展開全部

import jieba

# 創建停2113用詞52614102list

def stopwordslist(filepath):

stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]

return stopwords

# 對句子進行分詞

def seg_sentence(sentence):

sentence_seged = jieba.cut(sentence.strip())

stopwords = stopwordslist('./test/stopwords.txt') # 這里加載停用詞的路徑

outstr = ''

for word in sentence_seged:

if word not in stopwords:

if word != '\t':

outstr += word

outstr += " "

return outstr

inputs = open('./test/input.txt', 'r', encoding='utf-8')

outputs = open('./test/output.txt', 'w')

for line in inputs:

line_seg = seg_sentence(line) # 這里的返回值是1653字符串

outputs.write(line_seg + '\n')

outputs.close()

inputs.close()

總結

以上是生活随笔為你收集整理的python去除停用词_python jieba分词如何去除停用词的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。