AAAAAAABBgg的博客

import reimport oslist=[',','?','.','?','!','*','(',')','“','”',':','"','`','\''] ##要替换的标点符号做成一个列表with open(r"out1无空行.txt",'r',encoding="utf-8") as f: ##text.txt是用来训练的文本 result = f.read() for i in range(len(lis.

import jieba# 创建停用词列表def stopwordslist(): stopwords = [line.strip() for line in open(r'stopwords.txt',encoding='UTF-8').readlines()] return stopwords#扩展jieba分词词库dict='fencibuchong.txt'jieba.load_userdict(dict)# 对句子进行中文分词def seg_depart(s..