Loading deepchem/feat/base_classes.py +20 −1 Original line number Diff line number Diff line Loading @@ -7,6 +7,8 @@ import numpy as np import multiprocessing from typing import Any, Dict, List, Iterable, Sequence, Tuple, Union from deepchem.utils import get_print_threshold from deepchem.utils.typing import PymatgenStructure logger = logging.getLogger(__name__) Loading Loading @@ -96,7 +98,15 @@ class Featurizer(object): args_names = [arg for arg in args_spec.args if arg != 'self'] args_info = '' for arg_name in args_names: args_info += arg_name + '=' + str(self.__dict__[arg_name]) + ', ' value = self.__dict__[arg_name] # for str if isinstance(value, str): value = "'" + value + "'" # for list if isinstance(value, list): threshold = get_print_threshold() value = np.array2string(np.array(value), threshold=threshold) args_info += arg_name + '=' + str(value) + ', ' return self.__class__.__name__ + '[' + args_info[:-2] + ']' def __str__(self) -> str: Loading Loading @@ -126,6 +136,15 @@ class Featurizer(object): override_args_info = '' for arg_name, default in zip(args_names, args_default_values): arg_value = self.__dict__[arg_name] # validation # skip list if isinstance(arg_value, list): continue if isinstance(arg_value, str): # skip path string if "\\/." in arg_value or "/" in arg_value or '.' in arg_value: continue # main logic if default != arg_value: override_args_info += '_' + arg_name + '_' + str(arg_value) return self.__class__.__name__ + override_args_info Loading deepchem/feat/molecule_featurizers/mol_graph_conv_featurizer.py +1 −1 Original line number Diff line number Diff line Loading @@ -131,7 +131,7 @@ class MolGraphConvFeaturizer(MolecularFeaturizer): ---------- add_self_edges: 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. you sometimes need to add explicit self-connected edges. """ self.add_self_edges = add_self_edges Loading deepchem/feat/molecule_featurizers/one_hot_featurizer.py +3 −2 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ ZINC_CHARSET = [ class OneHotFeaturizer(MolecularFeaturizer): """Encodes SMILES as a one-hot array. This featurizer encodes its SMILES string as a one-hot array. This featurizer encodes SMILES string as a one-hot array. Notes ---- Loading @@ -34,7 +34,8 @@ class OneHotFeaturizer(MolecularFeaturizer): charset: List[str], optional (default ZINC_CHARSET) A list of strings, where each string is length 1 and unique. max_length: int, optional (default 100) length to pad the SMILES strings to. The max length for SMILES string. If the length of SMILES string is shorter than max_length, the SMILES is padded using space. """ if len(charset) != len(set(charset)): raise ValueError("All values in charset must be unique.") Loading Loading
deepchem/feat/base_classes.py +20 −1 Original line number Diff line number Diff line Loading @@ -7,6 +7,8 @@ import numpy as np import multiprocessing from typing import Any, Dict, List, Iterable, Sequence, Tuple, Union from deepchem.utils import get_print_threshold from deepchem.utils.typing import PymatgenStructure logger = logging.getLogger(__name__) Loading Loading @@ -96,7 +98,15 @@ class Featurizer(object): args_names = [arg for arg in args_spec.args if arg != 'self'] args_info = '' for arg_name in args_names: args_info += arg_name + '=' + str(self.__dict__[arg_name]) + ', ' value = self.__dict__[arg_name] # for str if isinstance(value, str): value = "'" + value + "'" # for list if isinstance(value, list): threshold = get_print_threshold() value = np.array2string(np.array(value), threshold=threshold) args_info += arg_name + '=' + str(value) + ', ' return self.__class__.__name__ + '[' + args_info[:-2] + ']' def __str__(self) -> str: Loading Loading @@ -126,6 +136,15 @@ class Featurizer(object): override_args_info = '' for arg_name, default in zip(args_names, args_default_values): arg_value = self.__dict__[arg_name] # validation # skip list if isinstance(arg_value, list): continue if isinstance(arg_value, str): # skip path string if "\\/." in arg_value or "/" in arg_value or '.' in arg_value: continue # main logic if default != arg_value: override_args_info += '_' + arg_name + '_' + str(arg_value) return self.__class__.__name__ + override_args_info Loading
deepchem/feat/molecule_featurizers/mol_graph_conv_featurizer.py +1 −1 Original line number Diff line number Diff line Loading @@ -131,7 +131,7 @@ class MolGraphConvFeaturizer(MolecularFeaturizer): ---------- add_self_edges: 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. you sometimes need to add explicit self-connected edges. """ self.add_self_edges = add_self_edges Loading
deepchem/feat/molecule_featurizers/one_hot_featurizer.py +3 −2 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ ZINC_CHARSET = [ class OneHotFeaturizer(MolecularFeaturizer): """Encodes SMILES as a one-hot array. This featurizer encodes its SMILES string as a one-hot array. This featurizer encodes SMILES string as a one-hot array. Notes ---- Loading @@ -34,7 +34,8 @@ class OneHotFeaturizer(MolecularFeaturizer): charset: List[str], optional (default ZINC_CHARSET) A list of strings, where each string is length 1 and unique. max_length: int, optional (default 100) length to pad the SMILES strings to. The max length for SMILES string. If the length of SMILES string is shorter than max_length, the SMILES is padded using space. """ if len(charset) != len(set(charset)): raise ValueError("All values in charset must be unique.") Loading
