Loading deepchem/__init__.py +5 −5 Original line number Diff line number Diff line Loading @@ -5,13 +5,13 @@ from __future__ import print_function from __future__ import division from __future__ import unicode_literals import deepchem.datasets import deepchem.featurizers import deepchem.hyperparameters import deepchem.data import deepchem.feat import deepchem.hyper import deepchem.metrics import deepchem.models import deepchem.nn import deepchem.splits import deepchem.transformers import deepchem.trans import deepchem.utils import deepchem.loaders import deepchem.load deepchem/datasets/__init__.py→deepchem/data/__init__.py +2 −2 Original line number Diff line number Diff line Loading @@ -6,5 +6,5 @@ from __future__ import division from __future__ import unicode_literals # TODO(rbharath): Get rid of * import from deepchem.datasets.datasets import * from deepchem.datasets.supports import * from deepchem.data.datasets import * from deepchem.data.supports import * deepchem/datasets/datasets.py→deepchem/data/datasets.py +0 −0 File moved. View file deepchem/datasets/supports.py→deepchem/data/supports.py +5 −5 Original line number Diff line number Diff line Loading @@ -6,7 +6,7 @@ from __future__ import division from __future__ import unicode_literals import numpy as np from deepchem.datasets import NumpyDataset from deepchem.data import NumpyDataset def get_task_dataset_minus_support(dataset, support, task): """Gets data for specified task, minus support points. Loading @@ -16,9 +16,9 @@ def get_task_dataset_minus_support(dataset, support, task): Parameters ---------- dataset: deepchem.datasets.Dataset dataset: dc.data.Dataset Source dataset. support: deepchem.datasets.Dataset support: dc.data.Dataset The support dataset task: int Task number of task to select. Loading Loading @@ -81,7 +81,7 @@ def get_task_support(dataset, n_pos, n_neg, task, replace=True): Parameters ---------- datasets: deepchem.datasets.Dataset datasets: dc.data.Dataset Dataset from which supports are sampled. n_pos: int Number of positive samples in support. Loading Loading @@ -133,7 +133,7 @@ class SupportGenerator(object): """ Parameters ---------- dataset: deepchem.datasets.Dataset dataset: dc.data.Dataset Holds dataset from which support sets will be sampled. tasks: list Indices of tasks from which supports are sampled. Loading deepchem/datasets/tests/__init__.py→deepchem/data/tests/__init__.py +12 −12 Original line number Diff line number Diff line Loading @@ -19,11 +19,11 @@ import deepchem as dc def load_solubility_data(): """Loads solubility dataset""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["log-solubility"] task_type = "regression" input_file = os.path.join(current_dir, "../../models/tests/example.csv") featurizer = dc.loaders.DataLoader( featurizer = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, Loading @@ -33,13 +33,13 @@ def load_solubility_data(): def load_multitask_data(): """Load example multitask data.""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["task0", "task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8", "task9", "task10", "task11", "task12", "task13", "task14", "task15", "task16"] input_file = os.path.join( current_dir, "../../models/tests/multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, Loading @@ -49,12 +49,12 @@ def load_multitask_data(): def load_classification_data(): """Loads classification data from example.csv""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["outcome"] task_type = "classification" input_file = os.path.join( current_dir, "../../models/tests/example_classification.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, verbosity="low") return loader.featurize(input_file) Loading @@ -63,12 +63,12 @@ def load_classification_data(): def load_sparse_multitask_dataset(): """Load sparse tox multitask data, sample dataset.""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8", "task9"] input_file = os.path.join( current_dir, "../../models/tests/sparse_multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, verbosity="low") return loader.featurize(input_file) Loading @@ -77,11 +77,11 @@ def load_feat_multitask_data(): """Load example with numerical features, tasks.""" current_dir = os.path.dirname(os.path.abspath(__file__)) features = ["feat0", "feat1", "feat2", "feat3", "feat4", "feat5"] featurizer = dc.featurizers.UserDefinedFeaturizer(features) featurizer = dc.feat.UserDefinedFeaturizer(features) tasks = ["task0", "task1", "task2", "task3", "task4", "task5"] input_file = os.path.join( current_dir, "../../models/tests/feat_multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, featurizer=featurizer, id_field="id", verbosity="low") return loader.featurize(input_file) Loading @@ -92,11 +92,11 @@ def load_gaussian_cdf_data(): from a normal distribution of mean 0, stdev 1.""" current_dir = os.path.dirname(os.path.abspath(__file__)) features = ["feat0","feat1"] featurizer = dc.featurizers.UserDefinedFeaturizer(features) featurizer = dc.feat.UserDefinedFeaturizer(features) tasks = ["task0","task1"] input_file = os.path.join( current_dir, "../../models/tests/gaussian_cdf_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, featurizer=featurizer, id_field="id", verbosity=None) return loader.featurize(input_file) Loading
