python使用jieba实现中文文档分词和去停用词

 1 import jieba
 2 
 3 # 创建停用词列表
 4 def stopwordslist():
 5     stopwords = [line.strip() for line in open(‘chinsesstoptxt.txt‘,encoding=‘UTF-8‘).readlines()]
 6     return stopwords
 7 
 8 # 对句子进行中文分词
 9 def seg_depart(sentence):
10     # 对文档中的每一行进行中文分词
11     print("正在分词")
12     sentence_depart = jieba.cut(sentence.strip())
13     # 创建一个停用词列表
14     stopwords = stopwordslist()
15     # 输出结果为outstr
16     outstr = ‘‘
17     # 去停用词
18     for word in sentence_depart:
19         if word not in stopwords:
20             if word != ‘\t‘:
21                 outstr += word
22                 outstr += " "
23     return outstr
24 
25 # 给出文档路径
26 filename = "Init.txt"
27 outfilename = "out.txt"
28 inputs = open(filename, ‘r‘, encoding=‘UTF-8‘)
29 outputs = open(outfilename, ‘w‘, encoding=‘UTF-8‘)
30 
31 # 将输出结果写入ou.txt中
32 for line in inputs:
33     line_seg = seg_depart(line)
34     outputs.write(line_seg + ‘\n‘)
35     print("-------------------正在分词和去停用词-----------")
36 outputs.close()
37 inputs.close()
38 print("删除停用词和分词成功！！！")