def test_gibbs_update(self): #This test checks if topic assignment are decrased and re-increased annots = self.create_annots(test.DELICIOUS_FILE) estimator = LDAEstimator(annots, 2, .5, .5, .5, 0, 0, 1, 0) changed = False for annot, old_topic in estimator._get_topic_assignments().items(): user, document, term = annot old_ut = estimator._get_user_topic_counts()[user, old_topic] old_td = estimator._get_topic_document_counts()[old_topic, document] old_tr = estimator._get_topic_term_counts()[old_topic, term] new_topic = estimator._gibbs_update(user, old_topic, document, term, 0) new_ut = estimator._get_user_topic_counts()[user, old_topic] new_td = estimator._get_topic_document_counts()[old_topic, document] new_tr = estimator._get_topic_term_counts()[old_topic, term] if old_topic != new_topic: changed = True self.assertEqual(new_ut, old_ut - 1) self.assertEqual(new_td, old_td - 1) self.assertEqual(new_tr, old_tr - 1) else: self.assertEqual(new_ut, old_ut) self.assertEqual(new_td, old_td) self.assertEqual(new_tr, old_tr) self.assertTrue(changed) self.assertEqual(len(estimator._get_topic_assignments()), estimator._get_topic_counts().sum())
def test_initial_population(self): annots = self.create_annots(test.SMALL_DEL_FILE) #With zero GIBBs will not run estimator = LDAEstimator(annots, 2, .5, .5, .5, 0, 0, 1, 0) user_cnt = estimator._get_user_counts() topic_cnt = estimator._get_topic_counts() document_cnt = estimator._get_document_counts() self.assertEquals(user_cnt[0], 4) self.assertEquals(user_cnt[1], 4) self.assertEquals(user_cnt[2], 2) self.assertEquals(document_cnt[0], 5) self.assertEquals(document_cnt[1], 1) self.assertEquals(document_cnt[2], 2) self.assertEquals(document_cnt[3], 1) self.assertEquals(document_cnt[4], 1) #10 assignments = 10 topics self.assertEquals(10, sum(topic_cnt)) user_topic_cnt = estimator._get_user_topic_counts() topic_document_cnt = estimator._get_topic_document_counts() topic_term_cnt = estimator._get_topic_term_counts() #We can only test shapes and sum, since assignments are random self.assertEqual((3, 2), user_topic_cnt.shape) self.assertEqual((2, 5), topic_document_cnt.shape) self.assertEqual((2, 6), topic_term_cnt.shape) self.assertEqual(10, user_topic_cnt.sum()) self.assertEqual(10, topic_document_cnt.sum()) self.assertEqual(10, topic_term_cnt.sum()) topic_assigments = estimator._get_topic_assignments() self.assertEqual(10, len(topic_assigments)) self.assertEqual(10, estimator._get_topic_counts().sum()) #Were the topics populated correctly? for annot in annots: aux = (annot['user'], annot['item'], annot['tag']) self.assertTrue(aux in topic_assigments) #Simple sanity check on topic assigmnets. Check if topics have valid #ids and if count matches count matrix from collections import Counter c = Counter(topic_assigments.values()) for topic in c: self.assertTrue(topic in [0, 1]) self.assertTrue(c[topic] == topic_cnt[topic])