class TestEI(unittest.TestCase):
def setUp(self):
self.model = MockModel()
self.ei = EI(self.model)
def test_1xD(self):
self.ei.update(model=self.model, eta=1.0)
configurations = [ConfigurationMock([1.0, 1.0, 1.0])]
acq = self.ei(configurations)
self.assertEqual(acq.shape, (1, 1))
self.assertAlmostEqual(acq[0][0], 0.3989422804014327)
def test_NxD(self):
self.ei.update(model=self.model, eta=1.0)
configurations = ([
ConfigurationMock([0.0, 0.0, 0.0]),
ConfigurationMock([0.1, 0.1, 0.1]),
ConfigurationMock([1.0, 1.0, 1.0])
])
acq = self.ei(configurations)
self.assertEqual(acq.shape, (3, 1))
self.assertAlmostEqual(acq[0][0], 0.0)
self.assertAlmostEqual(acq[1][0], 0.90020601136712231)
self.assertAlmostEqual(acq[2][0], 0.3989422804014327)
def test_1x1(self):
self.ei.update(model=self.model, eta=1.0)
configurations = [ConfigurationMock([1.0])]
acq = self.ei(configurations)
self.assertEqual(acq.shape, (1, 1))
self.assertAlmostEqual(acq[0][0], 0.3989422804014327)
def test_Nx1(self):
self.ei.update(model=self.model, eta=1.0)
configurations = [
ConfigurationMock([0.0001]),
ConfigurationMock([1.0]),
ConfigurationMock([2.0])
]
acq = self.ei(configurations)
self.assertEqual(acq.shape, (3, 1))
self.assertAlmostEqual(acq[0][0], 0.9999)
self.assertAlmostEqual(acq[1][0], 0.3989422804014327)
self.assertAlmostEqual(acq[2][0], 0.19964122837424575)
def test_zero_variance(self):
self.ei.update(model=self.model, eta=1.0)
X = np.array([ConfigurationMock([0.0])])
acq = np.array(self.ei(X))
self.assertAlmostEqual(acq[0][0], 0.0)
def plot_state(smac, model, x_points, y_points, x_smac, y_smac, step=None):
"""
plot function with all evaluated points,
EI acquisition function
Predictions with uncertainties
"""
from smac.optimizer.acquisition import EI
# cost all points for x
step = step or len(x_smac)
x_smac_ = np.array([[x] for x in x_smac[:step]])
y_smac_ = np.array([[y] for y in y_smac[:step]])
# as an alternative, we could extract the points from the runhistory again
# but these points will be scaled to a unit-hypercube
# X, Y = smac.solver.rh2EPM.transform(runhistory)
model.train(x_smac_, y_smac_)
acq_func = EI(model=model)
acq_func.update(model=model, eta=np.min(y_smac))
x_points_ = np.array([[x] for x in x_points])
acq_values = acq_func._compute(X=x_points_)[:, 0]
# plot acquisition function
y_mean, y_var = model.predict(x_points_)
y_mean = y_mean[:, 0]
y_std = np.sqrt(y_var)[:, 0]
fig1 = plt.figure()
ax1 = fig1.add_subplot(111)
ax1.plot(x_points, acq_values)
plt.title("Aquisition Function")
plt.savefig('fig%da.pdf' % step)
# plot uncertainties
fig1 = plt.figure()
ax1 = fig1.add_subplot(111)
ax1.plot(x_points, y_mean)
ax1.fill_between(x_points, y_mean - y_std,
y_mean + y_std, alpha=0.5)
ax1.plot(x_smac[:step], y_smac[:step], 'bo')
ax1.plot(x_smac[:step], y_smac[:step], 'ro')
ax1.plot(x_points, y_points, '--')
plt.title("Uncertainty Predictions")
plt.savefig('fig%db.pdf' % step)
def test_get_next_by_random_search_sorted(self,
patch_sample,
patch_ei,
patch_impute):
values = (10, 1, 9, 2, 8, 3, 7, 4, 6, 5)
patch_sample.return_value = [ConfigurationMock(i) for i in values]
patch_ei.return_value = np.array([[_] for _ in values], dtype=float)
patch_impute.side_effect = lambda l: values
cs = ConfigurationSpace()
ei = EI(None)
rs = RandomSearch(ei, cs)
rval = rs._maximize(
runhistory=None, stats=None, num_points=10, _sorted=True
)
self.assertEqual(len(rval), 10)
for i in range(10):
self.assertIsInstance(rval[i][1], ConfigurationMock)
self.assertEqual(rval[i][1].value, 10 - i)
self.assertEqual(rval[i][0], 10 - i)
self.assertEqual(rval[i][1].origin, 'Random Search (sorted)')
# Check that config.get_array works as desired and imputation is used
# in between, we therefore have to retrieve the value from the mock!
np.testing.assert_allclose([v.value for v in patch_ei.call_args[0][0]],
np.array(values, dtype=float))
def optimize(scenario, run, forest=False, seed=8, ratio=0.8):
types, bounds = get_types(scenario.cs, scenario.feature_array)
rfr = RandomForestWithInstances(types=types, bounds=bounds, instance_features=scenario.feature_array, seed=seed)
ei = EI(model=rfr)
if forest:
optimizer = ForestSearch(ei, scenario.cs, ratio=ratio)
else:
optimizer = InterleavedLocalAndRandomSearch(ei, scenario.cs)
scenario.output_dir = "%s_%s_%d_%lf" % ("./logs/run_", "forest_" if forest else "random_", seed, time.time())
smac = SMAC(
scenario=scenario,
rng=np.random.RandomState(seed),
model=rfr,
acquisition_function=ei,
acquisition_function_optimizer=optimizer,
tae_runner=run,
)
try:
incumbent = smac.optimize()
finally:
incumbent = smac.solver.incumbent
return smac.get_tae_runner().run(incumbent, 1)[1]
class TestAcquisitionFunction(unittest.TestCase):
def setUp(self):
self.model = unittest.mock.Mock()
self.acq = EI(model=self.model)
def test_update_model_and_eta(self):
model = 'abc'
self.assertIsNone(self.acq.eta)
self.acq.update(model=model, eta=0.1)
self.assertEqual(self.acq.model, model)
self.assertEqual(self.acq.eta, 0.1)
def test_update_other(self):
self.acq.other = 'other'
with self.assertRaisesRegex(
ValueError,
r"Acquisition function EI needs to be updated with key model, but only got keys "
r"\['other'\].",
):
self.acq.update(other=None)
model = 'abc'
self.acq.update(model=model, eta=0.1, other=None)
self.assertEqual(self.acq.other, 'other')
def test_inject_dependencies(self):
# initialize objects with missing dependencies
ta = ExecuteTAFuncDict(lambda x: x**2)
rh = RunHistory(aggregate_func=None)
acqu_func = EI(model=None)
intensifier = Intensifier(tae_runner=None,
stats=None,
traj_logger=None,
rng=np.random.RandomState(),
instances=None)
init_design = DefaultConfiguration(tae_runner=None,
scenario=None,
stats=None,
traj_logger=None,
rng=np.random.RandomState())
rh2epm = RunHistory2EPM4Cost(scenario=self.scenario, num_params=0)
rh2epm.scenario = None
# assert missing dependencies
self.assertIsNone(rh.aggregate_func)
self.assertIsNone(acqu_func.model)
self.assertIsNone(intensifier.tae_runner)
self.assertIsNone(intensifier.stats)
self.assertIsNone(intensifier.traj_logger)
self.assertIsNone(init_design.tae_runner)
self.assertIsNone(init_design.scenario)
self.assertIsNone(init_design.stats)
self.assertIsNone(init_design.traj_logger)
self.assertIsNone(rh2epm.scenario)
# initialize smac-object
SMAC(scenario=self.scenario,
tae_runner=ta,
runhistory=rh,
intensifier=intensifier,
acquisition_function=acqu_func,
runhistory2epm=rh2epm,
initial_design=init_design)
# assert that missing dependencies are injected
self.assertIsNotNone(rh.aggregate_func, AbstractAcquisitionFunction)
self.assertIsInstance(acqu_func.model, AbstractEPM)
self.assertIsInstance(intensifier.tae_runner, ExecuteTARun)
self.assertIsInstance(intensifier.stats, Stats)
self.assertIsInstance(intensifier.traj_logger, TrajLogger)
self.assertIsInstance(init_design.tae_runner, ExecuteTARun)
self.assertIsInstance(init_design.scenario, Scenario)
self.assertIsInstance(init_design.stats, Stats)
self.assertIsInstance(init_design.traj_logger, TrajLogger)
self.assertIsInstance(rh2epm.scenario, Scenario)
def test_challenger_list_callback(self, patch_sample, patch_ei,
patch_impute):
values = (10, 1, 9, 2, 8, 3, 7, 4, 6, 5)
patch_sample.return_value = ConfigurationMock(1)
patch_ei.return_value = np.array([[_] for _ in values], dtype=float)
patch_impute.side_effect = lambda l: values
cs = ConfigurationSpace()
ei = EI(None)
rs = RandomSearch(ei, cs)
rs._maximize = unittest.mock.Mock()
rs._maximize.return_value = [(0, 0)]
rval = rs.maximize(
runhistory=None,
stats=None,
num_points=10,
)
self.assertEqual(rs._maximize.call_count, 0)
next(rval)
self.assertEqual(rs._maximize.call_count, 1)
random_configuration_chooser = unittest.mock.Mock()
random_configuration_chooser.check.side_effect = [
True, False, False, False
]
rs._maximize = unittest.mock.Mock()
rs._maximize.return_value = [(0, 0), (1, 1)]
rval = rs.maximize(
runhistory=None,
stats=None,
num_points=10,
random_configuration_chooser=random_configuration_chooser,
)
self.assertEqual(rs._maximize.call_count, 0)
# The first configuration is chosen at random (see the random_configuration_chooser mock)
conf = next(rval)
self.assertIsInstance(conf, ConfigurationMock)
self.assertEqual(rs._maximize.call_count, 0)
# The 2nd configuration triggers the call to the callback (see the random_configuration_chooser mock)
conf = next(rval)
self.assertEqual(rs._maximize.call_count, 1)
self.assertEqual(conf, 0)
# The 3rd configuration doesn't trigger the callback any more
conf = next(rval)
self.assertEqual(rs._maximize.call_count, 1)
self.assertEqual(conf, 1)
with self.assertRaises(StopIteration):
next(rval)
def __init__(
self,
configspace,
random_fraction=1 / 2,
logger=None,
configs=None,
losses=None,
):
self.logger = logger
self.random_fraction = random_fraction
self.configspace = configspace
self.min_points_in_model = len(self.configspace.get_hyperparameters())
rng = np.random.RandomState(random.randint(0, 100))
self.model = _construct_model(configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(
acquisition_function=self.acquisition_func,
config_space=configspace,
rng=rng)
self.runhistory = RunHistory()
self.configs = configs or list()
self.losses = losses or list()
if self.has_model:
for config, cost in zip(self.configs, self.losses):
self.runhistory.add(config, cost, 0, StatusType.SUCCESS)
X = convert_configurations_to_array(self.configs)
Y = np.array(self.losses, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses),
)
def test_get_next_by_random_search(self, patch):
def side_effect(size):
return [ConfigurationMock()] * size
patch.side_effect = side_effect
cs = ConfigurationSpace()
ei = EI(None)
rs = RandomSearch(ei, cs)
rval = rs._maximize(
runhistory=None, stats=None, num_points=10, _sorted=False
)
self.assertEqual(len(rval), 10)
for i in range(10):
self.assertIsInstance(rval[i][1], ConfigurationMock)
self.assertEqual(rval[i][1].origin, 'Random Search')
self.assertEqual(rval[i][0], 0)
def test_get_next_by_local_search(
self,
_get_initial_points_patch,
patch
):
# Without known incumbent
class SideEffect(object):
def __call__(self, *args, **kwargs):
rval = []
for i in range(len(args[0])):
rval.append((i, ConfigurationMock(i)))
return rval
patch.side_effect = SideEffect()
cs = test_helpers.get_branin_config_space()
rand_confs = cs.sample_configuration(size=9)
_get_initial_points_patch.return_value = rand_confs
acq_func = EI(None)
ls = LocalSearch(acq_func, cs)
# To have some data in a mock runhistory
runhistory = unittest.mock.Mock()
runhistory.data = [None] * 1000
rval = ls._maximize(runhistory, None, 9)
self.assertEqual(len(rval), 9)
self.assertEqual(patch.call_count, 1)
for i in range(9):
self.assertIsInstance(rval[i][1], ConfigurationMock)
self.assertEqual(rval[i][1].value, 8 - i)
self.assertEqual(rval[i][0], 8 - i)
self.assertEqual(rval[i][1].origin, 'Local Search')
# Check that the known 'incumbent' is transparently passed through
patch.side_effect = SideEffect()
_get_initial_points_patch.return_value = ['Incumbent'] + rand_confs
rval = ls._maximize(runhistory, None, 10)
self.assertEqual(len(rval), 10)
self.assertEqual(patch.call_count, 2)
# Only the first local search in each iteration starts from the
# incumbent
self.assertEqual(patch.call_args_list[1][0][0][0], 'Incumbent')
for i in range(10):
self.assertEqual(rval[i][1].origin, 'Local Search')
def test_get_next_by_local_search(self, _get_initial_points_patch, patch):
# Without known incumbent
class SideEffect(object):
def __init__(self):
self.call_number = 0
def __call__(self, *args, **kwargs):
rval = 9 - self.call_number
self.call_number += 1
return (rval, ConfigurationMock(rval))
patch.side_effect = SideEffect()
cs = test_helpers.get_branin_config_space()
rand_confs = cs.sample_configuration(size=9)
_get_initial_points_patch.return_value = rand_confs
acq_func = EI(None)
ls = LocalSearch(acq_func, cs)
# To have some data in a mock runhistory
runhistory = unittest.mock.Mock()
runhistory.data = [None] * 1000
rval = ls._maximize(runhistory, None, 9)
self.assertEqual(len(rval), 9)
self.assertEqual(patch.call_count, 9)
for i in range(9):
self.assertIsInstance(rval[i][1], ConfigurationMock)
self.assertEqual(rval[i][1].value, 9 - i)
self.assertEqual(rval[i][0], 9 - i)
self.assertEqual(rval[i][1].origin, 'Local Search')
# With known incumbent
patch.side_effect = SideEffect()
_get_initial_points_patch.return_value = ['Incumbent'] + rand_confs
rval = ls._maximize(runhistory, None, 10)
self.assertEqual(len(rval), 10)
self.assertEqual(patch.call_count, 19)
# Only the first local search in each iteration starts from the
# incumbent
self.assertEqual(patch.call_args_list[9][0][0], 'Incumbent')
for i in range(10):
self.assertEqual(rval[i][1].origin, 'Local Search')
def __init__(self,
scenario: Scenario,
tae_runner: Optional[Union[Type[ExecuteTARun], Callable]] = None,
tae_runner_kwargs: Optional[dict] = None,
runhistory: Optional[Union[Type[RunHistory], RunHistory]] = None,
runhistory_kwargs: Optional[dict] = None,
intensifier: Optional[Type[Intensifier]] = None,
intensifier_kwargs: Optional[dict] = None,
acquisition_function: Optional[Type[AbstractAcquisitionFunction]] = None,
acquisition_function_kwargs: Optional[dict] = None,
integrate_acquisition_function: bool = False,
acquisition_function_optimizer: Optional[Type[AcquisitionFunctionMaximizer]] = None,
acquisition_function_optimizer_kwargs: Optional[dict] = None,
model: Optional[Type[AbstractEPM]] = None,
model_kwargs: Optional[dict] = None,
runhistory2epm: Optional[Type[AbstractRunHistory2EPM]] = None,
runhistory2epm_kwargs: Optional[dict] = None,
initial_design: Optional[Type[InitialDesign]] = None,
initial_design_kwargs: Optional[dict] = None,
initial_configurations: Optional[List[Configuration]] = None,
stats: Optional[Stats] = None,
restore_incumbent: Optional[Configuration] = None,
rng: Optional[Union[np.random.RandomState, int]] = None,
smbo_class: Optional[SMBO] = None,
run_id: Optional[int] = None,
random_configuration_chooser: Optional[Type[RandomConfigurationChooser]] = None,
random_configuration_chooser_kwargs: Optional[dict] = None
):
"""
Constructor
Parameters
----------
scenario : ~smac.scenario.scenario.Scenario
Scenario object
tae_runner : ~smac.tae.execute_ta_run.ExecuteTARun or callable
Callable or implementation of
:class:`~smac.tae.execute_ta_run.ExecuteTARun`. In case a
callable is passed it will be wrapped by
:class:`~smac.tae.execute_func.ExecuteTAFuncDict`.
If not set, it will be initialized with the
:class:`~smac.tae.execute_ta_run_old.ExecuteTARunOld`.
tae_runner_kwargs: Optional[dict]
arguments passed to constructor of '~tae_runner'
runhistory : RunHistory
runhistory to store all algorithm runs
runhistory_kwargs : Optional[dict]
arguments passed to constructor of runhistory.
