def test_psmac(self):
with joblib.parallel_backend('multiprocessing', n_jobs=1):
optimizer = PSMAC(self.scenario, n_optimizers=3, n_incs=2, validate=False)
incs = optimizer.optimize()
self.assertEqual(len(incs), 2)
optimizer = PSMAC(self.scenario, n_optimizers=1, n_incs=4, validate=False)
incs = optimizer.optimize()
self.assertEqual(len(incs), 2)
optimizer = PSMAC(self.scenario, n_optimizers=5, n_incs=4, validate=False)
incs = optimizer.optimize()
self.assertEqual(len(incs), 4)
class Hydra(object):
"""
Facade to use Hydra default mode
Attributes
----------
logger
stats : Stats
loggs information about used resources
solver : SMBO
handles the actual algorithm calls
rh : RunHistory
List with information about previous runs
portfolio : list
List of all incumbents
"""
def __init__(self,
scenario: Scenario,
n_iterations: int,
val_set: str = 'train',
incs_per_round: int = 1,
n_optimizers: int = 1,
rng: typing.Optional[typing.Union[np.random.RandomState,
int]] = None,
run_id: int = 1,
tae: typing.Type[ExecuteTARun] = ExecuteTARunOld,
tae_kwargs: typing.Union[dict, None] = None,
**kwargs):
"""
Constructor
Parameters
----------
scenario : ~smac.scenario.scenario.Scenario
Scenario object
n_iterations: int,
number of Hydra iterations
val_set: str
Set to validate incumbent(s) on. [train, valX].
train => whole training set,
valX => train_set * 100/X where X in (0, 100)
incs_per_round: int
Number of incumbents to keep per round
n_optimizers: int
Number of optimizers to run in parallel per round
rng: int/np.random.RandomState
The randomState/seed to pass to each smac run
run_id: int
run_id for this hydra run
tae: ExecuteTARun
Target Algorithm Runner (supports old and aclib format as well as AbstractTAFunc)
tae_kwargs: Optional[dict]
arguments passed to constructor of '~tae'
"""
self.logger = logging.getLogger(self.__module__ + "." +
self.__class__.__name__)
self.n_iterations = n_iterations
self.scenario = scenario
self.run_id, self.rng = get_rng(rng, run_id, self.logger)
self.kwargs = kwargs
self.output_dir = None
self.top_dir = None
self.solver = None
self.portfolio = None
self.rh = RunHistory(average_cost, file_system=scenario.file_system)
self._tae = tae
self._tae_kwargs = tae_kwargs
if incs_per_round <= 0:
self.logger.warning('Invalid value in %s: %d. Setting to 1',
'incs_per_round', incs_per_round)
self.incs_per_round = max(incs_per_round, 1)
if n_optimizers <= 0:
self.logger.warning('Invalid value in %s: %d. Setting to 1',
'n_optimizers', n_optimizers)
self.n_optimizers = max(n_optimizers, 1)
self.val_set = self._get_validation_set(val_set)
self.cost_per_inst = {}
self.optimizer = None
self.portfolio_cost = None
def _get_validation_set(self,
val_set: str,
delete: bool = True) -> typing.List[str]:
"""
Create small validation set for hydra to determine incumbent performance
Parameters
----------
val_set: str
Set to validate incumbent(s) on. [train, valX].
train => whole training set,
valX => train_set * 100/X where X in (0, 100)
delete: bool
Flag to delete all validation instances from the training set
Returns
-------
val: typing.List[str]
List of instance-ids to validate on
"""
if val_set == 'none':
return None
if val_set == 'train':
return self.scenario.train_insts
elif val_set[:3] != 'val':
self.logger.warning(
'Can not determine validation set size. Using full training-set!'
