extractFeatures.py 文件源码

def create_word_scores(posWords,negWords,posTag,negTag):
    from nltk.probability import FreqDist, ConditionalFreqDist
    import itertools 
    posWords = list(itertools.chain(*posWords)) #????????????
    negWords = list(itertools.chain(*negWords)) #??

    word_fd = FreqDist() #?????????
    cond_word_fd = ConditionalFreqDist() #????????????????????
    for word in posWords:
        #help(FreqDist)
        word_fd[word] += 1#word_fd.inc(word)
        cond_word_fd[posTag][word]+= 1#cond_word_fd['pos'].inc(word)
    for word in negWords:
        word_fd[word] += 1#word_fd.inc(word)
        cond_word_fd[negTag][word]+= 1#cond_word_fd['neg'].inc(word)

    pos_word_count = cond_word_fd[posTag].N() #??????
    neg_word_count = cond_word_fd[negTag].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[posTag][word], (freq, pos_word_count), total_word_count) #????????????????????????????
        neg_score = BigramAssocMeasures.chi_sq(cond_word_fd[negTag][word], (freq, neg_word_count), total_word_count) #??
        word_scores[word] = pos_score + neg_score #?????????????????????????

    return word_scores #??????????????