朴素贝叶斯算法——实现新闻分类(Sklearn实现)

2018-08-05 07:51:27来源:博客园 阅读 ()

新老客户大回馈,云服务器低至5折

1、朴素贝叶斯实现新闻分类的步骤

(1)提供文本文件,即数据集下载

(2)准备数据

         将数据集划分为训练集和测试集;使用jieba模块进行分词,词频统计,停用词过滤,文本特征提取,将文本数据向量化

         停用词文本stopwords_cn.txt下载

         jieba模块学习:https://github.com/fxsjy/jieba ;    https://www.oschina.net/p/jieba

(3)分析数据:使用matplotlib模块分析

(4)训练算法:使用sklearn.naive_bayes 的MultinomialNB进行训练

         Sklearn构建朴素贝叶斯分类器官方文档学习

         在scikit-learn中,一共有3个朴素贝叶斯的分类算法类。分别是GaussianNB,MultinomialNB和BernoulliNB。

        其中GaussianNB就是先验为高斯分布的朴素贝叶斯,MultinomialNB就是先验为多项式分布的朴素贝叶斯,而BernoulliNB就是先验为伯努利分布的朴素贝叶斯。

(5)测试算法:使用测试集对贝叶斯分类器进行测试

 2、代码实现

# -*- coding: UTF-8 -*-
import os
import random
import jieba
from sklearn.naive_bayes import MultinomialNB
import matplotlib.pyplot as plt
 
"""
函数说明:中文文本处理
Parameters:
    folder_path - 文本存放的路径
    test_size - 测试集占比,默认占所有数据集的百分之20
Returns:
    all_words_list - 按词频降序排序的训练集列表
    train_data_list - 训练集列表
    test_data_list - 测试集列表
    train_class_list - 训练集标签列表
    test_class_list - 测试集标签列表
"""
def TextProcessing(folder_path, test_size=0.2):
    folder_list = os.listdir(folder_path)  # 查看folder_path下的文件
    data_list = []  # 数据集数据
    class_list = []  # 数据集类别
    # 遍历每个子文件夹
    for folder in folder_list:
        new_folder_path = os.path.join(folder_path, folder)  # 根据子文件夹,生成新的路径
        files = os.listdir(new_folder_path)  # 存放子文件夹下的txt文件的列表
        j = 1
        # 遍历每个txt文件
        for file in files:
            if j > 100:  # 每类txt样本数最多100个
                break
            with open(os.path.join(new_folder_path, file), 'r', encoding='utf-8') as f:  # 打开txt文件
                raw = f.read()
 
            word_cut = jieba.cut(raw, cut_all=False)  # 精简模式,返回一个可迭代的generator
            word_list = list(word_cut)  # generator转换为list
 
            data_list.append(word_list)  # 添加数据集数据
            class_list.append(folder)  # 添加数据集类别
            j += 1
    data_class_list = list(zip(data_list, class_list))  # zip压缩合并,将数据与标签对应压缩
    random.shuffle(data_class_list)  # 将data_class_list乱序
    index = int(len(data_class_list) * test_size) + 1  # 训练集和测试集切分的索引值
    train_list = data_class_list[index:]  # 训练集
    test_list = data_class_list[:index]  # 测试集
    train_data_list, train_class_list = zip(*train_list)  # 训练集解压缩
    test_data_list, test_class_list = zip(*test_list)  # 测试集解压缩
 
    all_words_dict = {}  # 统计训练集词频
    for word_list in train_data_list:
        for word in word_list:
            if word in all_words_dict.keys():
                all_words_dict[word] += 1
            else:
                all_words_dict[word] = 1
 
    # 根据键的值倒序排序
    all_words_tuple_list = sorted(all_words_dict.items(), key=lambda f: f[1], reverse=True)
    all_words_list, all_words_nums = zip(*all_words_tuple_list)  # 解压缩
    all_words_list = list(all_words_list)  # 转换成列表
    return all_words_list, train_data_list, test_data_list, train_class_list, test_class_list
 
 
"""
函数说明:读取文件里的内容,并去重
Parameters:
    words_file - 文件路径
Returns:
    words_set - 读取的内容的set集合
"""
def MakeWordsSet(words_file):
    words_set = set()  # 创建set集合
    with open(words_file, 'r', encoding='utf-8') as f:  # 打开文件
        for line in f.readlines():  # 一行一行读取
            word = line.strip()  # 去回车
            if len(word) > 0:  # 有文本,则添加到words_set中
                words_set.add(word)
    return words_set  # 返回处理结果
 
