format code style

        save_dir, "full_protein-%s-%s-%s" % (subset, featurizer, split))

  if save_timestamp:

        save_folder = "%s-%s-%s" % (

            save_folder, time.strftime("%Y%m%d", time.localtime()),

    save_folder = "%s-%s-%s" % (save_folder,

                                time.strftime("%Y%m%d", time.localtime()),

                                re.search("\.(.*)", str(time.time())).group(1))

  if reload:

    if not os.path.exists(save_folder):

      raise IOError("Cannot find saved dataset from %s!" % save_folder)

        print("\nLoading featurized and splitted dataset from:\n%s\n" %

              save_folder)

    print("\nLoading featurized and splitted dataset from:\n%s\n" % save_folder)

    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(

        save_folder)

    if loaded:

      return pdbbind_tasks, all_dataset, transformers

    else:

            raise IOError(

                "Failed to load featurized and splitted dataset from:\n%s\n" %

                save_folder)

      raise IOError("Failed to load featurized and splitted dataset from:\n%s\n"

                    % save_folder)

  dataset_file = os.path.join(data_dir, "pdbbind_v2015.tar.gz")

  if not os.path.exists(dataset_file):

        logger.warning(

            "About to download PDBBind full dataset. Large file, 2GB")

    logger.warning("About to download PDBBind full dataset. Large file, 2GB")

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/' +

        "pdbbind_v2015.tar.gz",

  print("\nFeaturized and splitted dataset:\n%s" % save_folder)

  if subset == "core":

        index_labels_file = os.path.join(data_folder,

                                         "INDEX_core_data.2013")

    index_labels_file = os.path.join(data_folder, "INDEX_core_data.2013")

  elif subset == "refined":

        index_labels_file = os.path.join(data_folder,

                                         "INDEX_refined_data.2015")

    index_labels_file = os.path.join(data_folder, "INDEX_refined_data.2015")

  else:

    raise ValueError("Other subsets not supported")

    pdbs = [line[:4] for line in g.readlines() if line[0] != "#"]

  if load_binding_pocket:

    protein_files = [

            os.path.join(data_folder, pdb, "%s_pocket.pdb" % pdb)

            for pdb in pdbs

        os.path.join(data_folder, pdb, "%s_pocket.pdb" % pdb) for pdb in pdbs

    ]

  else:

    protein_files = [

            os.path.join(data_folder, pdb, "%s_protein.pdb" % pdb)

            for pdb in pdbs

        os.path.join(data_folder, pdb, "%s_protein.pdb" % pdb) for pdb in pdbs

    ]

  ligand_files = [

      os.path.join(data_folder, pdb, "%s_ligand.sdf" % pdb) for pdb in pdbs

    featurizer = rgf.RdkitGridFeaturizer(

        voxel_width=2.0,

        feature_types=[

                'ecfp', 'splif', 'hbond', 'salt_bridge', 'pi_stack',

                'cation_pi', 'charge'

            'ecfp', 'splif', 'hbond', 'salt_bridge', 'pi_stack', 'cation_pi',

            'charge'

        ],

        flatten=True)

  elif featurizer == "atomic" or featurizer == "atomic_conv":

  else:

    raise ValueError("Featurizer not supported")

  print("Featurizing Complexes")

  print("\nFeaturizing Complexes for \"%s\" ...\n" % data_folder)

  feat_t1 = time.time()

  features, failures = featurizer.featurize_complexes(ligand_files,

                                                      protein_files)

  # Delete labels for failing elements

  feat_t2 = time.time()

  print("\nFeaturization finished, took %0.3f s." % (feat_t2 - feat_t1))

  # Delete labels and ids for failing elements

  labels = np.delete(labels, failures)

  labels = labels.reshape((len(labels), 1))

  ids = np.delete(pdbs, failures)

      'random': deepchem.splits.RandomSplitter(),

  }

  splitter = splitters[split]

    train, valid, test = splitter.train_valid_test_split(

        dataset, seed=split_seed)

  train, valid, test = splitter.train_valid_test_split(dataset, seed=split_seed)

  all_dataset = (train, valid, test)

  print("\nSaving dataset to \"%s\" ..." % save_folder)