中文词频统计及词云制作

import jieba
xxx=open("熊出没.txt","r",encoding='utf-8').read()
words=jieba.lcut(xxx)
counts={}
for word in words:
    if len(word)==1:
        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 @ 2017-09-25 18:47  讲道理  阅读(161)  评论(0编辑  收藏  举报