NLP: Count frequent words in a file

mf_500_Bag_of_Words.py

#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")
                                             for word in line.split())

for word in words_gen:
    words[word] = words.get(word, 0) + 1
   
top_words = sorted(words.iteritems(), key=itemgetter(1), reverse=True)[:N]

for word, frequency in top_words:
  print "%s %d" % (word, frequency)