https://github.com/dingtom/python/blob/master/nlp%E6%95%B0%E6%8D%AE%E9%9B%86%E6%8E%A2%E7%B4%A2.ipynb

中文数据集：THUCNews

下载后共有四个文件：cnews.train、cnews.test、cnews.val、cnews.vocab分别为训练集，测试集，验证集和所有数据集中汇集成的词典。cnews.vocab的每一行表示一个词。

该数据下载后包含train和test两个文件夹和三个文件，其中test文件夹中的两个文件夹pos和neg分别为1.25W个代表积极和消极态度的训练样本。而train中的三个文件夹pos、neg、unsup分别为1.25W代表积极和消极态度的训练样本以及5W个未标记的样本。未标记样本可以用来作无监督学习时使用。

imdb数据集

import keras
import tensorflow as tf

from keras.datasets import imdb
(x_train,y_train),(x_test,y_test)=imdb.load_data()

print(x_train.shape)  # (25000,)
print(y_train.shape)  # (25000,)
print(len(x_train[0]))  # 218
print(len(x_train[1]))  # 189
# 查看第一个样本。影评文本已转换为整数，其中每个整数都表示字典中的一个特定字词。
# 查看第一条和第二条影评中的字词数。影评的长度可能会有所不同，由于神经网络的输入必须具有相同长度，因此需要解决此问题。
# print(y_train[0].shape)  # ()
# print(y_train[0])  # 1

将整数转换回字词

# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()
 
# The first indices are reserved
word_index = {k:(v+3) for k,v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
 
def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])
decode_review(train_data[0])

Tokenizer将影评文字转换成数字特征
当我们创建了一个Tokenizer对象后，使用该对象的fit_on_texts()函数，可以将输入的文本中的每个词编号，编号是根据词频的，词频越大，编号越小。它是以空格去识别每个词。

#英文文本不用切词，因为默认会将空格将词切开，所以如果是中文文本的话，就需要切词，且每个词用空格隔开
from keras.preprocessing.text import Tokenizer 
tokenizer =Tokenizer（num_words=2000）#建立一个2000个单词的字典
tokenizer.fit_on texts（train_texts）

去除该文本中的停用词

维度填充
每个句子的长度都固定为256，如果长度大于256，则将超过的部分截掉；如果小于256，则在最前面用0填充。每个句子如下：

x_train = keras.preprocessing.sequence.pad_sequences(x_train,
                                                        value=word_index["<PAD>"],
                                                        padding='post',
                                                        maxlen=256)
 
x_test = keras.preprocessing.sequence.pad_sequences(x_test,
                                                       value=word_index["<PAD>"],
                                                       padding='post',
                                                       maxlen=256)
print(len(train_data[0]), len(train_data[1]))

划分训练集测试集

from sklearn.model_selection import train_test_split
# 训练数据0.2作为验证集
X_train, X_val, Y_train, Y_val = train_test_split(x_train,y_train, test_size = 0.4, random_state = 0)

每个影评样本应该是以一个矩阵，每一行代表一个词，因此，需要将词编码转换成词向量。需要声明一点的是Embedding层是作为模型的第一层

构建模型

# 网络

# input shape is the vocabulary count used for the movie reviews (10,000 words)
vocab_size = 88588
model = keras.Sequential()

# Embedding 层：在整数编码的词汇表中查找每个字词-索引的嵌入向量。模型在接受训练时会学习这些向量。
# 这些向量会向输出数组添加一个维度。生成的维度为：(batch, sequence, embedding)。
model.add(keras.layers.Embedding(vocab_size, 16))

