Python collocations.BigramCollocationFinder类代码示例

def create_word_bigram_scores():
    posdata = tp.seg_fil_senti_excel("~", 1, 1)
    negdata = tp.seg_fil_senti_excel("~", 1, 1)
    
    posWords = list(itertools.chain(*posdata))
    negWords = list(itertools.chain(*negdata))

    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)

    pos = posWords + posBigrams
    neg = negWords + negBigrams

    word_fd = FreqDist()
    last_word = ConditionalFreqDist()
    for word in pos:
        word_fd.inc(word)
        last_word['pos'].inc(word)
    for word in neg:
        word_fd.inc(word)
        last_word['neg'].inc(word)

    pos_word_count = last_word['pos'].N()
    neg_word_count = last_word['neg'].N()
    totalnumber = pos_word_count + neg_word_count

    word_scores = {}
    for word, freq in word_fd.iteritems():
        pos_score = BigramAssocMeasures.chi_sq(last_word['pos'][word], (freq, pos_word_count), totalnumber)
        neg_score = BigramAssocMeasures.chi_sq(last_word['neg'][word], (freq, neg_word_count), totalnumber)
        word_scores[word] = pos_score + neg_score

    return word_scores

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_words_bigrams_scores():
    posdata = tp.seg_fil_senti_excel("./Machine-learning-features/seniment review set/pos_review.xlsx", 1, 1)
    negdata = tp.seg_fil_senti_excel("./Machine-learning-features/seniment review set/neg_review.xlsx", 1, 1)
    
    posWords = list(itertools.chain(*posdata))
    negWords = list(itertools.chain(*negdata))

    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)

    pos = posWords + posBigrams
    neg = negWords + negBigrams

    word_fd = FreqDist()
    cond_word_fd = ConditionalFreqDist()
    for word in pos:
        word_fd[word]+=1
        cond_word_fd['pos'][word]+=1

    for word in neg:
        word_fd[word]+=1
        cond_word_fd['neg'][word]+=1
    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_bigram_scores():
    posdata = pickle.load(open('/Users/genghaiyang/ghy_works/projects/weibo_crawler/textmining/sentiML/pos_neg_review/pos_review.pkl','r'))
    negdata = pickle.load(open('/Users/genghaiyang/ghy_works/projects/weibo_crawler/textmining/sentiML/pos_neg_review/neg_review.pkl','r'))
    
    posWords = list(itertools.chain(*posdata))
    negWords = list(itertools.chain(*negdata))

    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)

    pos = posWords + posBigrams #词和双词搭配
    neg = negWords + negBigrams

    word_fd = FreqDist()
    cond_word_fd = ConditionalFreqDist()
    for word in pos:
        word_fd[word] += 1#word_fd.inc(word)
        cond_word_fd['pos'][word]+= 1 #cond_word_fd['pos'].inc(word)
    for word in neg:
        word_fd[word] += 1#word_fd.inc(word)
        cond_word_fd['neg'][word]+= 1#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 _get_bigram_scores(self, posdata, negdata):
        pos_words = list(itertools.chain(*posdata))
        neg_words = list(itertools.chain(*negdata))

        pos_bigram_finder = BigramCollocationFinder.from_words(pos_words)
        neg_bigram_finder = BigramCollocationFinder.from_words(neg_words)
        pos_bigrams = pos_bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
        neg_bigrams = neg_bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)

        pos = pos_words + pos_bigrams
        neg = neg_words + neg_bigrams

        word_fd = FreqDist()
        cond_word_fd = ConditionalFreqDist()
        for word in pos:
            word_fd[word] += 1
            cond_word_fd['pos'][word] += 1
        for word in neg:
            word_fd[word] += 1
            cond_word_fd['neg'][word] += 1

        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_bigram_scores():
    posdata = tp.seg_fil_senti_excel("D:/code/sentiment_test/pos_review.xlsx", "1", "1")
    negdata = tp.seg_fil_senti_excel("D:/code/sentiment_test/neg_review.xlsx", "1", "1")
    
    posWords = list(itertools.chain(*posdata))
    negWords = list(itertools.chain(*negdata))

