tf-idf.py 文件源码

def get_similarity(query, ans_list):
    s_lenth = len(ans_list)
    Corp = ans_list
    # ??????????
    dictionary = corpora.Dictionary(Corp)
    # ??????????
    corpus = [dictionary.doc2bow(text) for text in Corp]

    tfidf = models.TfidfModel(corpus)
    corpus_tfidf = tfidf[corpus]

    vec_bow = dictionary.doc2bow(query)
    vec_tfidf = tfidf[vec_bow]

    index = similarities.MatrixSimilarity(corpus_tfidf)
    sims = index[vec_tfidf]
    similarity = list(sims)
    # print(similarity)
    end_lenth = len(similarity)
    if s_lenth != end_lenth:
        print('bug')
    return similarity