jieba 分词 红楼梦相关的分词,出现次数最高的20个

import jieba
text=open('D:/红楼梦/红楼梦.txt',"r",encoding='utf-8').read()
words=jieba.lcut(text)
counts={}
for word in words:
   if len(word)==1:  #排除带个字符的分词效果
      continue
   else:
      counts[word]=counts.get(word,0)+1
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
   word,count=items[i]
   print("{0:<10}{1:>5}".format(word,count))

 

posted @ 2020-11-12 15:20  决战到天亮  阅读(165)  评论(0)    收藏  举报