电影评论分类--二分类问题

from keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words = 10000)

print(train_data[0])
print(len(train_data[0]))
print(train_data[1])
print(train_labels)

max([max(sequence) for sequence in train_data])

"""将评论解码为英文单词"""

word_index = imdb.get_word_index()
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
decoded_review = ' '.join([reverse_word_index.get(i - 3, '?') for i in train_data[0]])
print(decoded_review)

"""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)

x_train[0]

"""将标签向量化"""

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

"""构建网络"""

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'))

"""编译模型"""

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

"""配置优化器"""

from keras import optimizers

model.compile(optimizers.RMSprop(lr = 0.001), loss = 'binary_crossentropy', metrics = ['accuracy'])

"""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])

"""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:]

"""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))

"""调用model.fit()返回了一个History对象。这个对象有一个成员history，它是一个字典，包含训练过程中的所有数据。"""

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

"""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()

"""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 acuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

"""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)

results

"""使用训练好的网络在新数据上生成预测结果"""

model.predict(x_test)