xhoz1843', 'xhrd9001', 'xhws8720', 'xhww2123', 'xice4861', 'xikk9692', 'ximm8122', 'xiox5186', 'xiqm1855', 'xiqq7756', 'xirf2928', 'xivy9405', 'xiwo1364', 'xizg3044', 'xizi8888', 'xizt3459', 'xjgh8748', 'xjhu2963', 'xjin8385', 'xjkj6610', 'xjmb6405', 'xjsv8087', 'xjtn2940', 'xjuh7012', 'xjun4559', 'xjvh9070', 'xkav6448', 'xkdm7659', 'xkdt7454', 'xkic8517', 'xkqi8374', 'xkuo6017', 'xkuq0880', 'xkuu6062', 'xkxq4443', 'xlem4437', 'xlkv1906', 'xlnz2131', 'xlqw1712', 'xlsb5009', 'xltb3747', 'xltb7177', 'xltn4997', 'xlwp5121', 'xlyr8021', 'xlzz0076', 'xmbf6448', 'xmcm3528', 'xmdn8501', 'xmdx0322', 'xmec7654', 'xmfp4294', 'xmjy4156', 'xmni6200', 'xmoj9339', 'xmtq6530', 'xmwe2777', 'xnag1520', 'xnga5687', 'xngm7661', 'xnpi8824', 'xnqr9000', 'xnrb6839', 'xntp0483', 'xntv8716', 'xnuf3328', 'xnxc9692', 'xnzr4051', 'xoaw9800', 'xodk5696', 'xoeb1729', 'xogz2932', 'xopj0353', 'xoyu9433', 'xpal0100', 'xpch1138', 'xpdw6190', 'xpfo1637', 'xpjc9928', 'xpkp0920', 'xppz5814', 'xpro3290', 'xpru0657', 'xpru0751', 'xpte1926', 'xpuf2691', 'xpvn1378', 'xpvv4101', 'xqcs9033', 'xqdr2611', 'xqeh3824', 'xqhr3286', 'xqia3022', 'xqnl0771', 'xqnr6088', 'xqru8517', 'xqyv1907', 'xrds3032', 'xrds9805', 'xrgw1159', 'xrlh0397', 'xrox3442', 'xrtf2942', 'xrub8742', 'xrvy0437', 'xrwp0927', 'xsff0287', 'xsgi3456', 'xsgp5181', 'xshi4785', 'xsjt3027', 'xskb9419', 'xsqt5966', 'xssi2691', 'xsvz6720', 'xtkp7439', 'xtmp6696', 'xtqa2531', 'xtqu1510', 'xtsz8957', 'xubc0772', 'xucq6015', 'xueg0578', 'xuir2608', 'xujw7545', 'xulk2697', 'xumf1061', 'xunr3339', 'xupb5030', 'xusg3264', 'xuwq7400', 'xuxh6424', 'xvdm4306', 'xver5439', 'xvio4032', 'xvle2095', 'xvoq4530', 'xvpu8349', 'xvqz2274', 'xvxc0789', 'xvxl2746', 'xwbd6989', 'xwel0494', 'xwfa2453', 'xwmu4247', 'xwod1371', 'xwpd2345', 'xwrr2595', 'xwwj1296', 'xxaf8727', 'xxct8931', 'xxde9351', 'xxfy9688', 'xxiv0104', 'xxjc2053', 'xxkq3153', 'xxmz5172', 'xxok1602', 'xxow1374', 'xxta0659', 'xxzm8137', 'xybm1809', 'xyfp9316', 'xygr8291', 'xygu5810', 'xygy8662', 'xyii1961', 'xykg9235', 'xymy6436', 'xypm4040', 'xyqj1972', 'xyrw9674', 'xywh4925', 'xzay9346', 'xzel4688', 'xzky0459', 'xzle9123', 'xzqk9603', 'xzrm0045', 'xzuk3196', 'xzvd7812', 'xzxt2364', 'yadk9447', 'yagf4005', 'yanh9105', 'yaod9398', 'yatm6254', 'yawr6736', 'ybes9150', 'ybhl4530', 'ybit7195', 'ybks2756', 'ybmp7571', 'ybne6751', 'ybnh5649', 'ybnv6676', 'ybsb4028', 'ybup5207', 'ybvv5944', 'ybwc7556', 'ybyj9584', 'ycdz2459', 'ycff5408', 'ycfp7722', 'ycgk7051', 'ycgt9836', 'ycik4105', 'ycit2036', 'ycms6342', 'ycpe2015', 'ycpm2228', 'ycqg8699', 'yctr4573', 'yctx7418', 'ycvh0590', 'ydag4169', 'ydav3348', 'ydaz1196', 'ydcy1063', 'ydeu6709', 'ydgt4727', 'ydpp2272', 'ydqg4760', 'ydqh6364', 'ydqw8183', 'ydsy3200', 'yduv2983', 'ydvt6905', 'ydxk0188', 'ydyq4242', 'yefs2624', 'yegn1534', 'yemo3857', 'yeqg6389', 'yeqh0309', 'yeti6635', 'yeul8076', 'yewb5957', 'yfir9735', 'yfky8972', 'yfmk0171', 'yfqq8206', 'yfsi2251', 'yfsz7691', 'yfvd1397', 'yfwu4640', 'yfyo0600', 'ygce4657', 'ygcg2101', 'ygfa5788', 'ygfc6025', 'ygfm8039', 'yglx3753', 'ygnq0847', 'ygqp8285', 'ygqt1978', 'ygqw0094', 'ygxh8547', 'yhco9018', 'yhdp0881', 'yhel8384', 'yhes9504', 'yhfr5861', 'yhgs6852', 'yhic5714', 'yhig8524', 'yhlr4475', 'yhpy4509', 'yhpy7140', 'yhsa5009', 'yhtj7722', 'yhut4089', 'yhwj3875', 'yhyd2647', 'yhyk3287', 'yibi9002', 'yidm1827', 'yifz3212', 'yigj7388', 'yigk1447', 'yijq7499', 'yiny7320', 'yivi5117', 'yizu6669', 'yjce3178', 'yjnx9989', 'yjxg3206', 'ykfg3219', 'ykgc3243', 'ykjt7673', 'yknm6970', 'yksx1029', 'yktm6931', 'ykux9291', 'ykwv3927', 'ykxq9774', 'ykxs3787', 'ylcq4678', 'ylfe1350', 'ylip0807', 'ylji5648', 'ylnd0093', 'ylvg5581', 'ymck8822', 'ymjr3650', 'ymow1108', 'ympf6213', 'ymsz9282', 'ymuo6133', 'ymuz5840', 'ymvt8026', 'ymvy0887', 'ymwf8964', 'ynfm2587', 'ynfz0957', 'yngs8204', 'ynky6224', 'ynmq7723', 'ynot9398', 'ynqy0963', 'ynry9591', 'ynuz8277', 'yocv2814', 'yoks5007', 'yooo1271', 'yopg6293', 'yorj1134', 'yosu4983', 'youc7286', 'yovx4845', 'ypdv1132', 'ypfh1634', 'ypgd7801', 'ypgg7424', 'yptk1552', 'ypui4099', 'ypwj5990', 'ypwy4479', 'ypyi9434', 'ypzr2192', 'ypzu2840', 'yqci1177', 'yqjh0429', 'yqji9099', 'yqkp1851', 'yqkr8387', 'yqll3789', 'yqly7675', 'yqqx4586', 'yqtf8731', 'yqwq1460', 'yqyd6105', 'yrai5287', 'yrbp7105', 'yrfz3042', 'yrur7308', 'yrya8924', 'yscf0850', 'ysft0931', 'ysjz9488', 'ysmf0918', 'ysmk3463', 'ysqp4997', 'ytbu0251', 'yteb3399', 'ytfi1236', 'ytgl7307', 'ytmi4112', 'ytqh3810', 'ytsd1193', 'ytud1329', 'ytwe8510', 'ytws7862', 'yuab7604', 'yuez3956', 'yugq5402', 'yuhy0395', 'yulf2748', 'yumd7884', 'yver5773', 'yvgi7560', 'yvnn4429', 'yvps1296', 'yvsh6940', 'yvsi8555', 'yvsw6735', 'ywgi0013', 'ywhb2236', 'ywhg3206', 'ywhw4903', 'ywjp1632', 'ywlp2636', 'ywmw4563', 'ywno8555', 'ywoh1778', 'ywqj9231', 'ywtz0929', 'ywvo4796', 'ywvu5599', 'ywwa7814', 'ywyt8863', 'ywze9735', 'ywzv6208', 'yxbe6514', 'yxgk3976', 'yxkj7169', 'yxpe5021', 'yxzo0728', 'yybl9755', 'yycv1033', 'yydn8824', 'yykj1835', 'yyld1471', 'yylq2719', 'yynr0143', 'yynz4884', 'yyom9283', 'yytn5237', 'yytp2125', 'yzdl8633', 'yzex2150', 'yzfn0458', 'yzhk4285', 'yzjq9693', 'yzke4284', 'yzkm0669', 'yzmd2672', 'yzmx9173', 'yzqb9977', 'yzsl6418', 'yzxz8227', 'yzyw2899', 'yzza1985', 'yzzn4264', 'zaav3545', 'zaee2730', 'zagq1848', 'zagt8577', 'zahh3391', 'zaiw7762', 'zaka0636', 'zako8163', 'zaml6388', 'zanq9636', 'zaxg2906', 'zayy7935', 'zbbb0437', 'zbct1031', 'zbjs9276', 'zboi4880', 'zbpo4708', 'zbqq3557', 'zbto9761', 'zbux4510', 'zcah6342', 'zcbd0933', 'zcfo8962', 'zcii0448', 'zclc1990', 'zclq1752', 'zcos4558', 'zcpw9410', 'zcub0517', 'zcwn8791', 'zcxl0469', 'zdcu1270', 'zdeb6327', 'zdlm4187', 'zduw8005', 'zdxc5048', 'zdzl4140', 'zeaj5114', 'zegi4539', 'zehs7226', 'zeid1501', 'zely3110', 'zeoe7421', 'zeqs0661', 'zfbt8682', 'zfcx9331', 'zfdq7473', 'zfip7517', 'zfkz1204', 'zfpu9242', 'zfrm7271', 'zftl8318', 'zfup7587', 'zfwj7685', 'zgbh4305', 'zgbv9588', 'zgev4681', 'zgge6705', 'zgrj2203', 'zgtt2980', 'zgvf9721', 'zgwi2447', 'zgxd8689', 'zgxf7182', 'zgym9889', 'zgys1749', 'zgze8193', 'zhel4443', 'zhgd0598', 'zhge1028', 'zhkb3023', 'zhom7915', 'zhor1781', 'zhpm9811', 'zhrn5854', 'zhsx8402', 'zhsy4140', 'zhxs3240', 'zhzn2318', 'ziag6735', 'zibc3924', 'zikb5758', 'zing1957', 'zinm3648', 'zinr0592', 'zipq9499', 'ziqs1848', 'zium5264', 'zium8344', 'zjak1163', 'zjbc4853', 'zjbl4588', 'zjca6008', 'zjda1902', 'zjeq2737', 'zjjj5504', 'zjmf4826', 'zjog0639', 'zjrb4481', 'zjtd6895', 'zjtn6539', 'zjwu4915', 'zjxw0266', 'zkag8228', 'zkhb8148', 'zkmi3152', 'zlcn6031', 'zlfx7839', 'zlht8621', 'zliu6706', 'zljh8057', 'zllq9078', 'zlnc6412', 'zlno4672', 'zlok9742', 'zlyb8036', 'zmao4818', 'zmbx6413', 'zmce0650', 'zmpy2023', 'zmql5644', 'zmrg9002', 'zmrt3724', 'zmtf0017', 'zmtt5176', 'zmye6884', 'zmzj6034', 'znad5597', 'znas4063', 'zncb0890', 'znff5996', 'zngg7239', 'znjl7127', 'znjx9286', 'znkc8118', 'znlf0135', 'znnx9828', 'znra6426', 'znri9432', 'znrr9554', 'znxa7818', 'znzk7824', 'znzo7327', 'zoam3496', 'zoaq0570', 'zoav6839', 'zoct4765', 'zogp4019', 'zopl2631', 'zorc9240', 'zork3376', 'zpam7370', 'zpda0324', 'zpfz6939', 'zpgh7163', 'zpha8257', 'zpjt4444', 'zpkz4790', 'zpra2720', 'zprk0588', 'zptw4492', 'zptw7109', 'zpuf4365', 'zpwg8048', 'zqbw0582', 'zqdg1277', 'zqdn0689', 'zqet7023', 'zqge6489', 'zqlq4271', 'zqum3059', 'zqvc7931', 'zqws4069', 'zqzk8714', 'zrcq0312', 'zrcr0121', 'zrhx3524', 'zrkm5522', 'zrlu8447', 'zrse8319', 'zrxe5546', 'zrzb5265', 'zrzq2431', 'zsdc9807', 'zsdz5020', 'zshn8387', 'zsjz1266', 'zsno6262', 'zsps2676', 'zsxs6048', 'ztec9345', 'ztmp5297', 'ztmv9162', 'ztqv8855', 'ztrq5218', 'zttn3064', 'zuav2440', 'zubi1744', 'zudq5940', 'zuix1852', 'zuiy6814', 'zulr7621', 'zunt0182', 'zuom5503', 'zuri1237', 'zuvi8323', 'zuwe4693', 'zuxv6361', 'zuxz4608', 'zuyc3563', 'zvbd1073', 'zvbu1954', 'zvcb5225', 'zvea7882', 'zvek2712', 'zvil1194', 'zvjk3817', 'zvrf6998', 'zvub8932', 'zvzg5989', 'zvzz0079', 'zwbz6699', 'zwdj5745', 'zwkm1265', 'zwoy3479', 'zwpm4309', 'zwqy7847', 'zwun7618', 'zwzu4416', 'zxat9960', 'zxba5637', 'zxcl3355', 'zxeb3067', 'zxhk0345', 'zxho6622', 'zxid9839', 'zxjt4400', 'zxmb8192', 'zxmx2109', 'zxng6468', 'zxov0951', 'zxrd8315', 'zxtb5697', 'zxuq6682', 'zybc0245', 'zyfz6005', 'zymd1629', 'zymf3506', 'zymh2353', 'zypb1939', 'zyqf2984', 'zyqs7351', 'zyrl8905', 'zyti6111', 'zyuf9013', 'zyun8588', 'zyuz4395', 'zywd1855', 'zyzt6276', 'zzcc5358', 'zzdt1581', 'zzdt1708', 'zzhd4675', 'zzie1203', 'zzih2520', 'zzlf7854', 'zzmr9316', 'zznx1511', 'zzpu4420', 'zztp1426']\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(liste_features)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Performance du modèle d'imputation linéaire - MAE: 1.33, R²: 0.97\n",
