中文词频统计

import jieba
txt = open(‘A.txt‘,‘r‘,encoding=‘utf-8‘).read()#转换成UTF-8编码
words = list(jieba.cut(txt))

exp={}
keys=set(words)

dic={}
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])#输出TOP20的词及出现次数
    
print(list(jieba.cut(txt)))

print(list(jieba.cut_for_search(txt)))

print(list(jieba.cut(txt,cut_all=True)))