Merge pull request #163 from rbharath/singletask_debug (59615278) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+23 −10

Original line number	Diff line number	Diff line
		@@ -74,7 +74,7 @@ class Dataset(object):
		metadata_rows = []
		metadata_rows.append(
		write_dataset_single(val=None, data_dir=self.data_dir, raw_data=raw_data,
		basename="data"))
		basename="data", tasks=tasks))
		self.metadata_df = pd.DataFrame(
		metadata_rows,
		columns=('df_file', 'task_names', 'ids',
		@@ -121,6 +121,7 @@ class Dataset(object):
		self.save_to_disk()

		else:
		log("Loading pre-existing metadata file.", self.verbosity)
		if os.path.exists(self._get_metadata_filename()):
		self.metadata_df = load_from_disk(self._get_metadata_filename())
		else:
		@@ -171,22 +172,24 @@ class Dataset(object):
		The order of shards returned is guaranteed to remain fixed.
		"""
		for _, row in self.metadata_df.iterrows():
		X = load_from_disk(row['X-transformed'])
		y = load_from_disk(row['y-transformed'])
		w = load_from_disk(row['w-transformed'])
		ids = load_from_disk(row['ids'])
		X = np.array(load_from_disk(row['X-transformed']))
		y = np.array(load_from_disk(row['y-transformed']))
		w = np.array(load_from_disk(row['w-transformed']))
		ids = np.array(load_from_disk(row['ids']), dtype=object)
		yield (X, y, w, ids)

		def iterbatches(self, batch_size=None, epoch=0):
		"""
		Returns minibatches from dataset.
		"""
		if batch_size == None:
		batch_size = len(self)
		for i, (X, y, w, ids) in enumerate(self.itershards()):
		nb_sample = np.shape(X)[0]
		if batch_size is None:
		shard_batch_size = nb_sample
		else:
		shard_batch_size = batch_size
		interval_points = np.linspace(
		0, nb_sample, np.ceil(float(nb_sample)/batch_size)+1, dtype=int)
		0, nb_sample, np.ceil(float(nb_sample)/shard_batch_size)+1, dtype=int)
		for j in range(len(interval_points)-1):
		indices = range(interval_points[j], interval_points[j+1])
		X_batch = X[indices, :]
		@@ -194,7 +197,7 @@ class Dataset(object):
		w_batch = w[indices]
		ids_batch = ids[indices]
		(X_batch, y_batch, w_batch, ids_batch) = self._pad_batch(
		X_batch, y_batch, w_batch, ids_batch, batch_size)
		X_batch, y_batch, w_batch, ids_batch, shard_batch_size)
		yield (X_batch, y_batch, w_batch, ids_batch)

		@staticmethod
		@@ -214,10 +217,20 @@ class Dataset(object):
		Xs.append(X_b)
		ys.append(y_b)
		ws.append(w_b)
		ids.append(np.squeeze(ids_b))
		ids.append(np.atleast_1d(np.squeeze(ids_b)))
		np.concatenate(ids)
		return (np.vstack(Xs), np.vstack(ys), np.vstack(ws),
		np.concatenate(ids))

		def get_ids(self):
		"""
		Returns all molecule-ids for this dataset.
		"""
		ids = []
		for (_, _, _, ids_b) in self.itershards():
		ids.append(np.atleast_1d(np.squeeze(ids_b)))
		return np.concatenate(ids)

		def get_labels(self):
		"""
		Returns all labels for this dataset.

deepchem/datasets/tests/test_datasets.py

+9 −0

Original line number	Diff line number	Diff line
		@@ -75,6 +75,15 @@ class TestBasicDatasetAPI(TestDatasetAPI):
		assert w.shape == (N_samples, N_tasks)
		assert ids.shape == (N_samples,)

		def test_consistent_ordering(self):
		"""Test that ordering of labels is consistent over time."""
		solubility_dataset = self._load_solubility_data()

		ids1 = solubility_dataset.get_ids()
		ids2 = solubility_dataset.get_ids()

		assert np.array_equal(ids1, ids2)

		def test_get_statistics(self):
		"""Test statistics computation of this dataset."""
		solubility_dataset = self._load_solubility_data()

deepchem/hyperparameters/init.py

+3 −9

Original line number	Diff line number	Diff line
		@@ -76,11 +76,8 @@ class HyperparamOpt(object):
		model.save()

		evaluator = Evaluator(model, valid_dataset, output_transformers)
		df, scores_df, multitask_scores = evaluator.compute_model_performance(
		[metric], valid_csv_out, valid_stats_out)
		if not metric.is_multitask:
		valid_score = scores_df.iloc[0][metric.name]
		else:
		multitask_scores = evaluator.compute_model_performance(
		[metric], valid_csv_out.name, valid_stats_out)
		valid_score = multitask_scores[metric.name]
		all_scores[hyperparameter_tuple] = valid_score

