统计文本中文字(单词)出现的频率

英文

from collections import Counter

with open(textinfo,'rb') as fp:

            data=fp.readlines()   

text=[line.strip().lower() for line in data]





 cnt=Counter()

  for word in text:

       cnt[word]+=1

   cnt=dict(cnt)



    sorted(cnt.items(),key = lambda x:x[1],reverse = True)   #排序

    for key,value in cnt.items():

        print(key+":"+str(value))

 

中文

from collections import Counter

with open(textinfo,'rb') as fp:

            data=fp.read()

 text=unicode(data,"gbk")

        

  cnt=Counter()

   for word in text:

        cnt[word]+=1

    cnt=dict(cnt)



    sorted(cnt.items(),key = lambda x:x[1],reverse = True)   #排序

    for key,value in cnt.items():

        print(key+":"+str(value))