)
return self.scenario.train_insts
else:
size = int(val_set[3:]) / 100
if size <= 0 or size >= 1:
raise ValueError(
'X invalid in valX, should be between 0 and 1')
insts = np.array(self.scenario.train_insts)
# just to make sure this also works with the small example we have to round up to 3
size = max(np.floor(insts.shape[0] * size).astype(int), 3)
ids = np.random.choice(insts.shape[0], size, replace=False)
val = insts[ids].tolist()
if delete:
self.scenario.train_insts = np.delete(insts, ids).tolist()
return val
def optimize(self) -> typing.List[Configuration]:
"""
Optimizes the algorithm provided in scenario (given in constructor)
Returns
-------
portfolio : typing.List[Configuration]
Portfolio of found configurations
"""
# Setup output directory
self.portfolio = []
portfolio_cost = np.inf
if self.output_dir is None:
self.top_dir = "hydra-output_%s" % (
datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f'))
self.scenario.output_dir = os.path.join(
self.top_dir,
"psmac3-output_%s" % (datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f')))
self.output_dir = create_output_directory(self.scenario,
run_id=self.run_id,
logger=self.logger)
scen = copy.deepcopy(self.scenario)
scen.output_dir_for_this_run = None
scen.output_dir = None
# parent process SMAC only used for validation purposes
self.solver = SMAC4AC(scenario=scen,
tae_runner=self._tae,
rng=self.rng,
run_id=self.run_id,
**self.kwargs)
for i in range(self.n_iterations):
self.logger.info("=" * 120)
self.logger.info("Hydra Iteration: %d", (i + 1))
if i == 0:
tae = self._tae
tae_kwargs = self._tae_kwargs
else:
tae = ExecuteTARunHydra
if self._tae_kwargs:
tae_kwargs = self._tae_kwargs
else:
tae_kwargs = {}
tae_kwargs['cost_oracle'] = self.cost_per_inst
self.optimizer = PSMAC(
scenario=self.scenario,
run_id=self.run_id,
rng=self.rng,
tae=tae,
tae_kwargs=tae_kwargs,
shared_model=False,
validate=True if self.val_set else False,
n_optimizers=self.n_optimizers,
val_set=self.val_set,
n_incs=self.
n_optimizers, # return all configurations (unvalidated)
**self.kwargs)
self.optimizer.output_dir = self.output_dir
incs = self.optimizer.optimize()
cost_per_conf_v, val_ids, cost_per_conf_e, est_ids = self.optimizer.get_best_incumbents_ids(
incs)
if self.val_set:
to_keep_ids = val_ids[:self.incs_per_round]
else:
to_keep_ids = est_ids[:self.incs_per_round]
config_cost_per_inst = {}
incs = incs[to_keep_ids]
self.logger.info('Kept incumbents')
for inc in incs:
self.logger.info(inc)
config_cost_per_inst[inc] = cost_per_conf_v[
inc] if self.val_set else cost_per_conf_e[inc]
cur_portfolio_cost = self._update_portfolio(
incs, config_cost_per_inst)
if portfolio_cost <= cur_portfolio_cost:
self.logger.info(
"No further progress (%f) --- terminate hydra",
portfolio_cost)
break
else:
portfolio_cost = cur_portfolio_cost
self.logger.info("Current pertfolio cost: %f", portfolio_cost)
self.scenario.output_dir = os.path.join(
self.top_dir,
"psmac3-output_%s" % (datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f')))
self.output_dir = create_output_directory(self.scenario,
run_id=self.run_id,
logger=self.logger)
read(self.rh,
os.path.join(self.top_dir, 'psmac3*', 'run_' + str(MAXINT)),
self.scenario.cs, self.logger)
self.rh.save_json(fn=os.path.join(
self.top_dir, 'all_validated_runs_runhistory.json'),
save_external=True)
with open(os.path.join(self.top_dir, 'portfolio.pkl'), 'wb') as fh:
pickle.dump(self.portfolio, fh)
self.logger.info("~" * 120)
self.logger.info('Resulting Portfolio:')
for configuration in self.portfolio:
self.logger.info(str(configuration))
self.logger.info("~" * 120)
return self.portfolio
def _update_portfolio(
self, incs: np.ndarray, config_cost_per_inst: typing.Dict
) -> typing.Union[np.float, float]:
"""
Validates all configurations (in incs) and determines which ones to add to the portfolio
Parameters
----------
incs: np.ndarray
List of Configurations
Returns
-------
cur_cost: typing.Union[np.float, float]
The current cost of the portfolio
"""
if self.val_set: # we have validated data
for kept in incs:
if kept not in self.portfolio:
self.portfolio.append(kept)
cost_per_inst = config_cost_per_inst[kept]
if self.cost_per_inst:
if len(self.cost_per_inst) != len(cost_per_inst):
raise ValueError(
'Num validated Instances mismatch!')
