Merge pull request #2186 from nd-02110114/fix-duplicated-error (59e02291) · Commits · 钟慕尧 / deepchem

deepchem/data/tests/test_datasets.py

+3 −3

Original line number	Diff line number	Diff line
		@@ -22,7 +22,7 @@ def load_solubility_data():
		tasks = ["log-solubility"]
		input_file = os.path.join(current_dir, "../../models/tests/example.csv")
		loader = dc.data.CSVLoader(
		tasks=tasks, smiles_field="smiles", featurizer=featurizer)
		tasks=tasks, feature_field="smiles", featurizer=featurizer)

		return loader.create_dataset(input_file)

		@@ -39,8 +39,8 @@ def load_multitask_data():
		input_file = os.path.join(current_dir,
		"../../models/tests/multitask_example.csv")
		loader = dc.data.CSVLoader(
		tasks=tasks, smiles_field="smiles", featurizer=featurizer)
		return loader.featurize(input_file)
		tasks=tasks, feature_field="smiles", featurizer=featurizer)
		return loader.create_dataset(input_file)


		class TestTransformer(dc.trans.Transformer):

deepchem/data/tests/test_drop.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -25,8 +25,8 @@ class TestDrop(unittest.TestCase):
		emols_tasks = ['activity']

		loader = dc.data.CSVLoader(
		tasks=emols_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file)
		tasks=emols_tasks, feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file)

		X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)
		assert len(X) == len(y) == len(w) == len(ids)

deepchem/data/tests/test_fasta_loader.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -20,7 +20,7 @@ class TestFASTALoader(unittest.TestCase):
		input_file = os.path.join(self.current_dir,
		"../../data/tests/example.fasta")
		loader = dc.data.FASTALoader()
		sequences = loader.featurize(input_file)
		sequences = loader.create_dataset(input_file)

		# example.fasta contains 3 sequences each of length 58.
		# The one-hot encoding turns base-pairs into vectors of length 5 (ATCGN).

deepchem/data/tests/test_image_loader.py

+8 −8

Original line number	Diff line number	Diff line
		@@ -58,45 +58,45 @@ class TestImageLoader(unittest.TestCase):

		def test_png_simple_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.face_path)
		dataset = loader.create_dataset(self.face_path)
		# These are the known dimensions of face.png
		assert dataset.X.shape == (1, 768, 1024, 3)

		def test_png_simple_load_with_labels(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize((self.face_path, np.array(1)))
		dataset = loader.create_dataset((self.face_path, np.array(1)))
		# These are the known dimensions of face.png
		assert dataset.X.shape == (1, 768, 1024, 3)
		assert (dataset.y == np.ones((1,))).all()

		def test_tif_simple_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.tif_image_path)
		dataset = loader.create_dataset(self.tif_image_path)
		# TODO(rbharath): Where are the color channels?
		assert dataset.X.shape == (1, 44, 330)

		def test_png_multi_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize([self.face_path, self.face_copy_path])
		dataset = loader.create_dataset([self.face_path, self.face_copy_path])
		assert dataset.X.shape == (2, 768, 1024, 3)

		def test_png_zip_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.zip_path)
		dataset = loader.create_dataset(self.zip_path)
		assert dataset.X.shape == (1, 768, 1024, 3)

		def test_png_multi_zip_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.multi_zip_path)
		dataset = loader.create_dataset(self.multi_zip_path)
		assert dataset.X.shape == (2, 768, 1024, 3)

		def test_multitype_zip_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.multitype_zip_path)
		dataset = loader.create_dataset(self.multitype_zip_path)
		# Since the different files have different shapes, makes an object array
		assert dataset.X.shape == (2,)

		def test_directory_load(self):
		loader = dc.data.ImageLoader()
		dataset = loader.featurize(self.image_dir)
		dataset = loader.create_dataset(self.image_dir)
		assert dataset.X.shape == (2, 768, 1024, 3)

deepchem/data/tests/test_load.py

+8 −8

Original line number	Diff line number	Diff line
		@@ -32,8 +32,8 @@ class TestLoad(unittest.TestCase):
		featurizer = dc.feat.CircularFingerprint(size=1024)
		tasks = ["log-solubility"]
		loader = dc.data.CSVLoader(
		tasks=tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, data_dir)
		tasks=tasks, feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file, data_dir)

		X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)
		shutil.move(data_dir, moved_data_dir)
		@@ -70,8 +70,8 @@ class TestLoad(unittest.TestCase):

		# featurization
		loader = dc.data.CSVLoader(
		tasks=all_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, data_dir)
		tasks=all_tasks, feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file, data_dir)

		# train/valid split.
		_, y_multi, w_multi, _ = (dataset.X, dataset.y, dataset.w, dataset.ids)
		@@ -121,8 +121,8 @@ class TestLoad(unittest.TestCase):

		# multitask load
		loader = dc.data.CSVLoader(
		tasks=tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, data_dir)
		tasks=tasks, feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file, data_dir)

		# Do train/valid split.
		_, y_multi, w_multi, _ = (dataset.X, dataset.y, dataset.w, dataset.ids)
		@@ -134,8 +134,8 @@ class TestLoad(unittest.TestCase):
		if os.path.exists(data_dir):
		shutil.rmtree(data_dir)
		loader = dc.data.CSVLoader(
		tasks=[task], smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, data_dir)
		tasks=[task], feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file, data_dir)

		_, y_task, w_task, ids_task = (dataset.X, dataset.y, dataset.w,
		dataset.ids)

Admin message