def test_predict_multiple_representations(self, model: Regressor):
lm = model
# Multiple representations filtered only items with score >= 2
alg = LinearPredictor({'Plot': ['tfidf', 'embedding'],
'Genre': ['tfidf', 'embedding'],
'imdbRating': [0]}, lm, only_greater_eq=2)
user_ratings = self.ratings.query('from_id == "A000"')
alg.process_rated(user_ratings, self.movies_dir)
alg.fit()
# predict with filter_list
res_filtered = alg.predict(user_ratings, self.movies_dir, filter_list=self.filter_list)
item_scored_set = set(res_filtered['to_id'])
self.assertEqual(len(item_scored_set), len(self.filter_list))
self.assertCountEqual(item_scored_set, self.filter_list)
# predict without filter_list
res_all_unrated = alg.predict(user_ratings, self.movies_dir)
item_rated_set = set(user_ratings['to_id'])
item_scored_set = set(res_all_unrated['to_id'])
# We expect this to be empty, since the alg should rank only unrated items (unless in filter list)
rated_in_scored = item_scored_set.intersection(item_rated_set)
self.assertEqual(len(rated_in_scored), 0)
def test_rank_single_representation(self, model: Regressor):
lm = model
# Single representation
alg = LinearPredictor({'Plot': ['tfidf']}, lm)
user_ratings = self.ratings.query('from_id == "A000"')
alg.process_rated(user_ratings, self.movies_dir)
alg.fit()
# rank with filter_list
res_filtered = alg.rank(user_ratings, self.movies_dir, filter_list=self.filter_list)
item_ranked_set = set(res_filtered['to_id'])
self.assertEqual(len(item_ranked_set), len(self.filter_list))
self.assertCountEqual(item_ranked_set, self.filter_list)
# rank without filter_list
res_all_unrated = alg.rank(user_ratings, self.movies_dir)
item_rated_set = set(user_ratings['to_id'])
item_ranked_set = set(res_all_unrated['to_id'])
# We expect this to be empty, since the alg should rank only unrated items (unless in filter list)
rated_in_ranked = item_ranked_set.intersection(item_rated_set)
self.assertEqual(len(rated_in_ranked), 0)
# rank with n_recs specified
n_recs = 5
res_n_recs = alg.rank(user_ratings, self.movies_dir, n_recs)
self.assertEqual(len(res_n_recs), n_recs)
item_rated_set = set(user_ratings['to_id'])
item_ranked_set = set(res_n_recs['to_id'])
# We expect this to be empty, since the alg should rank only unrated items (unless in filter list)
rated_in_ranked = item_ranked_set.intersection(item_rated_set)
self.assertEqual(len(rated_in_ranked), 0)