如何用python和jieba分词,统计词频?
发布网友
发布时间：2022-04-24 02:35
共2个回答
热心网友
时间：2022-04-18 04:11
#! python3
# -*- coding: utf-8 -*-
import os, codecs
import jieba
from collections import Counter
def get_words(txt):
seg_list = jieba.cut(txt)
c = Counter()
for x in seg_list:
if len(x)>1 and x != '\r\n':
c[x] += 1
print('常用词频度统计结果')
for (k,v) in c.most_common(100):
print('%s%s %s %d' % (' '*(5-len(k)), k, '*'*int(v/3), v))
if __name__ == '__main__':
with codecs.open('19d.txt', 'r', 'utf8') as f:
txt = f.read()
get_words(txt)
热心网友
时间：2022-04-18 05:29
https://github.com/williezh/
