Click here to Skip to main content
12,998,483 members (128,103 online)
Rate this:
Please Sign up or sign in to vote.
See more:
import sys, math, re
from operator import itemgetter
import math
#reading from test file
wF = open (r'C:\Craig\Data2\craiglist-file1.txt')
wordFile =
wordList = wordFile.upper()
wordList = wordFile.split()
#Reading from the keyword file
kWF = open('keywords.txt','r')
keywordFile =
KeywordList = keywordFile.upper()
keywordList = keywordFile.split()
word = 'k'
document = 'wordlist'
wordlist = 'w'

#total number of times terms occurs in file
def countTerm(word, document):
for k in keywordList:
    countTerm = 0
    for w in wordList:
        if k == w:
            countTerm = countTerm + 1
        if k == "the":
           print k, w, countTerm
    print k, countTerm

#total number of word in document
def wordfreq(wordList):
wordfreq = [wordList.count(p) for p in wordList]
dictionary = dict(zip(wordList, wordfreq))
count2 = 0
for t in wordList:
print 'total number of words', count2

#total number of file being processed
def docfreq(k, wF):
    count = 0
    for wordList in wF:
        if countTerm(k, w) > 0:
            count += 1
    return count
print countTerm
#docfreq = [wordList.count(z) for z in wF]
#dictionary = dict(zip(wF, docfreq))
#count3 = 1
#for j in wF:
    #count3 +=1
#print 'total number of document', count3
for n in range(0,len(keywordList)):
    print keywordList[n] wordfreq[n]/count2


# term frequency
# total number of times terms occurs in file / total number of word in document
#inverse document frequency
Posted 10-Dec-10 6:37am
Updated 10-Dec-10 6:46am
HimanshuJoshi 10-Dec-10 12:46pm
Added pre blocks.
HimanshuJoshi 10-Dec-10 12:46pm
So what seems to be the problem?
Dave Kreskowiak 10-Dec-10 13:40pm
Soooooooooooooooooooo...... did you have a question or did you just want to post a meaningless code snippet for everyone to completely ignore?
Keith Barrow 12-Dec-10 7:15am
Nice code. What is the problem?
caisar oentoro 6-Dec-13 4:01am
Well, no explanation about your code?

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

  Print Answers RSS
Top Experts
Last 24hrsThis month

Advertise | Privacy | Mobile
Web01 | 2.8.170622.1 | Last Updated 10 Dec 2010
Copyright © CodeProject, 1999-2017
All Rights Reserved. Terms of Service
Layout: fixed | fluid

CodeProject, 503-250 Ferrand Drive Toronto Ontario, M3C 3G8 Canada +1 416-849-8900 x 100