+ "Pourcentage de valeurs manquantes après imputation: 0.00%\n",
+ "Variable 'disease_duration' ajoutée avec succès.\n",
+ "Performance du modèle d'imputation linéaire - MAE: 6.04\n",
+ "Imputation des valeurs manquantes de 'on'...\n",
+ "Les valeurs de 'on' ont été imputées avec succès.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "( cohort sexM age_at_diagnosis age ledd time_since_intake_on \\\n",
+ " 0 1 0 48.5 52.1 607.0 1.9 \n",
+ " 1 1 0 48.5 53.0 666.0 1.9 \n",
+ " 2 1 0 48.5 53.9 717.0 1.2 \n",
+ " 3 1 0 48.5 54.8 770.0 1.5 \n",
+ " 4 1 0 48.5 56.9 885.0 0.3 \n",
+ " ... ... ... ... ... ... ... \n",
+ " 55598 1 1 59.0 60.6 NaN NaN \n",
+ " 55599 1 1 59.0 61.1 NaN NaN \n",
+ " 55600 1 1 59.0 61.8 NaN NaN \n",
+ " 55601 1 1 59.0 62.6 NaN NaN \n",
+ " 55602 1 1 59.0 63.5 NaN NaN \n",
+ " \n",
+ " time_since_intake_off on off est_LRRK2+ ... zznx1511 \\\n",
+ " 0 NaN 7.000000 NaN 1.0 ... 0 \n",
+ " 1 17.6 12.000000 44.0 1.0 ... 0 \n",
+ " 2 NaN 6.000000 NaN 1.0 ... 0 \n",
+ " 3 NaN 11.000000 NaN 1.0 ... 0 \n",
+ " 4 NaN 24.000000 NaN 1.0 ... 0 \n",
+ " ... ... ... ... ... ... ... \n",
+ " 55598 NaN 14.916040 1.0 1.0 ... 0 \n",
+ " 55599 NaN 15.455858 4.0 1.0 ... 0 \n",
+ " 55600 NaN 16.211603 0.0 1.0 ... 0 \n",
+ " 55601 NaN 17.075312 2.0 1.0 ... 0 \n",
+ " 55602 NaN 18.046985 7.0 1.0 ... 0 \n",
+ " \n",
+ " zzpu4420 zztp1426 num_visite nb_visites diff_on diff_on_first \\\n",
+ " 0 0 0 1 12 NaN 7.000000 \n",
+ " 1 0 0 2 12 5.000000 7.000000 \n",
+ " 2 0 0 3 12 -6.000000 7.000000 \n",
+ " 3 0 0 4 12 5.000000 7.000000 \n",
+ " 4 0 0 5 12 13.000000 7.000000 \n",
+ " ... ... ... ... ... ... ... \n",
+ " 55598 0 0 2 6 0.971673 13.944367 \n",
+ " 55599 0 0 3 6 0.539818 13.944367 \n",
+ " 55600 0 0 4 6 0.755745 13.944367 \n",
+ " 55601 0 0 5 6 0.863709 13.944367 \n",
+ " 55602 0 0 6 6 0.971673 13.944367 \n",
+ " \n",
+ " mean_on std_on time_since_last_visit \n",
+ " 0 15.000000 8.034019 NaN \n",
+ " 1 15.000000 8.034019 0.9 \n",
+ " 2 15.000000 8.034019 0.9 \n",
+ " 3 15.000000 8.034019 0.9 \n",
+ " 4 15.000000 8.034019 2.1 \n",
+ " ... ... ... ... \n",
+ " 55598 15.941694 1.487784 0.9 \n",
+ " 55599 15.941694 1.487784 0.5 \n",
+ " 55600 15.941694 1.487784 0.7 \n",
+ " 55601 15.941694 1.487784 0.8 \n",
+ " 55602 15.941694 1.487784 0.9 \n",
+ " \n",
+ " [55603 rows x 6991 columns],\n",
+ " Index target\n",
+ " 0 0 34.7\n",
+ " 1 1 38.1\n",
+ " 2 2 41.6\n",
+ " 3 3 44.9\n",
+ " 4 4 52.0\n",
+ " ... ... ...\n",
+ " 55598 55598 2.9\n",
+ " 55599 55599 3.4\n",
+ " 55600 55600 4.3\n",
+ " 55601 55601 5.3\n",
+ " 55602 55602 6.8\n",
+ " \n",
+ " [55603 rows x 2 columns])"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X=pd.read_csv('data/X_train_6ZIKlTY.csv')\n",
+ "y=pd.read_csv('data/y_train_lXj6X5y.csv')\n",
+ "p=PreprocessData(X,y)\n",
+ "p.process_transformation()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_process = p.get_X()\n",
+ "y_process = p.get_y()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>cohort</th>\n",
+ " <th>sexM</th>\n",
+ " <th>age_at_diagnosis</th>\n",
+ " <th>age</th>\n",
+ " <th>ledd</th>\n",
+ " <th>time_since_intake_on</th>\n",
+ " <th>time_since_intake_off</th>\n",
+ " <th>on</th>\n",
+ " <th>off</th>\n",
+ " <th>est_LRRK2+</th>\n",
+ " <th>...</th>\n",
+ " <th>zznx1511</th>\n",
+ " <th>zzpu4420</th>\n",
+ " <th>zztp1426</th>\n",
+ " <th>num_visite</th>\n",
+ " <th>nb_visites</th>\n",
+ " <th>diff_on</th>\n",
+ " <th>diff_on_first</th>\n",
+ " <th>mean_on</th>\n",
+ " <th>std_on</th>\n",
+ " <th>time_since_last_visit</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>52.1</td>\n",
+ " <td>607.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>12</td>\n",
+ " <td>NaN</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.0</td>\n",
+ " <td>666.0</td>\n",
+ " <td>1.9</td>\n",
+ " <td>17.6</td>\n",
+ " <td>12.000000</td>\n",
+ " <td>44.0</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>12</td>\n",
+ " <td>5.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>53.9</td>\n",
+ " <td>717.0</td>\n",
+ " <td>1.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>12</td>\n",
+ " <td>-6.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>54.8</td>\n",
+ " <td>770.0</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>11.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " <td>12</td>\n",
+ " <td>5.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>56.9</td>\n",
+ " <td>885.0</td>\n",
+ " <td>0.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>24.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>5</td>\n",
+ " <td>12</td>\n",
+ " <td>13.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>2.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>57.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>16.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>6</td>\n",
+ " <td>12</td>\n",
+ " <td>-8.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>0.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>58.9</td>\n",
+ " <td>835.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>10.000000</td>\n",
+ " <td>37.0</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>7</td>\n",
+ " <td>12</td>\n",
+ " <td>-6.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>1.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>59.9</td>\n",
+ " <td>888.0</td>\n",
+ " <td>0.2</td>\n",
+ " <td>9.6</td>\n",
+ " <td>31.000000</td>\n",
+ " <td>36.0</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>8</td>\n",
+ " <td>12</td>\n",
+ " <td>21.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>60.9</td>\n",
+ " <td>952.0</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>11.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>9</td>\n",
+ " <td>12</td>\n",
+ " <td>-20.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>61.5</td>\n",
+ " <td>984.0</td>\n",
+ " <td>1.1</td>\n",
+ " <td>13.5</td>\n",
+ " <td>11.000000</td>\n",
+ " <td>43.0</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>10</td>\n",
+ " <td>12</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>0.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>63.3</td>\n",
+ " <td>1079.0</td>\n",
+ " <td>3.7</td>\n",
+ " <td>15.9</td>\n",
+ " <td>14.000000</td>\n",
+ " <td>54.0</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>11</td>\n",
+ " <td>12</td>\n",
+ " <td>3.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>1.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>48.5</td>\n",
+ " <td>65.7</td>\n",
+ " <td>1214.0</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>27.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>13.000000</td>\n",
+ " <td>7.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " <td>8.034019</td>\n",
+ " <td>2.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>57.7</td>\n",
+ " <td>58.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>14.977019</td>\n",
+ " <td>18.0</td>\n",
+ " <td>0.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>14.977019</td>\n",
+ " <td>16.994255</td>\n",
+ " <td>1.642389</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>57.7</td>\n",
+ " <td>60.1</td>\n",
+ " <td>460.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>17.000000</td>\n",
+ " <td>28.0</td>\n",
+ " <td>0.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>4</td>\n",
+ " <td>2.022981</td>\n",
+ " <td>14.977019</td>\n",
+ " <td>16.994255</td>\n",
+ " <td>1.642389</td>\n",
+ " <td>1.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>57.7</td>\n",
+ " <td>61.4</td>\n",
+ " <td>522.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>17.000000</td>\n",
+ " <td>16.0</td>\n",
+ " <td>0.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>14.977019</td>\n",
+ " <td>16.994255</td>\n",
+ " <td>1.642389</td>\n",
+ " <td>1.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>57.7</td>\n",
+ " <td>62.9</td>\n",
+ " <td>604.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>19.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0000</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>2.000000</td>\n",
+ " <td>14.977019</td>\n",
+ " <td>16.994255</td>\n",
+ " <td>1.642389</td>\n",
