def main():
args = get_arguments()
# Data loading
data_reader = RecSys2019Reader(args.reader_path)
data_reader = New_DataSplitter_leave_k_out(data_reader, k_out_value=3, use_validation_set=False,
force_new_split=True, seed=args.seed)
data_reader.load_data()
URM_train, URM_test = data_reader.get_holdout_split()
if args.recommender_name == "sslim_bpr":
ICM_all = get_ICM_train(data_reader)
URM_train = sps.vstack([URM_train, ICM_all.T], format="csr")
if args.recommender_name == "rp3beta_side":
ICM_all = get_ICM_train(data_reader)
URM_train = sps.vstack([URM_train, ICM_all.T], format="csr")
URM_train = TF_IDF(URM_train).tocsr()
if args.recommender_name == "pure_svd":
URM_train = TF_IDF(URM_train).tocsr()
if args.recommender_name == "pure_svd_side":
ICM_all = get_ICM_train(data_reader)
URM_train = sps.vstack([URM_train, ICM_all.T], format="csr")
# Setting evaluator
exclude_cold_users = args.exclude_users
h = int(args.focus_on_high)
fol = int(args.focus_on_low)
if h != 0:
print("Excluding users with less than {} interactions".format(h))
ignore_users_mask = np.ediff1d(URM_train.tocsr().indptr) < h
ignore_users = np.arange(URM_train.shape[0])[ignore_users_mask]
elif fol != 0:
print("Excluding users with more than {} interactions".format(fol))
warm_users_mask = np.ediff1d(URM_train.tocsr().indptr) > fol
ignore_users = np.arange(URM_train.shape[0])[warm_users_mask]
if exclude_cold_users:
cold_user_mask = np.ediff1d(URM_train.tocsr().indptr) == 0
cold_users = np.arange(URM_train.shape[0])[cold_user_mask]
ignore_users = np.unique(np.concatenate((cold_users, ignore_users)))
elif exclude_cold_users:
print("Excluding cold users...")
cold_user_mask = np.ediff1d(URM_train.tocsr().indptr) == 0
ignore_users = np.arange(URM_train.shape[0])[cold_user_mask]
else:
ignore_users = None
cutoff_list = [10]
evaluator = EvaluatorHoldout(URM_test, cutoff_list=cutoff_list, 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
runParameterSearch_Collaborative(URM_train=URM_train,
recommender_class=RECOMMENDER_CLASS_DICT[args.recommender_name],
evaluator_validation=evaluator,
metric_to_optimize="MAP",
output_folder_path=version_path,
n_cases=int(args.n_cases),
n_random_starts=int(args.n_random_starts))
print("...tuning ended")
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=K_OUT,
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 ICMs
ICM_all = get_ICM_train(data_reader)
# Build UCMs
UCM_all = get_UCM_train(data_reader)
model = HybridWeightedAverageRecommender(URM_train, normalize=NORMALIZE)
all_models = _get_all_models(URM_train=URM_train,
UCM_all=UCM_all,
ICM_all=ICM_all)
for model_name, model_object in all_models.items():
model.add_fitted_model(model_name, model_object)
print("The models added in the hybrid are: {}".format(
list(all_models.keys())))
# Setting evaluator