		@@ -107,11 +104,8 @@ class HyperparamOpt(object):
		train_csv_out = tempfile.NamedTemporaryFile()
		train_stats_out = tempfile.NamedTemporaryFile()
		train_evaluator = Evaluator(best_model, train_dataset, output_transformers)
		train_df, train_score, multitask_scores = train_evaluator.compute_model_performance(
		multitask_scores = train_evaluator.compute_model_performance(
		[metric], train_csv_out, train_stats_out)
		if not metric.is_multitask:
		train_score = train_score.iloc[0][metric.name]
		else:
		train_score = multitask_scores[metric.name]
		log("Best hyperparameters: %s" % str(best_hyperparams),
		self.verbosity, "low")

deepchem/hyperparameters/tests/test_hyperparam_opt.py

+23 −7

Original line number	Diff line number	Diff line
		@@ -23,6 +23,7 @@ from deepchem.metrics import Metric
		from deepchem.models.multitask import SingletaskToMultitask
		from sklearn.linear_model import LogisticRegression
		from sklearn.ensemble import RandomForestRegressor
		from deepchem.datasets import Dataset

		def rf_model_builder(tasks, task_types, params_dict, model_dir, verbosity=None):
		"""Builds random forests given hyperparameters.
		@@ -33,6 +34,7 @@ def rf_model_builder(tasks, task_types, params_dict, model_dir, verbosity=None):
		max_features = params_dict["max_features"]
		return SklearnModel(
		tasks, task_types, params_dict, model_dir,
		mode="regression",
		model_instance=RandomForestRegressor(n_estimators=n_estimators,
		max_features=max_features))

		@@ -72,18 +74,32 @@ class TestHyperparamOptAPI(TestAPI):
		splittype = "scaffold"
		compound_featurizers = [CircularFingerprint(size=1024)]
		complex_featurizers = []
		output_transformer_classes = []
		input_transformer_classes = []
		output_transformers = []
		tasks = ["task0", "task1", "task2", "task3", "task4", "task5", "task6",
		"task7", "task8", "task9", "task10", "task11", "task12",
		"task13", "task14", "task15", "task16"]
		task_types = {task: "classification" for task in tasks}
		input_file = "multitask_example.csv"
		train_dataset, valid_dataset, _, output_transformers, = \
		self._featurize_train_test_split(
		splittype, compound_featurizers,
		complex_featurizers, input_transformer_classes,
		output_transformer_classes, input_file, tasks)

		n_features = 10
		n_tasks = len(tasks)
		# Define train dataset
		n_train = 100
		X_train = np.random.rand(n_train, n_features)
		y_train = np.random.randint(2, size=(n_train, n_tasks))
		w_train = np.ones_like(y_train)
		ids_train = ["C"] * n_train
		train_dataset = Dataset.from_numpy(self.train_dir, tasks,
		X_train, y_train, w_train, ids_train)

		# Define validation dataset
		n_valid = 10
		X_valid = np.random.rand(n_valid, n_features)
		y_valid = np.random.randint(2, size=(n_valid, n_tasks))
		w_valid = np.ones_like(y_valid)
		ids_valid = ["C"] * n_valid
		valid_dataset = Dataset.from_numpy(self.valid_dir, tasks,
		X_valid, y_valid, w_valid, ids_valid)
		params_dict = {
		"batch_size": [32],
		"data_shape": [train_dataset.get_data_shape()],

deepchem/hyperparameters/tests/test_tf_hyperparam_opt.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -23,7 +23,7 @@ class TestTFHyperparamOptAPI(TestAPI):
		"""
		Test hyperparameter optimization API.
		"""
		def test_multitask_keras_mlp_ECFP_classification_hyperparam_opt(self):
		def test_multitask_tf_mlp_ECFP_classification_hyperparam_opt(self):
		"""Straightforward test of Tensorflow multitask deepchem classification API."""
		splittype = "scaffold"
		output_transformers = []

Admin message