中文词频统计

import jieba
s=open(‘xiaoshuo.txt‘,‘r‘,encoding=‘utf-8‘)

#读入待分析的字符串
str=s.read()
s.close()

for i in ‘，。！、   \n “ ” ；‘:
    str=str.replace(i,‘‘)

words=jieba.cut(str)
word=set(words)

#计数字典 
dic={}
for i in word:
    if len(i)>1:
        dic[i]=str.count(i)
str=list(dic.items())

#排序
str.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
    print(str[i])