编写一个词频统计软件，使用jieba库，统计某个文档中出现频率前15的单词。

编写一个词频统计软件，使用jieba库，统计某个文档中出现频率前15的单词。

转载---

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)
        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'/tmp/abc.txt', top_limit=10)
    for k, v in result:
        print k, v

————————————————
版权声明：本文为CSDN博主「blue_lll」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：