👌 fix typo and update docstrings

  get_bond_stereo_one_hot

def constrcut_atom_feature(atom: RDKitAtom, h_bond_infos: List[Tuple[int, str]],

def construct_atom_feature(atom: RDKitAtom, h_bond_infos: List[Tuple[int, str]],

                           sssr: List[Sequence]) -> List[float]:

  """Construct an atom feature from a RDKit atom object.

  Parameters

  ---------

  ----------

  atom: rdkit.Chem.rdchem.Atom

    RDKit atom object

  h_bond_infos: List[Tuple[int, str]]

  Returns

  -------

  List[Union[int, float]]

  List[float]

    A one-hot vector of the atom feature.

  """

  atom_type = get_atom_type_one_hot(atom)

  Returns

  -------

  List[int]

  List[float]

    A one-hot vector of the bond feature.

  """

  bond_type = get_bond_type_one_hot(bond)

class MolGraphConvFeaturizer(MolecularFeaturizer):

  """This class is a featurizer of gerneral graph convolution networks for molecules.

  The default node(atom) and edge(bond) representations are based on WeaveNet paper.

  If you want to use your own representations, you could use this class as a guide

  to define your original Featurizer. In many cases, it's enough to modify return values of

  `constrcut_atom_feature` or `constrcut_bond_feature`.

  The default node(atom) and edge(bond) representations are based on

  `WeaveNet paper <https://arxiv.org/abs/1603.00856>`_. If you want to use your own representations,

  you could use this class as a guide to define your original Featurizer. In many cases, it's enough

  to modify return values of `construct_atom_feature` or `construct_bond_feature`.

  The default node representation are constructed by concatenating the following values,

  and the feature length is 38.

  def __init__(self, add_self_loop: bool = False):

    """

    Paramters

    ---------

    Parameters

    ----------

    add_self_loop: bool, default False

      Whether to add self-connected edges or not. If you want to use DGL,

      you sometimes need to add explict self-connected edges.

  def _featurize(self, mol: RDKitMol) -> GraphData:

    """Calculate molecule graph features from RDKit mol object.

    Parametrs

    ---------

    Parameters

    ----------

    mol: rdkit.Chem.rdchem.Mol

      RDKit mol object.

    # construct atom (node) feature

    atom_features = np.array(

        [

            constrcut_atom_feature(atom, h_bond_infos, sssr)

            construct_atom_feature(atom, h_bond_infos, sssr)

            for atom in mol.GetAtoms()

        ],

        dtype=np.float,

  featurizer = MolGraphConvFeaturizer()

  tasks, dataset, transformers, metric = get_dataset(

      'regression', featurizer=featurizer)

  n_tasks = len(tasks)

  # initialize models

  n_tasks = len(tasks)

  model = GATModel(

      in_node_dim=25,

      hidden_node_dim=64,

      heads=1,

      num_conv=3,

      predicator_hidden_feats=32,

      n_tasks=n_tasks,

      loss=losses.L2Loss(),

      batch_size=10,

      learning_rate=0.001)

      n_tasks=n_tasks, loss=losses.L2Loss(), batch_size=4, learning_rate=0.001)

  # overfit test

  model.fit(dataset, nb_epoch=100)

  scores = model.evaluate(dataset, [metric], transformers)

  assert scores['mean_absolute_error'] < 0.1

  # TODO: check this asseration is correct or not

  assert scores['mean_absolute_error'] < 1.0

  List[float]

    A vector of the formal charge.

  """

  return [atom.GetFormalCharge()]

  return [float(atom.GetFormalCharge())]

def get_atom_partial_charge(atom: RDKitAtom) -> List[float]: