def run_top_n_test(records_file,
recommenders,
binary_reviews_file,
reviews_type=None):
records = load_records(records_file)
# records = extractor.remove_users_with_low_reviews(records, 2)
with open(binary_reviews_file, 'rb') as read_file:
binary_reviews = pickle.load(read_file)
if len(records) != len(binary_reviews):
raise ValueError("The records and reviews should have the same length")
num_folds = 5
split = 0.986
min_like_score = 5.0
top_n = 10
dataset_info_map = {}
dataset_info_map['dataset'] = records_file.split('/')[-1]
dataset_info_map['cache_reviews'] = binary_reviews_file.split('/')[-1]
dataset_info_map['num_records'] = len(records)
dataset_info_map['reviews_type'] = reviews_type
dataset_info_map['cross_validation_folds'] = num_folds
dataset_info_map['min_like_score'] = min_like_score
dataset_info_map['top_n'] = top_n
results_list = []
results_log_list = []
count = 0
print('Total recommenders: %d' % (len(recommenders)))
for recommender in recommenders:
print('\n**************\nProgress: %d/%d\n**************' %
(count, len(recommenders)))
print(get_knn_recommender_info(recommender))
results = precision_in_top_n.calculate_recall_in_top_n(
records, recommender, top_n, num_folds, split, min_like_score,
binary_reviews, reviews_type)
results_list.append(results)
remaining_time = results['Execution time'] * (len(recommenders) -
count)
remaining_time /= 3600
print('Estimated remaining time: %.2f hours' % remaining_time)
count += 1
for recommender, results in zip(recommenders, results_list):
results_log_list.append(
process_topn_results(recommender, results, dataset_info_map))
timestamp = time.strftime("%Y%m%d-%H%M%S")
file_name = 'recommender-topn-results' + timestamp
ETLUtils.save_csv_file(file_name + '.csv', results_log_list, TOPN_HEADERS,
'\t')
def test_calculate_recall_in_top_n(self):
recommender = ItemAverageRecommender()
recommender.load(reviews_matrix_5)
actual_value = precision_in_top_n.calculate_recall_in_top_n(
reviews_matrix_5, recommender, 2, 2, None, 4.0)['Top N']
expected_value = 0.875
self.assertEqual(expected_value, actual_value)
def test_calculate_recall_in_top_n(self):
recommender = ItemAverageRecommender()
recommender.load(reviews_matrix_5)
actual_value = precision_in_top_n.calculate_recall_in_top_n(
reviews_matrix_5, recommender, 2, 2, None, 4.0)['Top N']
expected_value = 0.875
self.assertEqual(expected_value, actual_value)
def run_top_n_test(
records_file, recommenders, binary_reviews_file, reviews_type=None):
records = load_records(records_file)
# records = extractor.remove_users_with_low_reviews(records, 2)
with open(binary_reviews_file, 'rb') as read_file:
binary_reviews = pickle.load(read_file)
if len(records) != len(binary_reviews):
raise ValueError("The records and reviews should have the same length")
num_folds = 5
split = 0.986
min_like_score = 5.0
top_n = 10
dataset_info_map = {}
dataset_info_map['dataset'] = records_file.split('/')[-1]
dataset_info_map['cache_reviews'] = binary_reviews_file.split('/')[-1]
dataset_info_map['num_records'] = len(records)
dataset_info_map['reviews_type'] = reviews_type
dataset_info_map['cross_validation_folds'] = num_folds
dataset_info_map['min_like_score'] = min_like_score
dataset_info_map['top_n'] = top_n
results_list = []
results_log_list = []
count = 0
print('Total recommenders: %d' % (len(recommenders)))
for recommender in recommenders:
print('\n**************\nProgress: %d/%d\n**************' %
(count, len(recommenders)))
print(get_knn_recommender_info(recommender))
results = precision_in_top_n.calculate_recall_in_top_n(
records, recommender, top_n, num_folds, split, min_like_score,
binary_reviews, reviews_type)
results_list.append(results)
remaining_time = results['Execution time'] * (len(recommenders) - count)
remaining_time /= 3600
print('Estimated remaining time: %.2f hours' % remaining_time)
count += 1
for recommender, results in zip(recommenders, results_list):
results_log_list.append(process_topn_results(recommender, results, dataset_info_map))
timestamp = time.strftime("%Y%m%d-%H%M%S")
file_name = 'recommender-topn-results' + timestamp
ETLUtils.save_csv_file(file_name + '.csv', results_log_list, TOPN_HEADERS, '\t')
def run_topn_test_wrapper(args):
try:
return precision_in_top_n.calculate_recall_in_top_n(*args)
except Exception as e:
print('Caught exception in worker thread')
