How to use the chemprop.data.scaffold.scaffold_split function in chemprop

if i != test_fold_index and (val_fold_index is None or i != val_fold_index):
                train_val.extend(folds[i])

        if val_fold_index is not None:
            train = train_val
        else:
            random.seed(seed)
            random.shuffle(train_val)
            train_size = int(sizes[0] * len(train_val))
            train = train_val[:train_size]
            val = train_val[train_size:]

        return MoleculeDataset(train), MoleculeDataset(val), MoleculeDataset(test)

    elif split_type == 'scaffold':
        return scaffold_split(data, sizes=sizes, balanced=False, logger=logger)
    
    elif split_type == 'scaffold_balanced':
        return scaffold_split(data, sizes=sizes, balanced=True, seed=seed, logger=logger)

    elif split_type == 'scaffold_one':
        return scaffold_split_one(data)

    elif split_type == 'scaffold_overlap':
        assert scaffold_overlap is not None
        return scaffold_split_overlap(data, overlap=scaffold_overlap, seed=seed, logger=logger)

    elif split_type == 'random':
        data.shuffle(seed=seed)

        train_size = int(sizes[0] * len(data))
        train_val_size = int((sizes[0] + sizes[1]) * len(data))

if val_fold_index is not None:
            train = train_val
        else:
            random.seed(seed)
            random.shuffle(train_val)
            train_size = int(sizes[0] * len(train_val))
            train = train_val[:train_size]
            val = train_val[train_size:]

        return MoleculeDataset(train), MoleculeDataset(val), MoleculeDataset(test)

    elif split_type == 'scaffold':
        return scaffold_split(data, sizes=sizes, balanced=False, logger=logger)
    
    elif split_type == 'scaffold_balanced':
        return scaffold_split(data, sizes=sizes, balanced=True, seed=seed, logger=logger)

    elif split_type == 'scaffold_one':
        return scaffold_split_one(data)

    elif split_type == 'scaffold_overlap':
        assert scaffold_overlap is not None
        return scaffold_split_overlap(data, overlap=scaffold_overlap, seed=seed, logger=logger)

    elif split_type == 'random':
        data.shuffle(seed=seed)

        train_size = int(sizes[0] * len(data))
        train_val_size = int((sizes[0] + sizes[1]) * len(data))

        train = data[:train_size]
        val = data[train_size:train_val_size]