python高频词汇表大全_利用python统计word文档高频词汇

#!/usr/bin/env python

# -*- coding: utf-8 -*-

import jieba

import jieba.analyse

import codecs

import re

from collections import Counter

class WordCounter(object):

def count_from_file(self, file, top_limit=0):

with codecs.open(file, ‘r’, ‘utf-8′) as f:

content = f.read()

content = re.sub(r’\s+’, r’ ‘, content)

content = re.sub(r’\.+’, r’ ‘, content)

return self.count_from_str(content, top_limit=top_limit)

def count_from_str(self, content, top_limit=0):

if top_limit <= 0:

top_limit = 100

tags = jieba.analyse.extract_tags(content, topK=100)

words = jieba.cut(content,cut_all=True)    #自行设置jieba的模式

counter = Counter()

for word in words:

if word in tags:

counter[word] += 1

return counter.most_common(top_limit)

if __name__ == ‘__main__’:

counter = WordCounter()

result = counter.count_from_file(r’bj.txt’, top_limit=20)    #文件名bj.txt，选取前20高频词

for k, v in result:

print (k, v)