深度学习(python)-Keras-3 新闻分类：多分类问题

使用Python的Keras库来学习深度学习中的多分类问题 ------ 路透社新闻主题分类。
路透社数据集是一个简单的、广泛的使用的文本分类数据集，它包括46个不同的主题。

将评论解码为英文单词

用下面的代码解析第一条train_data[0]中的新闻

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

print(decoded_newswire)

训练网络

from keras.datasets import reuters
import numpy as np
from keras import models
from keras import layers
import matplotlib.pyplot as plt

#加载路透社数据集
(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)

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

#将数据向量化
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)

#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

#将标签向量化
one_hot_train_labels = to_one_hot(train_labels)
one_hot_test_labels = to_one_hot(test_labels)

#模型定义
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'])

#留出验证集
x_val = x_train[:1000]
partial_x_train = x_train[1000:]
y_val = one_hot_train_labels[:1000]
partial_y_train = one_hot_train_labels[1000:]

#训练模型
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))

#绘制训练损失和验证损失
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(loss) + 1)
plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, '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.history['acc']
val_acc = history.history['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('Loss')
plt.legend()
plt.show()