中文词频统计

import jieba
fo = open(‘傲慢与偏见前十章.txt‘,‘r‘,encoding=‘utf-8‘).read()
words = list(jieba.cut(fo,cut_all=True))

for i in ‘‘‘，。：‘’“”？！\n \u3000\u3000‘‘‘:
    fo = fo.replace(i,‘ ‘)
words = fo.split(‘ ‘)
exp={‘‘,‘噢‘,‘唔‘,‘她说‘,‘啊‘}
dic={}
keys=set(words)-exp
for w in keys:
    dic[w]=words.count(w)

wc = list(dic.items()) 
wc.sort(key= lambda x:x[1],reverse=True)

for i in range(20):
    print(wc[i])