    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 8000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 8000)

    pos = posBigrams
    neg = 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 get_unibigram_features(all_words, uni_feanum, bi_feanum):
        word_fd = nltk.FreqDist(all_words)
        bigram_fd = nltk.FreqDist(nltk.bigrams(all_words))

        if uni_feanum == 'max':
            uni_feanum = len(list(word_fd.keys()))
        elif uni_feanum > len(list(word_fd.keys())):
            uni_feanum = len(list(word_fd.keys()))

        if bi_feanum == 'max':
            bi_feanum = len(list(bigram_fd.keys()))
        elif bi_feanum > len(list(bigram_fd.keys())):
            bi_feanum = len(list(bigram_fd.keys()))

        finder = BigramCollocationFinder(word_fd, bigram_fd)
        bigrams = finder.nbest(BigramAssocMeasures.chi_sq, bi_feanum)

        print "the number of unigram features is", uni_feanum
        print "the number of bigram features is", bi_feanum

        featuples = word_fd.most_common(uni_feanum)

        selected_words = []

        for i in range(uni_feanum):
            selected_words.append(featuples[i][0])

        features = []
        for ngram in itertools.chain(selected_words, bigrams):
            features.append(ngram)

        return features

def create_word_bigram_scores(posWords, negWords):
    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 2000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 2000)

    pos = posWords + posBigrams #词和双词搭配
    neg = negWords + negBigrams

    word_fd = FreqDist()
    cond_word_fd = ConditionalFreqDist()
    for word in pos:
        word_fd[str(word)] += 1 
        cond_word_fd['pos'][str(word)] += 1
    for word in neg:
	    word_fd[str(word)] += 1
	    cond_word_fd['neg'][str(word)] += 1

    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 best_bigrams(sents_tagged, stopwords, score_fn=BigramAssocMeasures.likelihood_ratio, n=300):
    sents_pos = []
    sents_neg = []

    # Separate positive and negative sentences.
    for tag, sent in sents_tagged:
        if tag == 1:
            sents_pos.append(sent)
        elif tag == -1:
            sents_neg.append(sent)

    # Extract words from positive and negative sentences.
    words_pos = [word.lower() for s in sents_pos for word in word_tokenize(s) if word not in string.punctuation]
    words_neg = [word.lower() for s in sents_neg for word in word_tokenize(s) if word not in string.punctuation]

    # Find the best bigrams for positive sentences based on informative collocations
    bigram_finder1 = BigramCollocationFinder.from_words(words_pos)
    bigrams_best_pos = bigram_finder1.nbest(score_fn, n)

    # Find the best bigrams for negative sentences based on informative collocations
    bigram_finder2 = BigramCollocationFinder.from_words(words_neg)
    bigrams_best_neg = bigram_finder2.nbest(score_fn, n)

    bigrams_all = list(set(bigrams_best_pos).union(set(bigrams_best_neg)))

    # Select only the bigrams that have either one of the word greater than length 3
    bigrams_best = [bigram for bigram in bigrams_all
            if len(bigram[0]) > 3 and len(bigram[1]) > 3
            and bigram[0] not in ex and bigram[1] not in ex ]


    return bigrams_best

def create_word_bigram_scores(posWords, negWords, n = 5000):
    # (posWords,negWords) = readwordarr()
    posWords = list(itertools.chain(*posWords))
    negWords = list(itertools.chain(*negWords))
    bigramfinder = BigramCollocationFinder.from_words(posWords)
    posbigrams = bigramfinder.nbest(BigramAssocMeasures.chi_sq, n)
    bigramfinder = BigramCollocationFinder.from_words(negWords)
    negbigrams = bigramfinder.nbest(BigramAssocMeasures.chi_sq, n)
    posWords = posWords + posbigrams
    negWords = negWords + negbigrams
    wordscores = {}
    wordfd = FreqDist()
    conditionwordfd = ConditionalFreqDist()
    for word in posWords:
        wordfd[word]+=1
        conditionwordfd['pos'][word]+=1
        
    for word in negWords:
        wordfd[word]+=1
        conditionwordfd['neg'][word]+=1
    
    pos_word_count = conditionwordfd['pos'].N()
    neg_word_count = conditionwordfd['neg'].N()
    totalcount = pos_word_count + neg_word_count
    for word,freq in wordfd.items():
        pos_score = BigramAssocMeasures.chi_sq(conditionwordfd['pos'][word], (freq, pos_word_count), totalcount)
        neg_score = BigramAssocMeasures.chi_sq(conditionwordfd['neg'][word], (freq, neg_word_count), totalcount)
        wordscores[word] = pos_score + neg_score
    return wordscores