We strongly advise against changing the aggregation function,
since it will break some code assumptions
intensifier : Intensifier
intensification object to issue a racing to decide the current
incumbent
intensifier_kwargs: Optional[dict]
arguments passed to the constructor of '~intensifier'
acquisition_function : ~smac.optimizer.acquisition.AbstractAcquisitionFunction
Class or object that implements the :class:`~smac.optimizer.acquisition.AbstractAcquisitionFunction`.
Will use :class:`~smac.optimizer.acquisition.EI` or :class:`~smac.optimizer.acquisition.LogEI` if not set.
`~acquisition_function_kwargs` is passed to the class constructor.
acquisition_function_kwargs : Optional[dict]
dictionary to pass specific arguments to ~acquisition_function
integrate_acquisition_function : bool, default=False
Whether to integrate the acquisition function. Works only with models which can sample their
hyperparameters (i.e. GaussianProcessMCMC).
acquisition_function_optimizer : ~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer
Object that implements the :class:`~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer`.
Will use :class:`smac.optimizer.ei_optimization.InterleavedLocalAndRandomSearch` if not set.
acquisition_function_optimizer_kwargs: Optional[dict]
Arguments passed to constructor of '~acquisition_function_optimizer'
model : AbstractEPM
Model that implements train() and predict(). Will use a
:class:`~smac.epm.rf_with_instances.RandomForestWithInstances` if not set.
model_kwargs : Optional[dict]
Arguments passed to constructor of '~model'
runhistory2epm : ~smac.runhistory.runhistory2epm.RunHistory2EMP
Object that implements the AbstractRunHistory2EPM. If None,
will use :class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4Cost`
if objective is cost or
:class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4LogCost`
if objective is runtime.
runhistory2epm_kwargs: Optional[dict]
Arguments passed to the constructor of '~runhistory2epm'
initial_design : InitialDesign
initial sampling design
initial_design_kwargs: Optional[dict]
arguments passed to constructor of `~initial_design'
initial_configurations : List[Configuration]
list of initial configurations for initial design --
cannot be used together with initial_design
stats : Stats
optional stats object
rng : np.random.RandomState
Random number generator
restore_incumbent : Configuration
incumbent used if restoring to previous state
smbo_class : ~smac.optimizer.smbo.SMBO
Class implementing the SMBO interface which will be used to
instantiate the optimizer class.
run_id : int (optional)
Run ID will be used as subfolder for output_dir. If no ``run_id`` is given, a random ``run_id`` will be
chosen.
random_configuration_chooser : ~smac.optimizer.random_configuration_chooser.RandomConfigurationChooser
How often to choose a random configuration during the intensification procedure.
random_configuration_chooser_kwargs : Optional[dict]
arguments of constructor for '~random_configuration_chooser'
"""
self.logger = logging.getLogger(
self.__module__ + "." + self.__class__.__name__)
aggregate_func = average_cost
self.scenario = scenario
self.output_dir = ""
if not restore_incumbent:
# restore_incumbent is used by the CLI interface which provides a method for restoring a SMAC run given an
# output directory. This is the default path.
# initial random number generator
# run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
# run_id=datetime.now().strftime("%Y%m%d%H%M%S%f")
run_id=uuid1()
self.output_dir = create_output_directory(scenario, run_id) # fixme run_id
elif scenario.output_dir is not None:
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
# output-directory is created in CLI when restoring from a
# folder. calling the function again in the facade results in two
# folders being created: run_X and run_X.OLD. if we are
# restoring, the output-folder exists already and we omit creating it,
# but set the self-output_dir to the dir.
# necessary because we want to write traj to new output-dir in CLI.
self.output_dir = scenario.output_dir_for_this_run
if (
scenario.deterministic is True
and getattr(scenario, 'tuner_timeout', None) is None
and scenario.run_obj == 'quality'
):
self.logger.info('Optimizing a deterministic scenario for quality without a tuner timeout - will make '
'SMAC deterministic and only evaluate one configuration per iteration!')
scenario.intensification_percentage = 1e-10
scenario.min_chall = 1
scenario.write()
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario,file_system=scenario.file_system)
if self.scenario.run_obj == "runtime" and not self.scenario.transform_y == "LOG":
self.logger.warning("Runtime as objective automatically activates log(y) transformation")
self.scenario.transform_y = "LOG"
# initialize empty runhistory
runhistory_def_kwargs = {'aggregate_func': aggregate_func}
if runhistory_kwargs is not None:
runhistory_def_kwargs.update(runhistory_kwargs)
if runhistory is None:
runhistory = RunHistory(**runhistory_def_kwargs,file_system=scenario.file_system)
elif inspect.isclass(runhistory):
runhistory = runhistory(**runhistory_def_kwargs)
else:
if runhistory.aggregate_func is None:
runhistory.aggregate_func = aggregate_func
rand_conf_chooser_kwargs = {
'rng': rng
}
if random_configuration_chooser_kwargs is not None:
rand_conf_chooser_kwargs.update(random_configuration_chooser_kwargs)
if random_configuration_chooser is None:
if 'prob' not in rand_conf_chooser_kwargs:
rand_conf_chooser_kwargs['prob'] = scenario.rand_prob
random_configuration_chooser = ChooserProb(**rand_conf_chooser_kwargs)
elif inspect.isclass(random_configuration_chooser):
random_configuration_chooser = random_configuration_chooser(**rand_conf_chooser_kwargs)
elif not isinstance(random_configuration_chooser, RandomConfigurationChooser):
raise ValueError("random_configuration_chooser has to be"
" a class or object of RandomConfigurationChooser")
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(rng.randint(MAXINT))
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats,file_system=scenario.file_system)
# initial EPM
types, bounds = get_types(scenario.cs, scenario.feature_array)
model_def_kwargs = {
'types': types,
'bounds': bounds,
'instance_features': scenario.feature_array,
'seed': rng.randint(MAXINT),
'pca_components': scenario.PCA_DIM,
}
if model_kwargs is not None:
model_def_kwargs.update(model_kwargs)
if model is None:
for key, value in {
'log_y': scenario.transform_y in ["LOG", "LOGS"],
'num_trees': scenario.rf_num_trees,
'do_bootstrapping': scenario.rf_do_bootstrapping,
'ratio_features': scenario.rf_ratio_features,
'min_samples_split': scenario.rf_min_samples_split,
'min_samples_leaf': scenario.rf_min_samples_leaf,
'max_depth': scenario.rf_max_depth,
}.items():
if key not in model_def_kwargs:
model_def_kwargs[key] = value
model_def_kwargs['configspace'] = self.scenario.cs
model = RandomForestWithInstances(**model_def_kwargs)
elif inspect.isclass(model):
model_def_kwargs['configspace'] = self.scenario.cs
model = model(**model_def_kwargs)
else:
raise TypeError(
"Model not recognized: %s" %(type(model)))
# initial acquisition function
acq_def_kwargs = {'model': model}
if acquisition_function_kwargs is not None:
acq_def_kwargs.update(acquisition_function_kwargs)
if acquisition_function is None:
if scenario.transform_y in ["LOG", "LOGS"]:
acquisition_function = LogEI(**acq_def_kwargs)
else:
acquisition_function = EI(**acq_def_kwargs)
elif inspect.isclass(acquisition_function):
acquisition_function = acquisition_function(**acq_def_kwargs)
else:
raise TypeError(
"Argument acquisition_function must be None or an object implementing the "
"AbstractAcquisitionFunction, not %s."
% type(acquisition_function)
)
if integrate_acquisition_function:
acquisition_function = IntegratedAcquisitionFunction(
acquisition_function=acquisition_function,
**acq_def_kwargs
)
# initialize optimizer on acquisition function
acq_func_opt_kwargs = {
'acquisition_function': acquisition_function,
'config_space': scenario.cs,
'rng': rng,
}
if acquisition_function_optimizer_kwargs is not None:
acq_func_opt_kwargs.update(acquisition_function_optimizer_kwargs)
if acquisition_function_optimizer is None:
for key, value in {
'max_steps': scenario.sls_max_steps,
'n_steps_plateau_walk': scenario.sls_n_steps_plateau_walk,
}.items():
if key not in acq_func_opt_kwargs:
acq_func_opt_kwargs[key] = value
acquisition_function_optimizer = InterleavedLocalAndRandomSearch(**acq_func_opt_kwargs)
elif inspect.isclass(acquisition_function_optimizer):
acquisition_function_optimizer = acquisition_function_optimizer(**acq_func_opt_kwargs)
else:
raise TypeError(
"Argument acquisition_function_optimizer must be None or an object implementing the "
"AcquisitionFunctionMaximizer, but is '%s'" %
type(acquisition_function_optimizer)
)
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
tae_def_kwargs = {
'stats': self.stats,
'run_obj': scenario.run_obj,
'runhistory': runhistory,
'par_factor': scenario.par_factor,
'cost_for_crash': scenario.cost_for_crash,
'abort_on_first_run_crash': scenario.abort_on_first_run_crash
}
if tae_runner_kwargs is not None:
tae_def_kwargs.update(tae_runner_kwargs)
if 'ta' not in tae_def_kwargs:
tae_def_kwargs['ta'] = scenario.ta
if tae_runner is None:
tae_def_kwargs['ta'] = scenario.ta
tae_runner = ExecuteTARunOld(**tae_def_kwargs)
elif inspect.isclass(tae_runner):
tae_runner = tae_runner(**tae_def_kwargs)
elif callable(tae_runner):
tae_def_kwargs['ta'] = tae_runner
tae_runner = ExecuteTAFuncDict(**tae_def_kwargs)
else:
raise TypeError("Argument 'tae_runner' is %s, but must be "
"either None, a callable or an object implementing "
"ExecuteTaRun. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file."
% type(tae_runner))
# Check that overall objective and tae objective are the same
if tae_runner.run_obj != scenario.run_obj:
raise ValueError("Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" % (tae_runner.run_obj, scenario.run_obj))
# initialize intensification
intensifier_def_kwargs = {
'tae_runner': tae_runner,
'stats': self.stats,
'traj_logger': traj_logger,
'rng': rng,
'instances': scenario.train_insts,
'cutoff': scenario.cutoff,
'deterministic': scenario.deterministic,
'run_obj_time': scenario.run_obj == "runtime",
'always_race_against': scenario.cs.get_default_configuration()
if scenario.always_race_default else None,
'use_ta_time_bound': scenario.use_ta_time,
'instance_specifics': scenario.instance_specific,
'minR': scenario.minR,
'maxR': scenario.maxR,
'adaptive_capping_slackfactor': scenario.intens_adaptive_capping_slackfactor,
'min_chall': scenario.intens_min_chall
}
if intensifier_kwargs is not None:
intensifier_def_kwargs.update(intensifier_kwargs)
if intensifier is None:
intensifier = Intensifier(**intensifier_def_kwargs)
elif inspect.isclass(intensifier):
intensifier = intensifier(**intensifier_def_kwargs)
else:
raise TypeError(
"Argument intensifier must be None or an object implementing the Intensifier, but is '%s'" %
type(intensifier)
)
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both")
init_design_def_kwargs = {
'tae_runner': tae_runner,
'scenario': scenario,
'stats': self.stats,
'traj_logger': traj_logger,
'runhistory': runhistory,
'rng': rng,
'configs': initial_configurations,
'intensifier': intensifier,
'aggregate_func': aggregate_func,
'n_configs_x_params': 0,
'max_config_fracs': 0.0
}
if initial_design_kwargs is not None:
init_design_def_kwargs.update(initial_design_kwargs)
if initial_configurations is not None:
initial_design = InitialDesign(**init_design_def_kwargs)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT":
init_design_def_kwargs['max_config_fracs'] = 0.0
initial_design = DefaultConfiguration(**init_design_def_kwargs)
elif scenario.initial_incumbent == "RANDOM":
init_design_def_kwargs['max_config_fracs'] = 0.0
initial_design = RandomConfigurations(**init_design_def_kwargs)
elif scenario.initial_incumbent == "LHD":
initial_design = LHDesign(**init_design_def_kwargs)
elif scenario.initial_incumbent == "FACTORIAL":
initial_design = FactorialInitialDesign(**init_design_def_kwargs)
elif scenario.initial_incumbent == "SOBOL":
initial_design = SobolDesign(**init_design_def_kwargs)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" % scenario.initial_incumbent)
elif inspect.isclass(initial_design):
initial_design = initial_design(**init_design_def_kwargs)
else:
raise TypeError(
"Argument initial_design must be None or an object implementing the InitialDesign, but is '%s'" %
type(initial_design)
)
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
if scenario.transform_y in ["LOG", "LOGS"]:
cutoff = np.log(np.nanmin([np.inf, np.float_(scenario.cutoff)]))
threshold = cutoff + np.log(scenario.par_factor)
else:
cutoff = np.nanmin([np.inf, np.float_(scenario.cutoff)])
threshold = cutoff * scenario.par_factor
num_params = len(scenario.cs.get_hyperparameters())
imputor = RFRImputator(rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model,
change_threshold=0.01,
max_iter=2)
r2e_def_kwargs = {
'scenario': scenario,
'num_params': num_params,
'success_states': [StatusType.SUCCESS, ],
'impute_censored_data': True,
'impute_state': [StatusType.CAPPED, ],
'imputor': imputor,
'scale_perc': 5
}
if scenario.run_obj == 'quality':
r2e_def_kwargs.update({
'success_states': [StatusType.SUCCESS, StatusType.CRASHED],
'impute_censored_data': False,
'impute_state': None,
})
if runhistory2epm_kwargs is not None:
r2e_def_kwargs.update(runhistory2epm_kwargs)
if runhistory2epm is None:
if scenario.run_obj == 'runtime':
runhistory2epm = RunHistory2EPM4LogCost(**r2e_def_kwargs)
elif scenario.run_obj == 'quality':
if scenario.transform_y == "NONE":
runhistory2epm = RunHistory2EPM4Cost(**r2e_def_kwargs)
elif scenario.transform_y == "LOG":
runhistory2epm = RunHistory2EPM4LogCost(**r2e_def_kwargs)
elif scenario.transform_y == "LOGS":
runhistory2epm = RunHistory2EPM4LogScaledCost(**r2e_def_kwargs)
elif scenario.transform_y == "INVS":
runhistory2epm = RunHistory2EPM4InvScaledCost(**r2e_def_kwargs)
else:
raise ValueError('Unknown run objective: %s. Should be either '
'quality or runtime.' % self.scenario.run_obj)
elif inspect.isclass(runhistory2epm):
runhistory2epm = runhistory2epm(**r2e_def_kwargs)
else:
raise TypeError(
"Argument runhistory2epm must be None or an object implementing the RunHistory2EPM, but is '%s'" %
type(runhistory2epm)
)
smbo_args = {
'scenario': scenario,
'stats': self.stats,
'initial_design': initial_design,
'runhistory': runhistory,
'runhistory2epm': runhistory2epm,
'intensifier': intensifier,
'aggregate_func': aggregate_func,
'num_run': run_id,
'model': model,
'acq_optimizer': acquisition_function_optimizer,
'acquisition_func': acquisition_function,
'rng': rng,
'restore_incumbent': restore_incumbent,
'random_configuration_chooser': random_configuration_chooser
}
if smbo_class is None:
self.solver = SMBO(**smbo_args)
else:
self.solver = smbo_class(**smbo_args)
def __init__(
self,
configspace,
random_fraction=1 / 2,
logger=None,
previous_results=None
):
self.logger = logger
self.random_fraction = random_fraction
self.runhistory = RunHistory()
self.configs = list()
self.losses = list()
rng = np.random.RandomState(random.randint(0, 100))
if previous_results is not None and len(previous_results.batch_results) > 0:
# Assume same-task changing-configspace trajectory for now
results_previous_adjustment = previous_results.batch_results[-1]
configspace_previous = results_previous_adjustment.configspace
# Construct combined config space
configspace_combined = ConfigSpace.ConfigurationSpace()
development_step = CSH.CategoricalHyperparameter("development_step", choices=["old", "new"])
configspace_combined.add_hyperparameter(
development_step
)
configspace_only_old, configspace_both, configspace_only_new = get_configspace_partitioning_cond(configspace, configspace_previous)
configspace_combined.add_hyperparameters(configspace_both.get_hyperparameters())
configspace_combined.add_hyperparameters(configspace_only_old.get_hyperparameters())
configspace_combined.add_hyperparameters(configspace_only_new.get_hyperparameters())
for hyperparameter in configspace_only_old.get_hyperparameters():
configspace_combined.add_condition(
ConfigSpace.EqualsCondition(hyperparameter, development_step, "old")
)
for hyperparameter in configspace_only_new.get_hyperparameters():
configspace_combined.add_condition(
ConfigSpace.EqualsCondition(hyperparameter, development_step, "new")
)
# Read old configs and losses
result_previous = results_previous_adjustment.results[0]
all_runs = result_previous.get_all_runs(only_largest_budget=False)
self.losses_old = [run.loss for run in all_runs]
self.configs_old = [run.config_id for run in all_runs]
id2conf = result_previous.get_id2config_mapping()
self.configs_old = [id2conf[id_]["config"] for id_ in self.configs_old]
# Map old configs to combined space
for config in self.configs_old:
config["development_step"] = "old"
self.configs_old = [ConfigSpace.Configuration(configspace_combined, config) for config in self.configs_old]
for config, cost in zip(self.configs_old, self.losses_old):
self.runhistory.add(config, cost, 0, StatusType.SUCCESS)
# Construct and fit model
self.configspace = configspace_combined
self.model = _construct_model(self.configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(acquisition_function=self.acquisition_func,
config_space=self.configspace, rng=rng)
X = convert_configurations_to_array(self.configs_old)
Y = np.array(self.losses_old, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses_old),
)
else:
self.configspace = configspace
self.model = _construct_model(self.configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(acquisition_function=self.acquisition_func,
config_space=self.configspace, rng=rng)
self.min_points_in_model = len(self.configspace.get_hyperparameters()) # TODO
class GPCondSampler:
def __init__(
self,
configspace,
random_fraction=1 / 2,
logger=None,
previous_results=None
):
self.logger = logger
self.random_fraction = random_fraction
self.runhistory = RunHistory()
self.configs = list()
self.losses = list()
rng = np.random.RandomState(random.randint(0, 100))
if previous_results is not None and len(previous_results.batch_results) > 0:
# Assume same-task changing-configspace trajectory for now
results_previous_adjustment = previous_results.batch_results[-1]
configspace_previous = results_previous_adjustment.configspace
# Construct combined config space
configspace_combined = ConfigSpace.ConfigurationSpace()
development_step = CSH.CategoricalHyperparameter("development_step", choices=["old", "new"])
configspace_combined.add_hyperparameter(
development_step
)
configspace_only_old, configspace_both, configspace_only_new = get_configspace_partitioning_cond(configspace, configspace_previous)
configspace_combined.add_hyperparameters(configspace_both.get_hyperparameters())
configspace_combined.add_hyperparameters(configspace_only_old.get_hyperparameters())
configspace_combined.add_hyperparameters(configspace_only_new.get_hyperparameters())
for hyperparameter in configspace_only_old.get_hyperparameters():
configspace_combined.add_condition(
ConfigSpace.EqualsCondition(hyperparameter, development_step, "old")
)
for hyperparameter in configspace_only_new.get_hyperparameters():
configspace_combined.add_condition(
ConfigSpace.EqualsCondition(hyperparameter, development_step, "new")
)
# Read old configs and losses
result_previous = results_previous_adjustment.results[0]
all_runs = result_previous.get_all_runs(only_largest_budget=False)
self.losses_old = [run.loss for run in all_runs]
self.configs_old = [run.config_id for run in all_runs]
id2conf = result_previous.get_id2config_mapping()
self.configs_old = [id2conf[id_]["config"] for id_ in self.configs_old]
# Map old configs to combined space
for config in self.configs_old:
config["development_step"] = "old"
self.configs_old = [ConfigSpace.Configuration(configspace_combined, config) for config in self.configs_old]
for config, cost in zip(self.configs_old, self.losses_old):
self.runhistory.add(config, cost, 0, StatusType.SUCCESS)
# Construct and fit model
self.configspace = configspace_combined
self.model = _construct_model(self.configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(acquisition_function=self.acquisition_func,
config_space=self.configspace, rng=rng)
X = convert_configurations_to_array(self.configs_old)
Y = np.array(self.losses_old, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses_old),
)
else:
self.configspace = configspace
self.model = _construct_model(self.configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(acquisition_function=self.acquisition_func,
config_space=self.configspace, rng=rng)
self.min_points_in_model = len(self.configspace.get_hyperparameters()) # TODO
@property
def has_model(self):
return len(self.configs) >= self.min_points_in_model
def get_config(self, budget): # pylint: disable=unused-argument
self.logger.debug("start sampling a new configuration.")
