def main(): # Data loading root_data_path = os.path.join(get_project_root_path(), "data/") data_reader = RecSys2019Reader(root_data_path) data_reader = New_DataSplitter_leave_k_out( data_reader, k_out_value=K_OUT, use_validation_set=False, allow_cold_users=ALLOW_COLD_USERS, force_new_split=True, seed=get_split_seed()) data_reader.load_data() URM_train, URM_test = data_reader.get_holdout_split() ICM_all, _ = get_ICM_train_new(data_reader) UCM_all, _ = get_UCM_train_new(data_reader) # Ignoring users ignore_users = get_ignore_users( URM_train, data_reader.get_original_user_id_to_index_mapper(), lower_threshold=LOWER_THRESHOLD, upper_threshold=UPPER_THRESHOLD, ignore_non_target_users=IGNORE_NON_TARGET_USERS) evaluator = EvaluatorHoldout(URM_test, cutoff_list=[CUTOFF], ignore_users=ignore_users) # Model evaluation model = get_model(URM_train, ICM_all, UCM_all) print(evaluator.evaluateRecommender(model))
def main(): args = get_arguments() # Data loading data_reader = read_split_load_data(3, args.allow_cold_users, args.seed) URM_train, URM_test = data_reader.get_holdout_split() ICM_categorical = data_reader.get_ICM_from_name("ICM_sub_class") ICM_numerical, _ = get_ICM_numerical(data_reader.dataReader_object) ICM_all, _ = get_ICM_train_new(data_reader) similarity_type_list = None if args.recommender_name == "item_cbf_numerical": ICM = ICM_numerical ICM_name = "ICM_numerical" elif args.recommender_name == "item_cbf_categorical": ICM = ICM_categorical ICM_name = "ICM_categorical" else: ICM = ICM_all ICM_name = "ICM_all" # Setting evaluator ignore_users = get_ignore_users( URM_train, data_reader.get_original_user_id_to_index_mapper(), lower_threshold=args.lower_threshold, upper_threshold=args.upper_threshold, ignore_non_target_users=args.exclude_non_target) evaluator = EvaluatorHoldout(URM_test, cutoff_list=[10], ignore_users=ignore_users) # HP tuning print("Start tuning...") version_path = "../../report/hp_tuning/{}/".format(args.recommender_name) now = datetime.now().strftime('%b%d_%H-%M-%S') now = now + "_k_out_value_3/" version_path = version_path + "/" + now run_parameter_search_item_content( URM_train=URM_train, ICM_object=ICM, ICM_name=ICM_name, recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name], evaluator_validation=evaluator, metric_to_optimize="MAP", output_folder_path=version_path, similarity_type_list=similarity_type_list, parallelizeKNN=True, n_cases=args.n_cases, n_random_starts=args.n_random_starts) print("...tuning ended")
def setUp(self) -> None: self.k_out = 3 self.cutoff = 5 self.path = "../../data/" self.data_reader = read_split_load_data(self.k_out, allow_cold_users=False, seed=1000) self.URM_train, self.URM_test = self.data_reader.get_holdout_split() self.ICM_all, _ = get_ICM_train_new(self.data_reader) self.UCM_all = get_UCM_train(self.data_reader) self.main_rec = new_best_models.ItemCBF_CF.get_model( URM_train=self.URM_train, ICM_train=self.ICM_all)
if __name__ == '__main__': set_env_variables() seeds = get_seed_lists(N_FOLDS, get_split_seed()) # --------- DATA LOADING SECTION --------- # URM_train_list = [] ICM_train_list = [] UCM_train_list = [] evaluator_list = [] model_list = [] for fold_idx in range(N_FOLDS): # Read and split data data_reader = read_split_load_data(K_OUT, ALLOW_COLD_USERS, seeds[fold_idx]) URM_train, URM_test = data_reader.get_holdout_split() ICM_train, item_feature2range = get_ICM_train_new(data_reader) UCM_train, user_feature2range = get_UCM_train_new(data_reader) # Ignore users and setting evaluator ignore_users = get_ignore_users( URM_train, data_reader.get_original_user_id_to_index_mapper(), LOWER_THRESHOLD, UPPER_THRESHOLD, ignore_non_target_users=IGNORE_NON_TARGET_USERS) # Ignore users by age # UCM_age = data_reader.get_UCM_from_name("UCM_age") # age_feature_to_id_mapper = data_reader.dataReader_object.get_UCM_feature_to_index_mapper_from_name("UCM_age") # age_demographic = get_user_demographic(UCM_age, age_feature_to_id_mapper, binned=True) # ignore_users = np.unique(np.concatenate((ignore_users, get_ignore_users_age(age_demographic, AGE_TO_KEEP))))
