Transformers use Dataset.transform() (3e611c52) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -639,7 +639,7 @@ class DiskDataset(Dataset):
		newx, newy, neww = fn(X, y, w)
		basename = "dataset-%d" % shard_num
		metadata_rows.append(DiskDataset.write_data_to_disk(
		out_dir, basename, tasks, newx, newy, neww, ids))
		out_dir, basename, tasks, newx, newy, neww, ids, False))
		return DiskDataset(data_dir=out_dir,
		metadata_rows=metadata_rows,
		verbosity=self.verbosity)

+1 −1

Original line number	Diff line number	Diff line
		@@ -77,7 +77,7 @@ class TestReload(TestAPI):
		print("Transforming datasets")
		for dataset in [train_dataset, valid_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(dataset)
		dataset = transformer.transform(dataset)

		return (len(train_dataset), len(valid_dataset), len(test_dataset))

+1 −1

Original line number	Diff line number	Diff line
		@@ -57,7 +57,7 @@ class TestHyperparamOptAPI(TestAPI):
		NormalizationTransformer(transform_y=True, dataset=train_dataset)]
		for dataset in [train_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(dataset)
		dataset = transformer.transform(dataset)

		params_dict = {"n_estimators": [10, 100]}
		metric = Metric(metrics.r2_score)

+3 −3

Original line number	Diff line number	Diff line
		@@ -108,7 +108,7 @@ class TestModelAPI(TestAPI):
		transformers = input_transformers + output_transformers
		for dataset in [train_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(dataset)
		dataset = transformer.transform(dataset)

		regression_metrics = [Metric(metrics.r2_score),
		Metric(metrics.mean_squared_error),
		@@ -157,7 +157,7 @@ class TestModelAPI(TestAPI):
		transformers = input_transformers + output_transformers
		for dataset in [train_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(dataset)
		dataset = transformer.transform(dataset)

		regression_metrics = [Metric(metrics.r2_score),
		Metric(metrics.mean_squared_error),
		@@ -246,7 +246,7 @@ class TestModelAPI(TestAPI):

		for dataset in [train_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(dataset)
		dataset = transformer.transform(dataset)

		classification_metrics = [Metric(metrics.roc_auc_score),
		Metric(metrics.matthews_corrcoef),

+1 −1

Original line number	Diff line number	Diff line
		@@ -87,7 +87,7 @@ class TestGeneralization(TestAPI):
		NormalizationTransformer(transform_y=True, dataset=train_dataset)]
		for data in [train_dataset, test_dataset]:
		for transformer in transformers:
		transformer.transform(data)
		data = transformer.transform(data)

		verbosity = "high"
		regression_metric = Metric(metrics.r2_score, verbosity=verbosity)