1.1 文本训练实例：embedding_padding_pooling

使用embedding进行文本分类实例demo:

1. 文本数据集：keras.datasets.imdb，电影评论<好/坏>二分类
2. 每个句子都被映射为一组向量(text_ids)，通过设置max_length = 500，对句子进行补全/截断的操作。所以这里的dataset表示为一组向量。
3. 需要查看句子原始含义，需要从词典中，找到对应的text_id--->word。
4. 构建模型：embedding_dim = 16 # 每个word都embedding成长度为16的向量。
5. max_length(一个句子长度) embedding_dim(一个单词长度) max_length * embedding_dim代表一个句子总的长度
   这里的GlobalAveragePooling1D是为了消除max_length...  max_length * embedding_dim------->[................]

代码如下：

import matplotlib.pyplot as plt
import numpy as np
import sklearn
import pandas as pd
import os
import time
import sys
from tensorflow import keras

# 电影评论 <好/坏> - 二分类
imdb = keras.datasets.imdb
# 载入数据使用
vocab_size = 10000
index_from = 3 # 词表的index从几开始算
# 前一万个词语保留下来，后一万个当成特殊字符处理
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words = vocab_size,
                                                                     index_from = index_from)

print(train_data[0], train_labels[0]) # train
print(train_data.shape, train_labels.shape) 
print(len(train_data[0]), len(train_data[1])) # 变长

 

word_index = imdb.get_word_index() # 载入词表
print(len(word_index))
print(word_index)

word_index = {k: (v+3) for k, v in word_index.items()}
word_index['<PAD>'] = 0
word_index['<START>'] = 1
word_index['<UNK>'] = 2
word_index['<END>'] = 3

reverse_word_index = dict([(value, key) for key, value in word_index.items()])

def decode_review(text_ids):
    return ' '.join(
        [reverse_word_index.get(word_id, "<UNK>") for word_id in text_ids]
    )

decode_review(train_data[0])

# 构建模型
embedding_dim = 16 # 每个word都embedding成长度为16的向量
batch_size = 128
# max_length(一个句子长度) embedding_dim(一个单词长度) max_length * embedding_dim代表一个句子总的长度
# 这里的GlobalAveragePooling1D是为了消除max_length...  max_length * embedding_dim------->[................]
model = keras.models.Sequential([
    # 1. define matrix: [vocab_size, embedding_dim]
    # 2. [1,2,3,4...], max_length * embedding_dim
    # 3. batch_size * max_length * embedding_dim
    keras.layers.Embedding(vocab_size, embedding_dim, 
                          input_length = max_length),
    # batch_size * max_length * embedding_dim
    #---> batch_size * embedding_dim
    keras.layers.GlobalAveragePooling1D(), # 消除max_length部分,做一个合并pooling的操作
    keras.layers.Dense(64, activation = 'relu'),
    keras.layers.Dense(1, activation = 'sigmoid'),
])
model.summary()
model.compile(loss = "binary_crossentropy",
             optimizer = "adam",
             metrics =  ['accuracy'])

history = model.fit(train_data, train_labels,
                   epochs = 20,
                   batch_size = batch_size,
                   validation_split = 0.2,)

def plot_learning_curves(history, label, epochs, min_value, max_value):
    data = {}
    data[label] = history.history[label]
    data['val_' + label] = history.history['val_'+ label]
    pd.DataFrame(data).plot(figsize = (8,5))
    plt.grid(True)
    plt.axis([0, epochs, min_value, max_value])
    plt.show()

plot_learning_curves(history, 'accuracy', 20, 0.8, 1.2)
plot_learning_curves(history, 'loss', 20, 0, 1)

model.evaluate(test_data, test_labels,
              batch_size = batch_size)