# GlobalAveragePooling1D 层通过对序列维度求平均值，针对每个样本返回一个长度固定的输出向量。这样，
# 模型便能够以尽可能简单的方式处理各种长度的输入。
model.add(keras.layers.GlobalAveragePooling1D())

model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))

model.summary() #查看网络信息

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding_5 (Embedding)      (None, None, 16)          1417408   
_________________________________________________________________
global_average_pooling1d_5 ( (None, 16)                0         
_________________________________________________________________
dense_7 (Dense)              (None, 16)                272       
_________________________________________________________________
dense_8 (Dense)              (None, 1)                 17        
=================================================================
Total params: 1,417,697
Trainable params: 1,417,697
Non-trainable params: 0
_________________________________________________________________

# 损失函数和优化器
# binary_crossentropy 更适合处理概率问题，它可测量概率分布之间的“差距”，
# 在本例中则为实际分布和预测之间的“差距”。
model.compile(optimizer=tf.train.AdamOptimizer(),loss='binary_crossentropy', metrics=['accuracy'])

# 训练模型
history = model.fit(X_train,
                    Y_train,
                    epochs=40,
                    batch_size=512,
                    validation_data=(X_val, Y_val),
                    verbose=1)

# 评估模型
# 模型会返回两个值：损失（表示误差的数字，越低越好）和准确率
results = model.evaluate(x_test, y_test)
print(results)

# 可视化指标
# model.fit() 返回一个 History 对象，该对象包含一个字典，其中包括训练期间发生的所有情况。
history_dict = history.history
history_dict.keys()

dict_keys(['val_loss', 'val_acc', 'loss', 'acc'])

# 训练集与验证集损失可视化
import matplotlib.pyplot as plt

acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
 
epochs = range(1, len(acc) + 1)
 
# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
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()

# 训练集与验证集准确率可视化
plt.clf()   # clear figure
acc_values = history_dict['acc']
val_acc_values = history_dict['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('Accuracy')
plt.legend()
 
plt.show()

THUCNews

本数据集是清华NLP组提供的THUCNews新闻文本分类数据集的一个子集（原始的数据集大约74万篇文档，训练起来需要花较长的时间）。

本次训练使用了其中的10个分类（体育, 财经, 房产, 家居, 教育, 科技, 时尚, 时政, 游戏, 娱乐），每个分类6500条，总共65000条新闻数据。

数据集划分如下：

cnews.train.txt: 训练集(50000条)

cnews.val.txt: 验证集(5000条)

cnews.test.txt: 测试集(10000条)

# coding: utf-8
 
import sys
from collections import Counter
import numpy as np
import tensorflow.contrib.keras as kr
 
if sys.version_info[0] > 2:
    is_py3 = True
else:
    reload(sys)
    sys.setdefaultencoding("utf-8")
    is_py3 = False
 
 
def native_word(word, encoding='utf-8'):
    """如果在python2下面使用python3训练的模型，可考虑调用此函数转化一下字符编码"""
    if not is_py3:
        return word.encode(encoding)
    else:
        return word
 
 
def native_content(content):
    if not is_py3:
        return content.decode('utf-8')
    else:
        return content
 
 
def open_file(filename, mode='r'):
    """
    常用文件操作，可在python2和python3间切换.
    mode: 'r' or 'w' for read or write
    """
    if is_py3:
        return open(filename, mode, encoding='utf-8', errors='ignore')
    else:
        return open(filename, mode)
 
 
def read_file(filename):
    """读取文件数据"""
    contents, labels = [], []
    with open_file(filename) as f:
        for line in f:
            try:
                label, content = line.strip().split('\t')
                if content:
                    contents.append(list(native_content(content)))
                    labels.append(native_content(label))
            except:
                pass
    return contents, labels
 
def build_vocab(train_dir, vocab_dir, vocab_size=5000):
    """根据训练集构建词汇表，存储"""
    data_train, _ = read_file(train_dir)
 
    all_data = []
    for content in data_train:
        # 使用extend的时候，是将content看作一个序列，将这个序列和all_data序列合并，并放在其后面。
        all_data.extend(content)
        
