import tensorflow as tf
imdb = tf.keras.datasets.imdb
(train_data, train_labels),(test_data, test_labels) = imdb.load_data(num_words=10000)
print(train_data[0])
print(train_labels[0])

[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]
1

def get_text(comment_num):
    """將數字形式的評論轉化為文本"""
    # word_index = tf.keras.datasets.imdb.get_word_index()
    word_index = imdb.get_word_index()
    reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
    text = ' '.join([reverse_word_index.get(i - 3, '?') for i in comment_num])
    return text
comment = get_text(train_data[0])
print(comment)

? this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert ? is an amazing actor and now the same being director ?

def vectorize_sequences(sequences, diamension = 10000):
    results = np.zeros((len(sequences), diamension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1
    return results
x_train = vectorize_sequences(train_data)
print(x_train[0])
print(len(x_train[0]))
x_test = vectorize_sequences(test_data)
print(x_test[0])
print(len(x_test[0]))

y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')

model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

output = relu(dot(W, input) + b)

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
history = model.fit(partial_x_train, partial_y_train, epochs= 20, batch_size=512, validation_data=(x_val, y_val))

history_dict = history.history
print(history_dict.keys())

dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])

loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']
epochs = range(1, len(loss_values) + 1)
plt.plot(epochs, loss_values, 'bo', label='Training loss')
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()

plt.clf()
acc = history_dict['accuracy']
val_acc = history_dict['val_accuracy']
plt.plot(epochs, acc, 'bo', label='Training accuracy')
plt.plot(epochs, val_acc, 'b', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

history = model.fit(partial_x_train, partial_y_train, epochs= 4, batch_size=512, validation_data=(x_val, y_val))
results = model.evaluate(x_test, y_test)
print(results)

782/782 [==============================] - 1s 876us/step - loss: 0.3137 - accuracy: 0.8729
[0.3137112557888031, 0.8728799819946289]

result = model.predict(x_test)
print(result)