smac.tae.execute_ta_run_aclib module

class smac.tae.execute_ta_run_aclib.ExecuteTARunAClib(ta: Union[List[str], Callable], stats: smac.stats.stats.Stats, run_obj: str = 'runtime', par_factor: int = 1, cost_for_crash: float = 2147483647.0, abort_on_first_run_crash: bool = True)[source]

Bases: smac.tae.serial_runner.SerialRunner

Executes a target algorithm run with a given configuration on a given instance and some resource limitations. Uses the AClib 2.0 style

_abc_impl = <_abc_data object>
_call_ta(config: ConfigSpace.configuration_space.Configuration, instance: str, instance_specific: str, cutoff: float, seed: int) → Tuple[Dict, str, str][source]
run(config: ConfigSpace.configuration_space.Configuration, instance: str, cutoff: Optional[float] = None, seed: int = 12345, budget: Optional[float] = None, instance_specific: str = '0') → Tuple[smac.tae.StatusType, float, float, Dict][source]

Runs target algorithm <self.ta> with configuration <config> on instance <instance> with instance specifics <specifics> for at most <cutoff> seconds and random seed <seed>

Parameters
  • config (Configuration) – Dictionary param -> value

  • instance (str) – Problem instance

  • cutoff (float) – Runtime cutoff

  • seed (int) – Random seed

  • budget (float (optional)) – Not implemented

  • instance_specific (str) – Instance specific information – ignored here

Returns

  • status (enum of StatusType (int)) – {SUCCESS, TIMEOUT, CRASHED, ABORT}

  • cost (float) – cost/regret/quality/runtime (float) (None, if not returned by TA)

  • runtime (float) – runtime (None if not returned by TA)

  • additional_info (dict) – all further additional run information