def test_default_configuration(self):
transformation, original = _test_preprocessing(SelectPercentileClassification)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1]/2))
self.assertFalse((transformation == 0).all())
transformation, original = _test_preprocessing(SelectPercentileClassification, make_sparse=True)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1]/2))
# Custon preprocessing test to check if clipping to zero works
X_train, Y_train, X_test, Y_test = get_dataset(dataset='digits')
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = SelectPercentileClassification.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
preprocessor = SelectPercentileClassification(random_state=1,
**{hp_name: default[hp_name] for hp_name in
default if default[hp_name] is not None})
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1] / 2))
def test_default_configuration(self):
transformation, original = _test_preprocessing(SelectRates)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 3)
self.assertFalse((transformation == 0).all())
transformation, original = _test_preprocessing(SelectRates,
make_sparse=True)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1] / 2))
# Custon preprocessing test to check if clipping to zero works
X_train, Y_train, X_test, Y_test = get_dataset(dataset='digits')
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = SelectRates.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
preprocessor = SelectRates(random_state=1,
**{
hp_name: default[hp_name]
for hp_name in default
if default[hp_name] is not None
})
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(
X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
# I don't know why its 52 here and not 32 which would be half of the
# number of features. Seems to be related to a runtime warning raised
# by sklearn
self.assertEqual(transformation.shape[1], 52)
def test_default_configuration(self):
transformation, original = _test_preprocessing(SelectRates)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 3)
self.assertFalse((transformation == 0).all())
transformation, original = _test_preprocessing(SelectRates, make_sparse=True)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1] / 2))
# Custon preprocessing test to check if clipping to zero works
X_train, Y_train, X_test, Y_test = get_dataset(dataset="digits")
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = SelectRates.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
preprocessor = SelectRates(
random_state=1, **{hp_name: default[hp_name] for hp_name in default if default[hp_name] is not None}
)
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
# I don't know why its 52 here and not 32 which would be half of the
# number of features. Seems to be related to a runtime warning raised
# by sklearn
self.assertEqual(transformation.shape[1], 52)
def test_default_configuration(self):
transformation, original = _test_preprocessing(SelectRegressionRates)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 4)
self.assertFalse((transformation == 0).all())
transformation, original = _test_preprocessing(SelectRegressionRates,
make_sparse=True)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1] / 2))
# Makes sure that the features are reduced, not the number of samples
X_train, Y_train, X_test, Y_test = get_dataset(dataset='digits')
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = SelectRegressionRates.get_hyperparameter_search_space(
)
default = configuration_space.get_default_configuration()
preprocessor = SelectRegressionRates(
random_state=1,
**{
hp_name: default[hp_name]
for hp_name in default if default[hp_name] is not None
})
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(
X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 21)
def test_default_configuration(self):
transformation, original = _test_preprocessing(Nystroem)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
self.assertFalse((transformation == 0).all())
# Custon preprocessing test to check if clipping to zero works
X_train, Y_train, X_test, Y_test = get_dataset(dataset='digits')
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = Nystroem.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
preprocessor = Nystroem(random_state=1,
**{
hp_name: default[hp_name]
for hp_name in default
if default[hp_name] is not None
})
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(
X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
def test_default_configuration(self):
transformation, original = _test_preprocessing(RandomTreesEmbedding)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 216)
self.assertIsInstance(original, np.ndarray)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertTrue(all(transformation.data == 1))
def test_default_configuration(self):
transformation, original = _test_preprocessing(RandomTreesEmbedding)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 213)
self.assertIsInstance(original, np.ndarray)
self.assertTrue(scipy.sparse.issparse(transformation))
self.assertTrue(all(transformation.data == 1))
def test_default_configuration_sparse_data(self):
transformations = []
transformation, original = _test_preprocessing(VarianceThreshold,
make_sparse=True)
self.assertEqual(transformation.shape, (100, 3))
self.assertTrue((transformation.toarray() == original.toarray()[:, 1:]).all())
self.assertIsInstance(transformation, sparse.csr_matrix)
transformations.append(transformation)
def test_default_configuration_sparse_data(self):
transformations = []
transformation, original = _test_preprocessing(Imputation,
make_sparse=True)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue((transformation.data == original.data).all())
self.assertIsInstance(transformation, sparse.csc_matrix)
transformations.append(transformation)
def test_default_configuration(self):
transformation, original = _test_preprocessing(
dataset="boston",
Preprocessor=SelectPercentileRegression,
)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1] / 2))
self.assertFalse((transformation == 0).all())
def test_default_configuration_sparse_data(self):
transformations = []
transformation, original = _test_preprocessing(NumericalImputation,
make_sparse=True)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue((transformation.data == original.data).all())
self.assertIsInstance(transformation, sparse.csc_matrix)
transformations.append(transformation)
def test_default_configuration_sparse_data(self):
transformations = []
transformation, original = _test_preprocessing(VarianceThreshold,
make_sparse=True)
self.assertEqual(transformation.shape, (100, 3))
self.assertTrue((transformation.toarray() == original.toarray()[:, 1:]).all())
self.assertIsInstance(transformation, sparse.csr_matrix)
transformations.append(transformation)
def test_default_configuration(self):
