def _test_configurations(self, configurations_space, make_sparse=False,
data=None, dataset_properties=None):
# Use a limit of ~4GiB
limit = 3072 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
configurations_space.seed(1)
for i in range(10):
config = configurations_space.sample_configuration()
config._populate_values()
# Restrict configurations which could take too long on travis-ci
restrictions = {'regressor:passive_aggressive:n_iter': 5,
'regressor:sgd:n_iter': 5,
'regressor:adaboost:n_estimators': 50,
'regressor:adaboost:max_depth': 1,
'preprocessor:kernel_pca:n_components': 10,
'preprocessor:kitchen_sinks:n_components': 50,
'regressor:libsvm_svc:degree': 2,
'regressor:libsvm_svr:degree': 2,
'preprocessor:truncatedSVD:target_dim': 10,
'preprocessor:polynomial:degree': 2,
'regressor:lda:n_components': 10}
for restrict_parameter in restrictions:
restrict_to = restrictions[restrict_parameter]
if restrict_parameter in config and \
config[restrict_parameter] is not None:
config._values[restrict_parameter] = restrict_to
if data is None:
X_train, Y_train, X_test, Y_test = get_dataset(
dataset='boston', make_sparse=make_sparse, add_NaNs=True)
else:
X_train = data['X_train'].copy()
Y_train = data['Y_train'].copy()
X_test = data['X_test'].copy()
Y_test = data['Y_test'].copy()
cls = SimpleRegressionPipeline(random_state=1,
dataset_properties=dataset_properties)
cls.set_hyperparameters(config)
try:
cls.fit(X_train, Y_train)
predictions = cls.predict(X_test)
except MemoryError as e:
continue
except ValueError as e:
if "Floating-point under-/overflow occurred at epoch" in \
e.args[0]:
continue
elif "removed all features" in e.args[0]:
continue
elif "all features are discarded" in e.args[0]:
continue
elif "Numerical problems in QDA" in e.args[0]:
continue
elif 'Bug in scikit-learn' 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)
traceback.print_tb(sys.exc_info()[2])
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
except Exception as e:
if "Multiple input features cannot have the same target value" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
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_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_configurations(self,
configurations_space,
make_sparse=False,
data=None,
dataset_properties=None):
# Use a limit of ~4GiB
limit = 3072 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
configurations_space.seed(1)
for i in range(10):
config = configurations_space.sample_configuration()
config._populate_values()
# Restrict configurations which could take too long on travis-ci
restrictions = {
'regressor:adaboost:n_estimators': 50,
'regressor:adaboost:max_depth': 1,
'feature_preprocessor:kernel_pca:n_components': 10,
'feature_preprocessor:kitchen_sinks:n_components': 50,
'regressor:libsvm_svc:degree': 2,
'regressor:libsvm_svr:degree': 2,
'regressor:libsvm_svr:C': 1.,
'feature_preprocessor:truncatedSVD:target_dim': 10,
'feature_preprocessor:polynomial:degree': 2,
'regressor:lda:n_components': 10
}
for restrict_parameter in restrictions:
restrict_to = restrictions[restrict_parameter]
if restrict_parameter in config and config[
restrict_parameter] is not None:
config._values[restrict_parameter] = restrict_to
if data is None:
X_train, Y_train, X_test, Y_test = get_dataset(
dataset='boston', make_sparse=make_sparse, add_NaNs=True)
else:
X_train = data['X_train'].copy()
Y_train = data['Y_train'].copy()
X_test = data['X_test'].copy()
data['Y_test'].copy()
cls = SimpleRegressionPipeline(
random_state=1, dataset_properties=dataset_properties)
cls.set_hyperparameters(config)
# First make sure that for this configuration, setting the parameters
# does not mistakenly set the estimator as fitted
for name, step in cls.named_steps.items():
with self.assertRaisesRegex(sklearn.exceptions.NotFittedError,
"instance is not fitted yet"):
check_is_fitted(step)
try:
cls.fit(X_train, Y_train)
# After fit, all components should be tagged as fitted
# by sklearn. Check is fitted raises an exception if that
# is not the case
try:
for name, step in cls.named_steps.items():
check_is_fitted(step)
except sklearn.exceptions.NotFittedError:
self.fail(
"config={} raised NotFittedError unexpectedly!".format(
config))
cls.predict(X_test)
except MemoryError:
continue
except np.linalg.LinAlgError:
continue
except ValueError as e:
if "Floating-point under-/overflow occurred at epoch" in \
e.args[0]:
continue
elif "removed all features" in e.args[0]:
continue
elif "all features are discarded" in e.args[0]:
continue
elif "Numerical problems in QDA" in e.args[0]:
continue
elif 'Bug in scikit-learn' in e.args[0]:
continue
elif 'The condensed distance matrix must contain only finite ' \
'values.' 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
elif "invalid value encountered in multiply" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
except Exception as e:
if "Multiple input features cannot have the same target value" in e.args[
0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
def _test_configurations(self, configurations_space, make_sparse=False,
data=None, dataset_properties=None):
# Use a limit of ~4GiB
limit = 3072 * 1024 * 1024
resource.setrlimit(resource.RLIMIT_AS, (limit, limit))
configurations_space.seed(1)
for i in range(10):
config = configurations_space.sample_configuration()
config._populate_values()
# Restrict configurations which could take too long on travis-ci
restrictions = {'regressor:adaboost:n_estimators': 50,
'regressor:adaboost:max_depth': 1,
'preprocessor:kernel_pca:n_components': 10,
'preprocessor:kitchen_sinks:n_components': 50,
'regressor:libsvm_svc:degree': 2,
'regressor:libsvm_svr:degree': 2,
'preprocessor:truncatedSVD:target_dim': 10,
'preprocessor:polynomial:degree': 2,
'regressor:lda:n_components': 10}
for restrict_parameter in restrictions:
restrict_to = restrictions[restrict_parameter]
if restrict_parameter in config and \
config[restrict_parameter] is not None:
config._values[restrict_parameter] = restrict_to
if data is None:
X_train, Y_train, X_test, Y_test = get_dataset(
dataset='boston', make_sparse=make_sparse, add_NaNs=True)
else:
X_train = data['X_train'].copy()
Y_train = data['Y_train'].copy()
X_test = data['X_test'].copy()
Y_test = data['Y_test'].copy()
cls = SimpleRegressionPipeline(random_state=1,
dataset_properties=dataset_properties)
cls.set_hyperparameters(config)
try:
cls.fit(X_train, Y_train)
predictions = cls.predict(X_test)
except MemoryError as e:
continue
except ValueError as e:
if "Floating-point under-/overflow occurred at epoch" in \
e.args[0]:
continue
elif "removed all features" in e.args[0]:
continue
elif "all features are discarded" in e.args[0]:
continue
elif "Numerical problems in QDA" in e.args[0]:
continue
elif 'Bug in scikit-learn' in e.args[0]:
continue
elif 'The condensed distance matrix must contain only finite ' \
'values.' 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)
traceback.print_tb(sys.exc_info()[2])
raise e
except UserWarning as e:
if "FastICA did not converge" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
except Exception as e:
if "Multiple input features cannot have the same target value" in e.args[0]:
continue
else:
print(config)
traceback.print_tb(sys.exc_info()[2])
raise e
