新闻分类——多分类模型（78%精度版）

本程序使用路透社数据集，一个简单的、广泛使用的文本分类数据集

# coding=UTF-8
import numpy as np
from keras.datasets import reuters
from keras import models
from keras import layers
from matplotlib import pyplot as plt
import os

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

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

# one-hot 编码
def to_one_hot(labels, dimension=46):
    results = np.zeros((len(labels), dimension))
    for i, label in enumerate(labels):
        results[i, label] = 1
    return results


def MulticlassClassification():
    # 准备数据集
    (train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)
    x_train = vectorize_sequences(train_data)
    x_test = vectorize_sequences(test_data)
    y_train = to_one_hot(train_labels)
    y_test = to_one_hot(test_labels)

    # 构建网络
    model = models.Sequential()
    model.add(layers.Dense(64, activation='relu', input_shape=(10000,)))
    model.add(layers.Dense(64, activation='relu'))
    model.add(layers.Dense(46, activation='softmax'))

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

    # 训练模型
    x_val = x_train[:1000]
    partial_x_train = x_train[1000:]
    y_val = y_train[:1000]
    partial_y_train = y_train[1000:]
    history = model.fit(partial_x_train, partial_y_train, epochs=9, batch_size=512, validation_data=(x_val, y_val))

    # 模型评估
    results = model.evaluate(x_test, y_test)
    print(results)
    history_dict = history.history
    acc = history_dict['accuracy']
    val_acc = history_dict['val_accuracy']

    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__':
    MulticlassClassification()