中文词频统计

import jieba
news=open(‘小说.txt‘,‘r‘,encoding=‘utf-8‘).read()
words=list(jieba.cut(news))
exp={‘人‘,‘的‘,‘但是‘,‘他们‘,‘这个‘,‘一‘,‘已‘,‘啊‘,‘了‘}
dic={}
keys=set(words)-exp
for w in keys:
    if len(w)>1:
       dic[w]=words.count(w)
a=list(dic.items())
a.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
    print(a[i])