one line per epoch + independent models

cnn.py

@@ -7,7 +7,7 @@ from sklearn.metrics import confusion_matrix
 import numpy as np
 from sklearn.model_selection import train_test_split
 from imblearn.over_sampling import SMOTE
-from sklearn.model_selection import KFold
+from sklearn.model_selection import StratifiedKFold
 from tensorflow.keras.utils import to_categorical
 
 
@@ -21,12 +21,13 @@ def run_nn(input_, output_, n_experiences, params):
     c, b, e = params
 
 
-	#kfold validation
-	""""
+    # kfold validation
+    """
     X for the input and y for the output
     """
 
-	kfold = KFold(N_SPLITS, True, 1) #on definit la methode a utiliser en choisisant n_splits, shuffle on/off, random_state
+    skf = StratifiedKFold(N_SPLITS)
+    #kfold = KFold(N_SPLITS, True, 1) #on definit la methode a utiliser en choisisant n_splits, shuffle on/off, random_state
 
     X_train_kfold = []
     X_test_kfold = []
@@ -35,7 +36,8 @@ def run_nn(input_, output_, n_experiences, params):
 
     #split the input data into k sets
 
-	for train_index, test_index in kfold.split(input_):
+    #for train_index, test_index in kfold.split(input_):
+    for train_index, test_index in skf.split(input_, output_):
         X_train_kfold.append(input_[train_index])
         X_test_kfold.append(input_[test_index])
         y_train_kfold.append(output_[train_index])
@@ -53,7 +55,7 @@ def run_nn(input_, output_, n_experiences, params):
     y_validation = [[0]*(N_SPLITS-1) for i in range(N_SPLITS)]
     y_train = [[0]*(N_SPLITS-1) for i in range(N_SPLITS)]
 
-	len_validation = int(len(X_train_kfold[0])/4)
+    len_validation = int(len(X_train_kfold[0])/(N_SPLITS))
 
     for i in range(N_SPLITS):
         idx = 0
@@ -88,10 +90,6 @@ def run_nn(input_, output_, n_experiences, params):
             X_train[i][j] = X_train[i][j].astype('float32')
             X_validation[i][j] = X_validation[i][j].astype('float32')
 
-	# defining keras model
-	model = m.model_architecture(c)
-	#compile the keras model
-	model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
 
     #self reminder : warning! be careful not to use i and j as indexes later in here for something else
 
@@ -104,9 +102,11 @@ def run_nn(input_, output_, n_experiences, params):
 
     for i in range(N_SPLITS):
         for j in range(N_SPLITS-1):
-	    #train the model
-	        model.fit(X_train[i][j], train_Y_one_hot[i][j], batch_size = bs, epochs = ep, verbose = 1, validation_data = (X_validation[i][j], validation_Y_one_hot[i][j]))
-
+            #defining keras  model
+            model = m.model_architecture(c)
+            #compile the keras model
+            model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
+            model.fit(X_train[i][j], train_Y_one_hot[i][j], batch_size = bs, epochs = ep, verbose = 2, validation_data = (X_validation[i][j], validation_Y_one_hot[i][j]))
             #calculate accuracy
             _,accuracy = model.evaluate(X_validation[i][j], validation_Y_one_hot[i][j], verbose = 0)
             total_acc += accuracy
@@ -122,7 +122,7 @@ def run_nn(input_, output_, n_experiences, params):
 
 
     total_acc = total_acc/(N_SPLITS*(N_SPLITS-1))
-	total_auc = total_acc/(N_SPLITS*(N_SPLITS-1))
+    total_auc = total_auc/(N_SPLITS*(N_SPLITS-1))
     print("Average accuracy: ", total_acc)
     print("Average area under the curve: ", total_auc)
 
@@ -149,12 +149,6 @@ def run_kfold(X_train, X_test, y_train, y_test, params):
         X_train[i] = X_train[i].astype('float32')
         X_test[i] = X_test[i].astype('float32')
 
-	# defining keras model
-	model = m.model_architecture(c)
-	#compile the keras model
-	model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
-
-
     total_acc = 0
     total_auc = 0
     precs_k = [] 	#it will contain the average pr curve for each class
@@ -164,6 +158,9 @@ def run_kfold(X_train, X_test, y_train, y_test, params):
 
 
     for i in range(N_SPLITS):
+        model = m.model_architecture(c)
+        #compile the keras model
+        model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
         #train the model
         model.fit(X_train[i], y_train[i], batch_size = bs, epochs = ep, verbose = 1, validation_data = (X_test[i], y_test[i]))