Unverified Commit 500467de authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #2630 from arunppsg/tm_docs 

Minor fixes to examples in torch models
parents 4e98fc0c 3b13162f

deepchem/models/torch_models/attentivefp.py

+12 −11
Original line number Diff line number Diff line
@@ -189,17 +189,18 @@ class AttentiveFPModel(TorchModel): 


  Examples

  --------



  >>>

  >> import deepchem as dc

  >> from deepchem.models import AttentiveFPModel

  >> featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)

  >> tasks, datasets, transformers = dc.molnet.load_tox21(

  ..     reload=False, featurizer=featurizer, transformers=[])

  >> train, valid, test = datasets

  >> model = AttentiveFPModel(mode='classification', n_tasks=len(tasks),

  ..                          batch_size=32, learning_rate=0.001)

  >> model.fit(train, nb_epoch=50)

  >>> import deepchem as dc

  >>> from deepchem.models import AttentiveFPModel

  >>> # preparing dataset

  >>> smiles = ["C1CCC1", "C1=CC=CN=C1"]

  >>> labels = [0., 1.]

  >>> featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)

  >>> X = featurizer.featurize(smiles)

  >>> dataset = dc.data.NumpyDataset(X=X, y=labels)

  >>> # training model

  >>> model = AttentiveFPModel(mode='classification', n_tasks=1,

  ...    batch_size=16, learning_rate=0.001)

  >>> loss = model.fit(dataset, nb_epoch=5)



  References

  ----------

deepchem/models/torch_models/gat.py

+12 −11
Original line number Diff line number Diff line
@@ -227,17 +227,18 @@ class GATModel(TorchModel): 


  Examples

  --------



  >>>

  >> import deepchem as dc

  >> from deepchem.models import GATModel

  >> featurizer = dc.feat.MolGraphConvFeaturizer()

  >> tasks, datasets, transformers = dc.molnet.load_tox21(

  ..     reload=False, featurizer=featurizer, transformers=[])

  >> train, valid, test = datasets

  >> model = GATModel(mode='classification', n_tasks=len(tasks),

  ..                  batch_size=32, learning_rate=0.001)

  >> model.fit(train, nb_epoch=50)

  >>> import deepchem as dc

  >>> from deepchem.models import GATModel

  >>> # preparing dataset

  >>> smiles = ["C1CCC1", "C1=CC=CN=C1"]

  >>> labels = [0., 1.]

  >>> featurizer = dc.feat.MolGraphConvFeaturizer()

  >>> X = featurizer.featurize(smiles)

  >>> dataset = dc.data.NumpyDataset(X=X, y=labels)

  >>> # training model

  >>> model = GATModel(mode='classification', n_tasks=1,

  ...                  batch_size=16, learning_rate=0.001)

  >>> loss = model.fit(dataset, nb_epoch=5)



  References

  ----------

deepchem/models/torch_models/gcn.py

+12 −11
Original line number Diff line number Diff line
@@ -211,17 +211,18 @@ class GCNModel(TorchModel): 


  Examples

  --------



  >>>

  >> import deepchem as dc

  >> from deepchem.models import GCNModel

  >> featurizer = dc.feat.MolGraphConvFeaturizer()

  >> tasks, datasets, transformers = dc.molnet.load_tox21(

  ..     reload=False, featurizer=featurizer, transformers=[])

  >> train, valid, test = datasets

  >> model = GCNModel(mode='classification', n_tasks=len(tasks),

  ..                  batch_size=32, learning_rate=0.001)

  >> model.fit(train, nb_epoch=50)

  >>> import deepchem as dc

  >>> from deepchem.models import GCNModel

  >>> # preparing dataset

  >>> smiles = ["C1CCC1", "CCC"]

  >>> labels = [0., 1.]

  >>> featurizer = dc.feat.MolGraphConvFeaturizer()

  >>> X = featurizer.featurize(smiles)

  >>> dataset = dc.data.NumpyDataset(X=X, y=labels)

  >>> # training model

  >>> model = GCNModel(mode='classification', n_tasks=1,

  ...                  batch_size=16, learning_rate=0.001)

  >>> loss = model.fit(dataset, nb_epoch=5)



  References

  ----------

deepchem/models/torch_models/mpnn.py

+12 −11
Original line number Diff line number Diff line
@@ -188,17 +188,18 @@ class MPNNModel(TorchModel): 


  Examples

  --------



  >>>

  >> import deepchem as dc

  >> from deepchem.models.torch_models import MPNNModel

  >> featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)

  >> tasks, datasets, transformers = dc.molnet.load_tox21(

  ..     reload=False, featurizer=featurizer, transformers=[])

  >> train, valid, test = datasets

  >> model = MPNNModel(mode='classification', n_tasks=len(tasks),

  ..                   batch_size=32, learning_rate=0.001)

  >> model.fit(train, nb_epoch=50)

  >>> import deepchem as dc

  >>> from deepchem.models.torch_models import MPNNModel

  >>> # preparing dataset

  >>> smiles = ["C1CCC1", "CCC"]

  >>> labels = [0., 1.]

  >>> featurizer = dc.feat.MolGraphConvFeaturizer(use_edges=True)

  >>> X = featurizer.featurize(smiles)

  >>> dataset = dc.data.NumpyDataset(X=X, y=labels)

  >>> # training model

  >>> model = MPNNModel(mode='classification', n_tasks=1,

  ...                  batch_size=16, learning_rate=0.001)

  >>> loss =  model.fit(dataset, nb_epoch=5)



  References

  ----------

deepchem/models/torch_models/pagtn.py

+12 −11
Original line number Diff line number Diff line
@@ -197,17 +197,18 @@ class PagtnModel(TorchModel): 


  Examples

  --------



  >>>

  >> import deepchem as dc

  >> from deepchem.models import PagtnModel

  >> featurizer = dc.feat.PagtnMolGraphFeaturizer(max_length=5)

  >> tasks, datasets, transformers = dc.molnet.load_tox21(

  ..     reload=False, featurizer=featurizer, transformers=[])

  >> train, valid, test = datasets

  >> model = PagtnModel(mode='classification', n_tasks=len(tasks),

  ..                    batch_size=16, learning_rate=0.001)

  >> model.fit(train, nb_epoch=50)

  >>> import deepchem as dc

  >>> from deepchem.models import PagtnModel

  >>> # preparing dataset

  >>> smiles = ["C1CCC1", "CCC"]

  >>> labels = [0., 1.]

  >>> featurizer = dc.feat.PagtnMolGraphFeaturizer(max_length=5)

  >>> X = featurizer.featurize(smiles)

  >>> dataset = dc.data.NumpyDataset(X=X, y=labels)

  >>> # training model

  >>> model = PagtnModel(mode='classification', n_tasks=1,

  ...                    batch_size=16, learning_rate=0.001)

  >>> loss = model.fit(dataset, nb_epoch=5)



  References

  ----------

CRA Git | Maintained and supported by SUSTech CRA and CCSE