transformations = []
for i in range(2):
transformation, original = _test_preprocessing(PCA)
self.assertEqual(transformation.shape, original.shape)
self.assertFalse((transformation == original).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertTrue((transformations[-1] == transformations[-2]).all())
def test_default_configuration(self):
transformations = []
for i in range(10):
transformation, original = _test_preprocessing(PCA)
self.assertEqual(transformation.shape, original.shape)
self.assertFalse((transformation == original).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertTrue((transformations[-1] == transformations[-2]).all())
def test_default_configuration_regression(self):
transformation, original = _test_preprocessing(
SelectRegressionRates,
dataset='boston',
)
self.assertEqual(transformation.shape[0], original.shape[0])
# From 13 to 12 features
self.assertEqual(transformation.shape[1], 12)
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(NoPreprocessing)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], original.shape[1])
self.assertFalse((transformation == 0).all())
self.assertEqual(np.sum(original), np.sum(transformation))
self.assertEqual(np.min(original), np.min(transformation))
self.assertEqual(np.max(original), np.max(transformation))
self.assertEqual(np.std(original), np.std(transformation))
self.assertEqual(np.mean(original), np.mean(transformation))
def test_default_configuration_no_encoding(self):
transformations = []
for i in range(2):
transformation, original = _test_preprocessing(OneHotEncoder)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue((transformation == original).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertTrue(
(transformations[-1] == transformations[-2]).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(NoPreprocessing)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], original.shape[1])
self.assertFalse((transformation == 0).all())
self.assertEqual(np.sum(original), np.sum(transformation))
self.assertEqual(np.min(original), np.min(transformation))
self.assertEqual(np.max(original), np.max(transformation))
self.assertEqual(np.std(original), np.std(transformation))
self.assertEqual(np.mean(original), np.mean(transformation))
def test_default_configuration_no_encoding(self):
transformations = []
for i in range(10):
transformation, original = _test_preprocessing(OneHotEncoder)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue((transformation == original).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertTrue(
(transformations[-1] == transformations[-2]).all())
def test_default_configuration(self):
transformations = []
for i in range(2):
transformation, original = _test_preprocessing(PCA)
self.assertEqual(transformation.shape, original.shape)
self.assertFalse((transformation == original).all())
transformations.append(transformation)
if len(transformations) > 1:
np.testing.assert_allclose(transformations[-1],
transformations[-2], rtol=1e-4)
def test_default_configuration_sparse_no_encoding(self):
transformations = []
for i in range(10):
transformation, original = _test_preprocessing(OneHotEncoder,
make_sparse=True)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue((transformation.todense() == original.todense()).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertTrue(
(transformations[-1].todense() == transformations[-2].todense()).all())
def test_default_configuration_sparse_no_encoding(self):
transformations = []
for i in range(2):
transformation, original = _test_preprocessing(NoEncoding,
make_sparse=True)
self.assertEqual(transformation.shape, original.shape)
self.assertTrue(
(transformation.todense() == original.todense()).all())
transformations.append(transformation)
if len(transformations) > 1:
self.assertEqual((transformations[-1] !=
transformations[-2]).count_nonzero(), 0)
def test_default_configuration(self):
transformation, original = _test_preprocessing(Nystroem)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
self.assertFalse((transformation == 0).all())
# Custon preprocessing test to check if clipping to zero works
X_train, Y_train, X_test, Y_test = get_dataset(dataset='digits')
original_X_train = X_train.copy()
ss = sklearn.preprocessing.StandardScaler()
X_train = ss.fit_transform(X_train)
configuration_space = Nystroem.get_hyperparameter_search_space()
default = configuration_space.get_default_configuration()
preprocessor = Nystroem(random_state=1,
**{hp_name: default[hp_name]
for hp_name in default
if default[hp_name] is not None})
transformer = preprocessor.fit(X_train, Y_train)
transformation, original = transformer.transform(
X_train), original_X_train
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
def test_default_configuration_sparse(self):
transformation, original = _test_preprocessing(KernelPCA,
make_sparse=True,
dataset='digits')
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(Densifier, make_sparse=True)
self.assertIsInstance(transformation, np.ndarray)
self.assertEqual(transformation.shape, original.shape)
self.assertIsInstance(transformation, np.ndarray)
def test_default_configuration(self):
transformation, original = _test_preprocessing(RandomKitchenSinks)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(FeatureAgglomeration)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(LibLinear_Preprocessor)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(KernelPCA,
dataset='digits',
train_size_maximum=2000)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(dataset="boston", Preprocessor=SelectPercentileRegression)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], int(original.shape[1]/2))
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(LibLinear_Preprocessor)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(
ExtraTreesPreprocessorClassification)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(FastICA,
dataset="diabetes")
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(RandomKitchenSinks)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertEqual(transformation.shape[1], 100)
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(FeatureAgglomeration)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(TruncatedSVD)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(
ExtraTreesPreprocessorRegression)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(TruncatedSVD)
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration_sparse(self):
transformation, original = _test_preprocessing(KernelPCA,
make_sparse=True,
dataset='digits')
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())
def test_default_configuration(self):
transformation, original = _test_preprocessing(FastICA,
dataset="diabetes")
self.assertEqual(transformation.shape[0], original.shape[0])
self.assertFalse((transformation == 0).all())