is_random_fraction = np.random.rand() < self.random_fraction
if is_random_fraction or not self.has_model:
if "development_step" in self.configspace.get_hyperparameter_names():
while True:
sample = self.configspace.sample_configuration()
if sample["development_step"] == "new":
break
else:
sample = self.configspace.sample_configuration()
else:
# Use private _maximize to not return challenger list object
sample = self.acq_optimizer._maximize(
runhistory=self.runhistory,
stats=None,
num_points=1,
)
sample = sample[0][1]
sample = ConfigSpace.util.deactivate_inactive_hyperparameters(sample.get_dictionary(), self.configspace)
sample = sample.get_dictionary()
info = {}
self.logger.debug("done sampling a new configuration.")
return sample, info
def new_result(self, job, config_info): # pylint: disable=unused-argument
if job.exception is not None:
self.logger.warning(f"job {job.id} failed with exception\n{job.exception}")
if job.result is None:
# One could skip crashed results, but we decided to
# assign a +inf loss and count them as bad configurations
loss = np.inf
else:
# same for non numeric losses.
# Note that this means losses of minus infinity will count as bad!
loss = job.result["loss"] if np.isfinite(job.result["loss"]) else np.inf
config = ConfigSpace.Configuration(self.configspace, job.kwargs["config"])
self.configs.append(config)
self.losses.append(loss)
if self.has_model:
# TODO: include old
X = convert_configurations_to_array(self.configs)
Y = np.array(self.losses, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses),
)
def setUp(self):
self.model = unittest.mock.Mock()
self.model.models = [MockModel(), MockModel(), MockModel()]
self.ei = EI(self.model)
def setUp(self):
self.model = unittest.mock.Mock()
self.acq = EI(model=self.model)
def _component_builder(self, conf:typing.Union[Configuration, dict]) \
-> typing.Tuple[AbstractAcquisitionFunction, AbstractEPM]:
"""
builds new Acquisition function object
and EPM object and returns these
Parameters
----------
conf: typing.Union[Configuration, dict]
configuration specificing "model" and "acq_func"
Returns
-------
typing.Tuple[AbstractAcquisitionFunction, AbstractEPM]
"""
types, bounds = get_types(
self.config_space, instance_features=self.scenario.feature_array)
if conf["model"] == "RF":
model = RandomForestWithInstances(
configspace=self.config_space,
types=types,
bounds=bounds,
instance_features=self.scenario.feature_array,
seed=self.rng.randint(MAXINT),
pca_components=conf.get("pca_dim", self.scenario.PCA_DIM),
log_y=conf.get("log_y", self.scenario.transform_y
in ["LOG", "LOGS"]),
num_trees=conf.get("num_trees", self.scenario.rf_num_trees),
do_bootstrapping=conf.get("do_bootstrapping",
self.scenario.rf_do_bootstrapping),
ratio_features=conf.get("ratio_features",
self.scenario.rf_ratio_features),
min_samples_split=conf.get("min_samples_split",
self.scenario.rf_min_samples_split),
min_samples_leaf=conf.get("min_samples_leaf",
self.scenario.rf_min_samples_leaf),
max_depth=conf.get("max_depth", self.scenario.rf_max_depth),
)
elif conf["model"] == "GP":
from smac.epm.gp_kernels import ConstantKernel, HammingKernel, WhiteKernel, Matern
cov_amp = ConstantKernel(
2.0,
constant_value_bounds=(np.exp(-10), np.exp(2)),
prior=LognormalPrior(mean=0.0, sigma=1.0, rng=self.rng),
)
cont_dims = np.nonzero(types == 0)[0]
cat_dims = np.nonzero(types != 0)[0]
if len(cont_dims) > 0:
exp_kernel = Matern(
np.ones([len(cont_dims)]),
[(np.exp(-10), np.exp(2)) for _ in range(len(cont_dims))],
nu=2.5,
operate_on=cont_dims,
)
if len(cat_dims) > 0:
ham_kernel = HammingKernel(
np.ones([len(cat_dims)]),
[(np.exp(-10), np.exp(2)) for _ in range(len(cat_dims))],
operate_on=cat_dims,
)
noise_kernel = WhiteKernel(
noise_level=1e-8,
noise_level_bounds=(np.exp(-25), np.exp(2)),
prior=HorseshoePrior(scale=0.1, rng=self.rng),
)
if len(cont_dims) > 0 and len(cat_dims) > 0:
# both
kernel = cov_amp * (exp_kernel * ham_kernel) + noise_kernel
elif len(cont_dims) > 0 and len(cat_dims) == 0:
# only cont
kernel = cov_amp * exp_kernel + noise_kernel
elif len(cont_dims) == 0 and len(cat_dims) > 0:
# only cont
kernel = cov_amp * ham_kernel + noise_kernel
else:
raise ValueError()
n_mcmc_walkers = 3 * len(kernel.theta)
if n_mcmc_walkers % 2 == 1:
n_mcmc_walkers += 1
model = GaussianProcessMCMC(
self.config_space,
types=types,
bounds=bounds,
kernel=kernel,
n_mcmc_walkers=n_mcmc_walkers,
chain_length=250,
burnin_steps=250,
normalize_y=True,
seed=self.rng.randint(low=0, high=10000),
)
if conf["acq_func"] == "EI":
acq = EI(model=model, par=conf.get("par_ei", 0))
elif conf["acq_func"] == "LCB":
acq = LCB(model=model, par=conf.get("par_lcb", 0))
elif conf["acq_func"] == "PI":
acq = PI(model=model, par=conf.get("par_pi", 0))
elif conf["acq_func"] == "LogEI":
# par value should be in log-space
acq = LogEI(model=model, par=conf.get("par_logei", 0))
return acq, model
def create_optimizer(self):
from smac.epm.rf_with_instances import RandomForestWithInstances
from smac.initial_design.default_configuration_design import DefaultConfiguration
from smac.intensification.intensification import Intensifier
from smac.optimizer.smbo import SMBO
from smac.optimizer.acquisition import EI
from smac.optimizer.ei_optimization import InterleavedLocalAndRandomSearch
from smac.optimizer.objective import average_cost
from smac.runhistory.runhistory2epm import RunHistory2EPM4Cost
from smac.tae.execute_ta_run import StatusType
from smac.utils.constants import MAXINT
from smac.utils.util_funcs import get_types
TAE_RUNNER = self._priv_evaluator
runhistory2epm = RunHistory2EPM4Cost(
scenario=self.scenario,
num_params=len(self.param_space),
success_states=[StatusType.SUCCESS, StatusType.CRASHED],
impute_censored_data=False,
impute_state=None)
intensifier = Intensifier(tae_runner=TAE_RUNNER, stats=self.stats, traj_logger=self.traj_logger,
rng=self.rng, instances=self.scenario.train_insts, cutoff=self.scenario.cutoff,
deterministic=self.scenario.deterministic, run_obj_time=self.scenario.run_obj == "runtime",
always_race_against=self.scenario.cs.get_default_configuration() \
if self.scenario.always_race_default else None,
instance_specifics=self.scenario.instance_specific,
minR=self.scenario.minR, maxR=self.scenario.maxR)
types, bounds = get_types(self.scenario.cs,
self.scenario.feature_array)
model = RandomForestWithInstances(
types=types,
bounds=bounds,
seed=self.rng.randint(MAXINT),
instance_features=self.scenario.feature_array,
pca_components=self.scenario.PCA_DIM)
acq_func = EI(model=model)
smbo_args = {
'scenario':
self.scenario,
'stats':
self.stats,
'initial_design':
DefaultConfiguration(tae_runner=TAE_RUNNER,
scenario=self.scenario,
stats=self.stats,
traj_logger=self.traj_logger,
rng=self.rng),
'runhistory':
self.runhistory,
'runhistory2epm':
runhistory2epm,
'intensifier':
intensifier,
'aggregate_func':
average_cost,
'num_run':
self.seed,
'model':
model,
'acq_optimizer':
InterleavedLocalAndRandomSearch(
acq_func, self.scenario.cs,
np.random.RandomState(seed=self.rng.randint(MAXINT))),
'acquisition_func':
acq_func,
'rng':
self.rng,
'restore_incumbent':
None,
}
self.smbo = SMBO(**smbo_args)
def build_pc_smbo(self,
tae_runner,
stats,
scenario,
runhistory,
aggregate_func,
acq_func_name,
model_target_names,
logging_directory,
double_intensification=False,
constant_pipeline_steps=None,
variable_pipeline_steps=None,
cached_pipeline_steps=None,
seed=None,
intensification_instances=None,
num_marginalized_configurations_by_random_search=20,
num_configs_for_marginalization=40,
random_splitting_number=5,
random_splitting_enabled=False):
# Build intensifier
rng = np.random.RandomState(seed)
traj_logger = TrajLogger(logging_directory, stats)
intensifier = Intensifier(tae_runner=tae_runner,
stats=stats,
traj_logger=traj_logger,
rng=rng,
cutoff=scenario.cutoff,
deterministic=scenario.deterministic,
run_obj_time=scenario.run_obj == "runtime",
run_limit=scenario.ta_run_limit,
instances=intensification_instances,
maxR=len(intensification_instances))
# Build model
types, bounds = get_types(scenario.cs, scenario.feature_array)
#types = get_types(scenario.cs)
if len(model_target_names) > 1:
# model_target_names = ['cost','time']
model = UncorrelatedMultiObjectiveRandomForestWithInstances(
target_names=model_target_names, bounds=bounds, types=types)
# UncorrelatedMultiObjectiveRandomForestWithInstances(target_names=model_target_names,
# types=types)
elif len(model_target_names) == 1:
model = RandomForestWithInstances(types=types, bounds=bounds)
else:
model = RandomEPM(rng=rng)
# model = RandomForestWithInstances(types=types)
# Build acquisition function, runhistory2epm and local search
num_params = len(scenario.cs.get_hyperparameters())
if acq_func_name in ["ei", "pc-ei"]:
acquisition_func = EI(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name in ["m-ei", "pc-m-ei"]:
#acquisition_func = MEI(model)
acquisition_func = EI(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
# TODO: num_configs_for_marginalization
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name in ['eips', 'pc-eips']:
acquisition_func = EIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name in ["m-eips", "pc-m-eips"]:
acquisition_func = EIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
# TODO: num_configs_for_marginalization
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name == 'pceips':
acquisition_func = PCEIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapperWithCachingReduction(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
cached_pipeline_steps=cached_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
if constant_pipeline_steps == None or variable_pipeline_steps == None or cached_pipeline_steps == None:
raise ValueError(
"Constant_pipeline_steps and variable pipeline steps should not be none\
when using PCEIPS")
select_configuration = SelectConfigurations(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
elif acq_func_name == 'pc-m-pceips':
acquisition_func = PCEIPS(model)
acq_func_wrapper = PCAquisitionFunctionWrapperWithCachingReduction(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
cached_pipeline_steps=cached_pipeline_steps)
runhistory2epm = RunHistory2EPM4EIPS(
scenario, num_params, success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
if constant_pipeline_steps == None or variable_pipeline_steps == None or cached_pipeline_steps == None:
raise ValueError(
"Constant_pipeline_steps and variable pipeline steps should not be none\
when using PCEIPS")
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=
num_marginalized_configurations_by_random_search,
num_configs_for_marginalization=num_configs_for_marginalization
)
elif acq_func_name == "roar":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsRandom(
scenario=scenario)
elif acq_func_name == "pc-roar-mrs":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsMRS(
scenario=scenario,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
splitting_number=random_splitting_number,
random_splitting_enabled=random_splitting_enabled)
elif acq_func_name == "pc-roar-sigmoid-rs":
runhistory2epm = RunHistory2EPM4Cost(
scenario, num_params, success_states=[StatusType.SUCCESS])
select_configuration = SelectConfigurationsSigmoidRS(
scenario=scenario,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
fraction=random_splitting_number)
else:
# Not a valid acquisition function
raise ValueError("The provided acquisition function is not valid")
# Build initial design
# initial_design = RandomConfiguration(tae_runner=tae_runner,
# scenario=scenario,
# stats=stats,
# traj_logger=traj_logger,
# rng=rng)
initial_configs = scenario.cs.sample_configuration(size=2)
for config in initial_configs:
config._populate_values()
initial_design = MultiConfigInitialDesign(
tae_runner=tae_runner,
scenario=scenario,
stats=stats,
traj_logger=traj_logger,
runhistory=runhistory,
rng=rng,
configs=initial_configs,
intensifier=intensifier,
aggregate_func=aggregate_func)
# run id
num_run = rng.randint(1234567980)
# Build pc_smbo
if acq_func_name not in ['pc-roar-sigmoid-rs']:
smbo = PCSMBO(scenario=scenario,
stats=stats,
initial_design=initial_design,
runhistory=runhistory,
runhistory2epm=runhistory2epm,
intensifier=intensifier,
aggregate_func=aggregate_func,
num_run=num_run,
model=model,
rng=rng,
select_configuration=select_configuration,
double_intensification=double_intensification)
else:
smbo = PCSMBOSigmoidRandomSearch(
scenario=scenario,
stats=stats,
initial_design=initial_design,
runhistory=runhistory,
runhistory2epm=runhistory2epm,
intensifier=intensifier,
aggregate_func=aggregate_func,
num_run=num_run,
model=model,
rng=rng,
select_configuration=select_configuration)
return smbo
def __init__(
self,
scenario: Scenario,
# TODO: once we drop python3.4 add type hint
# typing.Union[ExecuteTARun, callable]
tae_runner=None,
runhistory: RunHistory = None,
intensifier: Intensifier = None,
acquisition_function: AbstractAcquisitionFunction = None,
model: AbstractEPM = None,
runhistory2epm: AbstractRunHistory2EPM = None,
initial_design: InitialDesign = None,
initial_configurations: typing.List[Configuration] = None,
stats: Stats = None,
rng: np.random.RandomState = None,
run_id: int = 1):
"""Constructor"""
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
aggregate_func = average_cost
self.runhistory = None
self.trajectory = None
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario)
self.output_dir = create_output_directory(scenario, run_id)
scenario.write()
# initialize empty runhistory
if runhistory is None:
runhistory = RunHistory(aggregate_func=aggregate_func)
# inject aggr_func if necessary
if runhistory.aggregate_func is None:
runhistory.aggregate_func = aggregate_func
# initial random number generator
num_run, rng = self._get_rng(rng=rng)
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(rng.randint(MAXINT))
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats)
# initial EPM
types, bounds = get_types(scenario.cs, scenario.feature_array)
if model is None:
model = RandomForestWithInstances(
types=types,
bounds=bounds,
instance_features=scenario.feature_array,
seed=rng.randint(MAXINT),
pca_components=scenario.PCA_DIM,
num_trees=scenario.rf_num_trees,
do_bootstrapping=scenario.rf_do_bootstrapping,
ratio_features=scenario.rf_ratio_features,
min_samples_split=scenario.rf_min_samples_split,
min_samples_leaf=scenario.rf_min_samples_leaf,
max_depth=scenario.rf_max_depth)
# initial acquisition function
if acquisition_function is None:
if scenario.run_obj == "runtime":
acquisition_function = LogEI(model=model)
else:
acquisition_function = EI(model=model)
# inject model if necessary
if acquisition_function.model is None:
acquisition_function.model = model
# initialize optimizer on acquisition function
local_search = LocalSearch(
acquisition_function,
scenario.cs,
max_steps=scenario.sls_max_steps,
n_steps_plateau_walk=scenario.sls_n_steps_plateau_walk)
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
if tae_runner is None:
tae_runner = ExecuteTARunOld(
ta=scenario.ta,
stats=self.stats,
run_obj=scenario.run_obj,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash)
# Second case, the tae_runner is a function to be optimized
elif callable(tae_runner):
tae_runner = ExecuteTAFuncDict(
ta=tae_runner,
stats=self.stats,
run_obj=scenario.run_obj,
memory_limit=scenario.memory_limit,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash)
# Third case, if it is an ExecuteTaRun we can simply use the
# instance. Otherwise, the next check raises an exception
elif not isinstance(tae_runner, ExecuteTARun):
raise TypeError("Argument 'tae_runner' is %s, but must be "
"either a callable or an instance of "
"ExecuteTaRun. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file." %
type(tae_runner))
# Check that overall objective and tae objective are the same
if tae_runner.run_obj != scenario.run_obj:
raise ValueError("Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" % (tae_runner.run_obj, scenario.run_obj))
# inject stats if necessary
if tae_runner.stats is None:
tae_runner.stats = self.stats
# inject runhistory if necessary
if tae_runner.runhistory is None:
tae_runner.runhistory = runhistory
# inject cost_for_crash
if tae_runner.crash_cost != scenario.cost_for_crash:
tae_runner.crash_cost = scenario.cost_for_crash
# initialize intensification
if intensifier is None:
intensifier = Intensifier(
tae_runner=tae_runner,
stats=self.stats,
traj_logger=traj_logger,
rng=rng,
instances=scenario.train_insts,
cutoff=scenario.cutoff,
deterministic=scenario.deterministic,
run_obj_time=scenario.run_obj == "runtime",
always_race_against=scenario.cs.get_default_configuration()
if scenario.always_race_default else None,
instance_specifics=scenario.instance_specific,
minR=scenario.minR,
maxR=scenario.maxR,
adaptive_capping_slackfactor=scenario.
