Upload New File

Deep_Learning_Resultats_matchs.py

+import numpy as np
+from keras.models import Sequential
+from keras.layers import Dense
+from keras.callbacks import EarlyStopping
+
+##Create a new model
+predictors=np.array(X_train)
+target=np.array(y_train)
+n=len(predictors[0])
+model = Sequential()
+
+#adding layers
+model.add(Dense(180,activation='relu',input_shape=(n,)))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+model.add(Dense(180,activation='relu'))
+
+#output layer
+model.add(Dense(3,activation="softmax"))
+
+#compiling
+model.compile(optimizer="adam",loss="categorical_crossentropy",metrics=['accuracy'])
+
+#fiting
+
+early_stopping_monitor = EarlyStopping(patience=3)
+
+model.fit(predictors,target,epochs=100,validation_split=0.3,callbacks=[early_stopping_monitor])
+
+## Score
+import sklearn.metrics
+
+y_predicted=model.predict(X_test)
+y_predicted_maxs=np.max(y_predicted,axis=1)
+
+y_predicted_bool=np.zeros(y_test.shape)
+y_predicted_bool[:,0]=(y_predicted_maxs==y_predicted[:,0])
+y_predicted_bool[:,1]=(y_predicted_maxs==y_predicted[:,1])
+y_predicted_bool[:,2]=(y_predicted_maxs==y_predicted[:,2])
+print(accuracy_score(y_test,y_predicted_bool))
+
+## Saving the model
+model.save("c:/Users/Antoine Rollet/Documents/Midas_indecis-2.1.h5")
+
+##Loading a model
+from keras.models import load_model
+
+my_model=load_model("c:/Users/Antoine Rollet/Documents/Midas-1.1.h5")
\ No newline at end of file