concordance for a few terms in zoolander. just for fun

concordance.py

#!/usr/bin/python
import nltk
import string

f = open('zoolander.txt','r').read()

# favorite way to strip punctuation, found on stackoverflow
# http://stackoverflow.com/questions/265960
# it helped the concordance results a little bit but this might
# not be the best approach.  
# concordance is sensitive to punctuation in tokens, i dont want it
# for my sample output.
# i'd like feedback on this
f = f.translate(string.maketrans("",""), string.punctuation)

# create an nltk text object
foo=nltk.Text(f.split())

# terms to run concordance against.  tried a few funny
# terms from the movie
terms = ['mugatu','hot','good','model',
          'stupid','freak','coal','work','derek',
          'hansel','read','kill','underwear']

# loop through the terms, print header row, the output, and 
# a blank line

for term in terms:
  print "concordance for %s....." % (term)
  foo.concordance(term)
  print