中文词频统计

import jieba

f = open('article.txt','r')
text = f.read()
f.close()
str = '''一！“”，。？；’"',.、：\n'''
for s in str:
    text = text.replace(s,' ')
jieba.add_word('钱先生')
wordlist = list(jieba.cut(text))
exclude = {'说','有','得','没','的','他','了','她','是','在','—','你','走','对','他们','着','把','不','也','我','人','而',
           '与','就','但是','那','要','又','想','和','一个',' ','呢','很','一点','都','去',
           '没有','个','上','给','来','还','到','这','\u3000','点','小','看'}
set = set(wordlist) - exclude
dict = {}
for key in set:
    dict[key]=wordlist.count(key)
dictlist = list(dict.items())
dictlist.sort(key=lambda x: x[1], reverse=True)
for i in range(20):
    print(dictlist[i])

运行结果

('日本', 665)
('本身', 647)
('什么', 608)
('老人', 536)
('瑞宣', 422)
('好', 415)
('知道', 394)
('北平', 350)
('钱', 338)
('起来', 295)
('钱先生', 291)
('里', 291)
('先生', 290)
('并', 286)
('象', 284)
('能', 282)
('似的', 280)
('那么', 279)
('不能', 279)
('会', 267)