python中TFIDF

最新推荐文章于 2023-10-30 21:39:36 发布

转载最新推荐文章于 2023-10-30 21:39:36 发布 · 97 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/ilxx1988/archive/2011/11/06/2238619.html

文章标签：

#python

#!/usr/bin/env python

import math
from operator import itemgetter

def freq(word, document):
open (r'd:\fenci.txt')
return document.split(None).count(word)

def wordCount(document):
open (r'd:\fenci.txt')
return len(document.split(None))

def numDocsContaining(word,documentList):
count = 0
for document in documentList:
if freq(word,document) > 0:
count += 1
return count

def tf(word, document):
open (r'd:\fenci.txt')
return (freq(word,document) / float(wordCount(document)))

def idf(word, documentList):
open (r'd:\fenci.txt')
return math.log(len(documentList) / numDocsContaining(word,documentList))

def tfidf(word, document, documentList):
open (r'd:\fenci.txt')
return (tf(word,document) * idf(word,documentList))

if __name__ == '__main__':
documentList = []
documentList.append('d:\语料.txt')
documentList.append('D:\分词.txt')
words = {}
documentNumber=0
for word in documentList[documentNumber].split(None):
words[word] = tfidf(word,documentList[documentNumber],documentList)
for item in sorted(words.items(), key=itemgetter(1), reverse=True):
print( "%f <= %s" % (item[1], item[0]))

为什么实现不了关键词提取呢？请高手帮忙

转载于:https://www.cnblogs.com/ilxx1988/archive/2011/11/06/2238619.html