new version yapf (f78e5afb) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/layers.py

+4 −4

Original line number	Diff line number	Diff line
		@@ -1436,8 +1436,8 @@ class NeighborList(Layer):
		# List of length N_atoms each of shape (M_nbrs)
		padded_dists = [
		tf.reduce_sum((atom_coord - padded_nbr_coord)**2, axis=1)
		for (atom_coord, padded_nbr_coord
		) in zip(atom_coords, padded_nbr_coords)
		for (atom_coord,
		padded_nbr_coord) in zip(atom_coords, padded_nbr_coords)
		]

		padded_closest_nbrs = [
		@@ -1448,8 +1448,8 @@ class NeighborList(Layer):
		# N_atoms elts of size (M_nbrs,) each
		padded_neighbor_list = [
		tf.gather(padded_atom_nbrs, padded_closest_nbr)
		for (padded_atom_nbrs, padded_closest_nbr
		) in zip(padded_nbrs, padded_closest_nbrs)
		for (padded_atom_nbrs,
		padded_closest_nbr) in zip(padded_nbrs, padded_closest_nbrs)
		]

		neighbor_list = tf.stack(padded_neighbor_list)

deepchem/models/tensorgraph/models/graph_models.py

+3 −3

Original line number	Diff line number	Diff line
		@@ -154,7 +154,8 @@ class WeaveTensorGraph(TensorGraph):
		C0, C1 = np.meshgrid(np.arange(n_atoms), np.arange(n_atoms))
		atom_to_pair.append(
		np.transpose(
		np.array([C1.flatten() + start, C0.flatten() + start])))
		np.array([C1.flatten() + start,
		C0.flatten() + start])))
		# number of pairs for each atom
		pair_split.extend(C1.flatten() + start)
		start = start + n_atoms
		@@ -483,8 +484,7 @@ class GraphConvTensorGraph(TensorGraph):

		"""
		self.n_tasks = n_tasks
		self.error_bars = True if 'error_bars' in kwargs and kwargs[
		'error_bars'] else False
		self.error_bars = True if 'error_bars' in kwargs and kwargs['error_bars'] else False
		kwargs['use_queue'] = False
		super(GraphConvTensorGraph, self).__init__(**kwargs)
		self.build_graph()

deepchem/molnet/run_benchmark_models.py

+20 −22

Original line number	Diff line number	Diff line
		@@ -315,11 +315,11 @@ def benchmark_classification(train_dataset,
		def model_builder(model_dir_rf):
		sklearn_model = RandomForestClassifier(
		class_weight="balanced", n_estimators=n_estimators, n_jobs=-1)
		return deepchem.models.sklearn_models.SklearnModel(sklearn_model,
		model_dir_rf)
		return deepchem.models.sklearn_models.SklearnModel(
		sklearn_model, model_dir_rf)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)

		elif model_name == 'kernelsvm':
		# Loading hyper parameters
		@@ -329,14 +329,12 @@ def benchmark_classification(train_dataset,

		# Building scikit learn Kernel SVM model
		def model_builder(model_dir_kernelsvm):
		sklearn_model = SVC(C=C,
		gamma=gamma,
		class_weight="balanced",
		probability=True)
		sklearn_model = SVC(
		C=C, gamma=gamma, class_weight="balanced", probability=True)
		return deepchem.models.SklearnModel(sklearn_model, model_dir_kernelsvm)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)

		elif model_name == 'xgb':
		# Loading hyper parameters
		@@ -376,11 +374,11 @@ def benchmark_classification(train_dataset,
		scale_pos_weight=scale_pos_weight,
		base_score=base_score,
		seed=seed)
		return deepchem.models.xgboost_models.XGBoostModel(xgboost_model,
		model_dir_xgb, **esr)
		return deepchem.models.xgboost_models.XGBoostModel(
		xgboost_model, model_dir_xgb, **esr)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)

		if nb_epoch is None:
		model.fit(train_dataset)
		@@ -711,8 +709,8 @@ def benchmark_regression(train_dataset,
		return deepchem.models.sklearn_models.SklearnModel(
		sklearn_model, model_dir_rf_regression)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)
		elif model_name == 'krr':
		# Loading hyper parameters
		alpha = hyper_parameters['alpha']
		@@ -724,8 +722,8 @@ def benchmark_regression(train_dataset,
		sklearn_model = KernelRidge(kernel="rbf", alpha=alpha, gamma=gamma)
		return deepchem.models.SklearnModel(sklearn_model, model_dir_krr)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)

		elif model_name == 'xgb_regression':
		# Loading hyper parameters
		@@ -765,11 +763,11 @@ def benchmark_regression(train_dataset,
		scale_pos_weight=scale_pos_weight,
		base_score=base_score,
		seed=seed)
		return deepchem.models.xgboost_models.XGBoostModel(xgboost_model,
		model_dir_xgb, **esr)
		return deepchem.models.xgboost_models.XGBoostModel(
		xgboost_model, model_dir_xgb, **esr)

		model = deepchem.models.multitask.SingletaskToMultitask(tasks,
		model_builder)
		model = deepchem.models.multitask.SingletaskToMultitask(
		tasks, model_builder)

		print('-----------------------------')
		print('Start fitting: %s' % model_name)

deepchem/molnet/load_function/bbbp_datasets.py

+1 −1

File changed.

Contains only whitespace changes.

Admin message