intens_adaptive_capping_slackfactor,
min_chall=scenario.intens_min_chall)
# inject deps if necessary
if intensifier.tae_runner is None:
intensifier.tae_runner = tae_runner
if intensifier.stats is None:
intensifier.stats = self.stats
if intensifier.traj_logger is None:
intensifier.traj_logger = traj_logger
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both"
)
if initial_configurations is not None:
initial_design = MultiConfigInitialDesign(
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
runhistory=runhistory,
rng=rng,
configs=initial_configurations,
intensifier=intensifier,
aggregate_func=aggregate_func)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT":
initial_design = DefaultConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "RANDOM":
initial_design = RandomConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" % scenario.initial_incumbent)
# inject deps if necessary
if initial_design.tae_runner is None:
initial_design.tae_runner = tae_runner
if initial_design.scenario is None:
initial_design.scenario = scenario
if initial_design.stats is None:
initial_design.stats = self.stats
if initial_design.traj_logger is None:
initial_design.traj_logger = traj_logger
# initial conversion of runhistory into EPM data
if runhistory2epm is None:
num_params = len(scenario.cs.get_hyperparameters())
if scenario.run_obj == "runtime":
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
cutoff = np.log(scenario.cutoff)
threshold = np.log(scenario.cutoff * scenario.par_factor)
imputor = RFRImputator(rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model,
change_threshold=0.01,
max_iter=2)
runhistory2epm = RunHistory2EPM4LogCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS,
],
impute_censored_data=True,
impute_state=[
StatusType.CAPPED,
],
imputor=imputor)
elif scenario.run_obj == 'quality':
runhistory2epm = RunHistory2EPM4Cost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS,
],
impute_censored_data=False,
impute_state=None)
else:
raise ValueError('Unknown run objective: %s. Should be either '
'quality or runtime.' % self.scenario.run_obj)
# inject scenario if necessary:
if runhistory2epm.scenario is None:
runhistory2epm.scenario = scenario
self.solver = EPILS_Solver(scenario=scenario,
stats=self.stats,
initial_design=initial_design,
runhistory=runhistory,
runhistory2epm=runhistory2epm,
intensifier=intensifier,
aggregate_func=aggregate_func,
num_run=num_run,
model=model,
acq_optimizer=local_search,
acquisition_func=acquisition_function,
rng=rng)
def __init__(self, api_config, config_space, parallel_setting="LS"):
super(SMAC4EPMOpimizer, self).__init__(api_config)
self.cs = config_space
self.num_hps = len(self.cs.get_hyperparameters())
if parallel_setting not in ["CL_min", "CL_max", "CL_mean", "KB", "LS"]:
raise ValueError(
"parallel_setting can only be one of the following: "
"CL_min, CL_max, CL_mean, KB, LS")
self.parallel_setting = parallel_setting
rng = np.random.RandomState(seed=0)
scenario = Scenario({
"run_obj": "quality", # we optimize quality (alt. to runtime)
"runcount-limit": 128,
"cs": self.cs, # configuration space
"deterministic": True,
"limit_resources": False,
})
self.stats = Stats(scenario)
# traj = TrajLogger(output_dir=None, stats=self.stats)
self.runhistory = RunHistory()
r2e_def_kwargs = {
"scenario": scenario,
"num_params": self.num_hps,
"success_states": [
StatusType.SUCCESS,
],
"impute_censored_data": False,
"scale_perc": 5,
}
self.random_chooser = ChooserProb(rng=rng, prob=0.0)
types, bounds = get_types(self.cs, instance_features=None)
model_kwargs = {
"configspace": self.cs,
"types": types,
"bounds": bounds,
"seed": rng.randint(MAXINT),
}
models = []
cov_amp = ConstantKernel(
2.0,
constant_value_bounds=(np.exp(-10), np.exp(2)),
prior=LognormalPrior(mean=0.0, sigma=1.0, rng=rng),
)
cont_dims = np.array(np.where(np.array(types) == 0)[0], dtype=np.int)
cat_dims = np.where(np.array(types) != 0)[0]
if len(cont_dims) > 0:
exp_kernel = Matern(
np.ones([len(cont_dims)]),
[(np.exp(-6.754111155189306), np.exp(0.0858637988771976))
for _ in range(len(cont_dims))],
nu=2.5,
operate_on=cont_dims,
)
if len(cat_dims) > 0:
ham_kernel = HammingKernel(
np.ones([len(cat_dims)]),
[(np.exp(-6.754111155189306), np.exp(0.0858637988771976))
for _ in range(len(cat_dims))],
operate_on=cat_dims,
)
assert len(cont_dims) + len(cat_dims) == len(
scenario.cs.get_hyperparameters())
noise_kernel = WhiteKernel(
noise_level=1e-8,
noise_level_bounds=(np.exp(-25), np.exp(2)),
prior=HorseshoePrior(scale=0.1, rng=rng),
)
if len(cont_dims) > 0 and len(cat_dims) > 0:
# both
kernel = cov_amp * (exp_kernel * ham_kernel) + noise_kernel
elif len(cont_dims) > 0 and len(cat_dims) == 0:
# only cont
kernel = cov_amp * exp_kernel + noise_kernel
elif len(cont_dims) == 0 and len(cat_dims) > 0:
# only cont
kernel = cov_amp * ham_kernel + noise_kernel
else:
raise ValueError()
gp_kwargs = {"kernel": kernel}
rf_kwargs = {}
rf_kwargs["num_trees"] = model_kwargs.get("num_trees", 10)
rf_kwargs["do_bootstrapping"] = model_kwargs.get(
"do_bootstrapping", True)
rf_kwargs["ratio_features"] = model_kwargs.get("ratio_features", 1.0)
rf_kwargs["min_samples_split"] = model_kwargs.get(
"min_samples_split", 2)
rf_kwargs["min_samples_leaf"] = model_kwargs.get("min_samples_leaf", 1)
rf_kwargs["log_y"] = model_kwargs.get("log_y", True)
rf_log = RandomForestWithInstances(**model_kwargs, **rf_kwargs)
rf_kwargs = copy.deepcopy(rf_kwargs)
rf_kwargs["log_y"] = False
rf_no_log = RandomForestWithInstances(**model_kwargs, **rf_kwargs)
rh2epm_cost = RunHistory2EPM4Cost(**r2e_def_kwargs)
rh2epm_log_cost = RunHistory2EPM4LogScaledCost(**r2e_def_kwargs)
rh2epm_copula = RunHistory2EPM4GaussianCopulaCorrect(**r2e_def_kwargs)
self.combinations = []
# 2 models * 4 acquisition functions
acq_funcs = [EI, PI, LogEI, LCB]
acq_func_instances = []
# acq_func_maximizer_instances = []
n_sls_iterations = {
1: 10,
2: 10,
3: 10,
4: 10,
5: 10,
6: 10,
7: 8,
8: 6,
}.get(len(self.cs.get_hyperparameters()), 5)
acq_func_maximizer_kwargs = {
"config_space": self.cs,
"rng": rng,
"max_steps": 5,
"n_steps_plateau_walk": 5,
"n_sls_iterations": n_sls_iterations,
}
self.idx_ei = 0
self.num_models = len(models)
self.num_acq_funcs = len(acq_funcs)
no_transform_gp = GaussianProcess(**copy.deepcopy(model_kwargs),
**copy.deepcopy(gp_kwargs))
ei = EI(model=no_transform_gp)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((no_transform_gp, ei, ei_opt, rh2epm_cost))
pi = PI(model=no_transform_gp)
acq_func_maximizer_kwargs["acquisition_function"] = pi
pi_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((no_transform_gp, pi, pi_opt, rh2epm_cost))
lcb = LCB(model=no_transform_gp)
acq_func_maximizer_kwargs["acquisition_function"] = lcb
lcb_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((no_transform_gp, lcb, lcb_opt, rh2epm_cost))
gp = GaussianProcess(**copy.deepcopy(model_kwargs),
**copy.deepcopy(gp_kwargs))
ei = EI(model=gp)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((gp, ei, ei_opt, rh2epm_copula))
gp = GaussianProcess(**copy.deepcopy(model_kwargs),
**copy.deepcopy(gp_kwargs))
ei = LogEI(model=gp)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((gp, ei, ei_opt, rh2epm_log_cost))
ei = EI(model=rf_no_log)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((rf_no_log, ei, ei_opt, rh2epm_cost))
ei = LogEI(model=rf_log)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((rf_log, ei, ei_opt, rh2epm_log_cost))
ei = EI(model=rf_no_log)
acq_func_maximizer_kwargs["acquisition_function"] = ei
ei_opt = LocalAndSortedRandomSearch(**acq_func_maximizer_kwargs)
self.combinations.append((rf_no_log, ei, ei_opt, rh2epm_copula))
self.num_acq_instances = len(acq_func_instances)
self.best_observation = np.inf
self.next_evaluations = []
def __init__(
self,
scenario: Scenario,
tae_runner: Optional[Union[Type[BaseRunner], Callable]] = None,
tae_runner_kwargs: Optional[Dict] = None,
runhistory: Optional[Union[Type[RunHistory], RunHistory]] = None,
runhistory_kwargs: Optional[Dict] = None,
intensifier: Optional[Type[AbstractRacer]] = None,
intensifier_kwargs: Optional[Dict] = None,
acquisition_function: Optional[
Type[AbstractAcquisitionFunction]] = None,
acquisition_function_kwargs: Optional[Dict] = None,
integrate_acquisition_function: bool = False,
acquisition_function_optimizer: Optional[
Type[AcquisitionFunctionMaximizer]] = None,
acquisition_function_optimizer_kwargs: Optional[Dict] = None,
model: Optional[Type[AbstractEPM]] = None,
model_kwargs: Optional[Dict] = None,
runhistory2epm: Optional[Type[AbstractRunHistory2EPM]] = None,
runhistory2epm_kwargs: Optional[Dict] = None,
initial_design: Optional[Type[InitialDesign]] = None,
initial_design_kwargs: Optional[Dict] = None,
initial_configurations: Optional[List[Configuration]] = None,
stats: Optional[Stats] = None,
restore_incumbent: Optional[Configuration] = None,
rng: Optional[Union[np.random.RandomState, int]] = None,
smbo_class: Optional[Type[SMBO]] = None,
run_id: Optional[int] = None,
random_configuration_chooser: Optional[
Type[RandomConfigurationChooser]] = None,
random_configuration_chooser_kwargs: Optional[Dict] = None,
dask_client: Optional[dask.distributed.Client] = None,
n_jobs: Optional[int] = 1,
):
"""
Constructor
Parameters
----------
scenario : ~smac.scenario.scenario.Scenario
Scenario object
tae_runner : ~smac.tae.base.BaseRunner or callable
Callable or implementation of
:class:`~smac.tae.base.BaseRunner`. In case a
callable is passed it will be wrapped by
:class:`~smac.tae.execute_func.ExecuteTAFuncDict`.
If not set, it will be initialized with the
:class:`~smac.tae.execute_ta_run_old.ExecuteTARunOld`.
tae_runner_kwargs: Optional[Dict]
arguments passed to constructor of '~tae_runner'
runhistory : RunHistory
runhistory to store all algorithm runs
runhistory_kwargs : Optional[Dict]
arguments passed to constructor of runhistory.
We strongly advise against changing the aggregation function,
since it will break some code assumptions
intensifier : Intensifier
intensification object to issue a racing to decide the current
incumbent
intensifier_kwargs: Optional[Dict]
arguments passed to the constructor of '~intensifier'
acquisition_function : ~smac.optimizer.acquisition.AbstractAcquisitionFunction
Class or object that implements the :class:`~smac.optimizer.acquisition.AbstractAcquisitionFunction`.
Will use :class:`~smac.optimizer.acquisition.EI` or :class:`~smac.optimizer.acquisition.LogEI` if not set.
`~acquisition_function_kwargs` is passed to the class constructor.
acquisition_function_kwargs : Optional[Dict]
dictionary to pass specific arguments to ~acquisition_function
integrate_acquisition_function : bool, default=False
Whether to integrate the acquisition function. Works only with models which can sample their
hyperparameters (i.e. GaussianProcessMCMC).
acquisition_function_optimizer : ~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer
Object that implements the :class:`~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer`.
