电影评论分类模型（88%精度版）

本程序使用了IMDB数据集，包含来自互联网电影数据库的50000条两极分化严重的评论。

# coding: utf-8
import numpy as np
from keras.datasets import imdb
from keras import models
from keras import layers
import os

from matplotlib import pyplot as plt

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'


# 数据向量化——one-hot编码
def vectorize_sequences(sequences, dimension=10000):
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1
    return results


def Classification():
    # 准备数据
    # 保留训练数据常出现的前10000个单词
    (train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
    # 数据向量化
    x_train = vectorize_sequences(train_data)
    x_test = vectorize_sequences(test_data)
    # 标签向量化
    y_train = np.asarray(train_labels).astype('float32')
    y_test = np.asarray(test_labels).astype('float32')

    # 构建网络
    model = models.Sequential()
    # 10000个二维向量
    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
    # 优化器、损失函数、指标
    model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

    # 训练模型
    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=4, batch_size=512, validation_data=(x_val, y_val))

    # 模型评估
    history_dict = history.history
    # print(history_dict.keys())
    acc = history_dict['accuracy']
    val_acc = history_dict['val_accuracy']

    results = model.evaluate(x_test, y_test)
    print(results)

    # pre = model.predict(x_test)
    # print(pre)

    epochs = range(1, len(acc) + 1)

    # 表示蓝色圆点
    plt.plot(epochs, acc, 'bo', label='Training acc')

    # 表示蓝色实线
    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()


if __name__ == '__main__':
    Classification()