Python列表里面两两比较的案例，不包括本身也不重复

最新推荐文章于 2023-02-09 00:00:49 发布

萧鼎

最新推荐文章于 2023-02-09 00:00:49 发布

阅读量950

点赞数 1

分类专栏：笔记文章标签： python 自然语言处理开发语言

本文链接：https://blog.csdn.net/liaoqingjian/article/details/125358715

版权

笔记专栏收录该内容

101 篇文章 9 订阅

订阅专栏

使用itertools库，使用itertools.combinations方法两两组合放一起

import itertools
 a=list(itertools.combinations(k, 2))

import itertools
import os
filePath = 'txt'
for i,j,k in os.walk(filePath):
        a=list(itertools.combinations(k, 2))
        print(a)
        print(a[0][1])

在这里插入图片描述

# -*- codeing = utf-8 -*-
# @time : 2022/6/19 14:39
# @Author : PXY
# @File : Jacc_sim.py
# @Software: PyCharm

# -*- coding: utf-8 -*-

# 正则包
import re
# 自然语言处理包
import jieba
import jieba.analyse
# html 包
import html
import os
import itertools

class JaccardSimilarity(object):
    """
    jaccard相似度
    """
    def __init__(self, content_x1, content_y2):
        self.s1 = content_x1
        self.s2 = content_y2

    @staticmethod
    def extract_keyword(content):  # 提取关键词
        # 正则过滤 html 标签
        re_exp = re.compile(r'(<style>.*?</style>)|(<[^>]+>)', re.S)
        content = re_exp.sub(' ', content)
        # html 转义符实体化
        content = html.unescape(content)
        # 切割
        seg = [i for i in jieba.cut(content, cut_all=True) if i != '']
        # 提取关键词
        keywords = jieba.analyse.extract_tags("|".join(seg), topK=200, withWeight=False)
        return keywords

    def main(self):
        # 去除停用词
        jieba.analyse.set_stop_words('.\\hit_stopwords.txt')

        # 分词与关键词提取
        keywords_x = self.extract_keyword(self.s1)
        keywords_y = self.extract_keyword(self.s2)

        # jaccard相似度计算
        intersection = len(list(set(keywords_x).intersection(set(keywords_y))))
        union = len(list(set(keywords_x).union(set(keywords_y))))
        # 除零处理
        sim = float(intersection)/union if union != 0 else 0
        return sim


# 测试
if __name__ == '__main__':
    filePath='txt'
    for i, j, k in os.walk(filePath):
        a=list(itertools.combinations(k, 2))
        for d in range(0,len(a)):
            with open('.\\txt\\{}'.format(a[d][0]), encoding='UTF8', mode='r') as x, open('.\\txt\\{}'.format(a[d][1]),encoding='UTF8', mode='r') as y:
                content_x = x.read()
                content_y = y.read()
                similarity = JaccardSimilarity(content_x, content_y)
                similarity = similarity.main()
                h='相似度: %.2f%%' % (similarity*100)
                with open("结果.txt","a", encoding='UTF8') as t:
                    t.write(h+"\n")
                print(h)