else:
for key in cost_per_inst:
self.cost_per_inst[key] = min(
self.cost_per_inst[key],
cost_per_inst[key])
else:
self.cost_per_inst = cost_per_inst
cur_cost = np.mean(list(
self.cost_per_inst.values())) # type: np.float
else: # No validated data. Set the mean to the approximated mean
means = [
] # can contain nans as not every instance was evaluated thus we should use nanmean to approximate
for kept in incs:
means.append(
np.nanmean(
list(
self.optimizer.rh.get_instance_costs_for_config(
kept).values())))
self.portfolio.append(kept)
if self.portfolio_cost:
new_mean = self.portfolio_cost * (
len(self.portfolio) - len(incs)) / len(self.portfolio)
new_mean += np.nansum(means)
else:
new_mean = np.mean(means)
self.cost_per_inst = defaultdict(lambda: new_mean)
cur_cost = new_mean
self.portfolio_cost = cur_cost
return cur_cost
def optimize(self) -> typing.List[Configuration]:
"""
Optimizes the algorithm provided in scenario (given in constructor)
Returns
-------
portfolio : typing.List[Configuration]
Portfolio of found configurations
"""
# Setup output directory
self.portfolio = []
portfolio_cost = np.inf
if self.output_dir is None:
self.top_dir = "hydra-output_%s" % (
datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f'))
self.scenario.output_dir = os.path.join(
self.top_dir,
"psmac3-output_%s" % (datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f')))
self.output_dir = create_output_directory(self.scenario,
run_id=self.run_id,
logger=self.logger)
scen = copy.deepcopy(self.scenario)
scen.output_dir_for_this_run = None
scen.output_dir = None
# parent process SMAC only used for validation purposes
self.solver = SMAC4AC(scenario=scen,
tae_runner=self._tae,
rng=self.rng,
run_id=self.run_id,
**self.kwargs)
for i in range(self.n_iterations):
self.logger.info("=" * 120)
self.logger.info("Hydra Iteration: %d", (i + 1))
if i == 0:
tae = self._tae
tae_kwargs = self._tae_kwargs
else:
tae = ExecuteTARunHydra
if self._tae_kwargs:
tae_kwargs = self._tae_kwargs
else:
tae_kwargs = {}
tae_kwargs['cost_oracle'] = self.cost_per_inst
self.optimizer = PSMAC(
scenario=self.scenario,
run_id=self.run_id,
rng=self.rng,
tae=tae,
tae_kwargs=tae_kwargs,
shared_model=False,
validate=True if self.val_set else False,
n_optimizers=self.n_optimizers,
val_set=self.val_set,
n_incs=self.
n_optimizers, # return all configurations (unvalidated)
**self.kwargs)
self.optimizer.output_dir = self.output_dir
incs = self.optimizer.optimize()
cost_per_conf_v, val_ids, cost_per_conf_e, est_ids = self.optimizer.get_best_incumbents_ids(
incs)
if self.val_set:
to_keep_ids = val_ids[:self.incs_per_round]
else:
to_keep_ids = est_ids[:self.incs_per_round]
config_cost_per_inst = {}
incs = incs[to_keep_ids]
self.logger.info('Kept incumbents')
for inc in incs:
self.logger.info(inc)
config_cost_per_inst[inc] = cost_per_conf_v[
inc] if self.val_set else cost_per_conf_e[inc]
cur_portfolio_cost = self._update_portfolio(
incs, config_cost_per_inst)
if portfolio_cost <= cur_portfolio_cost:
self.logger.info(
"No further progress (%f) --- terminate hydra",
portfolio_cost)
break
else:
portfolio_cost = cur_portfolio_cost
self.logger.info("Current pertfolio cost: %f", portfolio_cost)
self.scenario.output_dir = os.path.join(
self.top_dir,
"psmac3-output_%s" % (datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d_%H:%M:%S_%f')))
self.output_dir = create_output_directory(self.scenario,
run_id=self.run_id,
logger=self.logger)
read(self.rh,
os.path.join(self.top_dir, 'psmac3*', 'run_' + str(MAXINT)),
self.scenario.cs, self.logger)
self.rh.save_json(fn=os.path.join(
self.top_dir, 'all_validated_runs_runhistory.json'),
save_external=True)
with open(os.path.join(self.top_dir, 'portfolio.pkl'), 'wb') as fh:
pickle.dump(self.portfolio, fh)
self.logger.info("~" * 120)
self.logger.info('Resulting Portfolio:')
