diff --git a/read_cifar.py b/read_cifar.py
index 963000d69a97751b5f45b275935cea06e179440f..b88037c7d4e4e5c90269861522678a45059c02a6 100644
--- a/read_cifar.py
+++ b/read_cifar.py
@@ -9,104 +9,123 @@ from sklearn.neighbors import KNeighborsRegressor
import matplotlib.pyplot as plt
-def unpickle(file):
- import pickle
- with open(file, 'rb') as fo:
- dict = pickle.load(fo, encoding='bytes')
- return dict
-
-def read_cifar_batch(path):
- dictionary = unpickle(path)
- data = np.array(dictionary[b'data'], dtype = np.float32)
- labels = np.array(dictionary[b'labels'], dtype = np.int64)
-
- return data , labels
-
-def read_cifar(path1,path2,path3,path4,path5,path6):
- data , labels = read_cifar_batch(path1)
- dataAux , labelsAux = read_cifar_batch(path2)
- data = np.concatenate((data,dataAux),0)
- labels = np.concatenate((labels,labelsAux))
- dataAux , labelsAux = read_cifar_batch(path3)
- data = np.concatenate((data,dataAux),0)
- labels = np.concatenate((labels,labelsAux))
- dataAux , labelsAux = read_cifar_batch(path4)
- data = np.concatenate((data,dataAux),0)
- labels = np.concatenate((labels,labelsAux))
- dataAux , labelsAux = read_cifar_batch(path5)
- data = np.concatenate((data,dataAux),0)
- labels = np.concatenate((labels,labelsAux))
- dataAux , labelsAux = read_cifar_batch(path6)
- data = np.concatenate((data,dataAux),0)
- labels = np.concatenate((labels,labelsAux))
-
- return data , labels
-
-
-
-def split_dataset(data , labels):
-
- data_train, data_test , labels_train , labels_test = train_test_split(data, labels,shuffle = True ,test_size = 0.1)
-
- return data_train, data_test , labels_train , labels_test
-
-
-def distance_matrix(data_test,data_train):
+#
+# ATTENTION : THIS CODE IS CONCATENATION OF THE CODES read_cifar.py AND knn.py
+#
- dists = np.array([np.sum((data_train-l)**2,axis=1)**.5 for l in data_test])
- return dists
-#receives a 2d array data_train(M,k) and a data_test (N,k),
-#returning a 2d array(N,M) such that dists[i,j] represents
-#the distance between the i-th data_test row and the j-th data_train row
-#in resume, each column represent a distance of a training point to all other
-
-def knn_predict(dists , labels_train , k):
- #classif = np.array(0)
- print(labels_train[:20])
- print(labels_train.size)
- classif = []
-
- for testRows in dists.T:
-
- distances = np.stack((testRows,labels_train),axis = 1)
- distances = distances[distances[:, 0].argsort()]
- #for picturesClasses in distances[:k,1]:
- countArray = [np.count_nonzero(distances[:k,1]==i) for i in range(0,10)]
- classif = np.append(classif,np.argmax(countArray))
-
- classif = np.array(classif , dtype = int)
-
- return classif
-
-def evaluate_knn(data_train,labels_train,data_test,labels_test,k):
-
- classif = np.array(knn_predict(distance_matrix(data_train,data_test) , labels_train , k))
- result = np.array(classif == labels_test)
- acc = np.count_nonzero(result) / np.size(result)
-
- return acc*100
+def unpickle(file):
+ """Use to Unpack the CIFAR10 dataset as a pickle. It returns a dictinary with the dataset and its labels."""
