yapf

    if isinstance(dataset, DiskDataset):

      rem_dataset = dataset

    else:

      rem_dataset = DiskDataset.from_numpy(dataset.X, dataset.y, dataset.w, dataset.ids)

      rem_dataset = DiskDataset.from_numpy(dataset.X, dataset.y, dataset.w,

                                           dataset.ids)

    for fold in range(k):

      # Note starts as 1/k since fold starts at 0. Ends at 1 since fold goes up

      # to k-1.

    distances = np.ones(shape=(data_len, data_len))

    for i in range(data_len):

      for j in range(data_len):

        distances[i][j] = 1 - DataStructs.FingerprintSimilarity(

          fingerprints[i], fingerprints[j])

        distances[i][j] = 1 - DataStructs.FingerprintSimilarity(fingerprints[i],

                                                                fingerprints[j])

    train_cutoff = int(frac_train * len(dataset))

    valid_cutoff = int(frac_valid * len(dataset))