Will use :class:`smac.optimizer.ei_optimization.LocalAndSortedRandomSearch` if not set.
acquisition_function_optimizer_kwargs: Optional[Dict]
Arguments passed to constructor of '~acquisition_function_optimizer'
model : AbstractEPM
Model that implements train() and predict(). Will use a
:class:`~smac.epm.rf_with_instances.RandomForestWithInstances` if not set.
model_kwargs : Optional[Dict]
Arguments passed to constructor of '~model'
runhistory2epm : ~smac.runhistory.runhistory2epm.RunHistory2EMP
Object that implements the AbstractRunHistory2EPM. If None,
will use :class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4Cost`
if objective is cost or
:class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4LogCost`
if objective is runtime.
runhistory2epm_kwargs: Optional[Dict]
Arguments passed to the constructor of '~runhistory2epm'
initial_design : InitialDesign
initial sampling design
initial_design_kwargs: Optional[Dict]
arguments passed to constructor of `~initial_design'
initial_configurations : List[Configuration]
list of initial configurations for initial design --
cannot be used together with initial_design
stats : Stats
optional stats object
rng : np.random.RandomState
Random number generator
restore_incumbent : Configuration
incumbent used if restoring to previous state
smbo_class : ~smac.optimizer.smbo.SMBO
Class implementing the SMBO interface which will be used to
instantiate the optimizer class.
run_id : int (optional)
Run ID will be used as subfolder for output_dir. If no ``run_id`` is given, a random ``run_id`` will be
chosen.
random_configuration_chooser : ~smac.optimizer.random_configuration_chooser.RandomConfigurationChooser
How often to choose a random configuration during the intensification procedure.
random_configuration_chooser_kwargs : Optional[Dict]
arguments of constructor for '~random_configuration_chooser'
dask_client : dask.distributed.Client
User-created dask client, can be used to start a dask cluster and then attach SMAC to it.
n_jobs : int, optional
Number of jobs. If > 1 or -1, this creates a dask client if ``dask_client`` is ``None``. Will
be ignored if ``dask_client`` is not ``None``.
If ``None``, this value will be set to 1, if ``-1``, this will be set to the number of cpu cores.
"""
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
self.scenario = scenario
self.output_dir = ""
if not restore_incumbent:
# restore_incumbent is used by the CLI interface which provides a method for restoring a SMAC run given an
# output directory. This is the default path.
# initial random number generator
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
self.output_dir = create_output_directory(scenario, run_id)
elif scenario.output_dir is not None: # type: ignore[attr-defined] # noqa F821
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
# output-directory is created in CLI when restoring from a
# folder. calling the function again in the facade results in two
# folders being created: run_X and run_X.OLD. if we are
# restoring, the output-folder exists already and we omit creating it,
# but set the self-output_dir to the dir.
# necessary because we want to write traj to new output-dir in CLI.
self.output_dir = cast(str, scenario.output_dir_for_this_run
) # type: ignore[attr-defined] # noqa F821
rng = cast(np.random.RandomState, rng)
if (scenario.deterministic is
True # type: ignore[attr-defined] # noqa F821
and getattr(scenario, 'tuner_timeout', None) is None
and scenario.run_obj ==
'quality' # type: ignore[attr-defined] # noqa F821
):
self.logger.info(
'Optimizing a deterministic scenario for quality without a tuner timeout - will make '
'SMAC deterministic and only evaluate one configuration per iteration!'
)
scenario.intensification_percentage = 1e-10 # type: ignore[attr-defined] # noqa F821
scenario.min_chall = 1 # type: ignore[attr-defined] # noqa F821
scenario.write()
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario)
if self.scenario.run_obj == "runtime" and not self.scenario.transform_y == "LOG": # type: ignore[attr-defined] # noqa F821
self.logger.warning(
"Runtime as objective automatically activates log(y) transformation"
)
self.scenario.transform_y = "LOG" # type: ignore[attr-defined] # noqa F821
# initialize empty runhistory
runhistory_def_kwargs = {}
if runhistory_kwargs is not None:
runhistory_def_kwargs.update(runhistory_kwargs)
if runhistory is None:
runhistory = RunHistory(**runhistory_def_kwargs)
elif inspect.isclass(runhistory):
runhistory = runhistory(
**runhistory_def_kwargs) # type: ignore[operator] # noqa F821
elif isinstance(runhistory, RunHistory):
pass
else:
raise ValueError(
'runhistory has to be a class or an object of RunHistory')
rand_conf_chooser_kwargs = {'rng': rng}
if random_configuration_chooser_kwargs is not None:
rand_conf_chooser_kwargs.update(
random_configuration_chooser_kwargs)
if random_configuration_chooser is None:
if 'prob' not in rand_conf_chooser_kwargs:
rand_conf_chooser_kwargs[
'prob'] = scenario.rand_prob # type: ignore[attr-defined] # noqa F821
random_configuration_chooser_instance = (
ChooserProb(**rand_conf_chooser_kwargs
) # type: ignore[arg-type] # noqa F821
) # type: RandomConfigurationChooser
elif inspect.isclass(random_configuration_chooser):
random_configuration_chooser_instance = random_configuration_chooser(
**
rand_conf_chooser_kwargs) # type: ignore[arg-type] # noqa F821
elif not isinstance(random_configuration_chooser,
RandomConfigurationChooser):
raise ValueError(
"random_configuration_chooser has to be"
" a class or object of RandomConfigurationChooser")
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(
rng.randint(MAXINT)) # type: ignore[attr-defined] # noqa F821
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats)
# initial EPM
types, bounds = get_types(
scenario.cs,
scenario.feature_array) # type: ignore[attr-defined] # noqa F821
model_def_kwargs = {
'types': types,
'bounds': bounds,
'instance_features': scenario.feature_array,
'seed': rng.randint(MAXINT),
'pca_components': scenario.PCA_DIM,
}
if model_kwargs is not None:
model_def_kwargs.update(model_kwargs)
if model is None:
for key, value in {
'log_y': scenario.transform_y
in ["LOG",
"LOGS"], # type: ignore[attr-defined] # noqa F821
'num_trees': scenario.
rf_num_trees, # type: ignore[attr-defined] # noqa F821
'do_bootstrapping': scenario.
rf_do_bootstrapping, # type: ignore[attr-defined] # noqa F821
'ratio_features': scenario.
rf_ratio_features, # type: ignore[attr-defined] # noqa F821
'min_samples_split': scenario.
rf_min_samples_split, # type: ignore[attr-defined] # noqa F821
'min_samples_leaf': scenario.
rf_min_samples_leaf, # type: ignore[attr-defined] # noqa F821
'max_depth': scenario.
rf_max_depth, # type: ignore[attr-defined] # noqa F821
}.items():
if key not in model_def_kwargs:
model_def_kwargs[key] = value
model_def_kwargs[
'configspace'] = self.scenario.cs # type: ignore[attr-defined] # noqa F821
model_instance = (
RandomForestWithInstances(
**model_def_kwargs) # type: ignore[arg-type] # noqa F821
) # type: AbstractEPM
elif inspect.isclass(model):
model_def_kwargs[
'configspace'] = self.scenario.cs # type: ignore[attr-defined] # noqa F821
model_instance = model(
**model_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError("Model not recognized: %s" % (type(model)))
# initial acquisition function
acq_def_kwargs = {'model': model_instance}
if acquisition_function_kwargs is not None:
acq_def_kwargs.update(acquisition_function_kwargs)
if acquisition_function is None:
if scenario.transform_y in [
"LOG", "LOGS"
]: # type: ignore[attr-defined] # noqa F821
acquisition_function_instance = (
LogEI(**
acq_def_kwargs) # type: ignore[arg-type] # noqa F821
) # type: AbstractAcquisitionFunction
else:
acquisition_function_instance = EI(
**acq_def_kwargs) # type: ignore[arg-type] # noqa F821
elif inspect.isclass(acquisition_function):
acquisition_function_instance = acquisition_function(
**acq_def_kwargs)
else:
raise TypeError(
"Argument acquisition_function must be None or an object implementing the "
"AbstractAcquisitionFunction, not %s." %
type(acquisition_function))
if integrate_acquisition_function:
acquisition_function_instance = IntegratedAcquisitionFunction(
acquisition_function=acquisition_function_instance,
**acq_def_kwargs)
# initialize optimizer on acquisition function
acq_func_opt_kwargs = {
'acquisition_function': acquisition_function_instance,
'config_space':
scenario.cs, # type: ignore[attr-defined] # noqa F821
'rng': rng,
}
if acquisition_function_optimizer_kwargs is not None:
acq_func_opt_kwargs.update(acquisition_function_optimizer_kwargs)
if acquisition_function_optimizer is None:
for key, value in {
'max_steps': scenario.
sls_max_steps, # type: ignore[attr-defined] # noqa F821
'n_steps_plateau_walk': scenario.
sls_n_steps_plateau_walk, # type: ignore[attr-defined] # noqa F821
}.items():
if key not in acq_func_opt_kwargs:
acq_func_opt_kwargs[key] = value
acquisition_function_optimizer_instance = (
LocalAndSortedRandomSearch(
**
acq_func_opt_kwargs) # type: ignore[arg-type] # noqa F821
) # type: AcquisitionFunctionMaximizer
elif inspect.isclass(acquisition_function_optimizer):
acquisition_function_optimizer_instance = acquisition_function_optimizer(
**acq_func_opt_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError(
"Argument acquisition_function_optimizer must be None or an object implementing the "
"AcquisitionFunctionMaximizer, but is '%s'" %
type(acquisition_function_optimizer))
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
tae_def_kwargs = {
'stats': self.stats,
'run_obj': scenario.run_obj,
'par_factor':
scenario.par_factor, # type: ignore[attr-defined] # noqa F821
'cost_for_crash':
scenario.cost_for_crash, # type: ignore[attr-defined] # noqa F821
'abort_on_first_run_crash': scenario.
abort_on_first_run_crash # type: ignore[attr-defined] # noqa F821
}
if tae_runner_kwargs is not None:
tae_def_kwargs.update(tae_runner_kwargs)
if 'ta' not in tae_def_kwargs:
tae_def_kwargs[
'ta'] = scenario.ta # type: ignore[attr-defined] # noqa F821
if tae_runner is None:
tae_def_kwargs[
'ta'] = scenario.ta # type: ignore[attr-defined] # noqa F821
tae_runner_instance = (
ExecuteTARunOld(
**tae_def_kwargs) # type: ignore[arg-type] # noqa F821
) # type: BaseRunner
elif inspect.isclass(tae_runner):
tae_runner_instance = cast(BaseRunner, tae_runner(
**tae_def_kwargs)) # type: ignore[arg-type] # noqa F821
elif callable(tae_runner):
tae_def_kwargs['ta'] = tae_runner
tae_def_kwargs[
'use_pynisher'] = scenario.limit_resources # type: ignore[attr-defined] # noqa F821
tae_runner_instance = ExecuteTAFuncDict(
**tae_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError(
"Argument 'tae_runner' is %s, but must be "
"either None, a callable or an object implementing "
"BaseRunner. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file." % type(tae_runner))
# In case of a parallel run, wrap the single worker in a parallel
# runner
if n_jobs is None or n_jobs == 1:
_n_jobs = 1
elif n_jobs == -1:
_n_jobs = joblib.cpu_count()
elif n_jobs > 0:
_n_jobs = n_jobs
else:
raise ValueError(
'Number of tasks must be positive, None or -1, but is %s' %
str(n_jobs))
if _n_jobs > 1 or dask_client is not None:
tae_runner_instance = DaskParallelRunner(
tae_runner_instance,
n_workers=_n_jobs,
output_directory=self.output_dir,
dask_client=dask_client,
)
# Check that overall objective and tae objective are the same
# TODO: remove these two ignores once the scenario object knows all its attributes!
if tae_runner_instance.run_obj != scenario.run_obj: # type: ignore[union-attr] # noqa F821
raise ValueError(
"Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" %
(tae_runner_instance.run_obj,
scenario.run_obj)) # type: ignore[union-attr] # noqa F821
# initialize intensification
intensifier_def_kwargs = {
'stats': self.stats,
'traj_logger': traj_logger,
'rng': rng,
'instances':
scenario.train_insts, # type: ignore[attr-defined] # noqa F821
'cutoff':
scenario.cutoff, # type: ignore[attr-defined] # noqa F821
'deterministic':
scenario.deterministic, # type: ignore[attr-defined] # noqa F821
'run_obj_time': scenario.run_obj ==
"runtime", # type: ignore[attr-defined] # noqa F821
'instance_specifics': scenario.
instance_specific, # type: ignore[attr-defined] # noqa F821
'adaptive_capping_slackfactor': scenario.
intens_adaptive_capping_slackfactor, # type: ignore[attr-defined] # noqa F821
'min_chall':
scenario.intens_min_chall # type: ignore[attr-defined] # noqa F821
}
if isinstance(intensifier, Intensifier) \
or (intensifier is not None and inspect.isclass(intensifier) and issubclass(intensifier, Intensifier)):
intensifier_def_kwargs[
'always_race_against'] = scenario.cs.get_default_configuration(
) # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
'use_ta_time_bound'] = scenario.use_ta_time # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
'minR'] = scenario.minR # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
'maxR'] = scenario.maxR # type: ignore[attr-defined] # noqa F821
if intensifier_kwargs is not None:
intensifier_def_kwargs.update(intensifier_kwargs)
if intensifier is None:
intensifier_instance = (
Intensifier(**intensifier_def_kwargs
) # type: ignore[arg-type] # noqa F821
) # type: AbstractRacer
elif inspect.isclass(intensifier):
intensifier_instance = intensifier(
**intensifier_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError(
"Argument intensifier must be None or an object implementing the AbstractRacer, but is '%s'"
% type(intensifier))
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both"
)
init_design_def_kwargs = {
'cs': scenario.cs, # type: ignore[attr-defined] # noqa F821
'traj_logger': traj_logger,
'rng': rng,
'ta_run_limit':
scenario.ta_run_limit, # type: ignore[attr-defined] # noqa F821
'configs': initial_configurations,
'n_configs_x_params': 0,
'max_config_fracs': 0.0
}
if initial_design_kwargs is not None:
init_design_def_kwargs.update(initial_design_kwargs)
if initial_configurations is not None:
initial_design_instance = InitialDesign(**init_design_def_kwargs)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT": # type: ignore[attr-defined] # noqa F821
init_design_def_kwargs['max_config_fracs'] = 0.0
initial_design_instance = DefaultConfiguration(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "RANDOM": # type: ignore[attr-defined] # noqa F821
init_design_def_kwargs['max_config_fracs'] = 0.0
initial_design_instance = RandomConfigurations(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "LHD": # type: ignore[attr-defined] # noqa F821
initial_design_instance = LHDesign(**init_design_def_kwargs)
elif scenario.initial_incumbent == "FACTORIAL": # type: ignore[attr-defined] # noqa F821
initial_design_instance = FactorialInitialDesign(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "SOBOL": # type: ignore[attr-defined] # noqa F821
initial_design_instance = SobolDesign(**init_design_def_kwargs)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" % scenario.initial_incumbent
) # type: ignore[attr-defined] # noqa F821
elif inspect.isclass(initial_design):
initial_design_instance = initial_design(**init_design_def_kwargs)
else:
raise TypeError(
"Argument initial_design must be None or an object implementing the InitialDesign, but is '%s'"
% type(initial_design))
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
if scenario.transform_y in [
"LOG", "LOGS"
]: # type: ignore[attr-defined] # noqa F821
cutoff = np.log(np.nanmin([
np.inf, np.float_(scenario.cutoff)
])) # type: ignore[attr-defined] # noqa F821
threshold = cutoff + np.log(
scenario.par_factor) # type: ignore[attr-defined] # noqa F821
else:
cutoff = np.nanmin([np.inf, np.float_(scenario.cutoff)
]) # type: ignore[attr-defined] # noqa F821
threshold = cutoff * scenario.par_factor # type: ignore[attr-defined] # noqa F821
num_params = len(scenario.cs.get_hyperparameters()
) # type: ignore[attr-defined] # noqa F821
imputor = RFRImputator(rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model_instance,
change_threshold=0.01,
max_iter=2)
r2e_def_kwargs = {
'scenario': scenario,
'num_params': num_params,
'success_states': [
StatusType.SUCCESS,
],
'impute_censored_data': True,
'impute_state': [
StatusType.CAPPED,
],
'imputor': imputor,
'scale_perc': 5
}
if scenario.run_obj == 'quality':
r2e_def_kwargs.update({
'success_states':
[StatusType.SUCCESS, StatusType.CRASHED, StatusType.MEMOUT],
'impute_censored_data':
False,
'impute_state':
None,
})
if isinstance(
intensifier_instance,
(SuccessiveHalving, Hyperband)) and scenario.run_obj == "quality":
r2e_def_kwargs.update({
'success_states': [
StatusType.SUCCESS,
StatusType.CRASHED,
StatusType.MEMOUT,
StatusType.DONOTADVANCE,
],
'consider_for_higher_budgets_state': [
StatusType.DONOTADVANCE,
StatusType.TIMEOUT,
StatusType.CRASHED,
StatusType.MEMOUT,
],
})
if runhistory2epm_kwargs is not None:
r2e_def_kwargs.update(runhistory2epm_kwargs)
if runhistory2epm is None:
if scenario.run_obj == 'runtime':
rh2epm = (
RunHistory2EPM4LogCost(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
) # type: AbstractRunHistory2EPM
elif scenario.run_obj == 'quality':
if scenario.transform_y == "NONE": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4Cost(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
elif scenario.transform_y == "LOG": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4LogCost(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
elif scenario.transform_y == "LOGS": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4LogScaledCost(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
elif scenario.transform_y == "INVS": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4InvScaledCost(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise ValueError('Unknown run objective: %s. Should be either '
'quality or runtime.' % self.scenario.run_obj)
elif inspect.isclass(runhistory2epm):
rh2epm = runhistory2epm(
**r2e_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError(
"Argument runhistory2epm must be None or an object implementing the RunHistory2EPM, but is '%s'"
% type(runhistory2epm))
smbo_args = {
'scenario': scenario,
'stats': self.stats,
'initial_design': initial_design_instance,
'runhistory': runhistory,
'runhistory2epm': rh2epm,
'intensifier': intensifier_instance,
'num_run': run_id,
'model': model_instance,
'acq_optimizer': acquisition_function_optimizer_instance,
'acquisition_func': acquisition_function_instance,
'rng': rng,
'restore_incumbent': restore_incumbent,
'random_configuration_chooser':
random_configuration_chooser_instance,
'tae_runner': tae_runner_instance,
} # type: Dict[str, Any]
if smbo_class is None:
self.solver = SMBO(**
smbo_args) # type: ignore[arg-type] # noqa F821
else:
self.solver = smbo_class(
**smbo_args) # type: ignore[arg-type] # noqa F821
class GPSampler:
def __init__(
self,
configspace,
random_fraction=1 / 2,
logger=None,
configs=None,
losses=None,
):
self.logger = logger
self.random_fraction = random_fraction
self.configspace = configspace
self.min_points_in_model = len(self.configspace.get_hyperparameters())
rng = np.random.RandomState(random.randint(0, 100))
self.model = _construct_model(configspace, rng)
self.acquisition_func = EI(model=self.model)
self.acq_optimizer = LocalSearch(
acquisition_function=self.acquisition_func,
config_space=configspace,
rng=rng)
self.runhistory = RunHistory()
self.configs = configs or list()
self.losses = losses or list()
if self.has_model:
for config, cost in zip(self.configs, self.losses):
self.runhistory.add(config, cost, 0, StatusType.SUCCESS)
X = convert_configurations_to_array(self.configs)
Y = np.array(self.losses, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses),
)
@property
def has_model(self):
return len(self.configs) >= self.min_points_in_model
def get_config(self, budget): # pylint: disable=unused-argument
self.logger.debug("start sampling a new configuration.")
