中文詞頻統計

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('錢先生')
wordlist = list(jieba.cut(text))
exclude = {'說','有','得','沒','的','他','了','她','是','在','—','你','走','對','他們','着','把','不','也','我','人','而',
           '與','就','但是','那','要','又','想','和','一個',' ','呢','很','一點','都','去',
           '沒有','個','上','給','來','還','到','這','\u3000','點','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])

運行結果

('日本', 665)
('本身', 647)
('什麼', 608)
('老人', 536)
('瑞宣', 422)
('好', 415)
('知道', 394)
('北平', 350)
('錢', 338)
('起來', 295)
('錢先生', 291)
('裏', 291)
('先生', 290)
('並', 286)
('象', 284)
('能', 282)
('似的', 280)
('那麼', 279)
('不能', 279)
('會', 267)