def _save_model(self, out_fn: str, scenario: ASlibScenario, feature_pre_pipeline: list, pre_solver: Aspeed, selector, config: Configuration):
'''
save all pipeline objects for predictions
Arguments
---------
out_fn: str
filename of output file
scenario: AslibScenario
ASlib scenario with all the data
feature_pre_pipeline: list
list of preprocessing objects
pre_solver: Aspeed
aspeed object with pre-solving schedule
selector: autofolio.selector.*
fitted selector object
config: Configuration
parameter setting configuration
'''
scenario.logger = None
for fpp in feature_pre_pipeline:
fpp.logger = None
if pre_solver:
pre_solver.logger = None
selector.logger = None
model = [scenario, feature_pre_pipeline, pre_solver, selector, config]
with open(out_fn, "bw") as fp:
pickle.dump(model, fp)
def predict(self, scenario: ASlibScenario, config: Configuration, feature_pre_pipeline: list, pre_solver: Aspeed, selector):
'''
predicts algorithm schedules wrt a given config
and given pipelines
Arguments
---------
scenario: aslib_scenario.aslib_scenario.ASlibScenario
aslib scenario at hand
config: Configuration
parameter configuration
feature_pre_pipeline: list
list of fitted feature preprocessors
pre_solver: Aspeed
pre solver object with a saved static schedule
selector: autofolio.selector.*
fitted selector object
'''
self.logger.info("Predict on Test")
for f_pre in feature_pre_pipeline:
scenario = f_pre.transform(scenario)
if pre_solver:
pre_solving_schedule = pre_solver.predict(scenario=scenario)
else:
pre_solving_schedule = {}
pred_schedules = selector.predict(scenario=scenario)
# combine schedules
if pre_solving_schedule:
return dict((inst, pre_solving_schedule.get(inst, []) + schedule) for inst, schedule in pred_schedules.items())
else:
return pred_schedules
def predict(self, scenario: ASlibScenario, config: Configuration, feature_pre_pipeline: list, pre_solver: Aspeed, selector):
'''
predicts algorithm schedules wrt a given config
and given pipelines
Arguments
---------
scenario: autofolio.data.aslib_scenario.ASlibScenario
aslib scenario at hand
config: Configuration
parameter configuration
feature_pre_pipeline: list
list of fitted feature preprocessors
pre_solver: Aspeed
pre solver object with a saved static schedule
selector: autofolio.selector.*
fitted selector object
'''
self.logger.info("Predict on Test")
for f_pre in feature_pre_pipeline:
scenario = f_pre.transform(scenario)
if pre_solver:
pre_solving_schedule = pre_solver.predict(scenario=scenario)
else:
pre_solving_schedule = {}
pred_schedules = selector.predict(scenario=scenario)
# combine schedules
if pre_solving_schedule:
return dict((inst, pre_solving_schedule.get(inst, []) + schedule) for inst, schedule in pred_schedules.items())
else:
return pred_schedules
def _save_model(self, out_fn: str, scenario: ASlibScenario, feature_pre_pipeline: list, pre_solver: Aspeed, selector, config: Configuration):
'''
save all pipeline objects for predictions
Arguments
---------
out_fn: str
filename of output file
scenario: AslibScenario
ASlib scenario with all the data
feature_pre_pipeline: list
list of preprocessing objects
pre_solver: Aspeed
aspeed object with pre-solving schedule
selector: autofolio.selector.*
fitted selector object
config: Configuration
parameter setting configuration
'''
scenario.logger = None
for fpp in feature_pre_pipeline:
fpp.logger = None
if pre_solver:
pre_solver.logger = None
selector.logger = None
model = [scenario, feature_pre_pipeline, pre_solver, selector, config]
with open(out_fn, "bw") as fp:
pickle.dump(model, fp)
def get_cs(self, scenario: ASlibScenario):
'''
returns the parameter configuration space of AutoFolio
(based on the automl config space: https://github.com/automl/ConfigSpace)
Arguments
---------
scenario: aslib_scenario.aslib_scenario.ASlibScenario
aslib scenario at hand
'''
self.cs = ConfigurationSpace()
# add feature steps as binary parameters
for fs in scenario.feature_steps:
fs_param = CategoricalHyperparameter(name="fgroup_%s" % (
fs), choices=[True, False], default=fs in scenario.feature_steps_default)
self.cs.add_hyperparameter(fs_param)
# preprocessing
PCAWrapper.add_params(self.cs)
ImputerWrapper.add_params(self.cs)
StandardScalerWrapper.add_params(self.cs)
# Pre-Solving
if scenario.performance_type[0] == "runtime":
Aspeed.add_params(
cs=self.cs, cutoff=scenario.algorithm_cutoff_time)
# classifiers
RandomForest.add_params(self.cs)
XGBoost.add_params(self.cs)
# regressors
RandomForestRegressor.add_params(self.cs)
# selectors
PairwiseClassifier.add_params(self.cs)
PairwiseRegression.add_params(self.cs)
self.logger.debug(self.cs)
return self.cs
def fit_pre_solving(self, scenario: ASlibScenario, config: Configuration):
'''
fits an pre-solving schedule using Aspeed [Hoos et al, 2015 TPLP)