+ " <td>1.5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>71.6</td>\n",
+ " <td>72.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>20.540408</td>\n",
+ " <td>23.0</td>\n",
+ " <td>0.4705</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>12</td>\n",
+ " <td>NaN</td>\n",
+ " <td>20.540408</td>\n",
+ " <td>25.378367</td>\n",
+ " <td>7.961099</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>71.6</td>\n",
+ " <td>73.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>13.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.4705</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>12</td>\n",
+ " <td>-7.540408</td>\n",
+ " <td>20.540408</td>\n",
+ " <td>25.378367</td>\n",
+ " <td>7.961099</td>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>71.6</td>\n",
+ " <td>74.5</td>\n",
+ " <td>513.0</td>\n",
+ " <td>0.8</td>\n",
+ " <td>12.2</td>\n",
+ " <td>21.000000</td>\n",
+ " <td>26.0</td>\n",
+ " <td>0.4705</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>12</td>\n",
+ " <td>8.000000</td>\n",
+ " <td>20.540408</td>\n",
+ " <td>25.378367</td>\n",
+ " <td>7.961099</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>71.6</td>\n",
+ " <td>75.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>19.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.4705</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " <td>12</td>\n",
+ " <td>-2.000000</td>\n",
+ " <td>20.540408</td>\n",
+ " <td>25.378367</td>\n",
+ " <td>7.961099</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>20 rows × 6991 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " cohort sexM age_at_diagnosis age ledd time_since_intake_on \\\n",
+ "0 1 0 48.5 52.1 607.0 1.9 \n",
+ "1 1 0 48.5 53.0 666.0 1.9 \n",
+ "2 1 0 48.5 53.9 717.0 1.2 \n",
+ "3 1 0 48.5 54.8 770.0 1.5 \n",
+ "4 1 0 48.5 56.9 885.0 0.3 \n",
+ "5 1 0 48.5 57.5 NaN 2.4 \n",
+ "6 1 0 48.5 58.9 835.0 NaN \n",
+ "7 1 0 48.5 59.9 888.0 0.2 \n",
+ "8 1 0 48.5 60.9 952.0 1.5 \n",
+ "9 1 0 48.5 61.5 984.0 1.1 \n",
+ "10 1 0 48.5 63.3 1079.0 3.7 \n",
+ "11 1 0 48.5 65.7 1214.0 0.6 \n",
+ "12 0 1 57.7 58.7 NaN NaN \n",
+ "13 0 1 57.7 60.1 460.0 NaN \n",
+ "14 0 1 57.7 61.4 522.0 NaN \n",
+ "15 0 1 57.7 62.9 604.0 NaN \n",
+ "16 1 1 71.6 72.4 NaN NaN \n",
+ "17 1 1 71.6 73.5 NaN 1.4 \n",
+ "18 1 1 71.6 74.5 513.0 0.8 \n",
+ "19 1 1 71.6 75.5 NaN 2.1 \n",
+ "\n",
+ " time_since_intake_off on off est_LRRK2+ ... zznx1511 \\\n",
+ "0 NaN 7.000000 NaN 1.0000 ... 0 \n",
+ "1 17.6 12.000000 44.0 1.0000 ... 0 \n",
+ "2 NaN 6.000000 NaN 1.0000 ... 0 \n",
+ "3 NaN 11.000000 NaN 1.0000 ... 0 \n",
+ "4 NaN 24.000000 NaN 1.0000 ... 0 \n",
+ "5 NaN 16.000000 NaN 1.0000 ... 0 \n",
+ "6 NaN 10.000000 37.0 1.0000 ... 0 \n",
+ "7 9.6 31.000000 36.0 1.0000 ... 0 \n",
+ "8 NaN 11.000000 NaN 1.0000 ... 0 \n",
+ "9 13.5 11.000000 43.0 1.0000 ... 0 \n",
+ "10 15.9 14.000000 54.0 1.0000 ... 0 \n",
+ "11 NaN 27.000000 NaN 1.0000 ... 0 \n",
+ "12 NaN 14.977019 18.0 0.0000 ... 0 \n",
+ "13 NaN 17.000000 28.0 0.0000 ... 0 \n",
+ "14 NaN 17.000000 16.0 0.0000 ... 0 \n",
+ "15 NaN 19.000000 NaN 0.0000 ... 0 \n",
+ "16 NaN 20.540408 23.0 0.4705 ... 0 \n",
+ "17 NaN 13.000000 NaN 0.4705 ... 0 \n",
+ "18 12.2 21.000000 26.0 0.4705 ... 0 \n",
+ "19 NaN 19.000000 NaN 0.4705 ... 0 \n",
+ "\n",
+ " zzpu4420 zztp1426 num_visite nb_visites diff_on diff_on_first \\\n",
+ "0 0 0 1 12 NaN 7.000000 \n",
+ "1 0 0 2 12 5.000000 7.000000 \n",
+ "2 0 0 3 12 -6.000000 7.000000 \n",
+ "3 0 0 4 12 5.000000 7.000000 \n",
+ "4 0 0 5 12 13.000000 7.000000 \n",
+ "5 0 0 6 12 -8.000000 7.000000 \n",
+ "6 0 0 7 12 -6.000000 7.000000 \n",
+ "7 0 0 8 12 21.000000 7.000000 \n",
+ "8 0 0 9 12 -20.000000 7.000000 \n",
+ "9 0 0 10 12 0.000000 7.000000 \n",
+ "10 0 0 11 12 3.000000 7.000000 \n",
+ "11 0 0 12 12 13.000000 7.000000 \n",
+ "12 0 0 1 4 NaN 14.977019 \n",
+ "13 0 0 2 4 2.022981 14.977019 \n",
+ "14 0 0 3 4 0.000000 14.977019 \n",
+ "15 0 0 4 4 2.000000 14.977019 \n",
+ "16 0 0 1 12 NaN 20.540408 \n",
+ "17 0 0 2 12 -7.540408 20.540408 \n",
+ "18 0 0 3 12 8.000000 20.540408 \n",
+ "19 0 0 4 12 -2.000000 20.540408 \n",
+ "\n",
+ " mean_on std_on time_since_last_visit \n",
+ "0 15.000000 8.034019 NaN \n",
+ "1 15.000000 8.034019 0.9 \n",
+ "2 15.000000 8.034019 0.9 \n",
+ "3 15.000000 8.034019 0.9 \n",
+ "4 15.000000 8.034019 2.1 \n",
+ "5 15.000000 8.034019 0.6 \n",
+ "6 15.000000 8.034019 1.4 \n",
+ "7 15.000000 8.034019 1.0 \n",
+ "8 15.000000 8.034019 1.0 \n",
+ "9 15.000000 8.034019 0.6 \n",
+ "10 15.000000 8.034019 1.8 \n",
+ "11 15.000000 8.034019 2.4 \n",
+ "12 16.994255 1.642389 NaN \n",
+ "13 16.994255 1.642389 1.4 \n",
+ "14 16.994255 1.642389 1.3 \n",
+ "15 16.994255 1.642389 1.5 \n",
+ "16 25.378367 7.961099 NaN \n",
+ "17 25.378367 7.961099 1.1 \n",
+ "18 25.378367 7.961099 1.0 \n",
+ "19 25.378367 7.961099 1.0 \n",
+ "\n",
+ "[20 rows x 6991 columns]"
]
},
+ "execution_count": 5,
"metadata": {},
- "output_type": "display_data"
+ "output_type": "execute_result"
}
],
"source": [
- "# distribution des résidus\n",
- "residuals_test = y_test - y_pred_test\n",
- "plt.figure(figsize=(10, 6)) \n",
- "plt.hist(residuals_test, bins=30, alpha=0.7, color='blue')\n",
- "plt.axvline(0, color='red', linestyle='--')\n",
- "plt.xlabel('Résidus')\n",
- "plt.ylabel('Fréquence')\n",
- "plt.title('Distribution des résidus (Test)')\n",
- "plt.grid(True)\n",
- "plt.show()"
+ "X_process.head(20)"
]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
}
],
"metadata": {
diff --git a/preprocess/preprocess4.py b/preprocess/preprocess4.py
index 623ab72186b78e0c6bf8f96f453dc8664089d963..621228bfa30fb29532d7967243bdea3121bd1bc3 100644
--- a/preprocess/preprocess4.py
+++ b/preprocess/preprocess4.py
@@ -4,208 +4,772 @@ from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, r2_score
-'''
-fichier pour centraliser toutes les transformations de données
-
-'''
+from sklearn.impute import SimpleImputer
class PreprocessData:
- def __init__(self,path_X,path_y):
- self.X=path_X
+ def __init__(self, Xt, yt=None, Xv=None, yv=None):
+ """
+ Initialise le préprocesseur avec les données d'entraînement et de validation
+
+ Args:
+ Xt (DataFrame): Données d'entraînement X
+ yt (Series/DataFrame): Labels d'entraînement y
+ Xv (DataFrame): Données de validation/test X
+ yv (Series/DataFrame, optional): Labels de validation/test y
+ """
+ self.X_train = Xt
+ self.y_train = yt
+ self.X_val = Xv
+ self.y_val = yv
- self.y = path_y
-
+ self.patient_train= self.X_train['patient_id']
+ self.patient_val= self.X_val['patient_id']
+
+ # Pour stocker les modèles d'imputation
+ self.age_diagnosis_model = None
+ self.on_imputation_model = None
+
+ # Pour stocker les vectorizers et autres transformateurs
+ self.patient_vectorizer = None
+
+ # Pour stocker l'ordre des colonnes
+ self.feature_order = None
+ self.age_diagnosis_features = None
+ self.on_feature_cols = None
+ def process_transformation(self, is_train=True):
+ """
+ Méthode principale qui applique toutes les transformations
+ Args:
+ is_train (bool): True si on traite les données d'entraînement, False sinon
+ Returns:
+ tuple: (X transformé, y)
+ """
+ if is_train==True:
+ X = self.X_train.copy()
+ y = self.y_train
+ else:
+ X = self.X_val.copy()
+ y = self.y_val
+
+ # Étapes de transformation communes
+ X = self.enlever_index(X)
+ X = self.remplir_gene(X)
+ X = self.encoder_cohort(X)
- def process_transformation(self):
- self.enlever_index()
- self.remplir_gene()
-
- self.encoder_cohort()
- self.imputer_age_at_diagnosis()
- #self.rajout_feature_temps()
- self.encoder_patient()
- self.imputer_valeurs_on()
- self.rajout_feature_temps()
- self.virer_patient_et_autre()
- return self.X,self.y
-
- def enlever_index(self):
- self.X.drop('Index',axis=1,inplace=True)
+ # Imputation des valeurs "off" (doit être fait avant "on" pour profiter de la relation)
+ if is_train:
+ X = self.imputer_valeurs_off_train(X)
+ else:
+ X = self.imputer_valeurs_off_val(X)
- def encoder_cohort(self):
- self.X['cohort']=self.X['cohort'].apply(lambda x:1 if x=='A' else 0)
+ # Imputation de l'âge au diagnostic - différent selon train/test
+ if is_train:
+ X = self.imputer_age_at_diagnosis_train(X)
+ else:
+ # Vérifier si time_since_diagnosis existe déjà dans les données de validation
+ if 'time_since_diagnosis' in X.columns:
+ print("La colonne 'time_since_diagnosis' existe déjà dans les données de validation.")