is_random_fraction = np.random.rand() < self.random_fraction
if is_random_fraction:
sample = self.configspace.sample_configuration()
elif self.has_model:
# Use private _maximize to not return challenger list object
sample = self.acq_optimizer._maximize(
runhistory=self.runhistory,
stats=None,
num_points=1,
)
sample = sample[0][1]
else:
sample = self.configspace.sample_configuration()
sample = sample.get_dictionary()
info = {}
self.logger.debug("done sampling a new configuration.")
return sample, info
def new_result(self, job, config_info): # pylint: disable=unused-argument
if job.exception is not None:
self.logger.warning(
f"job {job.id} failed with exception\n{job.exception}")
if job.result is None:
# One could skip crashed results, but we decided to
# assign a +inf loss and count them as bad configurations
loss = np.inf
else:
# same for non numeric losses.
# Note that this means losses of minus infinity will count as bad!
loss = job.result["loss"] if np.isfinite(
job.result["loss"]) else np.inf
config = ConfigSpace.Configuration(self.configspace,
job.kwargs["config"])
self.configs.append(config)
self.losses.append(loss)
self.runhistory.add(config, loss, 0, StatusType.SUCCESS)
if self.has_model:
X = convert_configurations_to_array(self.configs)
Y = np.array(self.losses, dtype=np.float64)
self.model.train(X, Y)
self.acquisition_func.update(
model=self.model,
eta=min(self.losses),
)
def __init__(
self,
scenario: Scenario,
tae_runner: typing.Optional[typing.Union[ExecuteTARun,
typing.Callable]] = None,
runhistory: typing.Optional[RunHistory] = None,
intensifier: typing.Optional[Intensifier] = None,
acquisition_function: typing.
Optional[AbstractAcquisitionFunction] = None,
acquisition_function_optimizer: typing.
Optional[AcquisitionFunctionMaximizer] = None,
model: typing.Optional[AbstractEPM] = None,
runhistory2epm: typing.Optional[AbstractRunHistory2EPM] = None,
initial_design: typing.Optional[InitialDesign] = None,
initial_configurations: typing.Optional[
typing.List[Configuration]] = None,
stats: typing.Optional[Stats] = None,
restore_incumbent: typing.Optional[Configuration] = None,
rng: typing.Optional[typing.Union[np.random.RandomState, int]] = None,
smbo_class: typing.Optional[SMBO] = None,
run_id: typing.Optional[int] = None,
random_configuration_chooser: typing.
Optional[RandomConfigurationChooser] = None):
"""
Constructor
Parameters
----------
scenario : ~smac.scenario.scenario.Scenario
Scenario object
tae_runner : ~smac.tae.execute_ta_run.ExecuteTARun or callable
Callable or implementation of
:class:`~smac.tae.execute_ta_run.ExecuteTARun`. In case a
callable is passed it will be wrapped by
:class:`~smac.tae.execute_func.ExecuteTAFuncDict`.
If not set, it will be initialized with the
:class:`~smac.tae.execute_ta_run_old.ExecuteTARunOld`.
runhistory : RunHistory
runhistory to store all algorithm runs
intensifier : Intensifier
intensification object to issue a racing to decide the current
incumbent
acquisition_function : ~smac.optimizer.acquisition.AbstractAcquisitionFunction
Object that implements the :class:`~smac.optimizer.acquisition.AbstractAcquisitionFunction`.
Will use :class:`~smac.optimizer.acquisition.EI` if not set.
acquisition_function_optimizer : ~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer
Object that implements the :class:`~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer`.
Will use :class:`smac.optimizer.ei_optimization.InterleavedLocalAndRandomSearch` if not set.
model : AbstractEPM
Model that implements train() and predict(). Will use a
:class:`~smac.epm.rf_with_instances.RandomForestWithInstances` if not set.
runhistory2epm : ~smac.runhistory.runhistory2epm.RunHistory2EMP
Object that implements the AbstractRunHistory2EPM. If None,
will use :class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4Cost`
if objective is cost or
:class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4LogCost`
if objective is runtime.
initial_design : InitialDesign
initial sampling design
initial_configurations : typing.List[Configuration]
list of initial configurations for initial design --
cannot be used together with initial_design
stats : Stats
optional stats object
rng : np.random.RandomState
Random number generator
restore_incumbent : Configuration
incumbent used if restoring to previous state
smbo_class : ~smac.optimizer.smbo.SMBO
Class implementing the SMBO interface which will be used to
instantiate the optimizer class.
run_id : int (optional)
Run ID will be used as subfolder for output_dir. If no ``run_id`` is given, a random ``run_id`` will be
chosen.
random_configuration_chooser : ~smac.optimizer.random_configuration_chooser.RandomConfigurationChooser
How often to choose a random configuration during the intensification procedure.
"""
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
aggregate_func = average_cost
self.scenario = scenario
self.output_dir = ""
if not restore_incumbent:
# restore_incumbent is used by the CLI interface which provides a method for restoring a SMAC run given an
# output directory. This is the default path.
# initial random number generator
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
self.output_dir = create_output_directory(scenario, run_id)
elif scenario.output_dir is not None:
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
# output-directory is created in CLI when restoring from a
# folder. calling the function again in the facade results in two
# folders being created: run_X and run_X.OLD. if we are
# restoring, the output-folder exists already and we omit creating it,
# but set the self-output_dir to the dir.
# necessary because we want to write traj to new output-dir in CLI.
self.output_dir = scenario.output_dir_for_this_run
if (scenario.deterministic is True
and getattr(scenario, 'tuner_timeout', None) is None
and scenario.run_obj == 'quality'):
self.logger.info('Optimizing a deterministic scenario for '
'quality without a tuner timeout - will make '
'SMAC deterministic!')
scenario.intensification_percentage = 1e-10
scenario.write()
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario)
if self.scenario.run_obj == "runtime" and not self.scenario.transform_y == "LOG":
self.logger.warn(
"Runtime as objective automatically activates log(y) transformation"
)
self.scenario.transform_y = "LOG"
# initialize empty runhistory
if runhistory is None:
runhistory = RunHistory(aggregate_func=aggregate_func)
# inject aggr_func if necessary
if runhistory.aggregate_func is None:
runhistory.aggregate_func = aggregate_func
if not random_configuration_chooser:
random_configuration_chooser = ChooserProb(prob=scenario.rand_prob,
rng=rng)
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(rng.randint(MAXINT))
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats)
# initial EPM
types, bounds = get_types(scenario.cs, scenario.feature_array)
if model is None:
model = RandomForestWithInstances(
types=types,
bounds=bounds,
instance_features=scenario.feature_array,
seed=rng.randint(MAXINT),
pca_components=scenario.PCA_DIM,
log_y=scenario.transform_y in ["LOG", "LOGS"],
num_trees=scenario.rf_num_trees,
do_bootstrapping=scenario.rf_do_bootstrapping,
ratio_features=scenario.rf_ratio_features,
min_samples_split=scenario.rf_min_samples_split,
min_samples_leaf=scenario.rf_min_samples_leaf,
max_depth=scenario.rf_max_depth)
# initial acquisition function
if acquisition_function is None:
if scenario.transform_y in ["LOG", "LOGS"]:
acquisition_function = LogEI(model=model)
else:
acquisition_function = EI(model=model)
# inject model if necessary
if acquisition_function.model is None:
acquisition_function.model = model
# initialize optimizer on acquisition function
if acquisition_function_optimizer is None:
acquisition_function_optimizer = InterleavedLocalAndRandomSearch(
acquisition_function=acquisition_function,
config_space=scenario.cs,
rng=np.random.RandomState(seed=rng.randint(MAXINT)),
max_steps=scenario.sls_max_steps,
n_steps_plateau_walk=scenario.sls_n_steps_plateau_walk)
elif not isinstance(
acquisition_function_optimizer,
AcquisitionFunctionMaximizer,
):
raise ValueError(
"Argument 'acquisition_function_optimizer' must be of type"
"'AcquisitionFunctionMaximizer', but is '%s'" %
type(acquisition_function_optimizer))
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
if tae_runner is None:
tae_runner = ExecuteTARunOld(
ta=scenario.ta,
stats=self.stats,
run_obj=scenario.run_obj,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash,
abort_on_first_run_crash=scenario.abort_on_first_run_crash)
# Second case, the tae_runner is a function to be optimized
elif callable(tae_runner):
tae_runner = ExecuteTAFuncDict(
ta=tae_runner,
stats=self.stats,
run_obj=scenario.run_obj,
memory_limit=scenario.memory_limit,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash,
abort_on_first_run_crash=scenario.abort_on_first_run_crash)
# Third case, if it is an ExecuteTaRun we can simply use the
# instance. Otherwise, the next check raises an exception
elif not isinstance(tae_runner, ExecuteTARun):
raise TypeError("Argument 'tae_runner' is %s, but must be "
"either a callable or an instance of "
"ExecuteTaRun. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file." %
type(tae_runner))
# Check that overall objective and tae objective are the same
if tae_runner.run_obj != scenario.run_obj:
raise ValueError("Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" % (tae_runner.run_obj, scenario.run_obj))
# inject stats if necessary
if tae_runner.stats is None:
tae_runner.stats = self.stats
# inject runhistory if necessary
if tae_runner.runhistory is None:
tae_runner.runhistory = runhistory
# inject cost_for_crash
if tae_runner.crash_cost != scenario.cost_for_crash:
tae_runner.crash_cost = scenario.cost_for_crash
# initialize intensification
if intensifier is None:
intensifier = Intensifier(
tae_runner=tae_runner,
stats=self.stats,
traj_logger=traj_logger,
rng=rng,
instances=scenario.train_insts,
cutoff=scenario.cutoff,
deterministic=scenario.deterministic,
run_obj_time=scenario.run_obj == "runtime",
always_race_against=scenario.cs.get_default_configuration()
if scenario.always_race_default else None,
use_ta_time_bound=scenario.use_ta_time,
instance_specifics=scenario.instance_specific,
minR=scenario.minR,
maxR=scenario.maxR,
adaptive_capping_slackfactor=scenario.
intens_adaptive_capping_slackfactor,
min_chall=scenario.intens_min_chall)
# inject deps if necessary
if intensifier.tae_runner is None:
intensifier.tae_runner = tae_runner
if intensifier.stats is None:
intensifier.stats = self.stats
if intensifier.traj_logger is None:
intensifier.traj_logger = traj_logger
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both"
)
if initial_configurations is not None:
initial_design = MultiConfigInitialDesign(
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
runhistory=runhistory,
rng=rng,
configs=initial_configurations,
intensifier=intensifier,
aggregate_func=aggregate_func)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT":
initial_design = DefaultConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "RANDOM":
initial_design = RandomConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "LHD":
initial_design = LHDesign(runhistory=runhistory,
intensifier=intensifier,
aggregate_func=aggregate_func,
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "FACTORIAL":
initial_design = FactorialInitialDesign(
runhistory=runhistory,
intensifier=intensifier,
aggregate_func=aggregate_func,
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "SOBOL":
initial_design = SobolDesign(runhistory=runhistory,
intensifier=intensifier,
aggregate_func=aggregate_func,
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" % scenario.initial_incumbent)
# inject deps if necessary
if initial_design.tae_runner is None:
initial_design.tae_runner = tae_runner
if initial_design.scenario is None:
initial_design.scenario = scenario
if initial_design.stats is None:
initial_design.stats = self.stats
if initial_design.traj_logger is None:
initial_design.traj_logger = traj_logger
# initial conversion of runhistory into EPM data
if runhistory2epm is None:
num_params = len(scenario.cs.get_hyperparameters())
if scenario.run_obj == 'runtime':
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
cutoff = np.log(scenario.cutoff)
threshold = np.log(scenario.cutoff * scenario.par_factor)
imputor = RFRImputator(rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model,
change_threshold=0.01,
max_iter=2)
runhistory2epm = RunHistory2EPM4LogCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS,
],
impute_censored_data=True,
impute_state=[
StatusType.CAPPED,
],
imputor=imputor)
elif scenario.run_obj == 'quality':
if scenario.transform_y == "NONE":
runhistory2epm = RunHistory2EPM4Cost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS, StatusType.CRASHED
],
impute_censored_data=False,
impute_state=None)
elif scenario.transform_y == "LOG":
runhistory2epm = RunHistory2EPM4LogCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS, StatusType.CRASHED
],
impute_censored_data=False,
impute_state=None)
elif scenario.transform_y == "LOGS":
runhistory2epm = RunHistory2EPM4LogScaledCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS, StatusType.CRASHED
],
impute_censored_data=False,
impute_state=None)
elif scenario.transform_y == "INVS":
runhistory2epm = RunHistory2EPM4InvScaledCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS, StatusType.CRASHED
],
impute_censored_data=False,
impute_state=None)
else:
raise ValueError('Unknown run objective: %s. Should be either '
'quality or runtime.' % self.scenario.run_obj)
# inject scenario if necessary:
if runhistory2epm.scenario is None:
runhistory2epm.scenario = scenario
smbo_args = {
'scenario': scenario,
'stats': self.stats,
'initial_design': initial_design,
'runhistory': runhistory,
'runhistory2epm': runhistory2epm,
'intensifier': intensifier,
'aggregate_func': aggregate_func,
'num_run': run_id,
'model': model,
'acq_optimizer': acquisition_function_optimizer,
'acquisition_func': acquisition_function,
'rng': rng,
'restore_incumbent': restore_incumbent,
'random_configuration_chooser': random_configuration_chooser
}
if smbo_class is None:
self.solver = SMBO(**smbo_args)
else:
self.solver = smbo_class(**smbo_args)
def _component_builder(self, conf:typing.Union[Configuration, dict]) \
-> typing.Tuple[AbstractAcquisitionFunction, AbstractEPM]:
"""
builds new Acquisition function object
and EPM object and returns these
Parameters
----------
conf: typing.Union[Configuration, dict]
configuration specificing "model" and "acq_func"
Returns
-------
typing.Tuple[AbstractAcquisitionFunction, AbstractEPM]
"""
types, bounds = get_types(self.config_space, instance_features=self.scenario.feature_array)
if conf["model"] == "RF":
model = RandomForestWithInstances(
types=types,
bounds=bounds,
instance_features=self.scenario.feature_array,
seed=self.rng.randint(MAXINT),
pca_components=conf.get("pca_dim", self.scenario.PCA_DIM),
log_y=conf.get("log_y", self.scenario.transform_y in ["LOG", "LOGS"]),
num_trees=conf.get("num_trees", self.scenario.rf_num_trees),
do_bootstrapping=conf.get("do_bootstrapping", self.scenario.rf_do_bootstrapping),
ratio_features=conf.get("ratio_features", self.scenario.rf_ratio_features),
min_samples_split=conf.get("min_samples_split", self.scenario.rf_min_samples_split),
min_samples_leaf=conf.get("min_samples_leaf", self.scenario.rf_min_samples_leaf),
max_depth=conf.get("max_depth", self.scenario.rf_max_depth))
elif conf["model"] == "GP":
cov_amp = 2
n_dims = len(types)
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1, rng=self.rng)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
model = GaussianProcessMCMC(
types=types,
bounds=bounds,
kernel=kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=True,
rng=self.rng,
)
if conf["acq_func"] == "EI":
acq = EI(model=model,
par=conf.get("par_ei", 0))
elif conf["acq_func"] == "LCB":
acq = LCB(model=model,
par=conf.get("par_lcb", 0))
elif conf["acq_func"] == "PI":
acq = PI(model=model,
par=conf.get("par_pi", 0))
elif conf["acq_func"] == "LogEI":
# par value should be in log-space
acq = LogEI(model=model,
par=conf.get("par_logei", 0))
return acq, model
def __init__(
self,
scenario: Scenario,
tae_runner: typing.Union[ExecuteTARun, typing.Callable] = None,
runhistory: RunHistory = None,
intensifier: Intensifier = None,
acquisition_function: AbstractAcquisitionFunction = None,
acquisition_function_optimizer: AcquisitionFunctionMaximizer = None,
model: AbstractEPM = None,
runhistory2epm: AbstractRunHistory2EPM = None,
initial_design: InitialDesign = None,
initial_configurations: typing.List[Configuration] = None,
stats: Stats = None,
restore_incumbent: Configuration = None,
rng: typing.Union[np.random.RandomState, int] = None,
smbo_class: SMBO = None,
run_id: int = 1):
"""Constructor
Parameters
----------
scenario : ~smac.scenario.scenario.Scenario
Scenario object
tae_runner : ~smac.tae.execute_ta_run.ExecuteTARun or callable
Callable or implementation of
:class:`~smac.tae.execute_ta_run.ExecuteTARun`. In case a
callable is passed it will be wrapped by
:class:`~smac.tae.execute_func.ExecuteTAFuncDict`.
