How to use the deepchem.feat.ConvMolFeaturizer function in deepchem

deepchem.utils.download_url(
        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/clearance.csv'
    )

  clearance_tasks = ['exp']

  if reload:
    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(
        save_dir)
    if loaded:
      return clearance_tasks, all_dataset, transformers

  if featurizer == 'ECFP':
    featurizer = deepchem.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = deepchem.feat.ConvMolFeaturizer()
  elif featurizer == 'Weave':
    featurizer = deepchem.feat.WeaveFeaturizer()
  elif featurizer == 'Raw':
    featurizer = deepchem.feat.RawFeaturizer()

  loader = deepchem.data.CSVLoader(
      tasks=clearance_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  if split is None:
    # Initialize transformers
    transformers = [
        deepchem.trans.NormalizationTransformer(
            transform_y=True, dataset=dataset, move_mean=move_mean)
    ]

def load_sampl(featurizer='ECFP', split='index'):
  """Load SAMPL datasets."""
  # Featurize SAMPL dataset
  print("About to featurize SAMPL dataset.")
  current_dir = os.path.dirname(os.path.realpath(__file__))
  dataset_file = os.path.join(
      current_dir, "./SAMPL.csv")
  SAMPL_tasks = ['expt']
  if featurizer == 'ECFP':
    featurizer = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = dc.feat.ConvMolFeaturizer()
  loader = dc.data.CSVLoader(
      tasks=SAMPL_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(
      dataset_file, shard_size=8192)

  # Initialize transformers 
  transformers = [
      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

  print("About to transform data")
  for transformer in transformers:
      dataset = transformer.transform(dataset)

  splitters = {'index': dc.splits.IndexSplitter(),
               'random': dc.splits.RandomSplitter(),
               'scaffold': dc.splits.ScaffoldSplitter()}

dataset = deepchem.utils.save.load_from_disk(dataset_file)
  clintox_tasks = dataset.columns.values[1:].tolist()
  logger.info("Tasks in dataset: %s" % (clintox_tasks))
  logger.info("Number of tasks in dataset: %s" % str(len(clintox_tasks)))
  logger.info("Number of examples in dataset: %s" % str(dataset.shape[0]))
  if reload:
    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(
        save_dir)
    if loaded:
      return clintox_tasks, all_dataset, transformers
  # Featurize clintox dataset
  logger.info("About to featurize clintox dataset.")
  if featurizer == 'ECFP':
    featurizer = deepchem.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = deepchem.feat.ConvMolFeaturizer()
  elif featurizer == 'Weave':
    featurizer = deepchem.feat.WeaveFeaturizer()
  elif featurizer == 'Raw':
    featurizer = deepchem.feat.RawFeaturizer()

  loader = deepchem.data.CSVLoader(
      tasks=clintox_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  # Transform clintox dataset
  if split is None:
    transformers = [
        deepchem.trans.BalancingTransformer(transform_w=True, dataset=dataset)
    ]

    logger.info("Split is None, about to transform data.")

]

  dataset_dir = os.path.join(data_dir, "tox21", featurizer, split)
  train, valid, test = os.path.join(dataset_dir, 'train'), os.path.join(
      dataset_dir, 'valid'), os.path.join(dataset_dir, 'test')
  if os.path.isdir(dataset_dir):
    train, valid, test = DiskDataset(data_dir=train), DiskDataset(
        data_dir=valid), DiskDataset(data_dir=test)
    transformers = [
        dc.trans.BalancingTransformer(transform_w=True, dataset=train)
    ]
    return tox21_tasks, (train, valid, test), transformers
  if featurizer == 'ECFP':
    featurizer_func = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer_func = dc.feat.ConvMolFeaturizer()
  elif featurizer == 'AdjMatrix':
    featurizer_func = dc.feat.AdjacencyFingerprint(num_atoms_feature=True)
  loader = dc.data.CSVLoader(
      tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer_func)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  # Initialize transformers
  transformers = [
      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)
  ]

  print("About to transform data")
  for transformer in transformers:
    dataset = transformer.transform(dataset)

  splitters = {

def load_muv_convmol():
  """Load MUV datasets. Does not do train/test split"""
  # Load MUV dataset
  print("About to load MUV dataset.")
  current_dir = os.path.dirname(os.path.realpath(__file__))
  dataset_file = os.path.join(
      current_dir, "../../datasets/muv.csv.gz")
  # Featurize MUV dataset
  print("About to featurize MUV dataset.")
  featurizer = dc.feat.ConvMolFeaturizer()
  MUV_tasks = sorted(['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',
                      'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',
                      'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
                      'MUV-466', 'MUV-832'])

  loader = dc.data.CSVLoader(
      tasks=MUV_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file)