    counter = Counter(all_data)
    count_pairs = counter.most_common(vocab_size - 1)
    words, _ = list(zip(*count_pairs))
    # 添加一个 <PAD> 来将所有文本pad为同一长度
    words = ['<PAD>'] + list(words)
    open_file(vocab_dir, mode='w').write('\n'.join(words) + '\n')
 
 
def read_vocab(vocab_dir):
    """读取词汇表"""
    # words = open_file(vocab_dir).read().strip().split('\n')
    with open_file(vocab_dir) as fp:
        # 如果是py2 则每个值都转化为unicode
        words = [native_content(_.strip()) for _ in fp.readlines()]
    word_to_id = dict(zip(words, range(len(words))))
    return words, word_to_id
 
def read_category():
    """读取分类目录，固定"""
    categories = ['体育', '财经', '房产', '家居', '教育', '科技', '时尚', '时政', '游戏', '娱乐']
 
    categories = [native_content(x) for x in categories]
 
    cat_to_id = dict(zip(categories, range(len(categories))))
 
    return categories, cat_to_id
 
def to_words(content, words):
    """将id表示的内容转换为文字"""
    return ''.join(words[x] for x in content)
 
def process_file(filename, word_to_id, cat_to_id, max_length=600):
    """将文件转换为id表示"""
    contents, labels = read_file(filename)
 
    data_id, label_id = [], []
    for i in range(len(contents)):
        data_id.append([word_to_id[x] for x in contents[i] if x in word_to_id])
        label_id.append(cat_to_id[labels[i]])
 
    # 使用keras提供的pad_sequences来将文本pad为固定长度
    x_pad = kr.preprocessing.sequence.pad_sequences(data_id, max_length)
    y_pad = kr.utils.to_categorical(label_id, num_classes=len(cat_to_id))  # 将标签转换为one-hot表示
 
    return x_pad, y_pad
 
def batch_iter(x, y, batch_size=64):
    """生成批次数据"""
    data_len = len(x)
    num_batch = int((data_len - 1) / batch_size) + 1
 
    indices = np.random.permutation(np.arange(data_len))
    x_shuffle = x[indices]
    y_shuffle = y[indices]
 
    for i in range(num_batch):
        start_id = i * batch_size
        end_id = min((i + 1) * batch_size, data_len)
        yield x_shuffle[start_id:end_id], y_shuffle[start_id:end_id]

搭建CNN模型

# coding: utf-8
# 模型代码 
import tensorflow as tf
 
 
class TCNNConfig(object):
    """CNN配置参数"""
 
    embedding_dim = 64  # 词向量维度
    seq_length = 600  # 序列长度
    num_classes = 10  # 类别数
    num_filters = 256  # 卷积核数目
    kernel_size = 5  # 卷积核尺寸
    vocab_size = 5000  # 词汇表达小
 
    hidden_dim = 128  # 全连接层神经元
 
    dropout_keep_prob = 0.5  # dropout保留比例
    learning_rate = 1e-3  # 学习率
 
    batch_size = 64  # 每批训练大小
    num_epochs = 10  # 总迭代轮次
 
    print_per_batch = 100  # 每多少轮输出一次结果
    save_per_batch = 10  # 每多少轮存入tensorboard
 
 
class TextCNN(object):
    """文本分类，CNN模型"""
 
    def __init__(self, config):
        self.config = config
 
        # 三个待输入的数据
        self.input_x = tf.placeholder(tf.int32, [None, self.config.seq_length], name='input_x')
        self.input_y = tf.placeholder(tf.float32, [None, self.config.num_classes], name='input_y')
        self.keep_prob = tf.placeholder(tf.float32, name='keep_prob')
 
        self.cnn()
 
    def cnn(self):
        """CNN模型"""
        # 词向量映射
        with tf.device('/cpu:0'):
            embedding = tf.get_variable('embedding', [self.config.vocab_size, self.config.embedding_dim])
            embedding_inputs = tf.nn.embedding_lookup(embedding, self.input_x)
 
