《python深度学习》——新闻类别多分类问题

jyupter notebook内编写

"""路透社数据集：
   包含许多短新闻及其对应的主题，包含46个不同的主题，每个主题都至少含有10个样本
   但标签、多分类问题：每个数据点只能划分到一个类别"""
from tensorflow.python.keras.datasets import reuters


(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)

print(len(train_data), len(test_data)) # 8982个训练样本， 2246个测试数# 据
print('\n')
print(train_data[10])

print(train_labels[10]) # 标签是0~45内的整数，即话题索引号

"""编码数据"""
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) # 将训练数据向量化
x_test = vectorize_sequences(test_data) # 将测试数据向量化

"""编码标签，将标签向量化（one-hot）"""
# keras中的one-hot编码以及配置好了
from tensorflow.python.keras.utils import to_categorical


one_hot_train_labels = to_categorical(train_labels)
one_hot_test_labels = to_categorical(test_labels)

"""构建网络"""
from tensorflow.python.keras import models
from tensorflow.python.keras import layers

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'))

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

"""验证方法
   训练数据中留出1000个样本"""
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))
# 从第8伦开始过拟合

print(history.history.keys())

"""绘制训练损失和验证损失"""
import matplotlib.pyplot as plt


loss = history.history['loss']
val_loss = history.history['val_loss']

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

plt.plot(epochs, loss, 'ro', label='Training loss')
plt.plot(epochs, val_loss, 'r', label='Validation loss')
plt.title('Training and Validation loss')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.legend()
plt.show()

"""绘制训练和验证精度"""
import matplotlib.pyplot as plt


acc = history.history['acc']
val_acc = history.history['val_acc']

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

plt.plot(epochs, acc, 'ro', label='Training accuracy')
plt.plot(epochs, val_acc, 'r', label='Validation accuracy')
plt.title('Training and Validation accuracy')
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()

"""发现网络在第8伦之后过拟合，故将训练次数改为8"""
import matplotlib.pyplot as plt


# ---------------------------训练网络-------------------------
history = model.fit(partial_x_train,
                    partial_y_train,
                    epochs=8,
                    batch_size=512,
                    validation_data=(x_val, y_val))

# -----------------------输出history的形式---------------------
print(history.history.keys())

# ------------------------绘制图像----------------------------
loss = history.history['loss']
val_loss = history.history['val_loss']

acc = history.history['acc']
val_acc = history.history['val_acc']

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

plt.plot(epochs, loss, 'ro', label='Training loss')
plt.plot(epochs, val_loss, 'r', label='Validation loss')
plt.title('Training and Validation loss')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.legend()
plt.show()

plt.plot(epochs, acc, 'ro', label='Training accuracy')
plt.plot(epochs, val_acc, 'r', label='Validation accuracy')
plt.title('Training and Validation accuracy')
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.legend()
plt.show()

"""新数据上生成预测结果"""
predictions = model.predict(x_test)

print(predictions[0].shape) # 每个元素长度46
print(np.sum(predictions[0])) # 每个向量元素和1
print(np.argmax(predictions[0])) # 概率最大的为类别