Arguments
---------
scenario: aslib_scenario.aslib_scenario.ASlibScenario
aslib scenario at hand
config: Configuration
parameter configuration to use for preprocessing
Returns
-------
instance of Aspeed() with a fitted pre-solving schedule if performance_type of scenario is runtime; else None
'''
if scenario.performance_type[0] == "runtime":
aspeed = Aspeed()
aspeed.fit(scenario=scenario, config=config)
return aspeed
else:
return None
def fit_pre_solving(self, scenario: ASlibScenario, config: Configuration):
'''
fits an pre-solving schedule using Aspeed [Hoos et al, 2015 TPLP)
Arguments
---------
scenario: autofolio.data.aslib_scenario.ASlibScenario
aslib scenario at hand
config: Configuration
parameter configuration to use for preprocessing
Returns
-------
instance of Aspeed() with a fitted pre-solving schedule if performance_type of scenario is runtime; else None
'''
if scenario.performance_type[0] == "runtime":
aspeed = Aspeed()
aspeed.fit(scenario=scenario, config=config)
return aspeed
else:
return None
def get_cs(self, scenario: ASlibScenario):
'''
returns the parameter configuration space of AutoFolio
(based on the automl config space: https://github.com/automl/ConfigSpace)
Arguments
---------
scenario: autofolio.data.aslib_scenario.ASlibScenario
aslib scenario at hand
'''
self.cs = ConfigurationSpace()
# add feature steps as binary parameters
for fs in scenario.feature_steps:
fs_param = CategoricalHyperparameter(name="fgroup_%s" % (
fs), choices=[True, False], default=fs in scenario.feature_steps_default)
self.cs.add_hyperparameter(fs_param)
# preprocessing
PCAWrapper.add_params(self.cs)
ImputerWrapper.add_params(self.cs)
StandardScalerWrapper.add_params(self.cs)
# Pre-Solving
if scenario.performance_type[0] == "runtime":
Aspeed.add_params(
cs=self.cs, cutoff=scenario.algorithm_cutoff_time)
# classifiers
RandomForest.add_params(self.cs)
# selectors
PairwiseClassifier.add_params(self.cs)
return self.cs
def get_cs(self, scenario: ASlibScenario, autofolio_config:dict=None):
'''
returns the parameter configuration space of AutoFolio
(based on the automl config space: https://github.com/automl/ConfigSpace)
Arguments
---------
scenario: aslib_scenario.aslib_scenario.ASlibScenario
aslib scenario at hand
autofolio_config: dict, or None
An optional dictionary of configuration options
'''
self.cs = ConfigurationSpace()
# only allow the feature groups specified in the config file
# by default, though, all of the feature groups are allowed.
allowed_feature_groups = autofolio_config.get("allowed_feature_groups",
scenario.feature_steps)
if len(allowed_feature_groups) == 0:
msg = "Please ensure at least one feature group is allowed"
raise ValueError(msg)
if len(allowed_feature_groups) == 1:
choices = [True] # if we only have one feature group, it has to be active
else:
choices = [True, False]
default = True
for fs in allowed_feature_groups:
fs_param = CategoricalHyperparameter(name="fgroup_%s" % (fs),
choices=choices, default_value=default)
self.cs.add_hyperparameter(fs_param)
# preprocessing
if autofolio_config.get("pca", True):
PCAWrapper.add_params(self.cs)
if autofolio_config.get("impute", True):
ImputerWrapper.add_params(self.cs)
if autofolio_config.get("scale", True):
StandardScalerWrapper.add_params(self.cs)
# Pre-Solving
if scenario.performance_type[0] == "runtime":
if autofolio_config.get("presolve", True):
Aspeed.add_params(
cs=self.cs, cutoff=scenario.algorithm_cutoff_time)
if autofolio_config.get("classifier"):
# fix parameter
cls_choices = [autofolio_config["classifier"]]
cls_def = autofolio_config["classifier"]
else:
cls_choices = ["RandomForest","XGBoost"]
cls_def = "RandomForest"
classifier = CategoricalHyperparameter(
"classifier", choices=cls_choices,
default_value=cls_def)
self.cs.add_hyperparameter(classifier)
RandomForest.add_params(self.cs)
XGBoost.add_params(self.cs)
if autofolio_config.get("regressor"):
# fix parameter
reg_choices = [autofolio_config["regressor"]]
reg_def = autofolio_config["regressor"]
else:
reg_choices = ["RandomForestRegressor"]
reg_def = "RandomForestRegressor"
regressor = CategoricalHyperparameter(
"regressor", choices=reg_choices, default_value=reg_def)
self.cs.add_hyperparameter(regressor)
RandomForestRegressor.add_params(self.cs)
# selectors
if autofolio_config.get("selector"):
# fix parameter
sel_choices = [autofolio_config["selector"]]
sel_def = autofolio_config["selector"]
else:
sel_choices = ["PairwiseClassifier","PairwiseRegressor"]
sel_def = "PairwiseClassifier"
selector = CategoricalHyperparameter(
"selector", choices=sel_choices, default_value=sel_def)
self.cs.add_hyperparameter(selector)
PairwiseClassifier.add_params(self.cs)
PairwiseRegression.add_params(self.cs)
self.logger.debug(self.cs)
return self.cs