test_lee.py 文件源码

def test_lee(self):
        """correlation with human data > 0.6
        (this is the value which was achieved in the original paper)
        """

        global bg_corpus, corpus

        # create a dictionary and corpus (bag of words)
        dictionary = corpora.Dictionary(bg_corpus)
        bg_corpus = [dictionary.doc2bow(text) for text in bg_corpus]
        corpus = [dictionary.doc2bow(text) for text in corpus]

        # transform the bag of words with log_entropy normalization
        log_ent = models.LogEntropyModel(bg_corpus)
        bg_corpus_ent = log_ent[bg_corpus]

        # initialize an LSI transformation from background corpus
        lsi = models.LsiModel(bg_corpus_ent, id2word=dictionary, num_topics=200)
        # transform small corpus to lsi bow->log_ent->fold-in-lsi
        corpus_lsi = lsi[log_ent[corpus]]

        # compute pairwise similarity matrix and extract upper triangular
        res = np.zeros((len(corpus), len(corpus)))
        for i, par1 in enumerate(corpus_lsi):
            for j, par2 in enumerate(corpus_lsi):
                res[i, j] = matutils.cossim(par1, par2)
        flat = res[matutils.triu_indices(len(corpus), 1)]

        cor = np.corrcoef(flat, human_sim_vector)[0, 1]
        logging.info("LSI correlation coefficient is %s" % cor)
        self.assertTrue(cor > 0.6)


    # def test_lee_mallet(self):
    #     global bg_corpus, corpus, bg_corpus2, corpus2

    #     # create a dictionary and corpus (bag of words)
    #     dictionary = corpora.Dictionary(bg_corpus2)
    #     bg_corpus = [dictionary.doc2bow(text) for text in bg_corpus2]
    #     corpus = [dictionary.doc2bow(text) for text in corpus2]

    #     # initialize an LDA transformation from background corpus
    #     lda = models.LdaMallet('/Users/kofola/Downloads/mallet-2.0.7/bin/mallet',
    #         corpus=bg_corpus, id2word=dictionary, num_topics=200, optimize_interval=10)
    #     corpus_lda = lda[corpus]

    #     # compute pairwise similarity matrix and extract upper triangular
    #     res = np.zeros((len(corpus), len(corpus)))
    #     for i, par1 in enumerate(corpus_lda):
    #         for j, par2 in enumerate(corpus_lda):
    #             res[i, j] = matutils.cossim(par1, par2)
    #     flat = res[matutils.triu_indices(len(corpus), 1)]

    #     cor = np.corrcoef(flat, human_sim_vector)[0, 1]
    #     logging.info("LDA correlation coefficient is %s" % cor)
    #     self.assertTrue(cor > 0.35)