python中TFIDF

#!/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:\語料.txt')
  documentList.append('D:\分詞.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]))

為什麼實現不了關鍵詞提取呢？請高手幫忙