##### MAIN PART ######
print('Preparing data...')
start = time.time()
dataset_manager = DatasetManager(dataset_name)
data = dataset_manager.read_dataset()
train, test = dataset_manager.split_data(
data, train_ratio, split=data_split_type
) # to reproduce results of Tax et al., use 'ordered' instead of 'temporal'
dt_train = dataset_manager.encode_data_with_label_all_data(train)
dt_test = dataset_manager.encode_data_with_label_all_data(test)
if normalize_over == "train":
dataset_manager.calculate_divisors(dt_train)
elif normalize_over == "all":
dt_all = dataset_manager.extract_timestamp_features(data)
dt_all = dataset_manager.extract_duration_features(dt_all)
dataset_manager.calculate_divisors(dt_all)
else:
print("unknown normalization mode")
dt_test = dataset_manager.normalize_data(dt_test)
print("Done: %s" % (time.time() - start))
max_len = dataset_manager.get_max_case_length(dt_train)
activity_cols = [col for col in dt_train.columns if col.startswith("act")]
n_activities = len(activity_cols)
data_dim = dt_train.shape[1] - 3
