如何用python和jieba分词，统计词频？

 #! python3

# -*- coding: utf-8 -*-

import os, codecs

import jieba

from collections import Counter

 

def get_words(txt):

    seg_list = jieba.cut(txt)

    c = Counter()

    铅衫让for x in seg_list:

        if len(x)>1 and x != '塌镇\r\n':

            c[x] += 1

    print('常用词频度统计结果')

    for (k,v) in c.most_common(100):

 槐局       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)

def statistics(astr):

# astr.replace("\n", ""做宴渗)

slist = list(astr.split("\t"))

alist = []

[alist.append(i) for i in slist if i not in alist]

alist[-1] = alist[-1].replace("\n", "")

return alist

if __name__ == "__main__":

code_doc = {}

with open("test_data.txt"祥消, "纯脊r", encoding='utf-8') as fs:

for ln in fs.readlines():

l = statistics(ln)

for t in l:

if t not in code_doc:

code_doc.setdefault(t, 1)

else:

code_doc[t] += 1

for keys in code_doc.keys():

print(keys + ' ' + str(code_doc[keys]))

---