+ import pickle
+ with open(file, "rb") as fo:
+ dict = pickle.load(fo, encoding="bytes")
+ return dict
-datas,labels = read_cifar_batch('data_batch_1')
-print(datas.shape,labels.shape)
-dataTrain,dataTest,labelsTrain,labelsTest = split_dataset(datas,labels)
-print(dataTrain.shape,dataTest.shape,labelsTrain.shape)
-distanceMatrix = distance_matrix(dataTrain,dataTest)
-print(distanceMatrix.shape)
+def read_cifar_batch(path):
+ """Taking as parameter the path of a single batch as a string, and returning:
+ matrix data of size (batch_size x data_size) and a vector labels of size batch_size"""
+ dictionary = unpickle(path)
+ data = np.array(dictionary[b"data"], dtype=np.float32)
+ labels = np.array(dictionary[b"labels"], dtype=np.int64)
+
+ return data, labels
+
+
+def read_cifar(path1, path2, path3, path4, path5, path6):
+ """taking as parameter the path of the directory containing the six batches
+ (five data_batch and one test_batch) as a string, and returning:
+ a matrix data of shape (batch_size x data_size) and a vector labels of size batch_size"""
+ data, labels = read_cifar_batch(path1)
+ dataAux, labelsAux = read_cifar_batch(path2)
+ data = np.concatenate((data, dataAux), 0)
+ labels = np.concatenate((labels, labelsAux))
+ dataAux, labelsAux = read_cifar_batch(path3)
+ data = np.concatenate((data, dataAux), 0)
+ labels = np.concatenate((labels, labelsAux))
+ dataAux, labelsAux = read_cifar_batch(path4)
+ data = np.concatenate((data, dataAux), 0)
+ labels = np.concatenate((labels, labelsAux))
+ dataAux, labelsAux = read_cifar_batch(path5)
+ data = np.concatenate((data, dataAux), 0)
+ labels = np.concatenate((labels, labelsAux))
+ dataAux, labelsAux = read_cifar_batch(path6)
+ data = np.concatenate((data, dataAux), 0)
+ labels = np.concatenate((labels, labelsAux))
+
+ return data, labels
+
+
+def split_dataset(data, labels):
+ """which splits the dataset into a training set and a test set"""
+ data_train, data_test, labels_train, labels_test = train_test_split(
+ data, labels, shuffle=True, test_size=0.1
+ )
+
+ return data_train, data_test, labels_train, labels_test
+
+
+def distance_matrix(data_test, data_train):
+ """Takes the matrix data_test and data_train. It returning a 2d array(N,M) such that dists[i,j] represents
+ the distance between the i-th data_test row and the j-th data_train row
+ """
+ dists = np.array([np.sum((data_train - l) ** 2, axis=1) ** 0.5 for l in data_test])
+
+ return dists
+
+
+def knn_predict(dists, labels_train, k):
+ """Take the matrix of distances dists, the labels for training and k nearest neighbor
+ It returns the classification given by the module KNN.
+ """
+ # classif = np.array(0)
+ print(labels_train[:20])
+ print(labels_train.size)
+ classif = []
+
+ for testRows in dists.T:
+
+ distances = np.stack((testRows, labels_train), axis=1)
+ distances = distances[distances[:, 0].argsort()]
+ # for picturesClasses in distances[:k,1]:
+ countArray = [np.count_nonzero(distances[:k, 1] == i) for i in range(0, 10)]
+ classif = np.append(classif, np.argmax(countArray))
+
+ classif = np.array(classif, dtype=int)
+
+ return classif
+
+
+def evaluate_knn(data_train, labels_train, data_test, labels_test, k):
+ """Receives the datas ans labels for training and teste and k nearest neighbor.
+ It retuns the accuracy of the KNN module"""
+ classif = np.array(
+ knn_predict(distance_matrix(data_train, data_test), labels_train, k)
+ )
+ result = np.array(classif == labels_test)
+ acc = np.count_nonzero(result) / np.size(result)
+
+ return acc * 100
+
+
+datas, labels = read_cifar_batch("data_batch_1")
+dataTrain, dataTest, labelsTrain, labelsTest = split_dataset(datas, labels)
+distanceMatrix = distance_matrix(dataTrain, dataTest)
print()
result = []
-for i in range (1,21):
- result = np.append(result,evaluate_knn(dataTrain,labelsTrain,dataTest,labelsTest,i))
+# Apply various KNN moduli with k ranging from 1 to 20
+for i in range(1, 21):
+ result = np.append(
+ result, evaluate_knn(dataTrain, labelsTrain, dataTest, labelsTest, i)
+ )
x = np.arange(1, 21)
-
-# plotting
+
+# plot the graph of (Accuracy) x k
plt.title("Plot graph")
plt.xlabel("K neighbors")
plt.ylabel("Accuracy %")
-plt.plot(x, result, color ="red")
+plt.plot(x, result, color="red")
plt.show()
-