test_miislita.py 文件源码

def test_miislita_high_level(self):
        # construct corpus from file
        miislita = CorpusMiislita(datapath('miIslita.cor'))

        # initialize tfidf transformation and similarity index
        tfidf = models.TfidfModel(miislita, miislita.dictionary, normalize=False)
        index = similarities.SparseMatrixSimilarity(tfidf[miislita], num_features=len(miislita.dictionary))

        # compare to query
        query = 'latent semantic indexing'
        vec_bow = miislita.dictionary.doc2bow(query.lower().split())
        vec_tfidf = tfidf[vec_bow]

        # perform a similarity query against the corpus
        sims_tfidf = index[vec_tfidf]

        # for the expected results see the article
        expected = [0.0, 0.2560, 0.7022, 0.1524, 0.3334]
        for i, value in enumerate(expected):
            self.assertAlmostEqual(sims_tfidf[i], value, 2)