中文词频统计

Posted 2020-10-28 157 符致伟

import jieba

news = open(\'bignews.txt\',\'r\').read() 

news_cut = jieba.lcut(news)

dict = {}

for i in set(news_cut):
    dict[i]=news_cut.count(i)
    delete={\'的\',\'和\',\'了\',\'在\',\'为\',\'是\',\'为\',\'我\', \' \',\'-\',\'\\n\',\'，\',\'。\',\'？\',\'！\',\'“\',\'”\',\'：\',\'；\',\'、\',\'.\',\'‘\',\'’\'}

for i in delete:
    if i in dict:
        del dict[i]

nesw_print = sorted(dict.items(), key = lambda d:d[1], reverse = True)

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