def test_index_query(self):
movies_index = os.path.join(dir_test_files, 'complex_contents',
'index/')
filter_list = ['tt0114319', 'tt0114388']
recs_number = 3
# Test prediction and ranking with the Index Query algorithm
alg = IndexQuery({'Plot': ['index_original', 'index_preprocessed']})
rs = ContentBasedRS(alg, ratings, movies_index)
# Prediction should raise error since it's not a ScorePredictionAlg
with self.assertRaises(NotPredictionAlg):
rs.fit_predict('A000')
result_rank = rs.fit_rank('A000')
self.assertGreater(len(result_rank), 0)
# Test prediction and ranking with the IndexQuery algorithm on specified items, prediction will raise exception
# since it's not a PredictionAlgorithm
with self.assertRaises(NotPredictionAlg):
rs.fit_predict('A000', filter_list=filter_list)
result_rank_filtered = rs.fit_rank('A000', filter_list=filter_list)
self.assertGreater(len(result_rank_filtered), 0)
# Test top-n ranking with the IndexQuery algorithm
result_rank_numbered = rs.fit_rank('A000', recs_number=recs_number)
self.assertEqual(len(result_rank_numbered), recs_number)
def test_empty_frame(self):
ratings_only_positive = pd.DataFrame.from_records(
[("A000", "tt0114576", 5, "54654675")],
columns=["from_id", "to_id", "score", "timestamp"])
ratings_only_negative = pd.DataFrame.from_records(
[("A000", "tt0114576", 1, "54654675")],
columns=["from_id", "to_id", "score", "timestamp"])
ratings_item_inexistent = pd.DataFrame.from_records(
[("A000", "not exists", 1, "54654675")],
columns=["from_id", "to_id", "score", "timestamp"])
# ClassifierRecommender returns an empty frame
alg = ClassifierRecommender({'Plot': ['tfidf', 'embedding']},
SkSVC(),
threshold=3)
rs = ContentBasedRS(alg, ratings_only_positive, self.movies_multiple)
result = rs.fit_rank('A000')
self.assertTrue(result.empty)
alg = ClassifierRecommender({'Plot': ['tfidf', 'embedding']},
SkSVC(),
threshold=3)
rs = ContentBasedRS(alg, ratings_only_negative, self.movies_multiple)
result = rs.fit_rank('A000')
self.assertTrue(result.empty)
alg = ClassifierRecommender({'Plot': ['tfidf', 'embedding']},
SkSVC(),
threshold=3)
rs = ContentBasedRS(alg, ratings_item_inexistent, self.movies_multiple)
result = rs.fit_rank('A000')
self.assertTrue(result.empty)
# CentroidVector returns an empty frame
alg = CentroidVector({'Plot': ['tfidf', 'embedding']},
CosineSimilarity(),
threshold=3)
rs = ContentBasedRS(alg, ratings_only_negative, self.movies_multiple)
result = rs.fit_rank('A000')
self.assertTrue(result.empty)
alg = CentroidVector({'Plot': ['tfidf', 'embedding']},
CosineSimilarity(),
threshold=3)
rs = ContentBasedRS(alg, ratings_item_inexistent, self.movies_multiple)
result = rs.fit_rank('A000')
self.assertTrue(result.empty)
def test_classifier_recommender(self):
recs_number = 3
# Test prediction and ranking with the Classifier Recommender algorithm
alg = ClassifierRecommender({'Plot': ['tfidf', 'embedding']}, SkSVC())
rs = ContentBasedRS(alg, ratings, self.movies_multiple)
# Prediction should raise error since it's not a ScorePredictionAlg
with self.assertRaises(NotPredictionAlg):
rs.fit_predict('A000')
# Test ranking with the Classifier Recommender algorithm on specified items
result_rank_filtered = rs.fit_rank('A000',
filter_list=self.filter_list)
self.assertEqual(len(result_rank_filtered), len(self.filter_list))
# Test top-n ranking with the Classifier Recommender algorithm
result_rank_numbered = rs.fit_rank('A000', recs_number=recs_number)
self.assertEqual(len(result_rank_numbered), recs_number)
def test_linear_predictor(self):
recs_number = 3
# Test prediction and ranking with the Classifier Recommender algorithm
alg = LinearPredictor({'Plot': ['tfidf', 'embedding']},
SkLinearRegression())
rs = ContentBasedRS(alg, ratings, self.movies_multiple)
# Prediction
result_pred_filtered = rs.fit_predict('A000',
filter_list=self.filter_list)
self.assertEqual(len(result_pred_filtered), len(self.filter_list))
# Test ranking with the Classifier Recommender algorithm on specified items
result_rank_filtered = rs.fit_rank('A000',
filter_list=self.filter_list)
self.assertEqual(len(result_rank_filtered), len(self.filter_list))
# Test top-n ranking with the Classifier Recommender algorithm
result_rank_numbered = rs.fit_rank('A000', recs_number=recs_number)
self.assertEqual(len(result_rank_numbered), recs_number)
