def test_get_hyperparameter_search_space_include_exclude_models(self):
regressor = SimpleRegressionPipeline(
include={'regressor': ['random_forest']})
cs = regressor.get_hyperparameter_search_space()
self.assertEqual(
cs.get_hyperparameter('regressor:__choice__'),
CategoricalHyperparameter('regressor:__choice__',
['random_forest']),
)
# TODO add this test when more than one regressor is present
regressor = SimpleRegressionPipeline(
exclude={'regressor': ['random_forest']})
cs = regressor.get_hyperparameter_search_space()
self.assertNotIn('random_forest', str(cs))
regressor = SimpleRegressionPipeline(
include={'feature_preprocessor': ['pca']})
cs = regressor.get_hyperparameter_search_space()
self.assertEqual(
cs.get_hyperparameter('feature_preprocessor:__choice__'),
CategoricalHyperparameter('feature_preprocessor:__choice__',
['pca']))
regressor = SimpleRegressionPipeline(
exclude={'feature_preprocessor': ['no_preprocessing']})
cs = regressor.get_hyperparameter_search_space()
self.assertNotIn('no_preprocessing', str(cs))
def test_get_hyperparameter_search_space_preprocessor_contradicts_default_classifier(
self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
include={'preprocessor': ['densifier']},
dataset_properties={'sparse': True})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__').default,
'gradient_boosting')
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
include={'preprocessor': ['nystroem_sampler']})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__').default,
'sgd')
def test_get_hyperparameter_search_space_preprocessor_contradicts_default_classifier(
self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
include={'preprocessor': ['densifier']},
dataset_properties={'sparse': True})
self.assertEqual(cs.get_hyperparameter('regressor:__choice__').default,
'gradient_boosting')
cs = SimpleRegressionPipeline.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 = SimpleRegressionPipeline.get_hyperparameter_search_space()
self.assertIsInstance(cs, ConfigurationSpace)
conditions = cs.get_conditions()
hyperparameters = cs.get_hyperparameters()
self.assertEqual(143, len(hyperparameters))
self.assertEqual(len(hyperparameters) - 5, len(conditions))
def test_get_hyperparameter_search_space(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
self.assertIsInstance(cs, ConfigurationSpace)
conditions = cs.get_conditions()
hyperparameters = cs.get_hyperparameters()
self.assertEqual(143, 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 = SimpleRegressionPipeline.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 = SimpleRegressionPipeline(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 = SimpleRegressionPipeline.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 = SimpleRegressionPipeline.get_hyperparameter_search_space(
exclude={'regressor': ['random_forest']})
self.assertNotIn('random_forest', str(cs))
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
include={'preprocessor': ['pca']})
self.assertEqual(cs.get_hyperparameter('preprocessor:__choice__'),
CategoricalHyperparameter('preprocessor:__choice__', ['pca']))
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
exclude={'preprocessor': ['no_preprocessing']})
self.assertNotIn('no_preprocessing', str(cs))
def test_configurations_sparse(self):
# Use a limit of ~4GiB
limit = 4000 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
dataset_properties={'sparse': True})
print(cs)
for i in range(10):
config = cs.sample_configuration()
config._populate_values()
if 'classifier:passive_aggressive:n_iter' in config and \
config[
'classifier:passive_aggressive:n_iter'] is not None:
config._values['classifier:passive_aggressive:n_iter'] = 5
if 'classifier:sgd:n_iter' in config and \
config['classifier:sgd:n_iter'] is not None:
config._values['classifier:sgd:n_iter'] = 5
print(config)
X_train, Y_train, X_test, Y_test = get_dataset(dataset='boston',
make_sparse=True)
cls = SimpleRegressionPipeline(config, random_state=1)
try:
cls.fit(X_train, Y_train)
predictions = cls.predict(X_test)
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)
traceback.print_tb(sys.exc_info()[2])
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)
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
raise e
def test_configurations_sparse(self):
# Use a limit of ~4GiB
limit = 4000 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
dataset_properties={'sparse': True})
print(cs)
for i in range(10):
config = cs.sample_configuration()
config._populate_values()
if 'classifier:passive_aggressive:n_iter' in config and \
config[
'classifier:passive_aggressive:n_iter'] is not None:
config._values['classifier:passive_aggressive:n_iter'] = 5
if 'classifier:sgd:n_iter' in config and \
config['classifier:sgd:n_iter'] is not None:
config._values['classifier:sgd:n_iter'] = 5
print(config)
X_train, Y_train, X_test, Y_test = get_dataset(dataset='boston',
make_sparse=True)
cls = SimpleRegressionPipeline(config, random_state=1)
try:
cls.fit(X_train, Y_train)
predictions = cls.predict(X_test)
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)
traceback.print_tb(sys.exc_info()[2])
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)
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
raise e
def test_default_configuration(self):
for i in range(2):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes')
auto = SimpleRegressionPipeline(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(0.41732302035060087, r2_score)
model_score = auto.score(copy.deepcopy(X_test), Y_test)
self.assertEqual(model_score, r2_score)
def test_default_configuration(self):
for i in range(2):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes')
auto = SimpleRegressionPipeline(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(0.41732302035060087, r2_score)
model_score = auto.score(copy.deepcopy(X_test), Y_test)
self.assertEqual(model_score, r2_score)
def test_predict_batched(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
cls = SimpleRegressionPipeline(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_predict_batched(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
cls = SimpleRegressionPipeline(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_predict_batched(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space(
include={'regressor': ['decision_tree']})
default = cs.get_default_configuration()
cls = SimpleRegressionPipeline(default)
X_train, Y_train, X_test, Y_test = get_dataset(dataset='diabetes')
cls.fit(X_train, Y_train)
X_test_ = X_test.copy()
prediction_ = cls.predict(X_test_)
cls_predict = unittest.mock.Mock(wraps=cls.pipeline_)
cls.pipeline_ = cls_predict
prediction = cls.predict(X_test, batch_size=20)
self.assertEqual((292, ), prediction.shape)
self.assertEqual(15, cls_predict.predict.call_count)
assert_array_almost_equal(prediction_, prediction)
def test_set_hyperparameters_honors_configuration(self):
"""Makes sure that a given configuration is honored in practice.