def main(): set_env_variables() args = get_arguments() seeds = get_seed_lists(args.n_folds, get_split_seed()) # --------- DATA LOADING SECTION --------- # URM_train_list = [] ICM_train_list = [] UCM_train_list = [] evaluator_list = [] for fold_idx in range(args.n_folds): # Read and split data data_reader = read_split_load_data(K_OUT, args.allow_cold_users, seeds[fold_idx]) URM_train, URM_test = data_reader.get_holdout_split() ICM_train, item_feature2range = get_ICM_train_new(data_reader) UCM_train, user_feature2range = get_UCM_train_new(data_reader) # Ignore users and setting evaluator ignore_users = get_ignore_users(URM_train, data_reader.get_original_user_id_to_index_mapper(), args.lower_threshold, args.upper_threshold, ignore_non_target_users=args.exclude_non_target) # Ignore users by age # UCM_age = data_reader.get_UCM_from_name("UCM_age") # age_feature_to_id_mapper = data_reader.dataReader_object.get_UCM_feature_to_index_mapper_from_name("UCM_age") # age_demographic = get_user_demographic(UCM_age, age_feature_to_id_mapper, binned=True) # ignore_users = np.unique(np.concatenate((ignore_users, get_ignore_users_age(age_demographic, AGE_TO_KEEP)))) URM_train_list.append(URM_train) ICM_train_list.append(ICM_train) UCM_train_list.append(UCM_train) evaluator = EvaluatorHoldout(URM_test, cutoff_list=[CUTOFF], ignore_users=np.unique(ignore_users)) evaluator_list.append(evaluator) # --------- HYPER PARAMETERS TUNING SECTION --------- # print("Start tuning...") hp_tuning_path = "../../../report/hp_tuning/" + args.recommender_name + "/" date_string = datetime.now().strftime('%b%d_%H-%M-%S_k1_lt_{}/'.format(args.lower_threshold)) output_folder_path = hp_tuning_path + date_string if args.recommender_name in COLLABORATIVE_RECOMMENDER_CLASS_DICT.keys(): run_cv_parameter_search(URM_train_list=URM_train_list, recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name], evaluator_validation_list=evaluator_list, metric_to_optimize="MAP", output_folder_path=output_folder_path, parallelize_search=args.parallelize, n_jobs=args.n_jobs, n_cases=args.n_cases, n_random_starts=args.n_random_starts) elif args.recommender_name in CONTENT_RECOMMENDER_CLASS_DICT.keys(): run_cv_parameter_search(URM_train_list=URM_train_list, ICM_train_list=ICM_train_list, ICM_name="ICM_all", recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name], evaluator_validation_list=evaluator_list, metric_to_optimize="MAP", output_folder_path=output_folder_path, parallelize_search=args.parallelize, n_jobs=args.n_jobs, n_cases=args.n_cases, n_random_starts=args.n_random_starts) elif args.recommender_name in DEMOGRAPHIC_RECOMMENDER_CLASS_DICT.keys(): run_cv_parameter_search(URM_train_list=URM_train_list, UCM_train_list=UCM_train_list, UCM_name="UCM_all", recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name], evaluator_validation_list=evaluator_list, metric_to_optimize="MAP", output_folder_path=output_folder_path, parallelize_search=args.parallelize, n_jobs=args.n_jobs, n_cases=args.n_cases, n_random_starts=args.n_random_starts) elif args.recommender_name in SIDE_INFO_CLASS_DICT: temp_list = [] for i, URM in enumerate(URM_train_list): temp = sps.vstack([URM, ICM_train_list[i].T], format="csr") #temp = TF_IDF(temp).tocsr() temp_list.append(temp) run_cv_parameter_search(URM_train_list=temp_list, recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name], evaluator_validation_list=evaluator_list, metric_to_optimize="MAP", output_folder_path=output_folder_path, parallelize_search=args.parallelize, n_jobs=args.n_jobs, n_cases=args.n_cases, n_random_starts=args.n_random_starts) print("...tuning ended")
from src.utils.general_utility_functions import get_split_seed if __name__ == '__main__': # Data loading root_data_path = "../../data/" data_reader = RecSys2019Reader(root_data_path) data_reader = New_DataSplitter_leave_k_out(data_reader, k_out_value=1, allow_cold_users=False, use_validation_set=False, force_new_split=True, seed=get_split_seed()) data_reader.load_data() URM_train, URM_test = data_reader.get_holdout_split() ICM_all, _ = get_ICM_train_new(data_reader) UCM_all = get_UCM_train(data_reader) ignore_users = get_ignore_users( URM_train, data_reader.get_original_user_id_to_index_mapper(), lower_threshold=-1, upper_threshold=22, ignore_non_target_users=True) # Setting evaluator cutoff_list = [10] evaluator = EvaluatorHoldout(URM_test, cutoff_list=cutoff_list, ignore_users=ignore_users)
from src.tuning.holdout_validation.run_parameter_search_field_weight import run_parameter_search_field_ICM_weight from src.utils.general_utility_functions import get_split_seed if __name__ == '__main__': # Data loading data_reader = RecSys2019Reader("../../data/") data_reader = New_DataSplitter_leave_k_out(data_reader, k_out_value=3, use_validation_set=False, force_new_split=True, seed=get_split_seed()) data_reader.load_data() URM_train, URM_test = data_reader.get_holdout_split() # Build UCMs ICM_all, item_feature_to_range_mapper = get_ICM_train_new(data_reader) cold_users_mask = np.ediff1d(URM_train.tocsr().indptr) == 0 cold_users = np.arange(URM_train.shape[0])[cold_users_mask] # Setting evaluator cutoff_list = [10] evaluator = EvaluatorHoldout(URM_test, cutoff_list=cutoff_list, ignore_users=cold_users) version_path = "../../report/hp_tuning/search_weight_icm/" now = datetime.now().strftime('%b%d_%H-%M-%S') now = now + "_k_out_value_3/" version_path = version_path + "/" + now