def create_word_bigram_scores(posWords, negWords, score_method = BigramAssocMeasures.chi_sq):
    '''
    以双词来统计词的信息量
    '''
    bigram_finder = BigramCollocationFinder.from_words(posWords)
    posBigrams = bigram_finder.nbest(score_method, 5000)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    negBigrams = bigram_finder.nbest(score_method, 5000)
    pos = posWords + posBigrams #词和双词搭配
    neg = negWords + negBigrams

    word_fd = FreqDist()
    cond_word_fd = ConditionalFreqDist()
    for word in pos:
        word_fd[word] += 1
        cond_word_fd['pos'][word] += 1
    for word in neg:
        word_fd[word] += 1
        cond_word_fd['neg'][word] += 1
    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
    print("BIGRAM_IN_POSWORD_NUMS : %d\tBIGRAM_IN_NEGWORD_NUMS : %d" % (pos_word_count, neg_word_count))

    word_scores = {}
    for word, freq in word_fd.iteritems():
        pos_score = score_method(cond_word_fd['pos'][word], (freq, pos_word_count), total_word_count)
        neg_score = score_method(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_bigram_scores():
	bigram_finder = BigramCollocationFinder.from_words(posWords)
	bigram_finder = BigramCollocationFinder.from_words(negWords)
	posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
	negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
	pos = posWords + posBigrams #词和双词搭配
	neg = negWords + negBigrams
	return get_scores(pos, neg)

def create_word_bigram_scores():
    posWords = list(itertools.chain(*posdata))
    negWords = list(itertools.chain(*negdata))
    
    objWords = list(itertools.chain(*objdata))

    bigram_finder = BigramCollocationFinder.from_words(posWords)
    bigram_finder = BigramCollocationFinder.from_words(negWords)
    
    bigram_finder = BigramCollocationFinder.from_words(objWords)
    posBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
    negBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)
    
    objBigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 5000)


    pos = posWords + posBigrams
    neg = negWords + negBigrams
    
    obj = objWords + objBigrams

    word_fd = FreqDist()
    cond_word_fd = ConditionalFreqDist()
    for word in pos:
        word_fd[word] += 1
        cond_word_fd['pos'][word] += 1
    for word in neg:
        word_fd[word] += 1
        cond_word_fd['neg'][word] += 1
    for word in objWords:
        word_fd[word] += 1
        cond_word_fd['obj'][word] += 1

    pos_word_count = cond_word_fd['pos'].N()
    neg_word_count = cond_word_fd['neg'].N()
    
    obj_word_count = cond_word_fd['obj'].N()
    total_word_count = pos_word_count + neg_word_count + obj_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)
       
        obj_score = BigramAssocMeasures.chi_sq(cond_word_fd['obj'][word], (freq, obj_word_count), total_word_count)
        word_scores[word] = pos_score + neg_score + obj_score

    return word_scores

def best_bigram_word_features(words, score_fn=BigramAssocMeasures.chi_sq, n=200):
    bigram_finder = BigramCollocationFinder.from_words(words)
    bigrams = bigram_finder.nbest(score_fn, n)
    d = dict([(bigram, True) for bigram in bigrams])
    d.update(best_word_features(words))

    return d

    def collocations(self, num=20, window_size=2):
        """
        Print collocations derived from the text, ignoring stopwords.

        :seealso: find_collocations
        :param num: The maximum number of collocations to print.
        :type num: int
        :param window_size: The number of tokens spanned by a collocation (default=2)
        :type window_size: int
        """
        if not (
            '_collocations' in self.__dict__
            and self._num == num
            and self._window_size == window_size
        ):
            self._num = num
            self._window_size = window_size

            # print("Building collocations list")
            from nltk.corpus import stopwords

            ignored_words = stopwords.words('english')
            finder = BigramCollocationFinder.from_words(self.tokens, window_size)
            finder.apply_freq_filter(2)
            finder.apply_word_filter(lambda w: len(w) < 3 or w.lower() in ignored_words)
            bigram_measures = BigramAssocMeasures()
            self._collocations = finder.nbest(bigram_measures.likelihood_ratio, num)
        colloc_strings = [w1 + ' ' + w2 for w1, w2 in self._collocations]
        print(tokenwrap(colloc_strings, separator="; "))