+ else:
+ X = self.imputer_age_at_diagnosis_val(X)
- def encoder_patient(self):
- X_patient=self.X['patient_id']
- vectorizer = CountVectorizer()
- X_patient=vectorizer.fit_transform(X_patient)
- X_patient=pd.DataFrame(X_patient.toarray(),columns=vectorizer.get_feature_names_out())
- self.X=pd.concat([self.X,X_patient],axis=1)
- return self.X
+ # Vectorisation des patients
+ X = self.encoder_patient(X, is_train)
+
+ # Imputation des valeurs "on"
+ if is_train:
+ X = self.imputer_valeurs_on_train(X)
+ X=self.rajout_feature_temps(X)
+ else:
+ X = self.imputer_valeurs_on_val(X)
+ X=self.rajout_feature_temps(X,is_test=True)
+
+ # Autres transformations
+
+ X = self.virer_patient_et_autre(X)
+
+ if is_train:
+ # Sauvegarde de l'ordre des colonnes après toutes les transformations
+ self.feature_order = X.columns.tolist()
+ self.X_train = X
+ return X, y
+ else:
+ # Vérifier si les colonnes dans les données de test sont différentes
+ missing_cols = [col for col in self.feature_order if col not in X.columns]
+ extra_cols = [col for col in X.columns if col not in self.feature_order]
+
+ if missing_cols:
+ print(f"Attention : colonnes manquantes dans les données de test : {missing_cols}")
+ # Créer des colonnes vides pour les colonnes manquantes
+ for col in missing_cols:
+ X[col] = 0
+
+ if extra_cols:
+ print(f"Attention : colonnes supplémentaires dans les données de test : {extra_cols}")
+ # Supprimer les colonnes supplémentaires
+ X = X.drop(columns=extra_cols)
+ # Réorganiser les colonnes dans le même ordre que pour l'entraînement
+ X = X[self.feature_order]
+
+ self.X_val = X
+ return X, y
+
+ def enlever_index(self, X):
+ """Supprime la colonne Index"""
+ if 'Index' in X.columns:
+ X = X.drop('Index', axis=1)
+ return X
+
+ def encoder_cohort(self, X):
+ """Encode la colonne cohort en binaire"""
+ X['cohort'] = X['cohort'].apply(lambda x: 1 if x=='A' else 0)
+ return X
+
+ def encoder_patient(self, X, is_train=True):
+ """
+ Encode les IDs patients avec CountVectorizer
+
+ Args:
+ X (DataFrame): Les données à transformer
+ is_train (bool): Si True, on fit le vectorizer, sinon on réutilise
+
+ Returns:
+ DataFrame: Les données avec les colonnes encodées
+ """
+ X_patient = X['patient_id']
+
+ if is_train:
+ self.patient_vectorizer = CountVectorizer()
+ X_patient_encoded = self.patient_vectorizer.fit_transform(X_patient)
+ else:
+ # Pour les données de test, utiliser seulement les colonnes vues pendant l'entraînement
+ # et gérer les nouveaux patients inconnus
+ X_patient_encoded = self.patient_vectorizer.transform(X_patient)
+
+ X_patient_df = pd.DataFrame(
+ X_patient_encoded.toarray(),
+ columns=self.patient_vectorizer.get_feature_names_out(),
+ index=X.index
+ )
+
+ return pd.concat([X, X_patient_df], axis=1)
+
+ def remplir_gene(self, X):
+ """Remplit les valeurs manquantes dans la colonne gene et crée des features binaires"""
+ X_list = X['gene'].tolist()
- def remplir_gene(self):
- X_list=self.X['gene'].tolist()
def f_l(x):
if x=='Inconnu':
return 0.4705
elif x=='LRRK2+':
return 1
- else :
+ else:
return 0
+
def f_g(x):
if x=='GBA+':
return 1
elif x=='Inconnu':
return 0.4080
- else :
+ else:
return 0
+
def f_o(x):
if x=='OTHER+':
return 1
elif x=='Inconnu':
return 0.1211
- else :
+ else:
return 0
+
for i in range(len(X_list)):
- x=X_list[i]
-
- if type(x)==float:
-
- X_list[i]='Inconnu'
- self.X['gene']=X_list
- self.X['est_LRRK2+']=self.X['gene'].apply(lambda x: f_l(x))
- self.X['est_GBA+']=self.X['gene'].apply(lambda x: f_g(x))
- self.X['est_OTHER+']=self.X['gene'].apply(lambda x: f_o(x))
- self.X.drop('gene',axis=1,inplace=True)
- return self.X
- def virer_patient_et_autre(self):
- self.X.drop('patient_id',axis=1,inplace=True)
- self.X.drop(['time_since_intake_on','time_since_intake_off'],axis=1,inplace=True)
- return self.X
- def get_X(self):
- return self.X
- def get_y(self):
- return self.y
- def get_data(self):
- return self.X,self.y
- def rajout_feature_temps(self):
- '''
- Pour capturer la relation temporelle
- '''
-
- # rajouter le numéro de la visite
- self.X['num_visite'] = self.X.groupby('patient_id').cumcount() + 1
+ x = X_list[i]
+ if type(x) == float:
+ X_list[i] = 'Inconnu'
+
+ X['gene'] = X_list
+ X['est_LRRK2+'] = X['gene'].apply(lambda x: f_l(x))
+ X['est_GBA+'] = X['gene'].apply(lambda x: f_g(x))
+ X['est_OTHER+'] = X['gene'].apply(lambda x: f_o(x))
+ X.drop('gene', axis=1, inplace=True)
+
+ return X
+
+ def virer_patient_et_autre(self, X):
+ """Supprime les colonnes qui ne sont plus nécessaires"""
+ cols_to_drop = ['patient_id']
+
+ if 'time_since_intake_on' in X.columns:
+ cols_to_drop.append('time_since_intake_on')
+
+ if 'time_since_intake_off' in X.columns:
+ cols_to_drop.append('time_since_intake_off')
+
+ if 'disease_duration' in X.columns and 'time_since_diagnosis' not in X.columns:
+ X['time_since_diagnosis'] = X['disease_duration']
+ cols_to_drop.append('disease_duration')
+
+ X = X.drop(cols_to_drop, axis=1)
+ return X
+
+ def rajout_feature_temps(self, X,is_test=False):
+ """Ajoute des features temporelles basées sur les groupes de patients"""
+ X_copy = X.copy()
+ # rajout des patients
+ if is_test:
+ X_copy['patient_id'] = self.patient_val
+ print(X_copy.isna().sum())
+ else:
+ X_copy['patient_id'] = self.patient_train
+
+ X_copy['num_visite'] = X_copy.groupby('patient_id').cumcount() + 1
- # rajouter le nombre de visite total
- self.X['nb_visites'] = self.X.groupby('patient_id')['num_visite'].transform('max')
+ X_copy['nb_visites'] = X_copy.groupby('patient_id')['num_visite'].transform('max')
- # rajouter la progression du score on et off depuis la dernière visite
- self.X['diff_on'] = self.X.groupby('patient_id')['on'].diff()
- #self.X['diff_off'] = self.X.groupby('patient_id')['off'].diff()
+ X_copy['diff_on'] = X_copy.groupby('patient_id')['on'].diff()
+
+ mask_first_visit = X_copy['diff_on'].isna()
+ X_copy.loc[mask_first_visit, 'diff_on'] = 0
- # rajouter la progression du score on et off depuis la première visite
- self.X['diff_on_first'] = self.X.groupby('patient_id')['on'].transform('first')
- #self.X['diff_off_first'] = self.X.groupby('patient_id')['off'].transform('first')
+ X_copy['diff_on_first'] = X_copy.groupby('patient_id')['on'].transform('first')
+ X_copy['diff_on_first'] = X_copy['on'] - X_copy['diff_on_first']
- # rajouter la moyenne du score on et off sur toutes les visites
- self.X['mean_on'] = self.X.groupby('patient_id')['on'].transform('mean')
- #self.X['mean_off'] = self.X.groupby('patient_id')['off'].transform('mean')
+ X_copy['mean_on'] = X_copy.groupby('patient_id')['on'].transform('mean')
- # rajouter l'écart type du score on et off sur toutes les visites
- self.X['std_on'] = self.X.groupby('patient_id')['on'].transform('std')
- #self.X['std_off'] = self.X.groupby('patient_id')['off'].transform('std')
+ X_copy['std_on'] = X_copy.groupby('patient_id')['on'].transform('std')
+ X_copy['std_on'] = X_copy['std_on'].fillna(0)
- # rajouter le temps depuis la dernière visite
- self.X['time_since_last_visit'] = self.X.groupby('patient_id')['age'].diff()
+ X_copy['time_since_last_visit'] = X_copy.groupby('patient_id')['age'].diff()
+
+ X_copy.loc[mask_first_visit, 'time_since_last_visit'] = 0
+
+ return X_copy
- def imputer_age_at_diagnosis(self):
+ def imputer_age_at_diagnosis_train(self, X):
"""
- Impute les valeurs manquantes de age_at_diagnosis en utilisant une régression linéaire.
+ Impute les valeurs manquantes de age_at_diagnosis sur les données d'entraînement
+ et entraîne un modèle pour les données de validation.
"""
-
-
- patients_values = self.X.dropna(subset=['age_at_diagnosis']).groupby('patient_id')['age_at_diagnosis'].first().reset_index()
+ patients_values = X.dropna(subset=['age_at_diagnosis']).groupby('patient_id')['age_at_diagnosis'].first().reset_index()
patients_values.columns = ['patient_id', 'known_value']
- temp_df = self.X.merge(patients_values, on='patient_id', how='left')
+ temp_df = X.merge(patients_values, on='patient_id', how='left')
mask = temp_df['age_at_diagnosis'].isna() & temp_df['known_value'].notna()
- self.X.loc[mask.values, 'age_at_diagnosis'] = temp_df.loc[mask, 'known_value'].values
+ X.loc[mask.values, 'age_at_diagnosis'] = temp_df.loc[mask, 'known_value'].values
- patients_sans_diagnostic = self.X.groupby('patient_id')['age_at_diagnosis'].apply(
+ patients_sans_diagnostic = X.groupby('patient_id')['age_at_diagnosis'].apply(
lambda x: x.isna().all())
patients_sans_diagnostic = patients_sans_diagnostic[patients_sans_diagnostic].index.tolist()
nb_patients_sans_diagnostic = len(patients_sans_diagnostic)
- total_patients = len(self.X['patient_id'].unique())
+ total_patients = len(X['patient_id'].unique())
pourcentage = (nb_patients_sans_diagnostic / total_patients) * 100
-
+
+ self.age_diagnosis_features = ['age', 'sexM', 'est_LRRK2+', 'est_GBA+', 'est_OTHER+', 'cohort']
if nb_patients_sans_diagnostic > 0:
- patients_avec_diagnostic = ~self.X['patient_id'].isin(patients_sans_diagnostic)
- df_known = self.X[patients_avec_diagnostic].dropna(subset=['age_at_diagnosis'])
+ patients_avec_diagnostic = ~X['patient_id'].isin(patients_sans_diagnostic)
+ df_known = X[patients_avec_diagnostic].dropna(subset=['age_at_diagnosis'])
df_known_unique = df_known.drop_duplicates('patient_id')
- features = ['age', 'sexM', 'est_LRRK2+', 'est_GBA+', 'est_OTHER+', 'cohort']
- X_known = df_known_unique[features]
+ X_known = df_known_unique[self.age_diagnosis_features]
y_known = df_known_unique['age_at_diagnosis']
X_train, X_test, y_train, y_test = train_test_split(
X_known, y_known, test_size=0.2, random_state=42)
- model = LinearRegression()
- model.fit(X_train, y_train)
+ self.age_diagnosis_model = LinearRegression()
+ self.age_diagnosis_model.fit(X_train, y_train)
- y_pred = model.predict(X_test)
+ y_pred = self.age_diagnosis_model.predict(X_test)
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
- print(f"Performance du modèle d'imputation linéaire - MAE: {mae:.2f}, R²: {r2:.2f}")
+ print(f"Performance du modèle d'imputation age_at_diagnosis - MAE: {mae:.2f}, R²: {r2:.2f}")
- df_unknown = self.X[self.X['patient_id'].isin(patients_sans_diagnostic)].drop_duplicates('patient_id')
- X_unknown = df_unknown[features]
- predicted_ages = model.predict(X_unknown)
+ df_unknown = X[X['patient_id'].isin(patients_sans_diagnostic)].drop_duplicates('patient_id')
+ X_unknown = df_unknown[self.age_diagnosis_features]
+ predicted_ages = self.age_diagnosis_model.predict(X_unknown)
for i, patient_id in enumerate(df_unknown['patient_id']):
- self.X.loc[self.X['patient_id'] == patient_id, 'age_at_diagnosis'] = predicted_ages[i]
+ X.loc[X['patient_id'] == patient_id, 'age_at_diagnosis'] = predicted_ages[i]
- missing_pct = self.X['age_at_diagnosis'].isna().mean() * 100
+ missing_pct = X['age_at_diagnosis'].isna().mean() * 100
print(f"Pourcentage de valeurs manquantes après imputation: {missing_pct:.2f}%")
- self.X['disease_duration'] = self.X['age'] - self.X['age_at_diagnosis']
- print("Variable 'disease_duration' ajoutée avec succès.")
+ X['time_since_diagnosis'] = X['age'] - X['age_at_diagnosis']
+ print("Variable 'time_since_diagnosis' ajoutée avec succès.")
+
+ return X
- return self.X
- def imputer_valeurs_on(self):
+ def imputer_age_at_diagnosis_val(self, X):
"""
- Impute les valeurs manquantes de on en utilisant une régression linéaire.
+ Impute les valeurs manquantes de age_at_diagnosis sur les données de validation
+ en utilisant le modèle entraîné précédemment.
