yapf

    # Sort from largest to smallest scaffold sets

    scaffolds = {key: sorted(value) for key, value in scaffolds.items()}

    scaffold_sets = [

      scaffold_set

      for (scaffold, scaffold_set) in sorted(

        scaffold_set for (scaffold, scaffold_set) in sorted(

            scaffolds.items(), key=lambda x: (len(x[1]), x[1][0]), reverse=True)

    ]

    train_cutoff = frac_train * len(dataset)