        with tf.name_scope("cnn"):
            # CNN layer
            conv = tf.layers.conv1d(embedding_inputs, self.config.num_filters, self.config.kernel_size, name='conv')
            # global max pooling layer
            gmp = tf.reduce_max(conv, reduction_indices=[1], name='gmp')
 
        with tf.name_scope("score"):
            # 全连接层，后面接dropout以及relu激活
            fc = tf.layers.dense(gmp, self.config.hidden_dim, name='fc1')
            fc = tf.contrib.layers.dropout(fc, self.keep_prob)
            fc = tf.nn.relu(fc)
 
            # 分类器
            self.logits = tf.layers.dense(fc, self.config.num_classes, name='fc2')
            self.y_pred_cls = tf.argmax(tf.nn.softmax(self.logits), 1)  # 预测类别
 
        with tf.name_scope("optimize"):
            # 损失函数，交叉熵
            cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.input_y)
            self.loss = tf.reduce_mean(cross_entropy)
            # 优化器
            self.optim = tf.train.AdamOptimizer(learning_rate=self.config.learning_rate).minimize(self.loss)
 
        with tf.name_scope("accuracy"):
            # 准确率
            correct_pred = tf.equal(tf.argmax(self.input_y, 1), self.y_pred_cls)
            self.acc = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# -*- coding: utf-8 -*-
 
from __future__ import print_function
 
import os
import sys
import time
from datetime import timedelta
 
import numpy as np
import tensorflow as tf
from sklearn import metrics
 
# from cnn_model import TCNNConfig, TextCNN
# from preprocess import read_vocab, read_category, batch_iter, process_file, build_vocab
 
base_dir = 'M:\BaiduNetdiskDownload\cnews'
train_dir = os.path.join(base_dir, 'cnews.train.txt')
test_dir = os.path.join(base_dir, 'cnews.test.txt')
val_dir = os.path.join(base_dir, 'cnews.val.txt')
vocab_dir = os.path.join(base_dir, 'cnews.vocab.txt')
 
save_dir = 'checkpoints/textcnn'
save_path = os.path.join(save_dir, 'best_validation')  # 最佳验证结果保存路径
 
def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))
 
def feed_data(x_batch, y_batch, keep_prob):
    feed_dict = {
        model.input_x: x_batch,
        model.input_y: y_batch,
        model.keep_prob: keep_prob
    }
    return feed_dict
 
def evaluate(sess, x_, y_):
    """评估在某一数据上的准确率和损失"""
    data_len = len(x_)
    batch_eval = batch_iter(x_, y_, 128)
    total_loss = 0.0
    total_acc = 0.0
    for x_batch, y_batch in batch_eval:
        batch_len = len(x_batch)
        feed_dict = feed_data(x_batch, y_batch, 1.0)
        loss, acc = sess.run([model.loss, model.acc], feed_dict=feed_dict)
        total_loss += loss * batch_len
        total_acc += acc * batch_len
 
    return total_loss / data_len, total_acc / data_len
 
def train():
    print("Configuring TensorBoard and Saver...")
    # 配置 Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖
    tensorboard_dir = 'tensorboard/textcnn'
    if not os.path.exists(tensorboard_dir):
        os.makedirs(tensorboard_dir)
 
    tf.summary.scalar("loss", model.loss)
    tf.summary.scalar("accuracy", model.acc)
    merged_summary = tf.summary.merge_all()
    writer = tf.summary.FileWriter(tensorboard_dir)
 
    # 配置 Saver
    saver = tf.train.Saver()
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)
 
    print("Loading training and validation data...")
    # 载入训练集与验证集
    start_time = time.time()
    x_train, y_train = process_file(train_dir, word_to_id, cat_to_id, config.seq_length)
    x_val, y_val = process_file(val_dir, word_to_id, cat_to_id, config.seq_length)
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)
 
