Some test fixes (1b7140fe) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+9 −0

Original line number	Diff line number	Diff line
		@@ -598,7 +598,16 @@ def compute_sums_and_nb_sample(tensor, W=None):
		# make it easy to use multiprocessing.
		def convert_df_to_numpy(df, feature_type, tasks, mol_id_field):
		"""Transforms a featurized dataset df into standard set of numpy arrays"""
		############################################################## DEBUG
		print("SLKFJD:LSKJF:SLFKJ:SLDFKJSD:LKFJDSLKFJSDKFJSLKFJS:LFJSDLKJ")
		############################################################## DEBUG
		if feature_type not in df.keys():
		############################################################## DEBUG
		print("SLKFJD:LSKJF:SLFKJ:SLDFKJSD:LKFJDSLKFJSDKFJSLKFJS:LFJSDLKJ")
		print("feature_type")
		print(feature_type)
		############################################################## DEBUG

		raise ValueError(
		"Featurized data does not support requested feature_type.")
		# perform common train/test split across all tasks

deepchem/datasets/tests/init.py

+6 −6

Original line number	Diff line number	Diff line
		@@ -29,14 +29,14 @@ class TestDatasetAPI(TestAPI):
		"""Loads solubility data from example.csv"""
		if os.path.exists(self.data_dir):
		shutil.rmtree(self.data_dir)
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		tasks = ["log-solubility"]
		task_type = "regression"
		input_file = os.path.join(self.current_dir, "../../models/tests/example.csv")
		featurizer = DataFeaturizer(
		tasks=tasks,
		smiles_field=self.smiles_field,
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity="low")

		return featurizer.featurize(input_file, self.data_dir)
		@@ -45,7 +45,7 @@ class TestDatasetAPI(TestAPI):
		"""Loads classification data from example.csv"""
		if os.path.exists(self.data_dir):
		shutil.rmtree(self.data_dir)
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = [CircularFingerprint(size=1024)]
		tasks = ["outcome"]
		task_type = "classification"
		input_file = os.path.join(
		@@ -53,7 +53,7 @@ class TestDatasetAPI(TestAPI):
		featurizer = DataFeaturizer(
		tasks=tasks,
		smiles_field=self.smiles_field,
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity="low")
		return featurizer.featurize(input_file, self.data_dir)

		@@ -61,7 +61,7 @@ class TestDatasetAPI(TestAPI):
		"""Load example multitask data."""
		if os.path.exists(self.data_dir):
		shutil.rmtree(self.data_dir)
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		tasks = ["task0", "task1", "task2", "task3", "task4", "task5", "task6",
		"task7", "task8", "task9", "task10", "task11", "task12",
		"task13", "task14", "task15", "task16"]
		@@ -70,6 +70,6 @@ class TestDatasetAPI(TestAPI):
		featurizer = DataFeaturizer(
		tasks=tasks,
		smiles_field=self.smiles_field,
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity="low")
		return featurizer.featurize(input_file, self.data_dir)

deepchem/datasets/tests/test_drop.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -34,12 +34,12 @@ class TestDrop(TestAPI):

		# Featurize emols dataset
		print("About to featurize datasets.")
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		emols_tasks = ['activity']

		featurizer = DataFeaturizer(tasks=emols_tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(dataset_file, data_dir)

deepchem/datasets/tests/test_load.py

+7 −7

Original line number	Diff line number	Diff line
		@@ -35,11 +35,11 @@ class TestLoad(TestAPI):
		dataset_file = os.path.join(
		current_dir, "../../models/tests/example.csv")

		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		tasks = ["log-solubility"]
		featurizer = DataFeaturizer(tasks=tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(
		dataset_file, data_dir)
		@@ -89,13 +89,13 @@ class TestLoad(TestAPI):

		# Featurize tox21 dataset
		print("About to featurize dataset.")
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = [CircularFingerprint(size=1024)]
		all_tasks = ["task%d"%i for i in range(17)]

		####### Do featurization
		featurizer = DataFeaturizer(tasks=all_tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(
		dataset_file, data_dir)
		@@ -154,7 +154,7 @@ class TestLoad(TestAPI):

		# Featurize tox21 dataset
		print("About to featurize dataset.")
		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		all_tasks = ["task%d"%i for i in range(17)]
		# For debugging purposes
		n_tasks = 17
		@@ -163,7 +163,7 @@ class TestLoad(TestAPI):
		####### Do multitask load
		featurizer = DataFeaturizer(tasks=tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(dataset_file, data_dir)

		@@ -179,7 +179,7 @@ class TestLoad(TestAPI):
		shutil.rmtree(data_dir)
		featurizer = DataFeaturizer(tasks=[task],
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(dataset_file, data_dir)

deepchem/datasets/tests/test_merge.py

+4 −4

Original line number	Diff line number	Diff line
		@@ -34,11 +34,11 @@ class TestMerge(TestAPI):
		dataset_file = os.path.join(
		current_dir, "../../models/tests/example.csv")

		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		tasks = ["log-solubility"]
		featurizer = DataFeaturizer(tasks=tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		first_dataset = featurizer.featurize(
		dataset_file, first_data_dir)
		@@ -60,11 +60,11 @@ class TestMerge(TestAPI):
		dataset_file = os.path.join(
		current_dir, "../../models/tests/example.csv")

		featurizers = [CircularFingerprint(size=1024)]
		featurizer = CircularFingerprint(size=1024)
		tasks = ["log-solubility"]
		featurizer = DataFeaturizer(tasks=tasks,
		smiles_field="smiles",
		featurizers=featurizers,
		featurizer=featurizer,
		verbosity=verbosity)
		dataset = featurizer.featurize(
		dataset_file, data_dir, shard_size=2)

Admin message