 
"""
函数说明:文本特征选取
Parameters:
    all_words_list - 训练集所有文本列表
    deleteN - 删除词频最高的deleteN个词
    stopwords_set - 指定的结束语
Returns:
    feature_words - 特征集
"""
def words_dict(all_words_list, deleteN, stopwords_set=set()):
    feature_words = []  # 特征列表
    n = 1
    for t in range(deleteN, len(all_words_list), 1):
        if n > 1000:  # feature_words的维度为1000
            break
            # 如果这个词不是数字,并且不是指定的结束语,并且单词长度大于1小于5,那么这个词就可以作为特征词
        if not all_words_list[t].isdigit() and all_words_list[t] not in stopwords_set and 1 < len(all_words_list[t]) < 5:
            feature_words.append(all_words_list[t])
        n += 1
    return feature_words
 
 
"""
函数说明:根据feature_words将文本向量化
Parameters:
    train_data_list - 训练集
    test_data_list - 测试集
    feature_words - 特征集
Returns:
    train_feature_list - 训练集向量化列表
    test_feature_list - 测试集向量化列表
"""
def TextFeatures(train_data_list, test_data_list, feature_words):
    def text_features(text, feature_words):  # 出现在特征集中,则置1
        text_words = set(text)
        features = [1 if word in text_words else 0 for word in feature_words]
        return features
 
    train_feature_list = [text_features(text, feature_words) for text in train_data_list]
    test_feature_list = [text_features(text, feature_words) for text in test_data_list]
    return train_feature_list, test_feature_list  # 返回结果
 
 
"""
函数说明:新闻分类器
Parameters:
    train_feature_list - 训练集向量化的特征文本
    test_feature_list - 测试集向量化的特征文本
    train_class_list - 训练集分类标签
    test_class_list - 测试集分类标签
Returns:
    test_accuracy - 分类器精度
"""
def TextClassifier(train_feature_list, test_feature_list, train_class_list, test_class_list):
    classifier = MultinomialNB().fit(train_feature_list, train_class_list)
    test_accuracy = classifier.score(test_feature_list, test_class_list)
    return test_accuracy
 
 
if __name__ == '__main__':
    # 文本预处理
    folder_path = './SogouC/Sample'  # 训练集存放地址
    all_words_list, train_data_list, test_data_list, train_class_list, test_class_list = TextProcessing(folder_path,test_size=0.2)
    # 生成stopwords_set
    stopwords_file = './stopwords_cn.txt'
    stopwords_set = MakeWordsSet(stopwords_file)
 
    test_accuracy_list = []
    """
    deleteNs = range(0, 1000, 20)  # 0 20 40 60 ... 980
    for deleteN in deleteNs:
        feature_words = words_dict(all_words_list, deleteN, stopwords_set)
        train_feature_list, test_feature_list = TextFeatures(train_data_list, test_data_list, feature_words)
        test_accuracy = TextClassifier(train_feature_list, test_feature_list, train_class_list, test_class_list)
        test_accuracy_list.append(test_accuracy)
    plt.figure()
    plt.plot(deleteNs, test_accuracy_list)
    plt.title('Relationship of deleteNs and test_accuracy')
    plt.xlabel('deleteNs')
    plt.ylabel('test_accuracy')
    plt.show()
    """
    feature_words = words_dict(all_words_list, 450, stopwords_set)
    train_feature_list, test_feature_list = TextFeatures(train_data_list, test_data_list, feature_words)
    test_accuracy = TextClassifier(train_feature_list, test_feature_list, train_class_list, test_class_list)
    test_accuracy_list.append(test_accuracy)
    ave = lambda c: sum(c) / len(c)
    print(ave(test_accuracy_list))

  结果为:

 

标签:

版权申明:本站文章部分自网络,如有侵权,请联系:west999com@outlook.com
特别注意:本站所有转载文章言论不代表本站观点,本站所提供的摄影照片,插画,设计作品,如需使用,请与原作者联系,版权归原作者所有

上一篇:Python实现DDOS攻击,下个黑客就是你!

下一篇:[python爬虫]Requests-BeautifulSoup-Re库方案--Requests库介绍