中文词频统计

Posted 2020-10-28 司徒春燕

import jieba

f = open(\'article.txt\',\'r\',encoding=\'utf-8\')
text = f.read()
f.close()
stri = \'\'\'一！“”，。？；’"\',.、：\\n\'\'\'
for s in stri:
    text = text.replace(s,\' \')
wordlist = list(jieba.cut(text))
exclude = {\'你\',\'你们\',\'的\',\'他\',\'了\',\'她\',\'是\',\'在\',\'—\',\'他们\',\'着\',\'把\',\'不\',\'也\',\'我\',\'人\',\'而\',
           \'与\',\'有\',\'可是\',\'自己\',\'就\',\'又\',\'什么\',\'和\',\'一个\',\' \',\'呢\',\'很\',\'象\',\'一点\',\'都\',\'去\',
           \'没有\',\'个\',\'上\',\'给\',\'来\',\'还\',\'到\',\'这\',\'要\',\'不是\',\'得\',\'但是\',\'已经\',\'那么\',\'只\',\'因为\',}
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)
f1 = open(\'articleCount.txt\', \'a\',encoding=\'utf-8\')
for i in  range(20):
    f1.write(str(dictlist[i])+\'\\n\')
    print(dictlist[i])
f1.close()

结果截图：