This method tests that the set hyperparameters actually create objects
that comply with the given configuration. It iterates trough the pipeline to
make sure we did not miss a step, but also checks at the end that every
configuration from Config was checked
"""
all_combinations = list(itertools.product([True, False], repeat=4))
for sparse, multilabel, signed, multiclass, in all_combinations:
dataset_properties = {
'sparse': sparse,
'multilabel': multilabel,
'multiclass': multiclass,
'signed': signed,
}
auto = SimpleRegressionPipeline(
random_state=1,
dataset_properties=dataset_properties,
)
cs = auto.get_hyperparameter_search_space()
config = cs.sample_configuration()
# Set hyperparameters takes a given config and translate
# a config to an actual implementation
auto.set_hyperparameters(config)
config_dict = config.get_dictionary()
# keys to check is our mechanism to ensure that every
# every config key is checked
keys_checked = []
for name, step in auto.named_steps.items():
if name == 'data_preprocessing':
# We have to check both the numerical and categorical
to_check = {
'numerical_transformer': step.numer_ppl.named_steps,
'categorical_transformer': step.categ_ppl.named_steps,
}
for data_type, pipeline in to_check.items():
for sub_name, sub_step in pipeline.items():
# If it is a Choice, make sure it is the correct one!
if isinstance(sub_step, AutoSklearnChoice):
key = "data_preprocessing:{}:{}:__choice__".format(
data_type, sub_name)
keys_checked.extend(
self._test_set_hyperparameter_choice(
key, sub_step, config_dict))
# If it is a component, make sure it has the correct hyperparams
elif isinstance(sub_step, AutoSklearnComponent):
keys_checked.extend(
self._test_set_hyperparameter_component(
"data_preprocessing:{}:{}".format(
data_type, sub_name), sub_step,
config_dict))
else:
raise ValueError(
"New type of pipeline component!")
elif name == 'balancing':
keys_checked.extend(
self._test_set_hyperparameter_component(
'balancing', step, config_dict))
elif name == 'feature_preprocessor':
keys_checked.extend(
self._test_set_hyperparameter_choice(
'feature_preprocessor:__choice__', step,
config_dict))
elif name == 'regressor':
keys_checked.extend(
self._test_set_hyperparameter_choice(
'regressor:__choice__', step, config_dict))
else:
raise ValueError(
"Found another type of step! Need to update this check"
" {}. ".format(name))
# Make sure we checked the whole configuration
self.assertSetEqual(set(config_dict.keys()), set(keys_checked))
def test_set_hyperparameters_honors_configuration(self):
"""Makes sure that a given configuration is honored in practice.
This method tests that the set hyperparameters actually create objects
that comply with the given configuration. It iterates trough the pipeline to
make sure we did not miss a step, but also checks at the end that every
configuration from Config was checked
Also considers random_state and ensures pipeline steps correctly recieve
the right random_state
"""
all_combinations = list(itertools.product([True, False], repeat=4))
for sparse, multilabel, signed, multiclass, in all_combinations:
dataset_properties = {
'sparse': sparse,
'multilabel': multilabel,
'multiclass': multiclass,
'signed': signed,
}
random_state = 1
auto = SimpleRegressionPipeline(
random_state=random_state,
dataset_properties=dataset_properties,
)
cs = auto.get_hyperparameter_search_space()
config = cs.sample_configuration()
# Set hyperparameters takes a given config and translate
# a config to an actual implementation
auto.set_hyperparameters(config)
config_dict = config.get_dictionary()
# keys to check is our mechanism to ensure that every
# every config key is checked
keys_checked = []
for name, step in auto.named_steps.items():
if name == 'data_preprocessor':
keys_checked.extend(
self._test_set_hyperparameter_choice(
'data_preprocessor:__choice__', step, config_dict))
self.assertEqual(step.random_state, random_state)
elif name == 'feature_preprocessor':
keys_checked.extend(
self._test_set_hyperparameter_choice(
'feature_preprocessor:__choice__', step,
config_dict))
self.assertEqual(step.random_state, random_state)
elif name == 'regressor':
keys_checked.extend(
self._test_set_hyperparameter_choice(
'regressor:__choice__', step, config_dict))
self.assertEqual(step.random_state, random_state)
else:
raise ValueError(
"Found another type of step! Need to update this check"
" {}. ".format(name))
# Make sure we checked the whole configuration
self.assertSetEqual(set(config_dict.keys()), set(keys_checked))
def test_repr(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
representation = repr(SimpleRegressionPipeline(default))
cls = eval(representation)
self.assertIsInstance(cls, SimpleRegressionPipeline)
def test_repr(self):
cs = SimpleRegressionPipeline.get_hyperparameter_search_space()
default = cs.get_default_configuration()
representation = repr(SimpleRegressionPipeline(default))
cls = eval(representation)
self.assertIsInstance(cls, SimpleRegressionPipeline)