  # Initialize transformers 
  transformers = [
      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]
  print("About to transform data")
  for transformer in transformers:
      dataset = transformer.transform(dataset)

hopv_tasks = [
      'HOMO', 'LUMO', 'electrochemical_gap', 'optical_gap', 'PCE', 'V_OC',
      'J_SC', 'fill_factor'
  ]

  if reload:
    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(
        save_dir)
    if loaded:
      return hopv_tasks, all_dataset, transformers

  if featurizer == 'ECFP':
    featurizer = deepchem.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = deepchem.feat.ConvMolFeaturizer()
  elif featurizer == 'Weave':
    featurizer = deepchem.feat.WeaveFeaturizer()
  elif featurizer == 'Raw':
    featurizer = deepchem.feat.RawFeaturizer()

  loader = deepchem.data.CSVLoader(
      tasks=hopv_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  if split == None:
    transformers = [
        deepchem.trans.NormalizationTransformer(
            transform_y=True, dataset=dataset)
    ]

    logger.info("Split is None, about to transform data")

def load_dataset(dataset_file, featurizer='ECFP', split='index'):
  tasks = ['exp']

  if featurizer == 'ECFP':
    featurizer = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = dc.feat.ConvMolFeaturizer()

  loader = dc.data.CSVLoader(
      tasks=tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  transformers = [
      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)
  ]
  for transformer in transformers:
    dataset = transformer.transform(dataset)

  splitters = {
      'index': dc.splits.IndexSplitter(),
      'random': dc.splits.RandomSplitter(),
      'scaffold': dc.splits.ScaffoldSplitter()
  }

# Load TOXCAST dataset
  print("About to load TOXCAST dataset.")
  dataset_file = os.path.join(
      current_dir, "./processing/toxcast_data.csv.gz")
  dataset = dc.utils.save.load_from_disk(dataset_file)
  print("Columns of dataset: %s" % str(dataset.columns.values))
  print("Number of examples in dataset: %s" % str(dataset.shape[0]))

  # Featurize TOXCAST dataset
  print("About to featurize TOXCAST dataset.")

  if featurizer == 'ECFP':
      featurizer_func = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
      featurizer_func = dc.feat.ConvMolFeaturizer()

  TOXCAST_tasks = dataset.columns.values[1:].tolist()

  loader = dc.load.DataLoader(tasks=TOXCAST_tasks,
                              smiles_field="smiles",
                              featurizer=featurizer_func,
                              verbosity="high")
  dataset = loader.featurize(dataset_file)

  # Initialize transformers 
  transformers = [
      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]
  print("About to transform data")
  for transformer in transformers:
    dataset = transformer.transform(dataset)

def load_delaney(featurizer='ECFP', split='index'):
  """Load delaney datasets."""
  # Featurize Delaney dataset
  print("About to featurize Delaney dataset.")
  current_dir = os.path.dirname(os.path.realpath(__file__))
  dataset_file = os.path.join(current_dir,
                              "../../datasets/delaney-processed.csv")
  delaney_tasks = ['measured log solubility in mols per litre']
  if featurizer == 'ECFP':
    featurizer = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer = dc.feat.ConvMolFeaturizer()
  loader = dc.data.CSVLoader(
      tasks=delaney_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file, shard_size=8192)

  # Initialize transformers
  transformers = [
      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)
  ]

  print("About to transform data")
  for transformer in transformers:
    dataset = transformer.transform(dataset)

  splitters = {
      'index': dc.splits.IndexSplitter(),
      'random': dc.splits.RandomSplitter(),