8382_Gordiyenko_Alexandr_lb3

8382/Gordiyenko/lb/3/main.py

@@ -0,0 +1,80 @@
+import numpy as np
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.datasets import boston_housing
+import matplotlib.pyplot as plt
+import os
+
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+
+
+def build_model():
+    model = Sequential()
+    model.add(Dense(64, activation='relu', input_shape=(train_data.shape[1],)))
+    model.add(Dense(64, activation='relu'))
+    model.add(Dense(1))
+    model.compile(optimizer='rmsprop', loss='mse', metrics=['mean_absolute_error'])
+    return model
+
+
+(train_data, train_targets), (test_data, test_targets) = boston_housing.load_data()
+
+mean = train_data.mean(axis=0)
+train_data -= mean
+std = train_data.std(axis=0)
+train_data /= std
+
+test_data -= mean
+test_data /= std
+
+
+def learn(num):
+    k = num
+    num_val_samples = len(train_data) // k
+    num_epochs = 20
+    all_scores = []
+
+    mean_loss = []
+    mean_mae = []
+    mean_val_loss = []
+    mean_val_mae = []
+
+    for i in range(k):
+        print('processing fold #', i+1)
+        val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
+        val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]
+        partial_train_data = np.concatenate([train_data[:i * num_val_samples], train_data[(i + 1) * num_val_samples:]],
+                                            axis=0)
+        partial_train_targets = np.concatenate(
+            [train_targets[:i * num_val_samples], train_targets[(i + 1) * num_val_samples:]], axis=0)
+        model = build_model()
+        H = model.fit(partial_train_data, partial_train_targets, epochs=num_epochs, batch_size=1,
+                      validation_data=(val_data, val_targets), verbose=0)
+
+        # print(H.history.keys())
+        mean_val_mae.append(H.history['val_mean_absolute_error'])
+        mean_mae.append(H.history['mean_absolute_error'])
+
+        mean_val_loss.append(H.history['val_loss'])
+        mean_loss.append(H.history['loss'])
+
+    plt.plot(np.mean(mean_mae, axis=0), 'g')
+    plt.plot(np.mean(mean_val_mae, axis=0), 'b')
+    plt.title('Mean model mae for ' + str(val) + ' folds')
+    plt.ylabel('mae')
+    plt.xlabel('Epochs')
+    plt.legend(['Training', 'Validation'], loc='upper left')
+    plt.show()
+
+    plt.plot(np.mean(mean_loss, axis=0), 'g')
+    plt.plot(np.mean(mean_val_loss, axis=0), 'b')
+    plt.title('Mean model loss for ' + str(val) + ' folds')
+    plt.ylabel('loss')
+    plt.xlabel('Epochs')
+    plt.legend(['Training', 'Validation'], loc='upper left')
+    plt.show()
+
+
+if __name__ == '__main__':
+    for val in [2, 4, 6, 8]:
+        learn(val)