example_1.py 文件源码

def getTFIDF():
    """

    :return:
    """
    corpus,textList=getFenCiWords();
    vectorizer=CountVectorizer()#??????????????????????a[i][j] ??j??i???????
    transformer=TfidfTransformer()#??????????tf-idf??
    tfidf=transformer.fit_transform(vectorizer.fit_transform(corpus))#???fit_transform???tf-idf????fit_transform??????????
    word=vectorizer.get_feature_names()#????????????
    weight = tfidf.toarray()  # ?tf-idf?????????a[i][j]??j??i?????tf-idf??
    print "?" + str(len(weight)) + "???" + ",?" + str(len(word)) + "??"
    return weight, textList
    # for i in range(len(weight)):#???????tf-idf????????for??????????for?????????????
    #   print u"-------?????",i,u"??????tf-idf??------"
    # for j in range(len(word)):
    # print word[j],weight[i][j]