"""
- X_copy = self.X.copy()
- X_copy = X_copy.drop(['ledd','off','time_since_intake_on','time_since_intake_off','patient_id'],axis=1)
-
- X_copy_a_imputer = X_copy[X_copy['on'].isna()]
- X_copy_connu = X_copy[~X_copy['on'].isna()]
-
- y_copy = X_copy_connu['on']
-
- X_train, X_test, y_train, y_test = train_test_split(X_copy_connu.drop('on',axis=1), y_copy, test_size=0.2, random_state=42)
-
- model = LinearRegression()
- model.fit(X_train, y_train)
-
- y_pred = model.predict(X_test)
- mae = mean_absolute_error(y_test, y_pred)
- print(f"Performance du modèle d'imputation linéaire - MAE: {mae:.2f}")
- print("Imputation des valeurs manquantes de 'on'...")
- X_copy.loc[X_copy['on'].isna(),'on'] = model.predict(X_copy_a_imputer.drop('on',axis=1))
- self.X['on']=X_copy['on']
- print("Les valeurs de 'on' ont été imputées avec succès.")
- return self.X
-
-# test du code
-
+ if 'time_since_diagnosis' in X.columns:
+ print("La colonne 'time_since_diagnosis' existe déjà dans les données de validation. Conservation des valeurs existantes.")
+ return X
+
+ if self.age_diagnosis_model is None:
+ raise ValueError("Le modèle d'imputation d'âge n'a pas été entraîné. Appelez d'abord process_transformation sur les données d'entraînement.")
+
+ if not hasattr(self, 'age_diagnosis_features'):
+ raise ValueError("Les features pour le modèle d'âge n'ont pas été enregistrées.")
+
+ patients_values = X.dropna(subset=['age_at_diagnosis']).groupby('patient_id')['age_at_diagnosis'].first().reset_index()
+ patients_values.columns = ['patient_id', 'known_value']
+
+ temp_df = X.merge(patients_values, on='patient_id', how='left')
+
+ mask = temp_df['age_at_diagnosis'].isna() & temp_df['known_value'].notna()
+ X.loc[mask.values, 'age_at_diagnosis'] = temp_df.loc[mask, 'known_value'].values
+
+ mask_missing = X['age_at_diagnosis'].isna()
+ if mask_missing.any():
+ missing_cols = [col for col in self.age_diagnosis_features if col not in X.columns]
+ if missing_cols:
+ raise ValueError(f"Colonnes manquantes dans les données de validation pour age_at_diagnosis: {missing_cols}")
+
+ X_missing = X.loc[mask_missing, self.age_diagnosis_features]
+
+ predicted_ages = self.age_diagnosis_model.predict(X_missing)
+ X.loc[mask_missing, 'age_at_diagnosis'] = predicted_ages
+
+ if 'time_since_diagnosis' not in X.columns:
+ X['time_since_diagnosis'] = X['age'] - X['age_at_diagnosis']
+ print("Variable 'time_since_diagnosis' ajoutée aux données de validation.")
+
+ return X
+
+ def imputer_valeurs_on_train(self, X):
+ """
+ Impute les valeurs manquantes de 'on' avec des méthodes avancées
+ Args:
+ X (DataFrame): Les données à transformer
+
+ Returns:
+ DataFrame: Les données avec 'on' imputé
+ """
+ from sklearn.ensemble import GradientBoostingRegressor
+ from sklearn.impute import KNNImputer
+
+ X_copy = X.copy()
+
+ cols_to_exclude = ['on']
+ if 'ledd' in X_copy.columns:
+ cols_to_exclude.append('ledd')
+ if 'off' in X_copy.columns:
+ cols_to_exclude.append('off')
+ if 'time_since_intake_on' in X_copy.columns:
+ cols_to_exclude.append('time_since_intake_on')
+ if 'time_since_intake_off' in X_copy.columns:
+ cols_to_exclude.append('time_since_intake_off')
+ if 'patient_id' in X_copy.columns:
+ cols_to_exclude.append('patient_id')
+
+ mask_missing = X_copy['on'].isna()
+
+ if not mask_missing.any():
+ print("Aucune valeur 'on' à imputer.")
+ return X
+
+ print("Imputation préliminaire des autres features...")
+ features_with_missing = X_copy.columns[X_copy.isna().any()].tolist()
+ features_with_missing = [col for col in features_with_missing if col != 'on']
+
+ if features_with_missing:
+ preliminary_imputer = KNNImputer(n_neighbors=5)
+ X_copy[features_with_missing] = preliminary_imputer.fit_transform(X_copy[features_with_missing])
+
+ print("Ajout de features supplémentaires pour l'imputation...")
+
+ if 'patient_id' in X_copy.columns:
+ patient_stats = X_copy.groupby('patient_id')['on'].agg(['mean', 'median', 'min', 'max', 'std']).reset_index()
+ patient_stats.columns = ['patient_id', 'patient_mean_on', 'patient_median_on', 'patient_min_on', 'patient_max_on', 'patient_std_on']
+ patient_stats.fillna(0, inplace=True) # Pour les patients avec une seule observation
+
+ X_copy = X_copy.merge(patient_stats, on='patient_id', how='left')
+
+ feature_cols = [col for col in X_copy.columns if col not in cols_to_exclude]
+ self.on_feature_cols = feature_cols
+
+ X_with_on = X_copy[~mask_missing]
+ X_missing_on = X_copy[mask_missing]
+
+ X_train_on = X_with_on[feature_cols]
+ y_train_on = X_with_on['on']
+
+ print(f"Entraînement du modèle d'imputation pour {sum(mask_missing)} valeurs manquantes de 'on'...")
+
+ gb_model = GradientBoostingRegressor(
+ n_estimators=100,
+ learning_rate=0.1,
+ max_depth=3,
+ random_state=42
+ )
+
+ self.on_imputation_model = gb_model
+ self.on_imputation_model.fit(X_train_on, y_train_on)
+
+ from sklearn.model_selection import cross_val_score
+ from sklearn.metrics import make_scorer, mean_absolute_error
+
+ mae_scorer = make_scorer(mean_absolute_error)
+ cv_scores = cross_val_score(gb_model, X_train_on, y_train_on, cv=5, scoring=mae_scorer)
+
+ print(f"Performance du modèle d'imputation de 'on' - MAE CV: {-cv_scores.mean():.2f} ± {cv_scores.std():.2f}")
+
+ if mask_missing.any():
+ X_missing_features = X_missing_on[feature_cols]
+ predicted_values = self.on_imputation_model.predict(X_missing_features)
+ X.loc[mask_missing, 'on'] = predicted_values
+
+ return X
+
+ def imputer_valeurs_on_val(self, X):
+ """
+ Impute les valeurs manquantes de 'on' sur les données de validation
+ en utilisant le modèle entraîné précédemment.
+ """
+ if self.on_imputation_model is None:
+ raise ValueError("Le modèle d'imputation de 'on' n'a pas été entraîné. Appelez d'abord process_transformation sur les données d'entraînement.")
+
+ if not hasattr(self, 'on_feature_cols'):
+ raise ValueError("Les colonnes de features pour le modèle 'on' n'ont pas été enregistrées.")
+
+ mask_missing = X['on'].isna()
+
+ if not mask_missing.any():
+ print("Aucune valeur 'on' à imputer dans les données de validation.")
+ return X
+
+ print(f"Imputation de {sum(mask_missing)} valeurs 'on' dans les données de validation...")
+
+ X_copy = X.copy()
+
+ features_with_missing = X_copy.columns[X_copy.isna().any()].tolist()
+ features_with_missing = [col for col in features_with_missing if col != 'on' and col in self.on_feature_cols]
+
+ if features_with_missing:
+ from sklearn.impute import KNNImputer
+ preliminary_imputer = KNNImputer(n_neighbors=5)
+ X_copy[features_with_missing] = preliminary_imputer.fit_transform(X_copy[features_with_missing])
+
+ if 'patient_id' in X_copy.columns:
+ patient_stats = X_copy.groupby('patient_id')['on'].agg(['mean', 'median', 'min', 'max', 'std']).reset_index()
+ patient_stats.columns = ['patient_id', 'patient_mean_on', 'patient_median_on', 'patient_min_on', 'patient_max_on', 'patient_std_on']
+ patient_stats.fillna(0, inplace=True)
+
+ X_copy = X_copy.merge(patient_stats, on='patient_id', how='left')
+
+ missing_cols = [col for col in self.on_feature_cols if col not in X_copy.columns]
+
+ for col in missing_cols:
+ print(f"Ajout de la colonne manquante '{col}' avec des zéros.")
+ X_copy[col] = 0
+
+ X_missing = X_copy[mask_missing]
+ X_missing_features = X_missing[self.on_feature_cols]
+
+ predicted_values = self.on_imputation_model.predict(X_missing_features)
+ X.loc[mask_missing, 'on'] = predicted_values
+
+ return X
+ def imputer_valeurs_off_train(self, X):
+ """
+ Impute les valeurs manquantes de 'off' avec des méthodes avancées
+
+ Args:
+ X (DataFrame): Les données à transformer
+
+ Returns:
+ DataFrame: Les données avec 'off' imputé
+ """
+ from sklearn.ensemble import GradientBoostingRegressor
+ from sklearn.impute import KNNImputer
+
+ # Vérifier si la colonne 'off' existe
+ if 'off' not in X.columns:
+ print("La colonne 'off' n'existe pas dans les données. Aucune imputation effectuée.")
+ return X
+
+ # Copie pour éviter les warnings
+ X_copy = X.copy()
+
+ # Colonnes à exclure pour la prédiction
+ cols_to_exclude = ['off']
+ if 'ledd' in X_copy.columns:
+ cols_to_exclude.append('ledd')
+ if 'on' in X_copy.columns:
+ cols_to_exclude.append('on') # on exclut 'on' pour éviter la fuite d'information
+ if 'time_since_intake_on' in X_copy.columns:
+ cols_to_exclude.append('time_since_intake_on')
+ if 'time_since_intake_off' in X_copy.columns:
+ cols_to_exclude.append('time_since_intake_off')
+ if 'patient_id' in X_copy.columns:
+ cols_to_exclude.append('patient_id')
+
+ # Séparation des données avec/sans valeurs 'off'
+ mask_missing = X_copy['off'].isna()
+
+ # Si aucune valeur manquante, retourner directement
+ if not mask_missing.any():
+ print("Aucune valeur 'off' à imputer.")
+ return X
+
+ # Nombre de valeurs manquantes et pourcentage
+ n_missing = mask_missing.sum()
+ percent_missing = (n_missing / len(X_copy)) * 100
+ print(f"Imputation de {n_missing} valeurs manquantes ({percent_missing:.2f}%) pour 'off'...")