# This prints the type, value, and stack trace of the
# current exception being handled.
traceback.print_exc()
print()
raise e
def run_topn_test_wrapper(args):
try:
return precision_in_top_n.calculate_recall_in_top_n(*args)
except Exception as e:
print('Caught exception in worker thread')
# This prints the type, value, and stack trace of the
# current exception being handled.
traceback.print_exc()
print()
raise e
def main():
reviews_file =\
"/Users/fpena/tmp/yelp_training_set/yelp_training_set_review_hotels.json"
my_records = load_data(reviews_file)
my_ratings_matrix = create_ratings_matrix(my_records)
my_records = extractor.remove_users_with_low_reviews(my_records, 1)
print(len(my_records))
# print(len(my_ratings_matrix))
# basic_knn = BasicKNN(1)
# basic_knn.load(my_records)
# for record in my_records:
# print(basic_knn.predict_rating(record['user_id'], record['offering_id']))
# print(basic_knn.predict_rating('qLCpuCWCyPb4G2vN-WZz-Q', '8ZwO9VuLDWJOXmtAdc7LXQ')) # 4
# print(basic_knn.predict_rating('rVlgz-MGYRPa8UzTYO0RGQ', 'c0iszTWZwYtO3TgBx0Z0fQ')) # 2
# print(basic_knn.predict_rating('4o7r-QSYhOkxpxRMqpXcCg', 'EcHuaHD9IcoPEWNsU8vDTw')) # 4
# print(basic_knn.predict_rating('msgAEWFbD4df0EvyOR3TnQ', 'EcHuaHD9IcoPEWNsU8vDTw')) # 5
shuffle(my_records)
# Split 80-20 and see the results
num_records = len(my_records)
num_unknown_records = 0
training_size = int(num_records*0.8)
my_train_data = my_records[:training_size]
my_test_data = my_records[training_size:]
basic_knn = BasicKNN(None)
basic_knn.load(my_train_data)
# basic_knn.load(my_records)
# recommender_evaluator.perform_cross_validation(my_records, basic_knn, 3)
# precision_in_top_n.calculate_top_n_precision(my_records, basic_knn, 10000, 5.0, 5)
precision_in_top_n.calculate_recall_in_top_n(my_records, basic_knn, 10, 5)
def main():
# reviews_file = "/Users/fpena/tmp/yelp_training_set/yelp_training_set_review_hotels.json"
reviews_file = "/Users/fpena/UCC/Thesis/datasets/context/yelp_training_set_review_hotels_shuffled.json"
# reviews_file = "/Users/fpena/UCC/Thesis/datasets/context/yelp_training_set_review_restaurants_shuffled.json"
# my_records = context_utils.load_reviews(reviews_file)
my_records = load_data(reviews_file)
print("records:", len(my_records))
my_num_topics = 150
print("\n***************************\n")
# my_records = load_data(reviews_file)
# my_records = extractor.remove_users_with_low_reviews(my_records, 200)
# my_records = extractor.remove_users_with_low_reviews(my_records, 2)
# shuffle(my_records)
# my_index = 0
# my_reviews = []
# for record in my_records:
# my_index += 1
# my_reviews.append(Review(record))
# print('index', my_index)
# my_file = '/Users/fpena/UCC/Thesis/datasets/context/reviews_context_restaurants_200.pkl'
# my_file = '/Users/fpena/UCC/Thesis/datasets/context/reviews_context_hotel_2.pkl'
my_file = '/Users/fpena/tmp/reviews_hotel_shuffled.pkl'
# my_file = '/Users/fpena/tmp/reviews_restaurant_shuffled.pkl'
# with open(my_file, 'wb') as write_file:
# pickle.dump(my_reviews, write_file, pickle.HIGHEST_PROTOCOL)
with open(my_file, 'rb') as read_file:
my_cache_reviews = pickle.load(read_file)
print("reviews:", len(my_cache_reviews))
context_knn = ContextKnn(my_num_topics)
tknc = TopKNeighbourhoodCalculator()
nc = ContextNeighbourhoodCalculator()
ncc = NeighbourContributionCalculator()
ubc = UserBaselineCalculator()
usc = PBCSimilarityCalculator()
# contextual_knn2 = ContextualKNN(my_num_topics, tknc, ncc, ubc, usc, my_reviews)
bnc = BasicNeighbourhoodCalculator()
bncc = BasicNeighbourContributionCalculator()
bubc = BasicUserBaselineCalculator()
busc = BasicUserSimilarityCalculator()
snc = SimpleNeighbourhoodCalculator()
chnc = ContextHybridNeighbourhoodCalculator()
contextual_knn = ContextualKNN(my_num_topics, nc, ncc, ubc, usc, has_context=True)
contextual_knn2 = ContextualKNN(my_num_topics, nc, ncc, ubc, busc, has_context=True)
contextual_knn3 = ContextualKNN(my_num_topics, bnc, bncc, bubc, busc)
# basic_contextual_knn = BasicContextualKNN(my_num_topics, bnc, bncc, bubc, busc)
# contextual_knn.threshold1 = 0.8
# contextual_knn.threshold2 = 0.8
# contextual_knn.threshold3 = 0.8
# contextual_knn.threshold4 = 0.8
# print('Context KNN')
# context_knn.load(my_records)
# recommender_evaluator.perform_cross_validation(my_records, context_knn, 5, True)
basic_knn_rec = BasicKNN(None)
# print('Basic KNN')
# recommender_evaluator.perform_cross_validation(my_records, basic_knn_rec, 5)
# print('Context KNN')
# recommender_evaluator.perform_cross_validation(my_records, context_knn, 5, my_cache_reviews)
print('Contextual KNN')
recommender_evaluator.perform_cross_validation(my_records, contextual_knn, 5, my_cache_reviews)
print('Contextual KNN2')
recommender_evaluator.perform_cross_validation(my_records, contextual_knn2, 5, my_cache_reviews)
print('Contextual KNN3')
# recommender_evaluator.perform_cross_validation(my_records, contextual_knn3, 5)
# recommender_evaluator.perform_cross_validation(my_records, contextual_knn3, 5)
# recommender_evaluator.perform_cross_validation(my_records, contextual_knn3, 5, True, my_cache_reviews)
# precision_in_top_n.calculate_recall_in_top_n(my_records, basic_contextual_knn, 10, 65)
# precision_in_top_n.calculate_recall_in_top_n(my_records, basic_knn_rec, 10, 65)
print('Basic KNN')
precision_in_top_n.calculate_recall_in_top_n(my_records, basic_knn_rec, 10, 5, 5.0, my_cache_reviews)
# precision_in_top_n.calculate_recall_in_top_n(my_records, basic_knn_rec, 10, 5, 5.0, False, my_cache_reviews)
print('Context KNN')
precision_in_top_n.calculate_recall_in_top_n(my_records, context_knn, 10, 5, 5.0, my_cache_reviews)
print('Contextual KNN')
precision_in_top_n.calculate_recall_in_top_n(my_records, contextual_knn, 10, 5, 5.0, my_cache_reviews)
print('Contextual KNN 2')
precision_in_top_n.calculate_recall_in_top_n(my_records, contextual_knn2, 10, 5, 5.0, my_cache_reviews)
print('Contextual KNN 3')
precision_in_top_n.calculate_recall_in_top_n(my_records, contextual_knn3, 10, 5, 5.0, my_cache_reviews)
