Loading deepchem/datasets/tests/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -33,6 +33,7 @@ class TestDatasetAPI(TestSplitAPI): user_specified_features=None, split_field=None, shard_size=100): featurizers = compound_featurizers + complex_featurizers samples = self._gen_samples( compound_featurizers, complex_featurizers, input_transformer_classes, output_transformer_classes, Loading deepchem/datasets/tests/test_datasets.py +0 −12 Original line number Diff line number Diff line Loading @@ -87,15 +87,3 @@ class TestBasicDatasetAPI(TestDatasetAPI): np.testing.assert_allclose(comp_y_means, y_means) np.testing.assert_allclose(comp_X_stds, X_stds) np.testing.assert_allclose(comp_y_stds, y_stds) def test_balance_positives_and_negatives(self): """Test balancing of positive and negative examples.""" multitask_dataset = self._load_multitask_data() weights = multitask_dataset.balance_positives_and_negatives() X, y, w, ids = multitask_dataset.to_numpy() for ind, task in enumerate(multitask_dataset.get_task_names()): task_labels = y[:, ind] num_positives = np.count_nonzero(task_labels) num_negatives = len(task_labels) - num_positives pos_weight, neg_weight = weights[ind] assert np.isclose(num_positives * pos_weight, num_negatives * neg_weight) deepchem/featurizers/tests/test_featurized_samples.py +14 −4 Original line number Diff line number Diff line Loading @@ -13,6 +13,9 @@ import os import unittest import tempfile import shutil from deepchem.splits import RandomSplitter from deepchem.splits import ScaffoldSplitter from deepchem.splits import SpecifiedSplitter from deepchem.featurizers.featurize import DataFeaturizer from deepchem.featurizers.fingerprints import CircularFingerprint Loading Loading @@ -49,16 +52,23 @@ class TestFeaturizedSamples(unittest.TestCase): samples = featurizer.featurize(input_file, self.feature_dir, self.samples_dir) # Splits featurized samples into train/test assert splittype in ["random", "specified", "scaffold"] if splittype == "random": splitter = RandomSplitter() elif splittype == "specified": splitter = SpecifiedSplitter() elif splittype == "scaffold": splitter = ScaffoldSplitter() if frac_valid > 0: train_samples, valid_samples, test_samples = samples.train_valid_test_split( splittype, train_dir=self.train_dir, valid_dir=self.valid_dir, train_samples, valid_samples, test_samples = splitter.train_valid_test_split( samples, train_dir=self.train_dir, valid_dir=self.valid_dir, test_dir=self.test_dir, frac_train=frac_train, frac_valid=frac_valid, frac_test=frac_test) return train_samples, valid_samples, test_samples else: train_samples, test_samples = samples.train_test_split( splittype, train_dir=self.train_dir, test_dir=self.test_dir, train_samples, test_samples = splitter.train_test_split( samples, train_dir=self.train_dir, test_dir=self.test_dir, frac_train=frac_train) return train_samples, test_samples Loading Loading
deepchem/datasets/tests/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -33,6 +33,7 @@ class TestDatasetAPI(TestSplitAPI): user_specified_features=None, split_field=None, shard_size=100): featurizers = compound_featurizers + complex_featurizers samples = self._gen_samples( compound_featurizers, complex_featurizers, input_transformer_classes, output_transformer_classes, Loading
deepchem/datasets/tests/test_datasets.py +0 −12 Original line number Diff line number Diff line Loading @@ -87,15 +87,3 @@ class TestBasicDatasetAPI(TestDatasetAPI): np.testing.assert_allclose(comp_y_means, y_means) np.testing.assert_allclose(comp_X_stds, X_stds) np.testing.assert_allclose(comp_y_stds, y_stds) def test_balance_positives_and_negatives(self): """Test balancing of positive and negative examples.""" multitask_dataset = self._load_multitask_data() weights = multitask_dataset.balance_positives_and_negatives() X, y, w, ids = multitask_dataset.to_numpy() for ind, task in enumerate(multitask_dataset.get_task_names()): task_labels = y[:, ind] num_positives = np.count_nonzero(task_labels) num_negatives = len(task_labels) - num_positives pos_weight, neg_weight = weights[ind] assert np.isclose(num_positives * pos_weight, num_negatives * neg_weight)
deepchem/featurizers/tests/test_featurized_samples.py +14 −4 Original line number Diff line number Diff line Loading @@ -13,6 +13,9 @@ import os import unittest import tempfile import shutil from deepchem.splits import RandomSplitter from deepchem.splits import ScaffoldSplitter from deepchem.splits import SpecifiedSplitter from deepchem.featurizers.featurize import DataFeaturizer from deepchem.featurizers.fingerprints import CircularFingerprint Loading Loading @@ -49,16 +52,23 @@ class TestFeaturizedSamples(unittest.TestCase): samples = featurizer.featurize(input_file, self.feature_dir, self.samples_dir) # Splits featurized samples into train/test assert splittype in ["random", "specified", "scaffold"] if splittype == "random": splitter = RandomSplitter() elif splittype == "specified": splitter = SpecifiedSplitter() elif splittype == "scaffold": splitter = ScaffoldSplitter() if frac_valid > 0: train_samples, valid_samples, test_samples = samples.train_valid_test_split( splittype, train_dir=self.train_dir, valid_dir=self.valid_dir, train_samples, valid_samples, test_samples = splitter.train_valid_test_split( samples, train_dir=self.train_dir, valid_dir=self.valid_dir, test_dir=self.test_dir, frac_train=frac_train, frac_valid=frac_valid, frac_test=frac_test) return train_samples, valid_samples, test_samples else: train_samples, test_samples = samples.train_test_split( splittype, train_dir=self.train_dir, test_dir=self.test_dir, train_samples, test_samples = splitter.train_test_split( samples, train_dir=self.train_dir, test_dir=self.test_dir, frac_train=frac_train) return train_samples, test_samples Loading
