Change args

"""

import os

import logging

import numpy as np

import deepchem

from deepchem.feat import Featurizer

from deepchem.trans import Transformer

from deepchem.splits.splitters import Splitter

from deepchem.molnet.defaults import get_defaults

from typing import List, Tuple, Dict, Optional

from typing import List, Tuple, Dict, Optional, Union

logger = logging.getLogger(__name__)

            'transform_X': True

        }

    },

    zinc15_kwargs: Dict[str, str] = {

        'dataset_size': '250K',

        'dataset_dimension': '2D'

    },

    dataset_size: str = '250K',

    dataset_dimension: str = '2D',

    test_run: bool = False,

    **kwargs) -> Tuple[List, Optional[Tuple], List]:

  """Load zinc15.

  in 2D (SMILES string) format.

  MolNet provides subsets of 250K, 1M, and 10M "lead-like" compounds

  from ZINC15. Compounds in ZINC15 are labeled by their molecular weight 

  from ZINC15. The full dataset of 270M "goldilocks" compounds is also

  available. Compounds in ZINC15 are labeled by their molecular weight 

  and LogP (solubility) values. Each compound also has information about how

  readily available (purchasable) it is and its reactivity. Lead-like

  compounds have molecular weight between 300 and 350 Daltons and LogP

  between -1 and 3.5.

  between -1 and 3.5. Goldilocks compounds are lead-like compounds with

  LogP values further restricted to between 2 and 3.

  If `reload = True` and `data_dir` (`save_dir`) is specified, the loader

  will attempt to load the raw dataset (featurized dataset) from disk.

  transformer_kwargs : dict

    Maps transformer names to constructor arguments, e.g.

    {"BalancingTransformer": {"transform_x":True, "transform_y":False}}

  zinc15_kwargs : dict

    Specify parameters for the ZINC15 dataset. Accepted keywords are

    'dataset_size' and 'dataset_dimension'.

  dataset_size : str (default '250K')

    Number of compounds to download; '250K', '1M', '10M', or '270M'.

  dataset_dimension : str (default '2D')

    SMILES strings (2D) or 3D SDF files; '2D' or '3D'

  test_run : bool (default False)

    Flag to indicate tests, if True dataset is not downloaded.

  **kwargs : additional optional arguments.

  Returns

  -----

  The total ZINC dataset with SMILES strings contains hundreds of millions

  of compounds and is over 100GB! ZINC250K is recommended for experimentation.

  The full set of 270M goldilocks compounds is 23GB.

  References

  ----------

  Examples

  --------

  >> import deepchem as dc

  >> tasks, datasets, transformers = dc.molnet.load_zinc15(reload=False)

  >> train_dataset, val_dataset, test_dataset = datasets

  >> n_tasks = len(tasks)

  >> n_features = train_dataset.get_data_shape()[0]

  >> model = dc.models.MultitaskRegressor(n_tasks, n_features)

  >>> import deepchem as dc

  >>> tasks, datasets, transformers = dc.molnet.load_zinc15(test_run=True)

  >>> train_dataset, val_dataset, test_dataset = datasets

  >>> n_tasks = len(tasks)

  >>> n_features = train_dataset.X.shape[1]

  >>> model = dc.models.MultitaskRegressor(n_tasks, n_features)

  """

  logger.info("About to featurize zinc15.")

  my_tasks = ['mwt', 'logp', 'reactive']  # machine learning targets

  # Get params specific to ZINC15

  dataset_size = zinc15_kwargs.get('dataset_size', '250K')

  dataset_dimension = zinc15_kwargs.get('dataset_dimension', '2D')

  if test_run:

    ds = deepchem.data.NumpyDataset(np.zeros((10, 1)))

    return my_tasks, (ds, ds, ds), []

  # Raise warnings and list other available options

  if dataset_size not in ['250K', '1M', '10M']:

  if dataset_size not in ['250K', '1M', '10M', '270M']:

    raise ValueError("""

      Only '250K', '1M', and '10M' are supported for dataset_size.

      """)

    raise ValueError("""

      Currently, only '2D' is supported for dataset_dimension.

      """)

  if dataset_size == '270M':

    answer = ''

    while answer not in ['y', 'n']:

      answer = input("""You're about to download 270M SMILES strings.

        This dataset is 23GB. Are you sure you want to continue? (Y/N)"""

                    ).lower()

    if answer == 'n':

      raise ValueError('Choose a smaller dataset_size.')

  dataset_filename = 'zinc15_' + dataset_size + '_' + dataset_dimension + '.tar.gz'

        featurizer=featurizer)

  # Featurize dataset

  dataset = loader.create_dataset(dataset_file)

  dataset = loader.create_dataset(os.path.join(data_dir, dataset_file))

  train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

      dataset, **splitter_kwargs)

        save_folder, train_dataset, valid_dataset, test_dataset, transformers)

  return my_tasks, (train_dataset, valid_dataset, test_dataset), transformers

if __name__ == "__main__":

  import doctest

  doctest.testmod()