gupul2k

#Script tags POS and NER[Named Entity Recognition] for a supplied text file.
#Date: Nov 2 2012
#Author: Hota Sobhan

import nltk

f = open('C:\Python27\Test_File.txt')
data = f.readlines()

#Parse the text file for NER with POS Tagging

gupul2k

#Author: Sobhan Hota
#Date: Oct 20 2012
#Script can run to generate vector for bigram collected in Source File 
#captures the count from the supplied input file (if present), then divide by
#input file document length.


import itertools
from collections import Counter

gupul2k

#Author: Sobhan Hota
#Finds most frequent 500 words in a given file

from string import punctuation
from operator import itemgetter

N = 500
words = {}

words_gen = (word.strip(punctuation).lower() for line in open("C:\Python27\Corpus.txt")