for configuration in self.portfolio:
self.logger.info(str(configuration))
self.logger.info("~" * 120)
return self.portfolio
def fit(self, dataset: BinaryDataset,
clustering_algs: List[str],
feature_selection_algs: List[str],
n_evaluations: int = 30,
cutoff_time=20,
evaluator: Callable = Measures.silhouette,
experiments_dir: str = "../../experiments",
n_optimizers=2,
top_algorithms_count=5) -> List[str]:
cs = build_config_space(clustering_ls=clustering_algs, feature_selection_ls=feature_selection_algs)
config_name: str = "mixed"
if len(clustering_algs) == 1 and len(feature_selection_algs) == 1:
config_name: str = f"{feature_selection_algs[0]}_{clustering_algs[0]}"
base_dir_name = _create_smac_directory(experiments_dir, evaluator.__name__, config_name)
scenario_params: dict = {
"run_obj": "quality",
"runcount-limit": n_evaluations,
"cutoff_time": cutoff_time,
"cs": cs,
"deterministic": "false",
"output_dir": base_dir_name,
"abort_on_first_run_crash": False,
"shared_model": True,
"input_psmac_dirs": _create_psmac_dirs(base_dir_name, n_optimizers)
}
scenario = Scenario(scenario_params)
dataset_content = dataset.load_dataset()
def fit_models(cfg: dict, data: np.ndarray):
feature_selection_alg = Mapper.get_class(cfg["feature_selection_choice"])
cfg_feature_selection: dict = {
decode_parameter(k, feature_selection_alg.name): v for k, v in cfg.items()
if decode_parameter(k, feature_selection_alg.name) is not None
}
feature_selection_model = feature_selection_alg.model(**cfg_feature_selection)
selected_data: np.ndarray = feature_selection_model.fit_transform(data)
clustering_alg = Mapper.get_class(cfg["clustering_choice"])
cfg_clustering: dict = {
decode_parameter(k, clustering_alg.name): v for k, v in cfg.items()
if decode_parameter(k, clustering_alg.name) is not None
}
clustering_model = clustering_alg.model(**cfg_clustering)
clustering_result = clustering_model.fit_predict(selected_data)
return feature_selection_model, clustering_model, clustering_result
def cfg_to_dict(cfg):
cfg = {k: cfg[k] for k in cfg if cfg[k]}
return {k: v for k, v in cfg.items() if v is not None}
def evaluate_model(cfg):
cfg_dict = cfg_to_dict(cfg)
_, _, y_pred = fit_models(cfg_dict, dataset_content)
if len(np.unique(y_pred)) < 2:
return np.inf
else:
return evaluator(dataset_content, y_pred)
optimal_config = None
smac = SMAC(
scenario=scenario,
rng=np.random.RandomState(42),
tae=evaluate_model,
n_optimizers=n_optimizers,
validate=False,
n_incs=top_algorithms_count
)
# for some reason smac sets output dir to None in constructor, so we inject it manually
smac.output_dir = base_dir_name
scenario.output_dir = base_dir_name
self._smac = smac
optimal_configs: List[Configuration] = self._smac.optimize()
best_algorithms: List[str] = []
for i, optimal_config in enumerate(optimal_configs):
dict_config = cfg_to_dict(optimal_config)
feature_selection_model, clustering_model, clustering_result = \
fit_models(dict_config, dataset_content)
if len(np.unique(clustering_result)) < 2:
measure_value = np.inf
else:
measure_value = evaluator(dataset_content, clustering_result)
result = {
"optimal_config": dict_config,
"smac": self._smac,
"feature_selection_model": feature_selection_model,
"clustering_model": clustering_model,
"clustering_result": clustering_result,
"measure_value": measure_value
}
_save_clustering_result(result, f"{base_dir_name}", name=f"config_{i}")
best_algorithms.append(_encode(dict_config["clustering_choice"], dict_config["feature_selection_choice"]))
_save_best_algorithms(experiments_dir, best_algorithms, clustering_algs, feature_selection_algs)
return best_algorithms
def main_cli(
self,
commandline_arguments: typing.Optional[typing.List[str]] = None
) -> None:
"""Main function of SMAC for CLI interface"""
self.logger.info("SMAC call: %s" % (" ".join(sys.argv)))
