iqss_interface.py 文件源码

def build_lda(self, nt, corpus, dictionary, bow_matrix):
        ## Description: Builds LDA and does document similarity
        ## Params: Number of topics, corpus, dict, BOW matrix
        ## Returns: Similarity index and matrix

        lda_model = models.LdaModel(corpus, id2word= dictionary, num_topics=nt)
        self.lda_model = lda_model
        index = similarities.MatrixSimilarity(lda_model[corpus])
        matrix = bow_matrix.apply(lambda x: [lda_model[x[0]]], 1)
        return (index, matrix)