deepchem/__init__.py +5 −5 Original line number Diff line number Diff line Loading @@ -5,13 +5,13 @@ from __future__ import print_function from __future__ import division from __future__ import unicode_literals import deepchem.datasets import deepchem.featurizers import deepchem.hyperparameters import deepchem.data import deepchem.feat import deepchem.hyper import deepchem.metrics import deepchem.models import deepchem.nn import deepchem.splits import deepchem.transformers import deepchem.trans import deepchem.utils import deepchem.loaders import deepchem.load
deepchem/datasets/__init__.py→deepchem/data/__init__.py +2 −2 Original line number Diff line number Diff line Loading @@ -6,5 +6,5 @@ from __future__ import division from __future__ import unicode_literals # TODO(rbharath): Get rid of * import from deepchem.datasets.datasets import * from deepchem.datasets.supports import * from deepchem.data.datasets import * from deepchem.data.supports import *
deepchem/datasets/supports.py→deepchem/data/supports.py +5 −5 Original line number Diff line number Diff line Loading @@ -6,7 +6,7 @@ from __future__ import division from __future__ import unicode_literals import numpy as np from deepchem.datasets import NumpyDataset from deepchem.data import NumpyDataset def get_task_dataset_minus_support(dataset, support, task): """Gets data for specified task, minus support points. Loading @@ -16,9 +16,9 @@ def get_task_dataset_minus_support(dataset, support, task): Parameters ---------- dataset: deepchem.datasets.Dataset dataset: dc.data.Dataset Source dataset. support: deepchem.datasets.Dataset support: dc.data.Dataset The support dataset task: int Task number of task to select. Loading Loading @@ -81,7 +81,7 @@ def get_task_support(dataset, n_pos, n_neg, task, replace=True): Parameters ---------- datasets: deepchem.datasets.Dataset datasets: dc.data.Dataset Dataset from which supports are sampled. n_pos: int Number of positive samples in support. Loading Loading @@ -133,7 +133,7 @@ class SupportGenerator(object): """ Parameters ---------- dataset: deepchem.datasets.Dataset dataset: dc.data.Dataset Holds dataset from which support sets will be sampled. tasks: list Indices of tasks from which supports are sampled. Loading
deepchem/datasets/tests/__init__.py→deepchem/data/tests/__init__.py +12 −12 Original line number Diff line number Diff line Loading @@ -19,11 +19,11 @@ import deepchem as dc def load_solubility_data(): """Loads solubility dataset""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["log-solubility"] task_type = "regression" input_file = os.path.join(current_dir, "../../models/tests/example.csv") featurizer = dc.loaders.DataLoader( featurizer = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, Loading @@ -33,13 +33,13 @@ def load_solubility_data(): def load_multitask_data(): """Load example multitask data.""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["task0", "task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8", "task9", "task10", "task11", "task12", "task13", "task14", "task15", "task16"] input_file = os.path.join( current_dir, "../../models/tests/multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, Loading @@ -49,12 +49,12 @@ def load_multitask_data(): def load_classification_data(): """Loads classification data from example.csv""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["outcome"] task_type = "classification" input_file = os.path.join( current_dir, "../../models/tests/example_classification.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, verbosity="low") return loader.featurize(input_file) Loading @@ -63,12 +63,12 @@ def load_classification_data(): def load_sparse_multitask_dataset(): """Load sparse tox multitask data, sample dataset.""" current_dir = os.path.dirname(os.path.abspath(__file__)) featurizer = dc.featurizers.CircularFingerprint(size=1024) featurizer = dc.feat.CircularFingerprint(size=1024) tasks = ["task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8", "task9"] input_file = os.path.join( current_dir, "../../models/tests/sparse_multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, smiles_field="smiles", featurizer=featurizer, verbosity="low") return loader.featurize(input_file) Loading @@ -77,11 +77,11 @@ def load_feat_multitask_data(): """Load example with numerical features, tasks.""" current_dir = os.path.dirname(os.path.abspath(__file__)) features = ["feat0", "feat1", "feat2", "feat3", "feat4", "feat5"] featurizer = dc.featurizers.UserDefinedFeaturizer(features) featurizer = dc.feat.UserDefinedFeaturizer(features) tasks = ["task0", "task1", "task2", "task3", "task4", "task5"] input_file = os.path.join( current_dir, "../../models/tests/feat_multitask_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, featurizer=featurizer, id_field="id", verbosity="low") return loader.featurize(input_file) Loading @@ -92,11 +92,11 @@ def load_gaussian_cdf_data(): from a normal distribution of mean 0, stdev 1.""" current_dir = os.path.dirname(os.path.abspath(__file__)) features = ["feat0","feat1"] featurizer = dc.featurizers.UserDefinedFeaturizer(features) featurizer = dc.feat.UserDefinedFeaturizer(features) tasks = ["task0","task1"] input_file = os.path.join( current_dir, "../../models/tests/gaussian_cdf_example.csv") loader = dc.loaders.DataLoader( loader = dc.load.DataLoader( tasks=tasks, featurizer=featurizer, id_field="id", verbosity=None) return loader.featurize(input_file)
