def test_get_hyperparameter_search_space_preprocessor_contradicts_default_classifier(
self):
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
include={'preprocessor': ['densifier']},
dataset_properties={'sparse': True})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__').default,
'gradient_boosting')
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
include={'preprocessor': ['nystroem_sampler']})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__').default,
'sgd')
def test_get_hyperparameter_search_space(self):
cs = ParamSklearnRegressor.get_hyperparameter_search_space()
self.assertIsInstance(cs, ConfigurationSpace)
conditions = cs.get_conditions()
hyperparameters = cs.get_hyperparameters()
self.assertEqual(114, len(hyperparameters))
self.assertEqual(len(hyperparameters) - 5, len(conditions))
def test_configurations(self):
# Use a limit of ~4GiB
limit = 4000 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
cs = ParamSklearnRegressor.get_hyperparameter_search_space()
print(cs)
cs.seed(1)
for i in range(10):
config = cs.sample_configuration()
config._populate_values()
if config['regressor:sgd:n_iter'] is not None:
config._values['regressor:sgd:n_iter'] = 5
X_train, Y_train, X_test, Y_test = get_dataset(dataset='boston')
cls = ParamSklearnRegressor(config, random_state=1)
print(config)
try:
cls.fit(X_train, Y_train)
X_test_ = X_test.copy()
predictions = cls.predict(X_test)
self.assertIsInstance(predictions, np.ndarray)
predicted_probabiliets = cls.predict(X_test_)
self.assertIsInstance(predicted_probabiliets, np.ndarray)
except ValueError as e:
if "Floating-point under-/overflow occurred at epoch" in \
e.args[0] or \
"removed all features" in e.args[0] or \
"all features are discarded" in e.args[0]:
continue
else:
print(config)
print(traceback.format_exc())
raise e
except RuntimeWarning as e:
if "invalid value encountered in sqrt" in e.args[0]:
continue
elif "divide by zero encountered in" in e.args[0]:
continue
elif "invalid value encountered in divide" in e.args[0]:
continue
elif "invalid value encountered in true_divide" in e.args[0]:
continue
else:
print(config)
print(traceback.format_exc())
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
print(traceback.format_exc())
raise e
except MemoryError as e:
continue
def test_get_hyperparameter_search_space_include_exclude_models(self):
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
include={'regressor': ['random_forest']})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__'),
CategoricalHyperparameter('regressor:__choice__', ['random_forest']))
# TODO add this test when more than one regressor is present
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
exclude={'regressor': ['random_forest']})
self.assertNotIn('random_forest', str(cs))
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
include={'preprocessor': ['pca']})
self.assertEqual(cs.get_hyperparameter('preprocessor:__choice__'),
CategoricalHyperparameter('preprocessor:__choice__', ['pca']))
cs = ParamSklearnRegressor.get_hyperparameter_search_space(
exclude={'preprocessor': ['no_preprocessing']})
self.assertNotIn('no_preprocessing', str(cs))
def test_predict_batched(self):
cs = ParamSklearnRegressor.get_hyperparameter_search_space()
default = cs.get_default_configuration()
cls = ParamSklearnRegressor(default)
X_train, Y_train, X_test, Y_test = get_dataset(dataset='boston')
cls.fit(X_train, Y_train)
X_test_ = X_test.copy()
prediction_ = cls.predict(X_test_)
cls_predict = mock.Mock(wraps=cls.pipeline_)
cls.pipeline_ = cls_predict
prediction = cls.predict(X_test, batch_size=20)
self.assertEqual((356,), prediction.shape)
self.assertEqual(18, cls_predict.predict.call_count)
assert_array_almost_equal(prediction_, prediction)
def test_default_configuration(self):
for i in range(2):
cs = ParamSklearnRegressor.get_hyperparameter_search_space()
default = cs.get_default_configuration()
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes')
auto = ParamSklearnRegressor(default)
auto = auto.fit(X_train, Y_train)
predictions = auto.predict(copy.deepcopy(X_test))
# The lower the worse
r2_score = sklearn.metrics.r2_score(Y_test, predictions)
self.assertAlmostEqual(0.41626416529791199, r2_score)
model_score = auto.score(copy.deepcopy(X_test), Y_test)
self.assertEqual(model_score, r2_score)
def get_model(configuration, seed):
if 'classifier' in configuration:
return ParamSklearnClassifier(configuration, seed)
elif 'regressor' in configuration:
return ParamSklearnRegressor(configuration, seed)
def test_repr(self):
cs = ParamSklearnRegressor.get_hyperparameter_search_space()
default = cs.get_default_configuration()
representation = repr(ParamSklearnRegressor(default))
cls = eval(representation)
self.assertIsInstance(cls, ParamSklearnRegressor)