business_stats_file = sys.argv[4]
print('[ %04ds ] Program started' % (time.time() - start_time))
training_set: List[Review] = Review.load_from_file(training_set_file)
user_stats: Dict[str, User] = User.load_from_file(user_stats_file)
business_stats: Dict[str, Business] = Business.load_from_file(
business_stats_file)
print('[ %04ds ] Files loaded' % (time.time() - start_time))
all_user_features = ['NO_FEAT']
all_business_features = Business.collect_business_features(business_stats)
dataset = Dataset()
dataset.fit(User.extract_user_ids(user_stats),
Business.extract_business_ids(business_stats),
user_features=all_user_features,
item_features=all_business_features)
user_features = dataset.build_user_features(
User.build_user_features(user_stats,
User.extract_user_ids(user_stats)), True)
business_features = dataset.build_item_features(
Business.build_business_features(
business_stats, Business.extract_business_ids(business_stats)),
True)
print('[ %04ds ] Dataset initialized' % (time.time() - start_time))
business_stats_file = sys.argv[4]
output_file = sys.argv[5]
print('[ %04ds ] Program started' % (time.time() - start_time))
training_set: List[Review] = Review.load_from_file(training_set_file)
user_stats: Dict[str, User] = User.load_from_file(user_stats_file)
business_stats: Dict[str, Business] = Business.load_from_file(
business_stats_file)
print('[ %04ds ] Files loaded' % (time.time() - start_time))
all_user_features = ['NO_FEAT']
all_business_features = Business.collect_business_features(business_stats)
all_user_ids = User.extract_user_ids(user_stats)
all_business_ids = Business.extract_business_ids(business_stats)
dataset = Dataset()
dataset.fit(all_user_ids,
all_business_ids,
user_features=all_user_features,
item_features=all_business_features)
user_features = dataset.build_user_features(
User.build_user_features(user_stats, all_user_ids), True)
business_features = dataset.build_item_features(
Business.build_business_features(business_stats, all_business_ids),
True)
