Update KRR kernel for GDB7 (6337b0e2) · Commits · 钟慕尧 / deepchem

examples/gdb7/gdb7_sklearn.py

+4 −4

Original line number	Diff line number	Diff line
		@@ -32,9 +32,9 @@ mol_field = "mol"
		featurizer = dc.data.SDFLoader(tasks, smiles_field=smiles_field, mol_field=mol_field, featurizer=featurizers)
		dataset = featurizer.featurize(input_file, data_dir)
		random_splitter = dc.splits.RandomSplitter()
		train_dataset, test_dataset = random_splitter.train_test_split(dataset, train_dir, test_dir)
		transformers = [dc.trans.NormalizationTransformer(transform_X=True, dataset=train_dataset), dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]
		#transformers = [dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]
		train_dataset, test_dataset = random_splitter.train_test_split(dataset, train_dir, test_dir, frac_train=0.8)
		#transformers = [dc.trans.NormalizationTransformer(transform_X=True, dataset=train_dataset), dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]
		transformers = [dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]

		for transformer in transformers:
		train_dataset = transformer.transform(train_dataset)
		@@ -45,7 +45,7 @@ regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regr

		def model_builder(model_dir):
		sklearn_model = KernelRidge(
		kernel="laplacian", alpha=0.05, gamma=0.1)
		kernel="rbf", alpha=5e-4, gamma=0.008)
		return dc.models.SklearnModel(sklearn_model, model_dir)
		model = dc.models.SingletaskToMultitask(tasks, model_builder, model_dir)