中文词频统计

Posted 2020-10-09 yushanshan

import jieba
#打开文件，转换成UTF-8编码
fo=open(r\'C:\\Users\\Shaheen\\AppData\\Local\\Programs\\Python\\Python36\\西游记.txt\',\'r\',encoding=\'utf-8\')
a=fo.read()
fo.close()
#断词
words=list(jieba.cut(a))

s=set(words)

dic={}
#排除一些无意义词、合并同一词。
for i in s:
    if(i==" "):
        continue
    if(i==""):
        continue
    if len(i)==1:
        continue
    else:
        dic[i]=words.count(i)
lis=list(dic.items())
lis.sort(key=lambda x:x[1],reverse=True)
#输出TOP20的词及出现次数
for i in range(20):
    print(lis[i])