+
+ # 1. Imputation préliminaire avec KNN pour les autres caractéristiques qui pourraient être manquantes
+ features_with_missing = X_copy.columns[X_copy.isna().any()].tolist()
+ features_with_missing = [col for col in features_with_missing if col != 'off' and col != 'on'] # Exclure off et on
+
+ if features_with_missing:
+ print(f"Imputation préliminaire des features: {features_with_missing}")
+ preliminary_imputer = KNNImputer(n_neighbors=5)
+ feature_data = X_copy[features_with_missing]
+ X_copy[features_with_missing] = preliminary_imputer.fit_transform(feature_data)
+
+ # 2. Créer des features additionnelles pour améliorer l'imputation
+
+ # 2.1 Si on a des données longitudinales (plusieurs visites par patient)
+ if 'patient_id' in X_copy.columns:
+ # Calculer des statistiques par patient pour 'off' (pour les patients qui ont des valeurs)
+ patient_stats = X_copy.groupby('patient_id')['off'].agg(['mean', 'median', 'min', 'max', 'std']).reset_index()
+ patient_stats.columns = ['patient_id', 'patient_mean_off', 'patient_median_off', 'patient_min_off', 'patient_max_off', 'patient_std_off']
+ patient_stats.fillna(0, inplace=True) # Pour les patients avec une seule ou aucune observation
+
+ # Si on a aussi des valeurs pour 'on', on peut utiliser la relation on/off
+ if 'on' in X_copy.columns:
+ # Patients avec des valeurs pour 'on' et 'off'
+ valid_mask = ~X_copy['on'].isna() & ~X_copy['off'].isna()
+ if valid_mask.sum() > 0:
+ # Rapport moyen on/off par patient
+ patient_on_off = X_copy[valid_mask].groupby('patient_id').apply(
+ lambda x: x['on'].mean() / x['off'].mean() if x['off'].mean() != 0 else 1
+ ).reset_index()
+ patient_on_off.columns = ['patient_id', 'patient_on_off_ratio']
+
+ # Fusionner avec les autres statistiques
+ patient_stats = patient_stats.merge(patient_on_off, on='patient_id', how='left')
+ patient_stats['patient_on_off_ratio'].fillna(1, inplace=True) # Valeur par défaut
+
+ # Fusionner avec nos données principales
+ X_copy = X_copy.merge(patient_stats, on='patient_id', how='left')
+
+ # Pour les patients sans statistiques, utiliser les valeurs globales
+ for col in patient_stats.columns:
+ if col != 'patient_id' and col in X_copy.columns:
+ mask = X_copy[col].isna()
+ if mask.any() and col.startswith('patient_mean'):
+ X_copy.loc[mask, col] = X_copy.loc[~mask, col].mean()
+ elif mask.any() and col.startswith('patient_median'):
+ X_copy.loc[mask, col] = X_copy.loc[~mask, col].median()
+ elif mask.any():
+ X_copy.loc[mask, col] = 0
+
+ # 2.2 Utiliser la relation avec 'on' quand disponible
+ if 'on' in X_copy.columns:
+ global_ratio = 1.0 # Valeur par défaut
+ valid_mask = ~X_copy['on'].isna() & ~X_copy['off'].isna()
+
+ if valid_mask.sum() > 0:
+ # Moyenne globale du rapport on/off
+ global_on = X_copy.loc[valid_mask, 'on'].mean()
+ global_off = X_copy.loc[valid_mask, 'off'].mean()
+ if global_off != 0:
+ global_ratio = global_on / global_off
+
+ # Créer une feature prédictive utilisant on et le ratio
+ X_copy['predicted_off_from_on'] = X_copy['on'] / global_ratio
+ X_copy['predicted_off_from_on'].fillna(X_copy['off'].mean(), inplace=True)
+
+ # Sélectionner toutes les colonnes sauf celles à exclure pour le modèle
+ feature_cols = [col for col in X_copy.columns if col not in cols_to_exclude]
+
+ # Stocker ces colonnes pour garantir le même ordre lors de la prédiction
+ self.off_feature_cols = feature_cols
+
+ X_with_off = X_copy[~mask_missing]
+ X_missing_off = X_copy[mask_missing]
+
+ # Extraire les données d'entraînement
+ X_train_off = X_with_off[feature_cols]
+ y_train_off = X_with_off['off']
+
+ # 3. Utiliser un modèle plus robuste
+ gb_model = GradientBoostingRegressor(
+ n_estimators=100,
+ learning_rate=0.1,
+ max_depth=4, # Un peu plus profond pour capturer des relations plus complexes
+ subsample=0.8, # Ajouter du sous-échantillonnage pour éviter le surapprentissage
+ random_state=42
+ )
+
+ # Entraîner le modèle
+ self.off_imputation_model = gb_model
+ self.off_imputation_model.fit(X_train_off, y_train_off)
+
+ # Évaluer la performance sur l'ensemble d'entraînement
+ from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
+ import numpy as np
+
+ train_preds = self.off_imputation_model.predict(X_train_off)
+
+ train_mae = mean_absolute_error(y_train_off, train_preds)
+ train_rmse = np.sqrt(mean_squared_error(y_train_off, train_preds))
+ train_r2 = r2_score(y_train_off, train_preds)
+
+ print(f"Performance du modèle d'imputation 'off' sur l'entraînement:")
+ print(f" - MAE: {train_mae:.2f}")
+ print(f" - RMSE: {train_rmse:.2f}")
+ print(f" - R²: {train_r2:.2f}")
+
+ # Évaluer avec validation croisée également
+ from sklearn.model_selection import cross_val_score
+ from sklearn.metrics import make_scorer
+
+ cv_mae = -np.mean(cross_val_score(gb_model, X_train_off, y_train_off, cv=3,
+ scoring=make_scorer(mean_absolute_error)))
+
+ print(f" - MAE CV (3-fold): {cv_mae:.2f}")
+
+ # Appliquer le modèle aux données manquantes
+ if mask_missing.any():
+ X_missing_features = X_missing_off[feature_cols]
+ predicted_values = self.off_imputation_model.predict(X_missing_features)
+ X.loc[mask_missing, 'off'] = predicted_values
+
+ return X
-
+ def imputer_valeurs_off_val(self, X):
+ """
+ Impute les valeurs manquantes de 'off' sur les données de validation
+ en utilisant le modèle entraîné précédemment.
+ """
+ # Vérifier si la colonne 'off' existe
+ if 'off' not in X.columns:
+ print("La colonne 'off' n'existe pas dans les données de validation. Aucune imputation effectuée.")
+ return X
+
+ if not hasattr(self, 'off_imputation_model'):
+ raise ValueError("Le modèle d'imputation de 'off' n'a pas été entraîné. Appelez d'abord process_transformation sur les données d'entraînement.")
+
+ if not hasattr(self, 'off_feature_cols'):
+ raise ValueError("Les colonnes de features pour le modèle 'off' n'ont pas été enregistrées.")
+
+ # Identification des lignes avec valeurs manquantes
+ mask_missing = X['off'].isna()
+
+ if not mask_missing.any():
+ print("Aucune valeur 'off' à imputer dans les données de validation.")
+ return X
+
+ print(f"Imputation de {sum(mask_missing)} valeurs 'off' dans les données de validation...")
+
+ # Préparation des données de validation (similaire à l'entraînement)
+ X_copy = X.copy()
+
+ # 1. Imputation préliminaire des autres features
+ features_with_missing = X_copy.columns[X_copy.isna().any()].tolist()
+ features_with_missing = [col for col in features_with_missing if col != 'off' and col != 'on' and col in self.off_feature_cols]
+
+ if features_with_missing:
+ from sklearn.impute import KNNImputer
+ preliminary_imputer = KNNImputer(n_neighbors=5)
+ X_copy[features_with_missing] = preliminary_imputer.fit_transform(X_copy[features_with_missing])
+
+ # 2. Recréer les features additionnelles comme à l'entraînement
+
+ # 2.1 Statistiques par patient
+ if 'patient_id' in X_copy.columns:
+ patient_stats = X_copy.groupby('patient_id')['off'].agg(['mean', 'median', 'min', 'max', 'std']).reset_index()
+ patient_stats.columns = ['patient_id', 'patient_mean_off', 'patient_median_off', 'patient_min_off', 'patient_max_off', 'patient_std_off']
+ patient_stats.fillna(0, inplace=True)
+
+ # Ratio on/off si possible
+ if 'on' in X_copy.columns:
+ valid_mask = ~X_copy['on'].isna() & ~X_copy['off'].isna()
+ if valid_mask.sum() > 0:
+ patient_on_off = X_copy[valid_mask].groupby('patient_id').apply(
+ lambda x: x['on'].mean() / x['off'].mean() if x['off'].mean() != 0 else 1
+ ).reset_index()
+ patient_on_off.columns = ['patient_id', 'patient_on_off_ratio']
+
+ patient_stats = patient_stats.merge(patient_on_off, on='patient_id', how='left')
+ patient_stats['patient_on_off_ratio'].fillna(1, inplace=True)
+
+ X_copy = X_copy.merge(patient_stats, on='patient_id', how='left')
+
+ # Imputer des valeurs manquantes dans les statistiques
+ for col in patient_stats.columns:
+ if col != 'patient_id' and col in X_copy.columns:
+ mask = X_copy[col].isna()
+ if mask.any() and col.startswith('patient_mean'):
+ X_copy.loc[mask, col] = X_copy.loc[~mask, col].mean() if (~mask).any() else 0
+ elif mask.any() and col.startswith('patient_median'):
+ X_copy.loc[mask, col] = X_copy.loc[~mask, col].median() if (~mask).any() else 0
+ elif mask.any():
+ X_copy.loc[mask, col] = 0
+
+ # 2.2 Relation avec 'on'
+ if 'on' in X_copy.columns:
+ # Utiliser le même ratio global qu'à l'entraînement si possible
+ # Si non, estimer à partir des données actuelles
+ global_ratio = 1.0
+ valid_mask = ~X_copy['on'].isna() & ~X_copy['off'].isna()
+
+ if valid_mask.sum() > 0:
+ global_on = X_copy.loc[valid_mask, 'on'].mean()
+ global_off = X_copy.loc[valid_mask, 'off'].mean()
+ if global_off != 0:
+ global_ratio = global_on / global_off
+
+ X_copy['predicted_off_from_on'] = X_copy['on'] / global_ratio
+ X_copy['predicted_off_from_on'].fillna(X_copy['off'].mean() if ~X_copy['off'].isna().all() else 0, inplace=True)
+
+ # Vérifier les colonnes manquantes par rapport à l'entraînement
+ missing_cols = [col for col in self.off_feature_cols if col not in X_copy.columns]
+
+ # Ajouter les colonnes manquantes avec des valeurs par défaut
+ for col in missing_cols:
+ print(f"Ajout de la colonne manquante '{col}' avec des zéros.")
+ X_copy[col] = 0
+
+ # Sélectionner les features dans le même ordre que lors de l'entraînement
+ X_missing = X_copy[mask_missing]
+ try:
+ X_missing_features = X_missing[self.off_feature_cols]
+ except KeyError as e:
+ print(f"Erreur lors de la sélection des features: {e}")
+ print(f"Colonnes manquantes: {[col for col in self.off_feature_cols if col not in X_missing.columns]}")
+ raise
+
+ # Prédiction et imputation
+ predicted_values = self.off_imputation_model.predict(X_missing_features)
+ X.loc[mask_missing, 'off'] = predicted_values
+
+ return X
+ def get_X_train(self):
+ return self.X_train
+
+ def get_y_train(self):
+ return self.y_train
+
+ def get_X_val(self):
+ return self.X_val
+
+ def get_y_val(self):
+ return self.y_val
+
+ def get_train_data(self):
+ return self.X_train, self.y_train
+
+ def get_val_data(self):
+ return self.X_val, self.y_val
diff --git a/preprocess/preprocess_data.py b/preprocess/preprocess_data.py
new file mode 100644
index 0000000000000000000000000000000000000000..de9bc18ec3d17cf1cbc12a3fd4a14c898c15b402
--- /dev/null
+++ b/preprocess/preprocess_data.py
@@ -0,0 +1,345 @@
+import pandas as pd
+import numpy as np
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_absolute_error, r2_score
+from sklearn.linear_model import Ridge
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import PolynomialFeatures
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.pipeline import Pipeline
+from sklearn.impute import SimpleImputer
+
+'''
+fichier pour centraliser toutes les transformations de données
+
+'''
+class PreprocessData:
+ def __init__(self,path_X,path_y,X_test):
+ self.X=path_X
+ self.X_test=X_test
+ self.X.drop('ledd',axis=1,inplace=True)
+ self.X_test.drop('ledd',axis=1,inplace=True)
+
+ self.y = path_y
+ self.model_on=None
+
+ self.model_off=None
+ self.colonne=None
+ self.model_ledd=None
+ self.patient_test=self.X_test['patient_id'].tolist()
+ self.patient_train=self.X['patient_id']
+
+
+
+
+
+
+ def imputer_valeurs_on_test(self):
+ X_copy = self.X_test.copy()[self.colonne.tolist()]
+ print(self.colonne)
+
+ X_copy = X_copy.drop(['off','patient_id','time_since_intake_on','time_since_intake_off'],axis=1)
+
+ # ✅ Ajoute la même feature que pendant le fit
+ X_copy['is_missing_on'] = X_copy['on'].isna().astype(int)
+
+ print("Imputations des valeurs de 'on' manquantes sur les données de test...")
+ X_copy_a_imputer = X_copy[X_copy['on'].isna()]
+ X_copy_connu = X_copy[~X_copy['on'].isna()]
+ y_copy = X_copy_connu['on']
+ model = self.model_on
+
+ X_copy.loc[X_copy['on'].isna(),'on'] = model.predict(X_copy_a_imputer.drop('on',axis=1))
+
+ self.X_test['on'] = X_copy['on']
+ print("Les valeurs de 'on' ont été imputées avec succès.")
