def test_dtm_conversion(self):
topics = self.topics
dtm = self.dtm
num_topics, vocab_size = topics.shape
WS, DS = utils.matrix_to_lists(dtm)
self.assertEqual(max(WS) + 1, vocab_size)
self.assertEqual(max(DS) + 1, NUM_DOCS)
dtm_recovered = utils.lists_to_matrix(WS, DS)
np.testing.assert_allclose(dtm, dtm_recovered)
def test_matrix_to_lists(self):
dtm, D, N_WORDS_PER_DOC = self.dtm, self.D, self.N_WORDS_PER_DOC
N_BY_D, N_BY_W = self.N_BY_D, self.N_BY_W
WS, DS = utils.matrix_to_lists(dtm)
self.assertEqual(len(WS), D * N_WORDS_PER_DOC)
self.assertEqual(len(WS), len(DS))
self.assertEqual(dtm.shape, (max(DS) + 1, max(WS) + 1))
self.assertTrue(all(DS == sorted(DS)))
self.assertTrue(np.all(np.bincount(DS) == N_BY_D))
self.assertTrue(np.all(np.bincount(WS) == N_BY_W))
def test_lists_to_matrix(self):
dtm = self.dtm
WS, DS = utils.matrix_to_lists(dtm)
dtm_new = utils.lists_to_matrix(WS, DS)
self.assertTrue(np.all(dtm == dtm_new))