cmd_reader = CMDReader()
kwargs = {}
if commandline_arguments:
kwargs['commandline_arguments'] = commandline_arguments
main_args_, smac_args_, scen_args_ = cmd_reader.read_cmd(**kwargs)
root_logger = logging.getLogger()
root_logger.setLevel(main_args_.verbose_level)
logger_handler = logging.StreamHandler(stream=sys.stdout)
if root_logger.level >= logging.INFO:
formatter = logging.Formatter("%(levelname)s:\t%(message)s")
else:
formatter = logging.Formatter(
"%(asctime)s:%(levelname)s:%(name)s:\t%(message)s",
"%Y-%m-%d %H:%M:%S")
logger_handler.setFormatter(formatter)
root_logger.addHandler(logger_handler)
# remove default handler
if len(root_logger.handlers) > 1:
root_logger.removeHandler(root_logger.handlers[0])
# Create defaults
rh = None
initial_configs = None
stats = None
incumbent = None
# Create scenario-object
scenario = {}
scenario.update(vars(smac_args_))
scenario.update(vars(scen_args_))
scen = Scenario(scenario=scenario)
# Restore state
if main_args_.restore_state:
root_logger.debug("Restoring state from %s...",
main_args_.restore_state)
restore_state = main_args_.restore_state
rh, stats, traj_list_aclib, traj_list_old = self.restore_state(
scen, restore_state)
scen.output_dir_for_this_run = create_output_directory(
scen,
main_args_.seed,
root_logger,
)
scen.write()
incumbent = self.restore_state_after_output_dir(
scen, stats, traj_list_aclib, traj_list_old)
if main_args_.warmstart_runhistory:
rh = RunHistory()
scen, rh = merge_foreign_data_from_file(
scenario=scen,
runhistory=rh,
in_scenario_fn_list=main_args_.warmstart_scenario,
in_runhistory_fn_list=main_args_.warmstart_runhistory,
cs=scen.cs, # type: ignore[attr-defined] # noqa F821
)
if main_args_.warmstart_incumbent:
initial_configs = [scen.cs.get_default_configuration()
] # type: ignore[attr-defined] # noqa F821
for traj_fn in main_args_.warmstart_incumbent:
trajectory = TrajLogger.read_traj_aclib_format(
fn=traj_fn,
cs=scen.cs, # type: ignore[attr-defined] # noqa F821
)
initial_configs.append(trajectory[-1]["incumbent"])
if main_args_.mode == "SMAC4AC":
optimizer = SMAC4AC(scenario=scen,
rng=np.random.RandomState(main_args_.seed),
runhistory=rh,
initial_configurations=initial_configs,
stats=stats,
restore_incumbent=incumbent,
run_id=main_args_.seed)
elif main_args_.mode == "SMAC4HPO":
optimizer = SMAC4HPO(scenario=scen,
rng=np.random.RandomState(main_args_.seed),
runhistory=rh,
initial_configurations=initial_configs,
stats=stats,
restore_incumbent=incumbent,
run_id=main_args_.seed)
elif main_args_.mode == "SMAC4BB":
optimizer = SMAC4BB(scenario=scen,
rng=np.random.RandomState(main_args_.seed),
runhistory=rh,
initial_configurations=initial_configs,
stats=stats,
restore_incumbent=incumbent,
run_id=main_args_.seed)
elif main_args_.mode == "ROAR":
optimizer = ROAR(scenario=scen,
rng=np.random.RandomState(main_args_.seed),
runhistory=rh,
initial_configurations=initial_configs,
run_id=main_args_.seed)
elif main_args_.mode == "Hydra":
optimizer = Hydra(
scenario=scen,
rng=np.random.RandomState(main_args_.seed),
runhistory=rh,
initial_configurations=initial_configs,
stats=stats,
restore_incumbent=incumbent,
run_id=main_args_.seed,
random_configuration_chooser=main_args_.
random_configuration_chooser,
n_iterations=main_args_.hydra_iterations,
val_set=main_args_.hydra_validation,
incs_per_round=main_args_.hydra_incumbents_per_round,
n_optimizers=main_args_.hydra_n_optimizers)
elif main_args_.mode == "PSMAC":
optimizer = PSMAC(
scenario=scen,
rng=np.random.RandomState(main_args_.seed),
run_id=main_args_.seed,
shared_model=smac_args_.shared_model,
validate=main_args_.psmac_validate,
n_optimizers=main_args_.hydra_n_optimizers,
n_incs=main_args_.hydra_incumbents_per_round,
)
try:
optimizer.optimize()
except (TAEAbortException, FirstRunCrashedException) as err:
self.logger.error(err)