SentiWordLex.py

from __future__ import division
import sys
import time

import nltk
from nltk.corpus import movie_reviews
from nltk.corpus import sentiwordnet as swn
from nltk.corpus import wordnet as wn

start_time = time.time()
count = 0.00
correct = 0.00
ids = sorted(movie_reviews.fileids())

for reviews in ids:     #For every review
    score = 0.0
    positive = 0.0
    negative = 0.0
    tokens = nltk.pos_tag(nltk.word_tokenize(movie_reviews.raw(fileids=[reviews])))     #Tokenize all words with POS
    for token in tokens:
        if (token[1]== "JJ" or token[1] == "JJR" or token[1] == "JJS"):         # If adjective, check value
            if len(wn.synsets(token[0], pos=wn.ADJ)) != 0 and swn.senti_synset(wn.synsets(token[0], pos=wn.ADJ)[0].name()) :
                word = wn.synsets(token[0], pos=wn.ADJ)[0].name()
                print word
                print swn.senti_synset(word)
                positive = positive + swn.senti_synset(word).pos_score()
                negative = negative + swn.senti_synset(word).neg_score()
                print "%s, %d, %d" %(word,positive,negative)
    score = positive - negative
    if (score < 0):
        print "Negative at %f" % (score)
        sentiment = 'neg'
    else:
        sentiment = 'pos'
        print "Positive at %d" % (score)
    if (sentiment == movie_reviews.categories(fileids=[reviews])[0]):
        print "Correct"
        correct = correct + 1.00
    count = count + 1.00

print correct/count
print "Seconds: %d" %(time.time() - start_time)
print "correct:", correct/len(ids)
print "positive:", positive/len(ids)