nltk基本 

from nltk.corpus import PlaintextCorpusReader
import nltk

corpus_root=r"C:\Users\sun\AppData\Roaming\nltk_data\corpora\jieba"
file_pattern=r".*/.*\.txt"
ptb=PlaintextCorpusReader(corpus_root,file_pattern)
ptb.fileids()
text=ptb.words("jieba3.txt")
print(text)

 

posted @ 2017-12-06 15:20  不可叽叽歪歪  阅读(171)  评论(0)  编辑  收藏  举报