+ return self.X_test
+
+ def get_data_processed(self):
+ return self.X,self.y, self.X_test
+
+
+
+ def enlever_index(self,X):
+ X.drop('Index',axis=1,inplace=True)
+ return X
+
+ def encoder_cohort(self,X):
+
+ X['cohort']=X['cohort'].apply(lambda x:1 if x=='A' else 0)
+ return X
+
+ def encoder_patient(self,X):
+ X_patient=X['patient_id']
+ vectorizer = CountVectorizer()
+ X_patient=vectorizer.fit_transform(X_patient)
+ X_patient=pd.DataFrame(X_patient.toarray(),columns=vectorizer.get_feature_names_out())
+ X=pd.concat([X,X_patient],axis=1)
+ return X
+
+
+ def remplir_gene(self,X):
+ X_list=X['gene'].tolist()
+ def f_l(x):
+ if x=='Inconnu':
+ return 0.4705
+ elif x=='LRRK2+':
+ return 1
+ else :
+ return 0
+ def f_g(x):
+ if x=='GBA+':
+ return 1
+ elif x=='Inconnu':
+ return 0.4080
+ else :
+ return 0
+ def f_o(x):
+ if x=='OTHER+':
+ return 1
+ elif x=='Inconnu':
+ return 0.1211
+ else :
+ return 0
+ for i in range(len(X_list)):
+ x=X_list[i]
+
+ if type(x)==float:
+
+ X_list[i]='Inconnu'
+ X['gene']=X_list
+ X['est_LRRK2+']=X['gene'].apply(lambda x: f_l(x))
+ X['est_GBA+']=X['gene'].apply(lambda x: f_g(x))
+ X['est_OTHER+']=X['gene'].apply(lambda x: f_o(x))
+ X.drop('gene',axis=1,inplace=True)
+ return X
+ def virer_patient_et_autre(self,is_test=False):
+ if not is_test:
+
+ self.X.drop(['time_since_intake_on','time_since_intake_off'],axis=1,inplace=True)
+ return self.X
+ else:
+
+
+ self.X_test.drop(['time_since_intake_on','time_since_intake_off'],axis=1,inplace=True)
+ return self.X_test
+
+ def rajout_feature_temps(self, X, is_test=False):
+ '''
+ Ajoute des features temporelles avancées liées à la progression de 'off'
+ '''
+ import numpy as np
+ import pandas as pd
+ from sklearn.linear_model import LinearRegression
+
+ X = X.copy() # pour éviter les effets de bord
+
+ if not is_test:
+ X['patient_id'] = self.patient_train
+
+ else:
+ # rajouter les patients pour les données de test
+ X['patient_id'] = self.patient_test
+
+
+ X['num_visite'] = X.groupby('patient_id').cumcount() + 1
+ X['nb_visites'] = X.groupby('patient_id')['num_visite'].transform('max')
+
+ X['diff_on'] = X.groupby('patient_id')['on'].diff().fillna(0)
+ X['diff_off'] = X.groupby('patient_id')['off'].diff().fillna(0)
+
+ X['diff_on_first'] = X['on'] - X.groupby('patient_id')['on'].transform('first')
+ X['diff_off_first'] = X['off'] - X.groupby('patient_id')['off'].transform('first')
+
+ X['mean_on'] = X.groupby('patient_id')['on'].transform('mean')
+ X['mean_off'] = X.groupby('patient_id')['off'].transform('mean')
+
+ X['std_on'] = X.groupby('patient_id')['on'].transform('std').fillna(0)
+ X['std_off'] = X.groupby('patient_id')['off'].transform('std').fillna(0)
+
+ X['time_since_last_visit'] = X.groupby('patient_id')['age'].diff().fillna(0)
+
+ X['ratio_on_off'] = X['on'] / (X['off'] + 1e-6)
+ X['max_off'] = X.groupby('patient_id')['off'].transform('max')
+
+ # il faut surtout capter les flucutations non linéaires autout de 'off'
+
+ X['moyenne_geometriques_off'] = X.groupby('patient_id')['off'].transform('prod')
+ X['moyenne_geometriques_on'] = X.groupby('patient_id')['on'].transform('prod')
+
+ X['relative_diff_off'] = X['diff_off'] / (X['off'] + 1e-6)
+ X['relative_diff_on'] = X['diff_on'] / (X['on'] + 1e-6)
+
+
+ X['diff_off_mean'] = X['off'] - X['mean_off']
+ X['diff_off_max'] = X['off'] - X['max_off']
+
+ # capturer variabilité autour de la moyenne de off
+
+ X['diff_on_mean'] = X['on'] - X['mean_on']
+ X['diff_on_max'] = X['on'] - X['mean_on']
+
+
+
+
+
+
+ X['ratio_visite']=X['num_visite']/X['nb_visites']
+ X['mean_off_prog_interaction']=X['mean_off']*X['ratio_visite']
+
+ X['mean_off_based_on_age']=X.groupby('age')['mean_off'].transform('mean')
+ X['mean_off_based_on_disease_duration']=X.groupby('time_since_diagnosis')['mean_off'].transform('mean')
+
+
+
+
+
+
+
+
+ return X
+
+ def imputer_age_at_diagnosis(self):
+ """
+ Impute les valeurs manquantes de age_at_diagnosis en utilisant une régression linéaire.
+ """
+
+
+ patients_values = self.X.dropna(subset=['age_at_diagnosis']).groupby('patient_id')['age_at_diagnosis'].first().reset_index()
+ patients_values.columns = ['patient_id', 'known_value']
+
+ temp_df = self.X.merge(patients_values, on='patient_id', how='left')
+
+ mask = temp_df['age_at_diagnosis'].isna() & temp_df['known_value'].notna()
+ self.X.loc[mask.values, 'age_at_diagnosis'] = temp_df.loc[mask, 'known_value'].values
+
+ patients_sans_diagnostic = self.X.groupby('patient_id')['age_at_diagnosis'].apply(
+ lambda x: x.isna().all())
+ patients_sans_diagnostic = patients_sans_diagnostic[patients_sans_diagnostic].index.tolist()
+
+ nb_patients_sans_diagnostic = len(patients_sans_diagnostic)
+ total_patients = len(self.X['patient_id'].unique())
+ pourcentage = (nb_patients_sans_diagnostic / total_patients) * 100
+
+
+ if nb_patients_sans_diagnostic > 0:
+ patients_avec_diagnostic = ~self.X['patient_id'].isin(patients_sans_diagnostic)
+ df_known = self.X[patients_avec_diagnostic].dropna(subset=['age_at_diagnosis'])
+ df_known_unique = df_known.drop_duplicates('patient_id')
+
+ features = ['age', 'sexM', 'est_LRRK2+', 'est_GBA+', 'est_OTHER+', 'cohort']
+ X_known = df_known_unique[features]
+ y_known = df_known_unique['age_at_diagnosis']
+
+ X_train, X_test, y_train, y_test = train_test_split(
+ X_known, y_known, test_size=0.2, random_state=42)
+
+ model = LinearRegression()
+ model.fit(X_train, y_train)
+
+ y_pred = model.predict(X_test)
+ mae = mean_absolute_error(y_test, y_pred)
+ r2 = r2_score(y_test, y_pred)
+ print(f"Performance du modèle d'imputation linéaire - MAE: {mae:.2f}, R²: {r2:.2f}")
+
+ df_unknown = self.X[self.X['patient_id'].isin(patients_sans_diagnostic)].drop_duplicates('patient_id')
+ X_unknown = df_unknown[features]
+ predicted_ages = model.predict(X_unknown)
+
+ for i, patient_id in enumerate(df_unknown['patient_id']):
+ self.X.loc[self.X['patient_id'] == patient_id, 'age_at_diagnosis'] = predicted_ages[i]
+
+ missing_pct = self.X['age_at_diagnosis'].isna().mean() * 100
+ print(f"Pourcentage de valeurs manquantes après imputation: {missing_pct:.2f}%")
+ self.X['time_since_diagnosis'] = self.X['age'] - self.X['age_at_diagnosis']
+ print("Variable 'time_since_diagnosis' ajoutée avec succès.")
+
+ return self.X
+
+ def imputer_globale_on_off(self):
+ """
+ Impute les valeurs manquantes de 'on' et 'off' en utilisant un modèle entraîné sur l'ensemble train + test.
+ Met à jour self.X et self.X_test avec les valeurs imputées.
+ """
+ from xgboost import XGBRegressor
+ from sklearn.impute import SimpleImputer
+ from sklearn.ensemble import RandomForestRegressor
+ from sklearn.model_selection import train_test_split
+ from sklearn.metrics import mean_absolute_error
+
+ # Marquer les jeux
+ self.X['dataset'] = 'train'
+ self.X_test['dataset'] = 'test'
+
+ full_data = pd.concat([self.X, self.X_test], ignore_index=True)
+ full_data.reset_index(drop=True, inplace=True)
+
+ print("\n===== IMPUTATION GLOBALE DE 'on' =====")
+ features_on = ['age', 'sexM', 'cohort', 'off', 'age_at_diagnosis',
+ 'est_LRRK2+', 'est_GBA+', 'est_OTHER+']
+ df_known_on = full_data[full_data['on'].notna()].dropna(subset=features_on)
+ df_missing_on = full_data[full_data['on'].isna()].copy()
+
+ model_on = RandomForestRegressor(n_estimators=100, random_state=42)
+ model_on.fit(df_known_on[features_on], df_known_on['on'])
+ full_data.loc[df_missing_on.index, 'on'] = model_on.predict(df_missing_on[features_on])
+ self.model_on = model_on
+
+ print("\n===== IMPUTATION GLOBALE DE 'off' =====")
+ features_off = ['age', 'sexM', 'cohort', 'on', 'age_at_diagnosis',
+ 'est_LRRK2+', 'est_GBA+', 'est_OTHER+']
+ df_known_off = full_data[full_data['off'].notna()].dropna(subset=features_off)
+ df_missing_off = full_data[full_data['off'].isna()].copy()
+
+ model_off = XGBRegressor(n_estimators=500, learning_rate=0.05, max_depth=5,
+ objective='reg:squarederror', random_state=42, verbosity=0)
+ model_off.fit(df_known_off[features_off], df_known_off['off'])
+ full_data.loc[df_missing_off.index, 'off'] = model_off.predict(df_missing_off[features_off])
+ self.model_off = model_off
+
+ # Remettre les données séparées
+ self.X = full_data[full_data['dataset'] == 'train'].drop(columns=['dataset'])
+ self.X_test = full_data[full_data['dataset'] == 'test'].drop(columns=['dataset'])
+
+ print("\n✅ Imputation globale terminée.")
+ print(self.X.isna().sum())
+ return self.X, self.X_test
+ def process_transformation(self):
+
+ X_train_copy=self.X.copy()
+ X_test_copy=self.X_test.copy()
+
+ X_train_copy=self.encoder_cohort(X_train_copy)
+ X_test_copy=self.encoder_cohort(X_test_copy)
+
+ X_train_copy=self.enlever_index(X_train_copy)
+ X_test_copy=self.enlever_index(X_test_copy)
+
+ X_train_copy=self.remplir_gene(X_train_copy)
+ X_test_copy=self.remplir_gene(X_test_copy)
+
+
+ self.X_test=X_test_copy
+ self.X=X_train_copy
+ self.X=self.imputer_age_at_diagnosis()
+ self.imputer_globale_on_off()
+ self.X=self.rajout_feature_temps(self.X)
+ self.X_test=self.rajout_feature_temps(self.X_test,is_test=True)
+
+ self.X=self.virer_patient_et_autre()
+ self.X_test=self.virer_patient_et_autre(is_test=True)
+ def get_data(self):
+ return self.X,self.y,self.X_test
+
+# on va s'assurer que ca impute bien sur x_test
+
+X_train_full = pd.read_csv('data/X_train_6ZIKlTY.csv')
+y_train_full = pd.read_csv('data/y_train_lXj6X5y.csv')['target']
+X_test = pd.read_csv('data/X_test_oiZ2ukx.csv')
+preprocessor=PreprocessData(X_train_full,y_train_full,X_test)
+preprocessor.process_transformation()
+X_train,y_train,X_test=preprocessor.get_data()
+print(X_train.isna().sum().sum())
+print(X_test.isna().sum())
\ No newline at end of file
diff --git a/preprocess/test.py b/preprocess/test.py
new file mode 100644
index 0000000000000000000000000000000000000000..11f8bbf883f0c68c443ff4b30c60818758bf61df
--- /dev/null
+++ b/preprocess/test.py
@@ -0,0 +1,216 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error, r2_score
+from sklearn.ensemble import HistGradientBoostingRegressor
+from sklearn.impute import SimpleImputer
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Import de notre classe de prétraitement
+from preprocess_data import PreprocessData
+
+# Chemins des fichiers
+X_TRAIN_PATH = 'data/X_train_6ZIKlTY.csv'
+Y_TRAIN_PATH = 'data/y_train_lXj6X5y.csv'
+X_TEST_PATH = 'data/X_test_oiZ2ukx.csv'
+
+def main():
+ """
+ Script de test pour valider notre prétraitement et notre modèle
+ en simulant le contexte d'évaluation du challenge
+ """
+ # Chargement des données
+ print("Chargement des données...")
