How to use the chemprop.data.utils.split_data function in chemprop

data = get_data(path=args.data_path, args=args, logger=logger)
    args.num_tasks = data.num_tasks()
    args.features_size = data.features_size()
    args.real_num_tasks = args.num_tasks - args.features_size if args.predict_features else args.num_tasks
    debug(f'Number of tasks = {args.num_tasks}')

    if args.dataset_type == 'bert_pretraining':
        data.bert_init(args, logger)

    # Split data
    if args.dataset_type == 'regression_with_binning':  # Note: for now, binning based on whole dataset, not just training set
        data, bin_predictions, regression_data = data
        args.bin_predictions = bin_predictions
        debug(f'Splitting data with seed {args.seed}')
        train_data, _, _ = split_data(data=data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)
        _, val_data, test_data = split_data(regression_data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)
    else:
        debug(f'Splitting data with seed {args.seed}')
        if args.separate_test_set:
            test_data = get_data(path=args.separate_test_set, args=args, features_path=args.separate_test_set_features, logger=logger)
            if args.separate_val_set:
                val_data = get_data(path=args.separate_val_set, args=args, features_path=args.separate_val_set_features, logger=logger)
                train_data = data  # nothing to split; we already got our test and val sets
            else:
                train_data, val_data, _ = split_data(data=data, split_type=args.split_type, sizes=(0.8, 0.2, 0.0), seed=args.seed, args=args, logger=logger)
        else:
            train_data, val_data, test_data = split_data(data=data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)

    # Optionally replace test data with train or val data
    if args.test_split == 'train':
        test_data = train_data
    elif args.test_split == 'val':

# Split data
    if args.dataset_type == 'regression_with_binning':  # Note: for now, binning based on whole dataset, not just training set
        data, bin_predictions, regression_data = data
        args.bin_predictions = bin_predictions
        debug(f'Splitting data with seed {args.seed}')
        train_data, _, _ = split_data(data=data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)
        _, val_data, test_data = split_data(regression_data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)
    else:
        debug(f'Splitting data with seed {args.seed}')
        if args.separate_test_set:
            test_data = get_data(path=args.separate_test_set, args=args, features_path=args.separate_test_set_features, logger=logger)
            if args.separate_val_set:
                val_data = get_data(path=args.separate_val_set, args=args, features_path=args.separate_val_set_features, logger=logger)
                train_data = data  # nothing to split; we already got our test and val sets
            else:
                train_data, val_data, _ = split_data(data=data, split_type=args.split_type, sizes=(0.8, 0.2, 0.0), seed=args.seed, args=args, logger=logger)
        else:
            train_data, val_data, test_data = split_data(data=data, split_type=args.split_type, sizes=args.split_sizes, seed=args.seed, args=args, logger=logger)

    # Optionally replace test data with train or val data
    if args.test_split == 'train':
        test_data = train_data
    elif args.test_split == 'val':
        test_data = val_data

    if args.dataset_type == 'classification':
        class_sizes = get_class_sizes(data)
        debug('Class sizes')
        for i, task_class_sizes in enumerate(class_sizes):
            debug(f'{args.task_names[i]} '
                  f'{", ".join(f"{cls}: {size * 100:.2f}%" for cls, size in enumerate(task_class_sizes))}')

def run_random_forest(args: Namespace, logger: Logger = None) -> List[float]:
    if logger is not None:
        debug, info = logger.debug, logger.info
    else:
        debug = info = print

    debug(pformat(vars(args)))

    metric_func = get_metric_func(args.metric)

    debug('Loading data')
    data = get_data(path=args.data_path)

    debug(f'Splitting data with seed {args.seed}')
    # Need to have val set so that train and test sets are the same as when doing MPN
    train_data, _, test_data = split_data(data=data, split_type=args.split_type, seed=args.seed)

    debug(f'Total size = {len(data):,} | train size = {len(train_data):,} | test size = {len(test_data):,}')

    debug('Computing morgan fingerprints')
    for dataset in [train_data, test_data]:
        for datapoint in tqdm(dataset, total=len(dataset)):
            datapoint.set_features(morgan_fingerprint(smiles=datapoint.smiles, radius=args.radius, num_bits=args.num_bits))

    debug('Training')
    if args.single_task:
        scores = single_task_random_forest(train_data, test_data, metric_func, args)
    else:
        scores = multi_task_random_forest(train_data, test_data, metric_func, args)

    info(f'Test {args.metric} = {np.nanmean(scores)}')