# coding:utf_8
import jieba
filePath='source.txt'
fileSegWordDonePath ='sourceSegDone.txt'
f = open(filePath, mode='r',encoding='utf-8')
g = open(fileSegWordDonePath, mode='w',encoding='utf-8')
sentence = f.read()
words = jieba.cut(sentence,cut_all=False)
# print(" ".join(words))#结果是"迭代器"。可以用循环打开,还可以用" “.join()的方式打开
g.write(" ".join(words))
f.close()
g.close()
将语料分词后写入另一个文件
最新推荐文章于 2022-04-26 16:01:07 发布