Benchmark modified

import shutil

import deepchem as dc

def load_nci(base_dir, reload=True, force_transform=False,

             shard_size=1000, num_shards_per_batch=4):

  """Load NCI datasets. Does not do train/test split"""

  # Set some global variables up top

  verbosity = "high"

  model = "logistic"

  regen = False

def load_nci(shard_size=1000, num_shards_per_batch=4):

  # Create some directories for analysis

  # The base_dir holds the results of all analysis

  if not reload:

    if os.path.exists(base_dir):

      print("Deleting dir in nci_datasets.py")

      print(base_dir)

      shutil.rmtree(base_dir)

  if not os.path.exists(base_dir):

    os.makedirs(base_dir)

  current_dir = os.path.dirname(os.path.realpath(__file__))

  #Make directories to store the raw and featurized datasets.

  data_dir = os.path.join(base_dir, "dataset")

  # Load nci dataset

  print("About to load NCI dataset.")

      current_dir, "../../datasets/nci_1.csv.gz")

  dataset_file2_path = os.path.join(

      current_dir, "../../datasets/nci_2.csv.gz")

  dataset_paths = [dataset_file1_path, dataset_file2_path]

  dataset = load_sharded_csv(dataset_paths)

  print("Columns of dataset: %s" % str(dataset.columns.values))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))

  # Featurize nci dataset

  print("About to featurize nci dataset.")

  featurizer = CircularFingerprint(size=1024)

  #was sorted list originally in muv_datasets.py, but csv is ordered so removed

  featurizer = dc.feat.CircularFingerprint(size=1024)

  all_nci_tasks = (['CCRF-CEM', 'HL-60(TB)', 'K-562', 'MOLT-4', 'RPMI-8226',

                    'SR', 'A549/ATCC', 'EKVX', 'HOP-62', 'HOP-92', 'NCI-H226',

                    'NCI-H23', 'NCI-H322M', 'NCI-H460', 'NCI-H522', 'COLO 205',

                    'MDA-MB-231/ATCC', 'MDA-MB-468', 'HS 578T', 'BT-549',

                    'T-47D'])

  loader = DataLoader(tasks=all_nci_tasks,

  loader = dc.load.DataLoader(tasks=all_nci_tasks,

                     	      smiles_field="smiles",

	                      featurizer=featurizer,

                      verbosity=verbosity)

  if not reload or not os.path.exists(data_dir):

    dataset = loader.featurize(dataset_paths, data_dir, shard_size=shard_size,

        	              verbosity='high')

  dataset = loader.featurize(dataset_paths, shard_size=shard_size,

                             num_shards_per_batch=num_shards_per_batch)

    regen = True

  else:

    dataset = Dataset(data_dir, reload=True)

  # Initialize transformers

  transformers = []

  if regen or force_transform:

  print("About to transform data")

  transformers = [

        NormalizationTransformer(transform_y=True, dataset=dataset)]

      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

  for transformer in transformers:

    dataset = transformer.transform(dataset)

  return all_nci_tasks, dataset, transformers

  splitter = dc.splits.RandomSplitter()

  print("Performing new split.")

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

  return all_nci_tasks, (train, valid, test), transformers

  current_dir = os.path.dirname(os.path.realpath(__file__))

  print("About to load PCBA dataset.")

  dataset_file = os.path.join(

      current_dir, "../../datasets/pcba.csv.gz")

  dataset_file = os.path.join(current_dir, "../../datasets/pcba.csv.gz")

  # Featurize PCBA dataset

  print("About to featurize PCBA dataset.")