def get_hyperparameter_search_space(cls,
dataset_properties,
default=None,
include=None,
exclude=None):
cs = ConfigurationSpace()
# Compile a list of legal preprocessors for this problem
available_preprocessors = cls.get_available_components(
data_prop=dataset_properties, include=include, exclude=exclude)
if len(available_preprocessors) == 0:
raise ValueError(
"No preprocessors found, please add NoPreprocessing")
if default is None:
defaults = [
'no_preprocessing', 'select_percentile', 'pca', 'truncatedSVD'
]
for default_ in defaults:
if default_ in available_preprocessors:
default = default_
break
preprocessor = CategoricalHyperparameter(
'__choice__',
list(available_preprocessors.keys()),
default=default)
cs.add_hyperparameter(preprocessor)
for name in available_preprocessors:
preprocessor_configuration_space = available_preprocessors[name]. \
get_hyperparameter_search_space(dataset_properties)
for parameter in preprocessor_configuration_space.get_hyperparameters(
):
new_parameter = copy.deepcopy(parameter)
new_parameter.name = "%s:%s" % (name, new_parameter.name)
cs.add_hyperparameter(new_parameter)
# We must only add a condition if the hyperparameter is not
# conditional on something else
if len(
preprocessor_configuration_space.get_parents_of(
parameter)) == 0:
condition = EqualsCondition(new_parameter, preprocessor,
name)
cs.add_condition(condition)
for condition in available_preprocessors[name]. \
get_hyperparameter_search_space(
dataset_properties).get_conditions():
if not isinstance(condition, AbstractConjunction):
dlcs = [condition]
else:
dlcs = condition.get_descendent_literal_conditions()
for dlc in dlcs:
if not dlc.child.name.startswith(name):
dlc.child.name = "%s:%s" % (name, dlc.child.name)
if not dlc.parent.name.startswith(name):
dlc.parent.name = "%s:%s" % (name, dlc.parent.name)
cs.add_condition(condition)
for forbidden_clause in available_preprocessors[name]. \
get_hyperparameter_search_space(
dataset_properties).forbidden_clauses:
dlcs = forbidden_clause.get_descendant_literal_clauses()
for dlc in dlcs:
if not dlc.hyperparameter.name.startswith(name):
dlc.hyperparameter.name = "%s:%s" % (
name, dlc.hyperparameter.name)
cs.add_forbidden_clause(forbidden_clause)
return cs
def get_hyperparameter_search_space(cls, dataset_properties=None,
default=None,
include=None,
exclude=None):
cs = ConfigurationSpace()
# Compile a list of legal preprocessors for this problem
available_preprocessors = cls.get_available_components(
data_prop=dataset_properties,
include=include, exclude=exclude)
if len(available_preprocessors) == 0:
raise ValueError(
"No rescaling algorithm found.")
if default is None:
defaults = ['min/max', 'standardize', 'none', 'normalize']
for default_ in defaults:
if default_ in available_preprocessors:
default = default_
break
preprocessor = CategoricalHyperparameter('__choice__',
list(
available_preprocessors.keys()),
default=default)
cs.add_hyperparameter(preprocessor)
for name in available_preprocessors:
preprocessor_configuration_space = available_preprocessors[name]. \
get_hyperparameter_search_space(dataset_properties)
for parameter in preprocessor_configuration_space.get_hyperparameters():
new_parameter = copy.deepcopy(parameter)
new_parameter.name = "%s:%s" % (name, new_parameter.name)
cs.add_hyperparameter(new_parameter)
# We must only add a condition if the hyperparameter is not
# conditional on something else
if len(preprocessor_configuration_space.
get_parents_of(parameter)) == 0:
condition = EqualsCondition(new_parameter, preprocessor,
name)
cs.add_condition(condition)
for condition in available_preprocessors[name]. \
get_hyperparameter_search_space(
dataset_properties).get_conditions():
if not isinstance(condition, AbstractConjunction):
dlcs = [condition]
else:
dlcs = condition.get_descendent_literal_conditions()
for dlc in dlcs:
if not dlc.child.name.startswith(name):
dlc.child.name = "%s:%s" % (name, dlc.child.name)
if not dlc.parent.name.startswith(name):
dlc.parent.name = "%s:%s" % (name, dlc.parent.name)
cs.add_condition(condition)
for forbidden_clause in available_preprocessors[name]. \
get_hyperparameter_search_space(
dataset_properties).forbidden_clauses:
dlcs = forbidden_clause.get_descendant_literal_clauses()
for dlc in dlcs:
if not dlc.hyperparameter.name.startswith(name):
dlc.hyperparameter.name = "%s:%s" % (name,
dlc.hyperparameter.name)
cs.add_forbidden_clause(forbidden_clause)
return cs
