def test_X_normalization_transformer(self):
"""Tests normalization transformer."""
solubility_dataset = self.load_solubility_data()
normalization_transformer = NormalizationTransformer(
transform_X=True, dataset=solubility_dataset)
X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids)
normalization_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.
for id_elt, id_t_elt in zip(ids, ids_t):
assert id_elt == id_t_elt
# Check y is unchanged since this is a X transformer
np.testing.assert_allclose(y, y_t)
# Check w is unchanged since this is a y transformer
np.testing.assert_allclose(w, w_t)
# Check that X_t has zero mean, unit std.
#np.set_printoptions(threshold='nan')
mean = X_t.mean(axis=0)
assert np.amax(np.abs(mean-np.zeros_like(mean))) < 1e-7
orig_std_array = X.std(axis=0)
std_array = X_t.std(axis=0)
# Entries with zero std are not normalized
for orig_std, std in zip(orig_std_array, std_array):
if not np.isclose(orig_std, 0):
assert np.isclose(std, 1)
def test_X_normalization_transformer(self):
"""Tests normalization transformer."""
solubility_dataset = self.load_solubility_data()
normalization_transformer = NormalizationTransformer(
transform_X=True, dataset=solubility_dataset)
X, y, w, ids = solubility_dataset.to_numpy()
normalization_transformer.transform(solubility_dataset)
X_t, y_t, w_t, ids_t = solubility_dataset.to_numpy()
# Check ids are unchanged.
for id_elt, id_t_elt in zip(ids, ids_t):
assert id_elt == id_t_elt
# Check y is unchanged since this is a X transformer
np.testing.assert_allclose(y, y_t)
# Check w is unchanged since this is a y transformer
np.testing.assert_allclose(w, w_t)
# Check that X_t has zero mean, unit std.
#np.set_printoptions(threshold='nan')
mean = X_t.mean(axis=0)
assert np.amax(np.abs(mean-np.zeros_like(mean))) < 1e-7
orig_std_array = X.std(axis=0)
std_array = X_t.std(axis=0)
# Entries with zero std are not normalized
for orig_std, std in zip(orig_std_array, std_array):
if not np.isclose(orig_std, 0):
assert np.isclose(std, 1)
def test_y_normalization_transformer(self):
"""Tests normalization transformer."""
solubility_dataset = self.load_solubility_data()
normalization_transformer = NormalizationTransformer(
transform_y=True, dataset=solubility_dataset)
X, y, w, ids = (solubility_dataset.X, solubility_dataset.y, solubility_dataset.w, solubility_dataset.ids)
normalization_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.
for id_elt, id_t_elt in zip(ids, ids_t):
assert id_elt == id_t_elt
# Check X is unchanged since this is a y transformer
np.testing.assert_allclose(X, X_t)
# Check w is unchanged since this is a y transformer
np.testing.assert_allclose(w, w_t)
# Check that y_t has zero mean, unit std.
assert np.isclose(y_t.mean(), 0.)
assert np.isclose(y_t.std(), 1.)
# Check that untransform does the right thing.
np.testing.assert_allclose(normalization_transformer.untransform(y_t), y)
def test_y_normalization_transformer(self):
"""Tests normalization transformer."""
solubility_dataset = self.load_solubility_data()
normalization_transformer = NormalizationTransformer(
transform_y=True, dataset=solubility_dataset)
X, y, w, ids = solubility_dataset.to_numpy()
normalization_transformer.transform(solubility_dataset)
X_t, y_t, w_t, ids_t = solubility_dataset.to_numpy()
# Check ids are unchanged.
for id_elt, id_t_elt in zip(ids, ids_t):
assert id_elt == id_t_elt
# Check X is unchanged since this is a y transformer
np.testing.assert_allclose(X, X_t)
# Check w is unchanged since this is a y transformer
np.testing.assert_allclose(w, w_t)
# Check that y_t has zero mean, unit std.
assert np.isclose(y_t.mean(), 0.)
assert np.isclose(y_t.std(), 1.)
# Check that untransform does the right thing.
np.testing.assert_allclose(normalization_transformer.untransform(y_t), y)
