def create_word_bigram_scores():
posdata = tp.seg_fil_txt("/home/hadoop/goodnew.txt")
negdata = tp.seg_fil_txt("/home/hadoop/badnew.txt")
posWords = list(itertools.chain(*posdata))
negWords = list(itertools.chain(*negdata))
bigram_finderr = BigramCollocationFinder.from_words(posWords)
bigram_finder = BigramCollocationFinder.from_words(negWords)
posBigrams = bigram_finderr.nbest(BigramAssocMeasures.chi_sq,350000)
negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq,350000)
pos = posWords + posBigrams
neg = negWords + negBigrams
word_fd = FreqDist()
cond_word_fd = ConditionalFreqDist()
for word in pos:
word_fd.inc(word)
cond_word_fd['pos'].inc(word)
for word in neg:
word_fd.inc(word)
cond_word_fd['neg'].inc(word)
pos_word_count = cond_word_fd['pos'].N()
neg_word_count = cond_word_fd['neg'].N()
total_word_count = pos_word_count + neg_word_count
word_scores = {}
for word, freq in word_fd.iteritems():
pos_score = BigramAssocMeasures.chi_sq(cond_word_fd['pos'][word], (freq, pos_word_count), total_word_count)
neg_score = BigramAssocMeasures.chi_sq(cond_word_fd['neg'][word], (freq, neg_word_count), total_word_count)
word_scores[word] = pos_score + neg_score
return word_scores
def create_word_scores():
posdata = tp.seg_fil_txt("/home/hadoop/goodnew.txt")
negdata = tp.seg_fil_txt("/home/hadoop/badnew.txt")
posWords = list(itertools.chain(*posdata))
negWords = list(itertools.chain(*negdata))
word_fd = FreqDist()
cond_word_fd = ConditionalFreqDist()
for word in posWords:
word_fd.inc(word)
cond_word_fd['pos'].inc(word)
for word in negWords:
word_fd.inc(word)
cond_word_fd['neg'].inc(word)
pos_word_count = cond_word_fd['pos'].N()
neg_word_count = cond_word_fd['neg'].N()
total_word_count = pos_word_count + neg_word_count
word_scores = {}
for word, freq in word_fd.iteritems():
pos_score = BigramAssocMeasures.chi_sq(cond_word_fd['pos'][word], (freq, pos_word_count), total_word_count)
neg_score = BigramAssocMeasures.chi_sq(cond_word_fd['neg'][word], (freq, neg_word_count), total_word_count)
word_scores[word] = pos_score + neg_score
return word_scores
