Loading deepchem/trans/tests/test_transformers.py +87 −0 Original line number Diff line number Diff line Loading @@ -172,6 +172,93 @@ class TestTransformers(unittest.TestCase): # Check that untransform does the right thing. np.testing.assert_allclose(log_transformer.untransform(X_t), X) def test_y_minmax_transformer(self): """Tests MinMax transformer. """ solubility_dataset = dc.data.tests.load_solubility_data() minmax_transformer = dc.trans.MinMaxTransformer( transform_y=True, dataset=solubility_dataset) X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) solubility_dataset = minmax_transformer.transform(solubility_dataset) X_t, y_t, w_t, ids_t = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(X, X_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(y_t.min(), 0.) np.testing.assert_allclose(y_t.max(), 1.) # Check untransform works correctly np.testing.assert_allclose(minmax_transformer.untransform(y_t), y) # Test on random example n_samples = 100 n_features = 10 n_tasks = 10 X = np.random.randn(n_samples, n_features) y = np.random.randn(n_samples, n_tasks) dataset = dc.data.NumpyDataset(X, y) minmax_transformer = dc.trans.MinMaxTransformer( transform_y=True, dataset=dataset) w, ids = dataset.w, dataset.ids dataset = minmax_transformer.transform(dataset) X_t, y_t, w_t, ids_t = (dataset.X, dataset.y, dataset.w, dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(X, X_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(y_t.min(), 0.) np.testing.assert_allclose(y_t.max(), 1.) # Test if dimensionality expansion is handled correctly by untransform y_t = np.expand_dims(y_t, axis=-1) y_restored = minmax_transformer.untransform(y_t) assert y_restored.shape == y.shape + (1,) np.testing.assert_allclose(np.squeeze(y_restored, axis=-1), y) def test_X_minmax_transformer(self): solubility_dataset = dc.data.tests.load_solubility_data() minmax_transformer = dc.trans.MinMaxTransformer( transform_X=True, dataset=solubility_dataset) X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) solubility_dataset = minmax_transformer.transform(solubility_dataset) X_t, y_t, w_t, ids_t = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(y, y_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(X_t.min(), 0.) np.testing.assert_allclose(X_t.max(), 1.) # Check untransform works correctly np.testing.assert_allclose(minmax_transformer.untransform(X_t), X) def test_y_normalization_transformer(self): """Tests normalization transformer.""" solubility_dataset = dc.data.tests.load_solubility_data() Loading deepchem/trans/transformers.py +64 −6 Original line number Diff line number Diff line Loading @@ -104,15 +104,54 @@ class Transformer(object): class MinMaxTransformer(Transformer): """MinMax transformer transforms the dataset by shifting each axis of X or y (depending on whether transform_X or transform_y is True), except the first one by the minimum value along the axis and dividing the result by the range (maximum value - minimum value) along the axis. This ensures each axis is between 0 and 1. In case of multi-task learning, it ensures each task is given equal importance. Given original array A, the transformed array can be written as: A_min = np.min(A, axis=0) A_max = np.max(A, axis=0) A_t = np.nan_to_num((A - A_min)/(A_max - A_min)) Example: >>> n_samples = 10 >>> n_features = 3 >>> n_tasks = 1 >>> ids = np.arange(n_samples) >>> X = np.random.rand(n_samples, n_features) >>> y = np.zeros((n_samples, n_tasks)) >>> w = np.ones((n_samples, n_tasks)) >>> dataset = dc.data.NumpyDataset(X, y, w, ids) >>> transformer = dc.trans.MinMaxTransformer(transform_y=True) >>> dataset = transformer.transform(dataset) """ def __init__(self, transform_X=False, transform_y=False, transform_w=False, dataset=None): """Initialization of MinMax transformer. Parameters ---------- transform_X: bool, optional (default False) Whether to transform X transform_y: bool, optional (default False) Whether to transform y transform_w: bool, optional (default False) Whether to transform w dataset: dc.data.Dataset object, optional Dataset to be transformed """ if transform_X: raise NotImplementedError("MinMax transformer does not work for X yet.") if transform_y: self.X_min = np.min(dataset.X, axis=0) self.X_max = np.max(dataset.X, axis=0) elif transform_y: self.y_min = np.min(dataset.y, axis=0) self.y_max = np.max(dataset.y, axis=0) Loading @@ -126,26 +165,45 @@ class MinMaxTransformer(Transformer): dataset=dataset) def transform(self, dataset, parallel=False): """Transforms the dataset.""" return super(MinMaxTransformer, self).transform(dataset, parallel=parallel) def transform_array(self, X, y, w): """Transform the data in a set of (X, y, w) arrays.""" if self.transform_X: raise NotImplementedError("MinMax transformer does not work for X yet") if self.transform_y: X = np.nan_to_num((X - self.X_min) / (self.X_max - self.X_min)) elif self.transform_y: y = np.nan_to_num((y - self.y_min) / (self.y_max - self.y_min)) return (X, y, w) def untransform(self, z): """ Undo transformation on provided data. Parameters ---------- z: np.ndarray, Transformed X or y array """ if self.transform_X: raise NotImplementedError("MinMax does not work for X yet.") if self.transform_y: X_max = self.X_max X_min = self.X_min return z * (X_max - X_min) + X_min elif self.transform_y: y_min = self.y_min y_max = self.y_max n_tasks = len(y_min) z_shape = list(z.shape) z_shape.reverse() for dim in z_shape: if dim != n_tasks and dim == 1: y_min = np.expand_dims(y_min, -1) y_max = np.expand_dims(y_max, -1) y = z * (y_max - y_min) + y_min return y Loading Loading
deepchem/trans/tests/test_transformers.py +87 −0 Original line number Diff line number Diff line Loading @@ -172,6 +172,93 @@ class TestTransformers(unittest.TestCase): # Check that untransform does the right thing. np.testing.assert_allclose(log_transformer.untransform(X_t), X) def test_y_minmax_transformer(self): """Tests MinMax transformer. """ solubility_dataset = dc.data.tests.load_solubility_data() minmax_transformer = dc.trans.MinMaxTransformer( transform_y=True, dataset=solubility_dataset) X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) solubility_dataset = minmax_transformer.transform(solubility_dataset) X_t, y_t, w_t, ids_t = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(X, X_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(y_t.min(), 0.) np.testing.assert_allclose(y_t.max(), 1.) # Check untransform works correctly np.testing.assert_allclose(minmax_transformer.untransform(y_t), y) # Test on random example n_samples = 100 n_features = 10 n_tasks = 10 X = np.random.randn(n_samples, n_features) y = np.random.randn(n_samples, n_tasks) dataset = dc.data.NumpyDataset(X, y) minmax_transformer = dc.trans.MinMaxTransformer( transform_y=True, dataset=dataset) w, ids = dataset.w, dataset.ids dataset = minmax_transformer.transform(dataset) X_t, y_t, w_t, ids_t = (dataset.X, dataset.y, dataset.w, dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(X, X_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(y_t.min(), 0.) np.testing.assert_allclose(y_t.max(), 1.) # Test if dimensionality expansion is handled correctly by untransform y_t = np.expand_dims(y_t, axis=-1) y_restored = minmax_transformer.untransform(y_t) assert y_restored.shape == y.shape + (1,) np.testing.assert_allclose(np.squeeze(y_restored, axis=-1), y) def test_X_minmax_transformer(self): solubility_dataset = dc.data.tests.load_solubility_data() minmax_transformer = dc.trans.MinMaxTransformer( transform_X=True, dataset=solubility_dataset) X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) solubility_dataset = minmax_transformer.transform(solubility_dataset) X_t, y_t, w_t, ids_t = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids) # Check ids are unchanged before and after transformation for id_elt, id_t_elt in zip(ids, ids_t): assert id_elt == id_t_elt # Check X is unchanged since transform_y is true np.testing.assert_allclose(y, y_t) # Check w is unchanged since transform_y is true np.testing.assert_allclose(w, w_t) # Check minimum and maximum values of transformed y are 0 and 1 np.testing.assert_allclose(X_t.min(), 0.) np.testing.assert_allclose(X_t.max(), 1.) # Check untransform works correctly np.testing.assert_allclose(minmax_transformer.untransform(X_t), X) def test_y_normalization_transformer(self): """Tests normalization transformer.""" solubility_dataset = dc.data.tests.load_solubility_data() Loading
deepchem/trans/transformers.py +64 −6 Original line number Diff line number Diff line Loading @@ -104,15 +104,54 @@ class Transformer(object): class MinMaxTransformer(Transformer): """MinMax transformer transforms the dataset by shifting each axis of X or y (depending on whether transform_X or transform_y is True), except the first one by the minimum value along the axis and dividing the result by the range (maximum value - minimum value) along the axis. This ensures each axis is between 0 and 1. In case of multi-task learning, it ensures each task is given equal importance. Given original array A, the transformed array can be written as: A_min = np.min(A, axis=0) A_max = np.max(A, axis=0) A_t = np.nan_to_num((A - A_min)/(A_max - A_min)) Example: >>> n_samples = 10 >>> n_features = 3 >>> n_tasks = 1 >>> ids = np.arange(n_samples) >>> X = np.random.rand(n_samples, n_features) >>> y = np.zeros((n_samples, n_tasks)) >>> w = np.ones((n_samples, n_tasks)) >>> dataset = dc.data.NumpyDataset(X, y, w, ids) >>> transformer = dc.trans.MinMaxTransformer(transform_y=True) >>> dataset = transformer.transform(dataset) """ def __init__(self, transform_X=False, transform_y=False, transform_w=False, dataset=None): """Initialization of MinMax transformer. Parameters ---------- transform_X: bool, optional (default False) Whether to transform X transform_y: bool, optional (default False) Whether to transform y transform_w: bool, optional (default False) Whether to transform w dataset: dc.data.Dataset object, optional Dataset to be transformed """ if transform_X: raise NotImplementedError("MinMax transformer does not work for X yet.") if transform_y: self.X_min = np.min(dataset.X, axis=0) self.X_max = np.max(dataset.X, axis=0) elif transform_y: self.y_min = np.min(dataset.y, axis=0) self.y_max = np.max(dataset.y, axis=0) Loading @@ -126,26 +165,45 @@ class MinMaxTransformer(Transformer): dataset=dataset) def transform(self, dataset, parallel=False): """Transforms the dataset.""" return super(MinMaxTransformer, self).transform(dataset, parallel=parallel) def transform_array(self, X, y, w): """Transform the data in a set of (X, y, w) arrays.""" if self.transform_X: raise NotImplementedError("MinMax transformer does not work for X yet") if self.transform_y: X = np.nan_to_num((X - self.X_min) / (self.X_max - self.X_min)) elif self.transform_y: y = np.nan_to_num((y - self.y_min) / (self.y_max - self.y_min)) return (X, y, w) def untransform(self, z): """ Undo transformation on provided data. Parameters ---------- z: np.ndarray, Transformed X or y array """ if self.transform_X: raise NotImplementedError("MinMax does not work for X yet.") if self.transform_y: X_max = self.X_max X_min = self.X_min return z * (X_max - X_min) + X_min elif self.transform_y: y_min = self.y_min y_max = self.y_max n_tasks = len(y_min) z_shape = list(z.shape) z_shape.reverse() for dim in z_shape: if dim != n_tasks and dim == 1: y_min = np.expand_dims(y_min, -1) y_max = np.expand_dims(y_max, -1) y = z * (y_max - y_min) + y_min return y Loading