+ X_train_full = pd.read_csv(X_TRAIN_PATH)
+ y_train_full = pd.read_csv(Y_TRAIN_PATH)['target']
+
+ print(f"Dimensions des données originales:")
+ print(f"X_train: {X_train_full.shape}")
+ print(f"y_train: {y_train_full.shape}")
+
+ # Diviser les données pour simuler l'environnement d'évaluation
+ # Nous utilisons une division par patients pour éviter les fuites
+ print("\nDivision des données par patients...")
+
+ # Obtenir la liste unique des patients
+ unique_patients = X_train_full['patient_id'].unique()
+
+ # Diviser les patients en ensembles d'entraînement et de test
+ train_patients, test_patients = train_test_split(
+ unique_patients, test_size=0.2, random_state=42
+ )
+
+ print(f"Nombre de patients dans l'entraînement: {len(train_patients)}")
+ print(f"Nombre de patients dans le test: {len(test_patients)}")
+
+ # Filtrer les données par patients
+ train_mask = X_train_full['patient_id'].isin(train_patients)
+ test_mask = X_train_full['patient_id'].isin(test_patients)
+
+ X_train = X_train_full[train_mask].copy()
+ y_train = y_train_full[train_mask].copy()
+ X_val = X_train_full[test_mask].copy()
+ y_val = y_train_full[test_mask].copy()
+
+ print(f"\nDimensions après division:")
+ print(f"X_train: {X_train.shape}")
+ print(f"y_train: {y_train.shape}")
+ print(f"X_val: {X_val.shape}")
+ print(f"y_val: {y_val.shape}")
+
+ # Prétraitement des données
+ print("\nPrétraitement des données...")
+ preprocessor = PreprocessData(X_train, y_train, X_val, y_val)
+
+ # Prétraiter les données d'entraînement
+ X_train_processed, y_train_processed = preprocessor.process_transformation(is_train=True)
+
+ # Prétraiter les données de validation
+ X_val_processed, y_val_processed = preprocessor.process_transformation(is_train=False)
+
+ # Vérifier s'il reste des valeurs manquantes
+ train_na = X_train_processed.isna().sum().sum()
+ val_na = X_val_processed.isna().sum().sum()
+
+ if train_na > 0:
+ print(f"ATTENTION: {train_na} valeurs manquantes dans les données d'entraînement transformées!")
+ # Utiliser fillna au lieu de SimpleImputer pour préserver les colonnes
+ for col in X_train_processed.columns:
+ if X_train_processed[col].isna().any():
+ X_train_processed[col] = X_train_processed[col].fillna(X_train_processed[col].median())
+
+ if val_na > 0:
+ print(f"ATTENTION: {val_na} valeurs manquantes dans les données de validation transformées!")
+ # Utiliser fillna au lieu de SimpleImputer pour préserver les colonnes
+ for col in X_val_processed.columns:
+ if X_val_processed[col].isna().any():
+ X_val_processed[col] = X_val_processed[col].fillna(X_train_processed[col].median())
+
+ # Vérifier les dimensions après traitement des valeurs manquantes
+ print(f"Dimensions après traitement des valeurs manquantes:")
+ print(f"X_train_processed: {X_train_processed.shape}")
+ print(f"X_val_processed: {X_val_processed.shape}")
+
+ # Entraînement d'un modèle
+ print("\nEntraînement d'un modèle HistGradientBoosting...")
+ model = HistGradientBoostingRegressor(
+ max_iter=200,
+ learning_rate=0.05,
+ max_depth=6,
+ random_state=42
+ )
+
+ model.fit(X_train_processed, y_train_processed)
+
+ # Évaluation sur l'ensemble d'entraînement
+ train_preds = model.predict(X_train_processed)
+ train_rmse = np.sqrt(mean_squared_error(y_train_processed, train_preds))
+ train_r2 = r2_score(y_train_processed, train_preds)
+
+ print(f"Performance sur l'entraînement:")
+ print(f" - RMSE: {train_rmse:.2f}")
+ print(f" - R²: {train_r2:.2f}")
+
+ # Évaluation sur l'ensemble de validation
+ val_preds = model.predict(X_val_processed)
+ val_rmse = np.sqrt(mean_squared_error(y_val_processed, val_preds))
+ val_r2 = r2_score(y_val_processed, val_preds)
+
+ print(f"\nPerformance sur la validation:")
+ print(f" - RMSE: {val_rmse:.2f}")
+ print(f" - R²: {val_r2:.2f}")
+
+ # Calculer l'écart entre train et validation
+ rmse_diff = val_rmse - train_rmse
+ rmse_ratio = val_rmse / train_rmse if train_rmse > 0 else float('inf')
+
+ print(f"\nÉcart de RMSE entre validation et entraînement: {rmse_diff:.2f}")
+ print(f"Ratio RMSE validation/entraînement: {rmse_ratio:.2f}x")
+
+ # Visualisation des prédictions vs réelles
+ plt.figure(figsize=(12, 10))
+
+ # Distribution des valeurs réelles et prédites
+ plt.subplot(2, 2, 1)
+ sns.histplot(y_train_processed, color='blue', label='Train réel', alpha=0.6)
+ sns.histplot(train_preds, color='red', label='Train prédit', alpha=0.6)
+ plt.legend()
+ plt.title('Distribution des valeurs (Train)')
+
+ plt.subplot(2, 2, 2)
+ sns.histplot(y_val_processed, color='blue', label='Validation réel', alpha=0.6)
+ sns.histplot(val_preds, color='red', label='Validation prédit', alpha=0.6)
+ plt.legend()
+ plt.title('Distribution des valeurs (Validation)')
+
+ # Scatter plot réel vs prédit
+ plt.subplot(2, 2, 3)
+ plt.scatter(y_train_processed, train_preds, alpha=0.5)
+ plt.plot([min(y_train_processed), max(y_train_processed)],
+ [min(y_train_processed), max(y_train_processed)], 'r--')
+ plt.xlabel('Valeurs réelles')
+ plt.ylabel('Prédictions')
+ plt.title('Réel vs Prédit (Train)')
+
+ plt.subplot(2, 2, 4)
+ plt.scatter(y_val_processed, val_preds, alpha=0.5)
+ plt.plot([min(y_val_processed), max(y_val_processed)],
+ [min(y_val_processed), max(y_val_processed)], 'r--')
+ plt.xlabel('Valeurs réelles')
+ plt.ylabel('Prédictions')
+ plt.title('Réel vs Prédit (Validation)')
+
+ plt.tight_layout()
+ plt.savefig('predictions_analysis.png')
+ print("Graphique d'analyse des prédictions sauvegardé.")
+ # Analyser la distribution des cibles
+ plt.figure(figsize=(10, 6))
+ sns.histplot(y_train, bins=50)
+ plt.title("Distribution de la variable cible")
+ plt.savefig("target_distribution.png")
+
+ # Entraîner un modèle par quantile
+ from sklearn.ensemble import GradientBoostingRegressor
+ quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
+ quantile_models = {}
+
+ for q in quantiles:
+ model = GradientBoostingRegressor(
+ loss="quantile", alpha=q,
+ n_estimators=200, max_depth=5
+ )
+ model.fit(X_train_processed, y_train_processed)
+ quantile_models[q] = model
+
+ # Analyser les 20 features les plus importantes
+ if hasattr(model, 'feature_importances_'):
+ importance_df = pd.DataFrame({
+ 'Feature': X_train_processed.columns,
+ 'Importance': model.feature_importances_
+ }).sort_values('Importance', ascending=False)
+
+ plt.figure(figsize=(12, 8))
+ sns.barplot(x='Importance', y='Feature', data=importance_df.head(20))
+ plt.title('Top 20 Features les plus importantes')
+ plt.tight_layout()
+ plt.savefig('feature_importance.png')
+ print("Graphique d'importance des features sauvegardé.")
+
+ # Afficher les 10 features les plus importantes
+ print("\nTop 10 features les plus importantes:")
+ for i, (feature, importance) in enumerate(zip(importance_df['Feature'].head(10),
+ importance_df['Importance'].head(10))):
+ print(f"{i+1}. {feature}: {importance:.4f}")
+
+ # Si le ratio d'écart est acceptable, entraîner un modèle final
+ if rmse_ratio < 1.5:
+ print("\nL'écart entre l'entraînement et la validation est acceptable.")
+ print("Le modèle semble généraliser correctement aux nouveaux patients.")
+ else:
+ print("\nATTENTION: L'écart entre l'entraînement et la validation est important.")
+ print("Le modèle pourrait avoir des problèmes de généralisation aux nouveaux patients.")
+ print("Considérez des ajustements au prétraitement ou au modèle.")
+
+if __name__ == "__main__":
+ main()
\ No newline at end of file
diff --git a/preprocess/valeursoff.ipynb b/preprocess/valeursoff.ipynb
index a88f6c0be805d9968778a79528d41d7a8b88e934..b79dc3ac3ca545ef2cca65876a6ac69cfcdcefa9 100644
--- a/preprocess/valeursoff.ipynb
+++ b/preprocess/valeursoff.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 36,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -288,11 +288,42 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "FileNotFoundError",
+ "evalue": "[Errno 2] No such file or directory: 'preprocess/data/X_train_6ZIKlTY.csv'",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m X_train \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mpreprocess/data/X_train_6ZIKlTY.csv\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m y_train \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpreprocess/data/y_train_lXj6X5y.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 3\u001b[0m X_test \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpreprocess/data/X_test_oiZ2ukx.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 1014\u001b[0m dialect,\n\u001b[1;32m 1015\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1022\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 1023\u001b[0m )\n\u001b[1;32m 1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/pandas/io/parsers/readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m 619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m 623\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1617\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/pandas/io/parsers/readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1878\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[1;32m 1879\u001b[0m mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1881\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1882\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1883\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1884\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1885\u001b[0m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1886\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1887\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1888\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1889\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
+ "File \u001b[0;32m~/.pyenv/versions/3.10.12/lib/python3.10/site-packages/pandas/io/common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 869\u001b[0m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[1;32m 870\u001b[0m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[1;32m 871\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[1;32m 872\u001b[0m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[0;32m--> 873\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 874\u001b[0m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 875\u001b[0m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 876\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 877\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 878\u001b[0m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 879\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 880\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 881\u001b[0m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[1;32m 882\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
+ "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'preprocess/data/X_train_6ZIKlTY.csv'"
+ ]
+ }
+ ],
"source": [
- "x_2.groupby()"
+ "\n",
+ "X_train = pd.read_csv('preprocess/data/X_train_6ZIKlTY.csv')\n",
+ "y_train = pd.read_csv('preprocess/data/y_train_lXj6X5y.csv')\n",
+ "X_test = pd.read_csv('preprocess/data/X_test_oiZ2ukx.csv')\n",
+ "preprocessor = PreprocessData(X_train, y_train, X_test)\n",
+ "\n",
+ "# Prétraitement des données d'entraînement\n",
+ "X_train_processed, y_train = preprocessor.process_transformation(is_train=True)\n",
+ "\n",
+ "# Prétraitement des données de test (sans y_test)\n",
+ "X_test_processed, _ = preprocessor.process_transformation(is_train=False)\n",
+ "\n",
+ "# pour le moment on vire off\n",
+ "X_train_processed = X_train_processed.drop(['off','ledd'], axis=1)\n",
+ "X_test_processed = X_test_processed.drop(['off','ledd'], axis=1)\n"
]
}
],