diff --git a/preprocess/__pycache__/preprocess4.cpython-310.pyc b/preprocess/__pycache__/preprocess4.cpython-310.pyc
index 23bcd7bad89c160503474ec19b0f7b2749e102af..b6a7cb001a2fe8ebb2b767265c01b7938ada5423 100644
Binary files a/preprocess/__pycache__/preprocess4.cpython-310.pyc and b/preprocess/__pycache__/preprocess4.cpython-310.pyc differ
diff --git a/preprocess/prediction_on.ipynb b/preprocess/prediction_on.ipynb
index 99c13c03f7da97f25216c158f812239adc3f8a7c..028cda3f3e6d78dd462bb22303b66108b091f7de 100644
--- a/preprocess/prediction_on.ipynb
+++ b/preprocess/prediction_on.ipynb
@@ -4046,7 +4046,6 @@
"for metric_name, metric_value in metrics.items():\n",
" print(f\"{metric_name}: {metric_value:.4f}\")\n",
"\n",
- "# 1. Graphique des valeurs prédites vs réelles (jeu de test)\n",
"plt.figure(figsize=(10, 6))\n",
"plt.scatter(y_test, y_pred_test, alpha=0.5)\n",
"plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')\n",
@@ -4056,7 +4055,6 @@
"plt.grid(True)\n",
"plt.show()\n",
"\n",
- "# 2. Histogramme 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",
@@ -4067,7 +4065,6 @@
"plt.grid(True)\n",
"plt.show()\n",
"\n",
- "# 3. Graphique des résidus vs valeurs prédites\n",
"plt.figure(figsize=(10, 6))\n",
"plt.scatter(y_pred_test, residuals_test, alpha=0.5)\n",
"plt.axhline(y=0, color='r', linestyle='--')\n",
@@ -4077,14 +4074,12 @@
"plt.grid(True)\n",
"plt.show()\n",
"\n",
- "# 4. Visualisation de l'importance des features\n",
"plt.figure(figsize=(12, 8))\n",
"xgb.plot_importance(model, importance_type='weight', max_num_features=20)\n",
"plt.title('Importance des features')\n",
"plt.tight_layout()\n",
"plt.show()\n",
"\n",
- "# 5. Graphique des valeurs prédites et réelles dans l'ordre des indices\n",
"plt.figure(figsize=(12, 6))\n",
"plt.plot(y_test.reset_index(drop=True), 'b-', label='Valeurs réelles')\n",
"plt.plot(y_pred_test, 'r-', label='Valeurs prédites')\n",
@@ -4095,7 +4090,6 @@
"plt.grid(True)\n",
"plt.show()\n",
"\n",
- "# 6. Courbe d'apprentissage si disponible\n",
"if hasattr(model, 'evals_result'):\n",
" results = model.evals_result()\n",
" if results:\n",
diff --git a/preprocess/preprocess4.py b/preprocess/preprocess4.py
index ddd88f693cb6c2b41acb9efb57fa4763fc9c3d8a..623ab72186b78e0c6bf8f96f453dc8664089d963 100644
--- a/preprocess/preprocess4.py
+++ b/preprocess/preprocess4.py
@@ -15,15 +15,21 @@ class PreprocessData:
self.y = path_y
+
+
+
+ def process_transformation(self):
self.enlever_index()
self.remplir_gene()
- #self.virer_patient()
+
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)
@@ -37,7 +43,6 @@ class PreprocessData:
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)
- self.X.drop('patient_id',axis=1,inplace=True)
return self.X
@@ -76,8 +81,10 @@ class PreprocessData:
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(self):
+ 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):
@@ -97,19 +104,19 @@ class PreprocessData:
# 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()
+ #self.X['diff_off'] = self.X.groupby('patient_id')['off'].diff()
# 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')
+ #self.X['diff_off_first'] = self.X.groupby('patient_id')['off'].transform('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')
+ #self.X['mean_off'] = self.X.groupby('patient_id')['off'].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')
+ #self.X['std_off'] = self.X.groupby('patient_id')['off'].transform('std')
# rajouter le temps depuis la dernière visite
self.X['time_since_last_visit'] = self.X.groupby('patient_id')['age'].diff()
@@ -170,4 +177,35 @@ class PreprocessData:
print("Variable 'disease_duration' ajoutée avec succès.")
return self.X
-
\ No newline at end of file
+ def imputer_valeurs_on(self):
+ """
+ Impute les valeurs manquantes de on en utilisant une régression linéaire.
+ """
+ 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
+
+
+
+
+