    # 创建session
    session = tf.Session()
    session.run(tf.global_variables_initializer())
    writer.add_graph(session.graph)
 
    print('Training and evaluating...')
    start_time = time.time()
    total_batch = 0  # 总批次
    best_acc_val = 0.0  # 最佳验证集准确率
    last_improved = 0  # 记录上一次提升批次
    require_improvement = 1000  # 如果超过1000轮未提升，提前结束训练
 
    flag = False
    for epoch in range(config.num_epochs):
        print('Epoch:', epoch + 1)
        batch_train = batch_iter(x_train, y_train, config.batch_size)
        for x_batch, y_batch in batch_train:
            feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob)
 
            if total_batch % config.save_per_batch == 0:
                # 每多少轮次将训练结果写入tensorboard scalar
                s = session.run(merged_summary, feed_dict=feed_dict)
                writer.add_summary(s, total_batch)
 
            if total_batch % config.print_per_batch == 0:
                # 每多少轮次输出在训练集和验证集上的性能
                feed_dict[model.keep_prob] = 1.0
                loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict)
                loss_val, acc_val = evaluate(session, x_val, y_val)  # todo
 
                if acc_val > best_acc_val:
                    # 保存最好结果
                    best_acc_val = acc_val
                    last_improved = total_batch
                    saver.save(sess=session, save_path=save_path)
                    improved_str = '*'
                else:
                    improved_str = ''
 
                time_dif = get_time_dif(start_time)
                msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' \
                      + ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}'
                print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str))
 
            session.run(model.optim, feed_dict=feed_dict)  # 运行优化
            total_batch += 1
 
            if total_batch - last_improved > require_improvement:
                # 验证集正确率长期不提升，提前结束训练
                print("No optimization for a long time, auto-stopping...")
                flag = True
                break  # 跳出循环
        if flag:  # 同上
            break
 
 
def test():
    print("Loading test data...")
    start_time = time.time()
    x_test, y_test = process_file(test_dir, word_to_id, cat_to_id, config.seq_length)
 
    session = tf.Session()
    session.run(tf.global_variables_initializer())
    saver = tf.train.Saver()
    saver.restore(sess=session, save_path=save_path)  # 读取保存的模型
 
    print('Testing...')
    loss_test, acc_test = evaluate(session, x_test, y_test)
    msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}'
    print(msg.format(loss_test, acc_test))
 
    batch_size = 128
    data_len = len(x_test)
    num_batch = int((data_len - 1) / batch_size) + 1
 
    y_test_cls = np.argmax(y_test, 1)
    y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32)  # 保存预测结果
    for i in range(num_batch):  # 逐批次处理
        start_id = i * batch_size
        end_id = min((i + 1) * batch_size, data_len)
        feed_dict = {
            model.input_x: x_test[start_id:end_id],
            model.keep_prob: 1.0
        }
        y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, feed_dict=feed_dict)
 
    # 评估
    print("Precision, Recall and F1-Score...")
    print(metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories))
 
    # 混淆矩阵
    print("Confusion Matrix...")
    cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
    print(cm)
 
    time_dif = get_time_dif(start_time)
    print("Time usage:", time_dif)
 
 
if __name__ == '__main__':
    if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
        pass
        # raise ValueError("""usage: python run_cnn.py [train / test]""")
 
    print('Configuring CNN model...')
    config = TCNNConfig()
    if not os.path.exists(vocab_dir):  # 如果不存在词汇表，重建
        build_vocab(train_dir, vocab_dir, config.vocab_size)
    categories, cat_to_id = read_category()
    words, word_to_id = read_vocab(vocab_dir)
    config.vocab_size = len(words)
    model = TextCNN(config)
    train()
    
#     if sys.argv[1] == 'train':
#         train()
#     else:
#         test()

参考：
https://blog.csdn.net/SMith7412/article/details/88087819
https://blog.csdn.net/yyy430/article/details/88072490