If not set, it will be initialized with the
:class:`~smac.tae.execute_ta_run_old.ExecuteTARunOld`.
runhistory : RunHistory
runhistory to store all algorithm runs
intensifier : Intensifier
intensification object to issue a racing to decide the current
incumbent
acquisition_function : ~smac.optimizer.acquisition.AbstractAcquisitionFunction
Object that implements the :class:`~smac.optimizer.acquisition.AbstractAcquisitionFunction`.
Will use :class:`~smac.optimizer.acquisition.EI` if not set.
acquisition_function_optimizer : ~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer
Object that implements the :class:`~smac.optimizer.ei_optimization.AcquisitionFunctionMaximizer`.
Will use :class:`smac.optimizer.ei_optimization.InterleavedLocalAndRandomSearch` if not set.
model : AbstractEPM
Model that implements train() and predict(). Will use a
:class:`~smac.epm.rf_with_instances.RandomForestWithInstances` if not set.
runhistory2epm : ~smac.runhistory.runhistory2epm.RunHistory2EMP
Object that implements the AbstractRunHistory2EPM. If None,
will use :class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4Cost`
if objective is cost or
:class:`~smac.runhistory.runhistory2epm.RunHistory2EPM4LogCost`
if objective is runtime.
initial_design : InitialDesign
initial sampling design
initial_configurations : typing.List[Configuration]
list of initial configurations for initial design --
cannot be used together with initial_design
stats : Stats
optional stats object
rng : np.random.RandomState
Random number generator
restore_incumbent : Configuration
incumbent used if restoring to previous state
smbo_class : ~smac.optimizer.smbo.SMBO
Class implementing the SMBO interface which will be used to
instantiate the optimizer class.
run_id: int, (default: 1)
Run ID will be used as subfolder for output_dir.
"""
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
aggregate_func = average_cost
self.output_dir = create_output_directory(scenario, run_id)
scenario.write()
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario)
# initialize empty runhistory
if runhistory is None:
runhistory = RunHistory(aggregate_func=aggregate_func)
# inject aggr_func if necessary
if runhistory.aggregate_func is None:
runhistory.aggregate_func = aggregate_func
# initial random number generator
num_run, rng = self._get_rng(rng=rng)
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(rng.randint(MAXINT))
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats)
# initial EPM
types, bounds = get_types(scenario.cs, scenario.feature_array)
if model is None:
model = RandomForestWithInstances(
types=types,
bounds=bounds,
instance_features=scenario.feature_array,
seed=rng.randint(MAXINT),
pca_components=scenario.PCA_DIM)
# initial acquisition function
if acquisition_function is None:
if scenario.run_obj == "runtime":
acquisition_function = LogEI(model=model)
else:
acquisition_function = EI(model=model)
# inject model if necessary
if acquisition_function.model is None:
acquisition_function.model = model
# initialize optimizer on acquisition function
if acquisition_function_optimizer is None:
acquisition_function_optimizer = InterleavedLocalAndRandomSearch(
acquisition_function, scenario.cs,
np.random.RandomState(seed=rng.randint(MAXINT)))
elif not isinstance(
acquisition_function_optimizer,
AcquisitionFunctionMaximizer,
):
raise ValueError(
"Argument 'acquisition_function_optimizer' must be of type"
"'AcquisitionFunctionMaximizer', but is '%s'" %
type(acquisition_function_optimizer))
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
if tae_runner is None:
tae_runner = ExecuteTARunOld(
ta=scenario.ta,
stats=self.stats,
run_obj=scenario.run_obj,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash)
# Second case, the tae_runner is a function to be optimized
elif callable(tae_runner):
tae_runner = ExecuteTAFuncDict(
ta=tae_runner,
stats=self.stats,
run_obj=scenario.run_obj,
memory_limit=scenario.memory_limit,
runhistory=runhistory,
par_factor=scenario.par_factor,
cost_for_crash=scenario.cost_for_crash)
# Third case, if it is an ExecuteTaRun we can simply use the
# instance. Otherwise, the next check raises an exception
elif not isinstance(tae_runner, ExecuteTARun):
raise TypeError("Argument 'tae_runner' is %s, but must be "
"either a callable or an instance of "
"ExecuteTaRun. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file." %
type(tae_runner))
# Check that overall objective and tae objective are the same
if tae_runner.run_obj != scenario.run_obj:
raise ValueError("Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" % (tae_runner.run_obj, scenario.run_obj))
# inject stats if necessary
if tae_runner.stats is None:
tae_runner.stats = self.stats
# inject runhistory if necessary
if tae_runner.runhistory is None:
tae_runner.runhistory = runhistory
# inject cost_for_crash
if tae_runner.crash_cost != scenario.cost_for_crash:
tae_runner.crash_cost = scenario.cost_for_crash
# initialize intensification
if intensifier is None:
intensifier = Intensifier(tae_runner=tae_runner,
stats=self.stats,
traj_logger=traj_logger,
rng=rng,
instances=scenario.train_insts,
cutoff=scenario.cutoff,
deterministic=scenario.deterministic,
run_obj_time=scenario.run_obj == "runtime",
always_race_against=scenario.cs.get_default_configuration() \
if scenario.always_race_default else None,
instance_specifics=scenario.instance_specific,
minR=scenario.minR,
maxR=scenario.maxR)
# inject deps if necessary
if intensifier.tae_runner is None:
intensifier.tae_runner = tae_runner
if intensifier.stats is None:
intensifier.stats = self.stats
if intensifier.traj_logger is None:
intensifier.traj_logger = traj_logger
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both"
)
if initial_configurations is not None:
initial_design = MultiConfigInitialDesign(
tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
runhistory=runhistory,
rng=rng,
configs=initial_configurations,
intensifier=intensifier,
aggregate_func=aggregate_func)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT":
initial_design = DefaultConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
elif scenario.initial_incumbent == "RANDOM":
initial_design = RandomConfiguration(tae_runner=tae_runner,
scenario=scenario,
stats=self.stats,
traj_logger=traj_logger,
rng=rng)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" % scenario.initial_incumbent)
# inject deps if necessary
if initial_design.tae_runner is None:
initial_design.tae_runner = tae_runner
if initial_design.scenario is None:
initial_design.scenario = scenario
if initial_design.stats is None:
initial_design.stats = self.stats
if initial_design.traj_logger is None:
initial_design.traj_logger = traj_logger
# initial conversion of runhistory into EPM data
if runhistory2epm is None:
num_params = len(scenario.cs.get_hyperparameters())
if scenario.run_obj == "runtime":
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
cutoff = np.log10(scenario.cutoff)
threshold = np.log10(scenario.cutoff * scenario.par_factor)
imputor = RFRImputator(rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model,
change_threshold=0.01,
max_iter=2)
runhistory2epm = RunHistory2EPM4LogCost(
scenario=scenario,
num_params=num_params,
success_states=[
StatusType.SUCCESS,
],
impute_censored_data=True,
impute_state=[
StatusType.CAPPED,
],
imputor=imputor)
elif scenario.run_obj == 'quality':
runhistory2epm = RunHistory2EPM4Cost(
scenario=scenario,
num_params=num_params,
success_states=[StatusType.SUCCESS, StatusType.CRASHED],
impute_censored_data=False,
impute_state=None)
else:
raise ValueError('Unknown run objective: %s. Should be either '
'quality or runtime.' % self.scenario.run_obj)
# inject scenario if necessary:
if runhistory2epm.scenario is None:
runhistory2epm.scenario = scenario
smbo_args = {
'scenario': scenario,
'stats': self.stats,
'initial_design': initial_design,
'runhistory': runhistory,
'runhistory2epm': runhistory2epm,
'intensifier': intensifier,
'aggregate_func': aggregate_func,
'num_run': num_run,
'model': model,
'acq_optimizer': acquisition_function_optimizer,
'acquisition_func': acquisition_function,
'rng': rng,
'restore_incumbent': restore_incumbent
}
if smbo_class is None:
self.solver = SMBO(**smbo_args)
else:
self.solver = smbo_class(**smbo_args)
def setUp(self):
self.model = MockModel()
self.ei = EI(self.model)
def __init__(
self,
scenario: Scenario,
tae_runner: Optional[Union[Type[BaseRunner], Callable]] = None,
tae_runner_kwargs: Optional[Dict] = None,
runhistory: Optional[Union[Type[RunHistory], RunHistory]] = None,
runhistory_kwargs: Optional[Dict] = None,
intensifier: Optional[Type[AbstractRacer]] = None,
intensifier_kwargs: Optional[Dict] = None,
acquisition_function: Optional[
Type[AbstractAcquisitionFunction]] = None,
acquisition_function_kwargs: Optional[Dict] = None,
integrate_acquisition_function: bool = False,
acquisition_function_optimizer: Optional[
Type[AcquisitionFunctionMaximizer]] = None,
acquisition_function_optimizer_kwargs: Optional[Dict] = None,
model: Optional[Type[AbstractEPM]] = None,
model_kwargs: Optional[Dict] = None,
runhistory2epm: Optional[Type[AbstractRunHistory2EPM]] = None,
runhistory2epm_kwargs: Optional[Dict] = None,
multi_objective_algorithm: Optional[
Type[AbstractMultiObjectiveAlgorithm]] = None,
multi_objective_kwargs: Optional[Dict] = None,
initial_design: Optional[Type[InitialDesign]] = None,
initial_design_kwargs: Optional[Dict] = None,
initial_configurations: Optional[List[Configuration]] = None,
stats: Optional[Stats] = None,
restore_incumbent: Optional[Configuration] = None,
rng: Optional[Union[np.random.RandomState, int]] = None,
smbo_class: Optional[Type[SMBO]] = None,
run_id: Optional[int] = None,
random_configuration_chooser: Optional[
Type[RandomConfigurationChooser]] = None,
random_configuration_chooser_kwargs: Optional[Dict] = None,
dask_client: Optional[dask.distributed.Client] = None,
n_jobs: Optional[int] = 1,
):
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
self.scenario = scenario
self.output_dir = ""
if not restore_incumbent:
# restore_incumbent is used by the CLI interface which provides a method for restoring a SMAC run given an
# output directory. This is the default path.
# initial random number generator
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
self.output_dir = create_output_directory(scenario, run_id)
elif scenario.output_dir is not None: # type: ignore[attr-defined] # noqa F821
run_id, rng = get_rng(rng=rng, run_id=run_id, logger=self.logger)
# output-directory is created in CLI when restoring from a
# folder. calling the function again in the facade results in two
# folders being created: run_X and run_X.OLD. if we are
# restoring, the output-folder exists already and we omit creating it,
# but set the self-output_dir to the dir.
# necessary because we want to write traj to new output-dir in CLI.
self.output_dir = cast(str, scenario.output_dir_for_this_run
) # type: ignore[attr-defined] # noqa F821
rng = cast(np.random.RandomState, rng)
if (scenario.deterministic is
True # type: ignore[attr-defined] # noqa F821
and getattr(scenario, "tuner_timeout", None) is None
and scenario.run_obj ==
"quality" # type: ignore[attr-defined] # noqa F821
):
self.logger.info(
"Optimizing a deterministic scenario for quality without a tuner timeout - will make "
"SMAC deterministic and only evaluate one configuration per iteration!"
)
scenario.intensification_percentage = 1e-10 # type: ignore[attr-defined] # noqa F821
scenario.min_chall = 1 # type: ignore[attr-defined] # noqa F821
scenario.write()
# initialize stats object
if stats:
self.stats = stats
else:
self.stats = Stats(scenario)
if self.scenario.run_obj == "runtime" and not self.scenario.transform_y == "LOG": # type: ignore[attr-defined] # noqa F821
self.logger.warning(
"Runtime as objective automatically activates log(y) transformation"
)
self.scenario.transform_y = "LOG" # type: ignore[attr-defined] # noqa F821
# initialize empty runhistory
num_obj = len(scenario.multi_objectives
) # type: ignore[attr-defined] # noqa F821
runhistory_def_kwargs = {}
if runhistory_kwargs is not None:
runhistory_def_kwargs.update(runhistory_kwargs)
if runhistory is None:
runhistory = RunHistory(**runhistory_def_kwargs)
elif inspect.isclass(runhistory):
runhistory = runhistory(
**runhistory_def_kwargs) # type: ignore[operator] # noqa F821
elif isinstance(runhistory, RunHistory):
pass
else:
raise ValueError(
"runhistory has to be a class or an object of RunHistory")
rand_conf_chooser_kwargs = {"rng": rng}
if random_configuration_chooser_kwargs is not None:
rand_conf_chooser_kwargs.update(
random_configuration_chooser_kwargs)
if random_configuration_chooser is None:
if "prob" not in rand_conf_chooser_kwargs:
rand_conf_chooser_kwargs[
"prob"] = scenario.rand_prob # type: ignore[attr-defined] # noqa F821
random_configuration_chooser_instance = ChooserProb(
**
rand_conf_chooser_kwargs # type: ignore[arg-type] # noqa F821 # type: RandomConfigurationChooser
)
elif inspect.isclass(random_configuration_chooser):
random_configuration_chooser_instance = random_configuration_chooser( # type: ignore # noqa F821
**
rand_conf_chooser_kwargs # type: ignore[arg-type] # noqa F821
)
elif not isinstance(random_configuration_chooser,
RandomConfigurationChooser):
raise ValueError(
"random_configuration_chooser has to be"
" a class or object of RandomConfigurationChooser")
# reset random number generator in config space to draw different
# random configurations with each seed given to SMAC
scenario.cs.seed(
rng.randint(MAXINT)) # type: ignore[attr-defined] # noqa F821
# initial Trajectory Logger
traj_logger = TrajLogger(output_dir=self.output_dir, stats=self.stats)
# initial EPM
types, bounds = get_types(
scenario.cs,
scenario.feature_array) # type: ignore[attr-defined] # noqa F821
model_def_kwargs = {
"types": types,
"bounds": bounds,
"instance_features": scenario.feature_array,
"seed": rng.randint(MAXINT),
"pca_components": scenario.PCA_DIM,
}
if model_kwargs is not None:
model_def_kwargs.update(model_kwargs)
if model is None:
for key, value in {
"log_y": scenario.transform_y
in ["LOG",
"LOGS"], # type: ignore[attr-defined] # noqa F821
"num_trees": scenario.
rf_num_trees, # type: ignore[attr-defined] # noqa F821
"do_bootstrapping": scenario.
rf_do_bootstrapping, # type: ignore[attr-defined] # noqa F821
"ratio_features": scenario.
rf_ratio_features, # type: ignore[attr-defined] # noqa F821
"min_samples_split": scenario.
rf_min_samples_split, # type: ignore[attr-defined] # noqa F821
"min_samples_leaf": scenario.
rf_min_samples_leaf, # type: ignore[attr-defined] # noqa F821
"max_depth": scenario.
