iqss_interface.py 文件源码

def build_lsa(self, nt, dictionary, tfidf_corpus, tfidf_matrix):
        ## Description: Builds LSA model and performs document similarity
        ## Params: Number of topics, dict, TFIDF corpus, TFIDF matrix
        ## Returns: Similarity index and matrix

        lsa_model = models.LsiModel(tfidf_corpus, id2word= dictionary, num_topics=nt)
        index = similarities.MatrixSimilarity(lsa_model[tfidf_corpus])
        matrix = tfidf_matrix.apply(lambda x: lsa_model[x], 1)
        return (index, matrix)