根据电影评论的 文字内容将其划分为正面或负面。

使用IMDB 数据集，它包含来自互联网电影数据库（IMDB）的50 000 条严重两极分
化的评论。数据集被分为用于训练的25 000 条评论与用于测试的25 000 条评论，训练集和测试
集都包含50% 的正面评论和50% 的负面评论。(only use 10000 recotds because of memory error )

1 加载IMDB 数据集
from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

2 将整数序列编码为二进制矩阵
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
results[i, sequence] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)

模型定义
from keras import models
from keras import layers
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'))

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

5 配置优化器
from keras import optimizers
model.compile(optimizer=optimizers.RMSprop(lr=0.001),
loss='binary_crossentropy',
metrics=['accuracy'])

6使用自定义的损失和指标
from keras import losses
from keras import metrics
model.compile(optimizer=optimizers.RMSprop(lr=0.001),
loss=losses.binary_crossentropy,
metrics=[metrics.binary_accuracy])

7 留出验证集
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]

8　训练模型
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))

9　绘制训练损失和验证损失
import matplotlib.pyplot as plt
history_dict = history.history
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()

10　绘制训练精度和验证精度
plt.clf()
acc = history_dict['acc']
val_acc = history_dict['val_acc']
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

11　从头开始重新训练一个模型
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'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=4, batch_size=512)
results = model.evaluate(x_test, y_test)

12使用训练好的网络在新数据上生成预测结果
训练好网络之后，你希望将其用于实践。你可以用predict 方法来得到评论为正面的可能
性大小。
>>> model.predict(x_test)
array([[ 0.98006207]
[ 0.99758697]
[ 0.99975556]
...,
[ 0.82167041]
[ 0.02885115]
[ 0.65371346]], dtype=float32)