Loading deepchem/feat/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ from deepchem.feat.base_classes import MaterialStructureFeaturizer from deepchem.feat.base_classes import MaterialCompositionFeaturizer from deepchem.feat.base_classes import ComplexFeaturizer from deepchem.feat.base_classes import UserDefinedFeaturizer from deepchem.feat.base_classes import DummyFeaturizer from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.graph_features import WeaveFeaturizer Loading deepchem/feat/base_classes.py +37 −0 Original line number Diff line number Diff line Loading @@ -421,3 +421,40 @@ class UserDefinedFeaturizer(Featurizer): def __init__(self, feature_fields): """Creates user-defined-featurizer.""" self.feature_fields = feature_fields class DummyFeaturizer(Featurizer): """Class that implements a no-op featurization. This is useful when the raw dataset has to be used without featurizing the examples. The Molnet loader requires a featurizer input and such datasets can be used in their original form by passing the raw featurizer. Examples -------- >>> import deepchem as dc >>> smi_map = [["N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]", "N#CSCC(=O)c1ccc(C(F)(F)F)cc1"], ["C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O", "FCC(c1cccc(Br)n1)N1CCOCC1"]] >>> Featurizer = dc.feat.DummyFeaturizer() >>> smi_feat = Featurizer.featurize(smi_map) >>> smi_feat array([['N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]', 'N#CSCC(=O)c1ccc(C(F)(F)F)cc1'], ['C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O', 'FCC(c1cccc(Br)n1)N1CCOCC1']], dtype='<U55') """ def featurize(self, datapoints: Iterable[Any], log_every_n: int = 1000) -> np.ndarray: """Passes through dataset, and returns the datapoint. Parameters ---- datapoints: Iterable[Any] A sequence of objects that you'd like to featurize. Returns ---- datapoints: np.ndarray A numpy array containing a featurized representation of the datapoints. """ return np.asarray(datapoints) deepchem/feat/tests/test_dummy_featurizer.py 0 → 100644 +25 −0 Original line number Diff line number Diff line import unittest import deepchem as dc import numpy as np class TestDummyFeaturizer(unittest.TestCase): """ Test for DummyFeaturizer. """ def test_featurize(self): """ Test the featurize method on an array of inputs. """ input_array = np.array([[ "N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]", "N#CSCC(=O)c1ccc(C(F)(F)F)cc1" ], [ "C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O", "FCC(c1cccc(Br)n1)N1CCOCC1" ]]) featurizer = dc.feat.DummyFeaturizer() out = featurizer.featurize(input_array) assert (type(out) == np.ndarray) assert (out.shape == input_array.shape) docs/source/api_reference/featurizers.rst +7 −0 Original line number Diff line number Diff line Loading @@ -403,6 +403,13 @@ UserDefinedFeaturizer :members: :inherited-members: DummyFeaturizer ^^^^^^^^^^^^^^^^^^^^^ .. autoclass:: deepchem.feat.DummyFeaturizer :members: :inherited-members: Base Featurizers (for develop) ------------------------------ Loading Loading
deepchem/feat/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -10,6 +10,7 @@ from deepchem.feat.base_classes import MaterialStructureFeaturizer from deepchem.feat.base_classes import MaterialCompositionFeaturizer from deepchem.feat.base_classes import ComplexFeaturizer from deepchem.feat.base_classes import UserDefinedFeaturizer from deepchem.feat.base_classes import DummyFeaturizer from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.graph_features import WeaveFeaturizer Loading
deepchem/feat/base_classes.py +37 −0 Original line number Diff line number Diff line Loading @@ -421,3 +421,40 @@ class UserDefinedFeaturizer(Featurizer): def __init__(self, feature_fields): """Creates user-defined-featurizer.""" self.feature_fields = feature_fields class DummyFeaturizer(Featurizer): """Class that implements a no-op featurization. This is useful when the raw dataset has to be used without featurizing the examples. The Molnet loader requires a featurizer input and such datasets can be used in their original form by passing the raw featurizer. Examples -------- >>> import deepchem as dc >>> smi_map = [["N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]", "N#CSCC(=O)c1ccc(C(F)(F)F)cc1"], ["C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O", "FCC(c1cccc(Br)n1)N1CCOCC1"]] >>> Featurizer = dc.feat.DummyFeaturizer() >>> smi_feat = Featurizer.featurize(smi_map) >>> smi_feat array([['N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]', 'N#CSCC(=O)c1ccc(C(F)(F)F)cc1'], ['C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O', 'FCC(c1cccc(Br)n1)N1CCOCC1']], dtype='<U55') """ def featurize(self, datapoints: Iterable[Any], log_every_n: int = 1000) -> np.ndarray: """Passes through dataset, and returns the datapoint. Parameters ---- datapoints: Iterable[Any] A sequence of objects that you'd like to featurize. Returns ---- datapoints: np.ndarray A numpy array containing a featurized representation of the datapoints. """ return np.asarray(datapoints)
deepchem/feat/tests/test_dummy_featurizer.py 0 → 100644 +25 −0 Original line number Diff line number Diff line import unittest import deepchem as dc import numpy as np class TestDummyFeaturizer(unittest.TestCase): """ Test for DummyFeaturizer. """ def test_featurize(self): """ Test the featurize method on an array of inputs. """ input_array = np.array([[ "N#C[S-].O=C(CBr)c1ccc(C(F)(F)F)cc1>CCO.[K+]", "N#CSCC(=O)c1ccc(C(F)(F)F)cc1" ], [ "C1COCCN1.FCC(Br)c1cccc(Br)n1>CCN(C(C)C)C(C)C.CN(C)C=O.O", "FCC(c1cccc(Br)n1)N1CCOCC1" ]]) featurizer = dc.feat.DummyFeaturizer() out = featurizer.featurize(input_array) assert (type(out) == np.ndarray) assert (out.shape == input_array.shape)
docs/source/api_reference/featurizers.rst +7 −0 Original line number Diff line number Diff line Loading @@ -403,6 +403,13 @@ UserDefinedFeaturizer :members: :inherited-members: DummyFeaturizer ^^^^^^^^^^^^^^^^^^^^^ .. autoclass:: deepchem.feat.DummyFeaturizer :members: :inherited-members: Base Featurizers (for develop) ------------------------------ Loading