rf_max_depth, # type: ignore[attr-defined] # noqa F821
}.items():
if key not in model_def_kwargs:
model_def_kwargs[key] = value
model_def_kwargs[
"configspace"] = self.scenario.cs # type: ignore[attr-defined] # noqa F821
model_instance = RandomForestWithInstances(
**
model_def_kwargs # type: ignore[arg-type] # noqa F821 # type: AbstractEPM
)
elif inspect.isclass(model):
model_def_kwargs[
"configspace"] = self.scenario.cs # type: ignore[attr-defined] # noqa F821
model_instance = model(
**model_def_kwargs) # type: ignore # noqa F821
else:
raise TypeError("Model not recognized: %s" % (type(model)))
# initial acquisition function
acq_def_kwargs = {"model": model_instance}
if acquisition_function_kwargs is not None:
acq_def_kwargs.update(acquisition_function_kwargs)
acquisition_function_instance = (
None) # type: Optional[AbstractAcquisitionFunction]
if acquisition_function is None:
if scenario.transform_y in [
"LOG", "LOGS"
]: # type: ignore[attr-defined] # noqa F821
acquisition_function_instance = LogEI(
**acq_def_kwargs # type: ignore[arg-type] # noqa F821
)
else:
acquisition_function_instance = EI(
**acq_def_kwargs # type: ignore[arg-type] # noqa F821
)
elif inspect.isclass(acquisition_function):
acquisition_function_instance = acquisition_function(
**acq_def_kwargs)
else:
raise TypeError(
"Argument acquisition_function must be None or an object implementing the "
"AbstractAcquisitionFunction, not %s." %
type(acquisition_function))
if integrate_acquisition_function:
acquisition_function_instance = IntegratedAcquisitionFunction(
acquisition_function=
acquisition_function_instance, # type: ignore
**acq_def_kwargs,
)
# initialize optimizer on acquisition function
acq_func_opt_kwargs = {
"acquisition_function": acquisition_function_instance,
"config_space":
scenario.cs, # type: ignore[attr-defined] # noqa F821
"rng": rng,
}
if acquisition_function_optimizer_kwargs is not None:
acq_func_opt_kwargs.update(acquisition_function_optimizer_kwargs)
if acquisition_function_optimizer is None:
for key, value in {
"max_steps": scenario.
sls_max_steps, # type: ignore[attr-defined] # noqa F821
"n_steps_plateau_walk": scenario.
sls_n_steps_plateau_walk, # type: ignore[attr-defined] # noqa F821
}.items():
if key not in acq_func_opt_kwargs:
acq_func_opt_kwargs[key] = value
acquisition_function_optimizer_instance = LocalAndSortedRandomSearch(
**acq_func_opt_kwargs # type: ignore
)
elif inspect.isclass(acquisition_function_optimizer):
acquisition_function_optimizer_instance = acquisition_function_optimizer( # type: ignore # noqa F821
**acq_func_opt_kwargs) # type: ignore # noqa F821
else:
raise TypeError(
"Argument acquisition_function_optimizer must be None or an object implementing the "
"AcquisitionFunctionMaximizer, but is '%s'" %
type(acquisition_function_optimizer))
# initialize tae_runner
# First case, if tae_runner is None, the target algorithm is a call
# string in the scenario file
tae_def_kwargs = {
"stats": self.stats,
"run_obj": scenario.run_obj,
"par_factor":
scenario.par_factor, # type: ignore[attr-defined] # noqa F821
"cost_for_crash":
scenario.cost_for_crash, # type: ignore[attr-defined] # noqa F821
"abort_on_first_run_crash": scenario.
abort_on_first_run_crash, # type: ignore[attr-defined] # noqa F821
"multi_objectives": scenario.
multi_objectives, # type: ignore[attr-defined] # noqa F821
}
if tae_runner_kwargs is not None:
tae_def_kwargs.update(tae_runner_kwargs)
if "ta" not in tae_def_kwargs:
tae_def_kwargs[
"ta"] = scenario.ta # type: ignore[attr-defined] # noqa F821
if tae_runner is None:
tae_def_kwargs[
"ta"] = scenario.ta # type: ignore[attr-defined] # noqa F821
tae_runner_instance = ExecuteTARunOld(
**tae_def_kwargs
) # type: ignore[arg-type] # noqa F821 # type: BaseRunner
elif inspect.isclass(tae_runner):
tae_runner_instance = cast(
BaseRunner, tae_runner(**tae_def_kwargs)) # type: ignore
elif callable(tae_runner):
tae_def_kwargs["ta"] = tae_runner
tae_def_kwargs[
"use_pynisher"] = scenario.limit_resources # type: ignore[attr-defined] # noqa F821
tae_def_kwargs[
"memory_limit"] = scenario.memory_limit # type: ignore[attr-defined] # noqa F821
tae_runner_instance = ExecuteTAFuncDict(
**tae_def_kwargs) # type: ignore
else:
raise TypeError(
"Argument 'tae_runner' is %s, but must be "
"either None, a callable or an object implementing "
"BaseRunner. Passing 'None' will result in the "
"creation of target algorithm runner based on the "
"call string in the scenario file." % type(tae_runner))
# In case of a parallel run, wrap the single worker in a parallel
# runner
if n_jobs is None or n_jobs == 1:
_n_jobs = 1
elif n_jobs == -1:
_n_jobs = joblib.cpu_count()
elif n_jobs > 0:
_n_jobs = n_jobs
else:
raise ValueError(
"Number of tasks must be positive, None or -1, but is %s" %
str(n_jobs))
if _n_jobs > 1 or dask_client is not None:
tae_runner_instance = DaskParallelRunner( # type: ignore
tae_runner_instance,
n_workers=_n_jobs,
output_directory=self.output_dir,
dask_client=dask_client,
)
# Check that overall objective and tae objective are the same
# TODO: remove these two ignores once the scenario object knows all its attributes!
if tae_runner_instance.run_obj != scenario.run_obj: # type: ignore[union-attr] # noqa F821
raise ValueError(
"Objective for the target algorithm runner and "
"the scenario must be the same, but are '%s' and "
"'%s'" %
(tae_runner_instance.run_obj,
scenario.run_obj)) # type: ignore[union-attr] # noqa F821
if intensifier is None:
intensifier = Intensifier
if isinstance(intensifier, AbstractRacer):
intensifier_instance = intensifier
elif inspect.isclass(intensifier):
# initialize intensification
intensifier_def_kwargs = {
"stats": self.stats,
"traj_logger": traj_logger,
"rng": rng,
"instances":
scenario.train_insts, # type: ignore[attr-defined] # noqa F821
"cutoff":
scenario.cutoff, # type: ignore[attr-defined] # noqa F821
"deterministic": scenario.
deterministic, # type: ignore[attr-defined] # noqa F821
"run_obj_time": scenario.run_obj ==
"runtime", # type: ignore[attr-defined] # noqa F821
"instance_specifics": scenario.
instance_specific, # type: ignore[attr-defined] # noqa F821
"adaptive_capping_slackfactor": scenario.
intens_adaptive_capping_slackfactor, # type: ignore[attr-defined] # noqa F821
"min_chall": scenario.
intens_min_chall, # type: ignore[attr-defined] # noqa F821
}
if issubclass(intensifier, Intensifier):
intensifier_def_kwargs[
"always_race_against"] = scenario.cs.get_default_configuration(
) # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
"use_ta_time_bound"] = scenario.use_ta_time # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
"minR"] = scenario.minR # type: ignore[attr-defined] # noqa F821
intensifier_def_kwargs[
"maxR"] = scenario.maxR # type: ignore[attr-defined] # noqa F821
if intensifier_kwargs is not None:
intensifier_def_kwargs.update(intensifier_kwargs)
intensifier_instance = intensifier(
**intensifier_def_kwargs) # type: ignore[arg-type] # noqa F821
else:
raise TypeError(
"Argument intensifier must be None or an object implementing the AbstractRacer, but is '%s'"
% type(intensifier))
# initialize multi objective
# the multi_objective_algorithm_instance will be passed to the runhistory2epm object
multi_objective_algorithm_instance = (
None) # type: Optional[AbstractMultiObjectiveAlgorithm]
if scenario.multi_objectives is not None and num_obj > 1: # type: ignore[attr-defined] # noqa F821
# define any defaults here
_multi_objective_kwargs = {"rng": rng, "num_obj": num_obj}
if multi_objective_kwargs is not None:
_multi_objective_kwargs.update(multi_objective_kwargs)
if multi_objective_algorithm is None:
multi_objective_algorithm_instance = MeanAggregationStrategy(
**_multi_objective_kwargs
) # type: ignore[arg-type] # noqa F821
elif inspect.isclass(multi_objective_algorithm):
multi_objective_algorithm_instance = multi_objective_algorithm(
**_multi_objective_kwargs)
else:
raise TypeError(
"Multi-objective algorithm not recognized: %s" %
(type(multi_objective_algorithm)))
# initial design
if initial_design is not None and initial_configurations is not None:
raise ValueError(
"Either use initial_design or initial_configurations; but not both"
)
init_design_def_kwargs = {
"cs": scenario.cs, # type: ignore[attr-defined] # noqa F821
"traj_logger": traj_logger,
"rng": rng,
"ta_run_limit":
scenario.ta_run_limit, # type: ignore[attr-defined] # noqa F821
"configs": initial_configurations,
"n_configs_x_params": 0,
"max_config_fracs": 0.0,
}
if initial_design_kwargs is not None:
init_design_def_kwargs.update(initial_design_kwargs)
if initial_configurations is not None:
initial_design_instance = InitialDesign(**init_design_def_kwargs)
elif initial_design is None:
if scenario.initial_incumbent == "DEFAULT": # type: ignore[attr-defined] # noqa F821
init_design_def_kwargs["max_config_fracs"] = 0.0
initial_design_instance = DefaultConfiguration(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "RANDOM": # type: ignore[attr-defined] # noqa F821
init_design_def_kwargs["max_config_fracs"] = 0.0
initial_design_instance = RandomConfigurations(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "LHD": # type: ignore[attr-defined] # noqa F821
initial_design_instance = LHDesign(**init_design_def_kwargs)
elif scenario.initial_incumbent == "FACTORIAL": # type: ignore[attr-defined] # noqa F821
initial_design_instance = FactorialInitialDesign(
**init_design_def_kwargs)
elif scenario.initial_incumbent == "SOBOL": # type: ignore[attr-defined] # noqa F821
initial_design_instance = SobolDesign(**init_design_def_kwargs)
else:
raise ValueError("Don't know what kind of initial_incumbent "
"'%s' is" %
scenario.initial_incumbent # type: ignore
) # type: ignore[attr-defined] # noqa F821
elif inspect.isclass(initial_design):
initial_design_instance = initial_design(**init_design_def_kwargs)
else:
raise TypeError(
"Argument initial_design must be None or an object implementing the InitialDesign, but is '%s'"
% type(initial_design))
# if we log the performance data,
# the RFRImputator will already get
# log transform data from the runhistory
if scenario.transform_y in [
"LOG", "LOGS"
]: # type: ignore[attr-defined] # noqa F821
cutoff = np.log(np.nanmin([
np.inf, np.float_(scenario.cutoff)
])) # type: ignore[attr-defined] # noqa F821
threshold = cutoff + np.log(
scenario.par_factor) # type: ignore[attr-defined] # noqa F821
else:
cutoff = np.nanmin([np.inf, np.float_(scenario.cutoff)
]) # type: ignore[attr-defined] # noqa F821
threshold = cutoff * scenario.par_factor # type: ignore[attr-defined] # noqa F821
num_params = len(scenario.cs.get_hyperparameters()
) # type: ignore[attr-defined] # noqa F821
imputor = RFRImputator(
rng=rng,
cutoff=cutoff,
threshold=threshold,
model=model_instance,
change_threshold=0.01,
max_iter=2,
)
r2e_def_kwargs = {
"scenario": scenario,
"num_params": num_params,
"success_states": [
StatusType.SUCCESS,
],
"impute_censored_data": True,
"impute_state": [
StatusType.CAPPED,
],
"imputor": imputor,
"scale_perc": 5,
}
# TODO: consider other sorts of multi-objective algorithms
if isinstance(multi_objective_algorithm_instance, AggregationStrategy):
r2e_def_kwargs.update({
"multi_objective_algorithm":
multi_objective_algorithm_instance
})
if scenario.run_obj == "quality":
r2e_def_kwargs.update({
"success_states": [
StatusType.SUCCESS,
StatusType.CRASHED,
StatusType.MEMOUT,
],
"impute_censored_data":
False,
"impute_state":
None,
})
if (isinstance(intensifier_instance, (SuccessiveHalving, Hyperband))
and scenario.run_obj == "quality"):
r2e_def_kwargs.update({
"success_states": [
StatusType.SUCCESS,
StatusType.CRASHED,
StatusType.MEMOUT,
StatusType.DONOTADVANCE,
],
"consider_for_higher_budgets_state": [
StatusType.DONOTADVANCE,
StatusType.TIMEOUT,
StatusType.CRASHED,
StatusType.MEMOUT,
],
})
if runhistory2epm_kwargs is not None:
r2e_def_kwargs.update(runhistory2epm_kwargs)
if runhistory2epm is None:
if scenario.run_obj == "runtime":
rh2epm = RunHistory2EPM4LogCost(
**r2e_def_kwargs # type: ignore
) # type: ignore[arg-type] # noqa F821 # type: AbstractRunHistory2EPM
elif scenario.run_obj == "quality":
if scenario.transform_y == "NONE": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4Cost(
**r2e_def_kwargs) # type: ignore # noqa F821
elif scenario.transform_y == "LOG": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4LogCost(
**r2e_def_kwargs) # type: ignore # noqa F821
elif scenario.transform_y == "LOGS": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4LogScaledCost(
**r2e_def_kwargs) # type: ignore # noqa F821
elif scenario.transform_y == "INVS": # type: ignore[attr-defined] # noqa F821
rh2epm = RunHistory2EPM4InvScaledCost(
**r2e_def_kwargs) # type: ignore # noqa F821
else:
raise ValueError(
"Unknown run objective: %s. Should be either "
"quality or runtime." %
self.scenario.run_obj # type: ignore # noqa F821
)
elif inspect.isclass(runhistory2epm):
rh2epm = runhistory2epm(**
r2e_def_kwargs) # type: ignore # noqa F821
else:
raise TypeError(
"Argument runhistory2epm must be None or an object implementing the RunHistory2EPM, but is '%s'"
% type(runhistory2epm))
smbo_args = {
"scenario": scenario,
"stats": self.stats,
"initial_design": initial_design_instance,
"runhistory": runhistory,
"runhistory2epm": rh2epm,
"intensifier": intensifier_instance,
"num_run": run_id,
"model": model_instance,
"acq_optimizer": acquisition_function_optimizer_instance,
"acquisition_func": acquisition_function_instance,
"rng": rng,
"restore_incumbent": restore_incumbent,
"random_configuration_chooser":
random_configuration_chooser_instance,
"tae_runner": tae_runner_instance,
} # type: Dict[str, Any]
if smbo_class is None:
self.solver = SMBO(**
smbo_args) # type: ignore[arg-type] # noqa F821
else:
self.solver = smbo_class(
**smbo_args) # type: ignore[arg-type] # noqa F821
def run_experiment():
pipeline_space = PipelineSpace()
o_s = OneHotEncodingStep()
i_s = ImputationStep()
r_s = RescalingStep()
b_s = BalancingStep()
p_s = PreprocessingStep()
c_s = ClassificationStep()
pipeline_space.add_pipeline_steps([o_s, i_s, r_s, b_s, p_s, c_s])
runhistory = PCRunHistory(average_cost)
cs_builder = ConfigSpaceBuilder(pipeline_space)
config_space = cs_builder.build_config_space()
args = {
'cs': config_space,
'run_obj': "quality",
'runcount_limit': 100,
'wallclock_limit': 100,
'memory_limit': 100,
'cutoff_time': 100,
'deterministic': "true"
}
scenario = Scenario(args)
# Build stats
stats = Stats(scenario, output_dir=None, stamp="")
types, bounds = get_types(scenario.cs, scenario.feature_array)
model = RandomForestWithInstances(types=types, bounds=bounds)
constant_pipeline_steps = [
"one_hot_encoder", "imputation", "rescaling", "balancing",
"feature_preprocessor"
]
variable_pipeline_steps = ["classifier"]
rng = np.random.RandomState()
num_params = len(scenario.cs.get_hyperparameters())
acquisition_func = EI(model)
acq_func_wrapper = PCAquisitionFunctionWrapper(
acquisition_func=acquisition_func,
config_space=scenario.cs,
runhistory=runhistory,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps)
runhistory2epm = RunHistory2EPM4Cost(scenario,
num_params,
success_states=[StatusType.SUCCESS])
local_search = LocalSearch(acquisition_function=acq_func_wrapper,
config_space=scenario.cs)
select_configuration = SelectConfigurationsWithMarginalization(
scenario=scenario,
stats=stats,
runhistory=runhistory,
model=model,
acq_optimizer=local_search,
acquisition_func=acq_func_wrapper,
rng=rng,
constant_pipeline_steps=constant_pipeline_steps,
variable_pipeline_steps=variable_pipeline_steps,
num_marginalized_configurations_by_random_search=40,
num_configs_for_marginalization=200)
# sample configurations to fill runhistory
sample_configs = config_space.sample_configuration(size=10)
for config in sample_configs:
runhistory.add(config, 1, 1, StatusType.SUCCESS)
# test select_configurations procedure
X, Y = runhistory2epm.transform(runhistory)
challengers = select_configuration.run(
X,
Y,
sample_configs[0],
num_configurations_by_random_search_sorted=100,
num_configurations_by_local_search=10,
random_leaf_size=1)
print(challengers[0])