cblexicon.py

import math
import nltk
from nltk.corpus import wordnet as wn
from nltk.corpus import brown as sc
from collections import Counter
from sets import Set

class cblexicon:

    def genSets(self):
        f = open('words.txt', 'r+')
        content = f.readlines()
        positive = Set([])
        negative = Set([])

        for pair in content:
            current = pair.split(' ')
            if (current[1][0] == 'p'):
                positive.add(current[0])
            elif (current[1][0] == 'n'):
                negative.add(current[0])

        print len(positive)
        print len(negative)

cblexicon().genSets()