Updating data loader

  return y.astype(float), w.astype(float)

def _featurize_smiles_df(df, featurizer, field, log_every_N=1000):

def _featurize_smiles_df(df, featurizer, field, log_every_n=1000):

  """Featurize individual compounds in dataframe.

  Given a featurizer that operates on individual chemical

    if mol:

      new_order = rdmolfiles.CanonicalRankAtoms(mol)

      mol = rdmolops.RenumberAtoms(mol, new_order)

    if ind % log_every_N == 0:

    if ind % log_every_n == 0:

      logger.info("Featurizing sample %d" % ind)

    features.append(featurizer.featurize([mol]))

  valid_inds = np.array(

  return X_shard

def _featurize_mol_df(df, featurizer, field, log_every_N=1000):

def _featurize_mol_df(df, featurizer, field, log_every_n=1000):

  """Featurize individual compounds in dataframe.

  Used when processing .sdf files, so the 3-D structure should be

    Should be created by dc.utils.save.load_sdf_files.

  featurizer: dc.feat.MolecularFeaturizer

    Featurizer for molecules.

  log_every_n: int, optional

    Controls how often logging statements are emitted.

  """

  sample_elems = df[field].tolist()

  features = []

  for ind, mol in enumerate(sample_elems):

    if ind % log_every_N == 0:

    if ind % log_every_n == 0:

      logger.info("Featurizing sample %d" % ind)

    features.append(featurizer.featurize([mol]))

  valid_inds = np.array(

        shard,

        self.featurizer,

        field=self.smiles_field,

        log_every_N=self.log_every_n)

        log_every_n=self.log_every_n)

class UserCSVLoader(CSVLoader):

        shard,

        self.featurizer,

        field=self.mol_field,

        log_every_N=self.log_every_n)

        log_every_n=self.log_every_n)

class FASTALoader(DataLoader):