Sqrt scaled encoder

smac.runhistory.encoder.sqrt_scaled_encoder

RunHistorySqrtScaledEncoder

RunHistorySqrtScaledEncoder(*args: Any, **kwargs: Any)

Bases: RunHistoryEncoder

Source code in smac/runhistory/encoder/sqrt_scaled_encoder.py

def __init__(self, *args: Any, **kwargs: Any) -> None:
    super().__init__(*args, **kwargs)
    if self._instances is not None and len(self._instances) > 1:
        raise NotImplementedError("Handling more than one instance is not supported for sqrt scaled cost.")

meta property

meta: dict[str, Any]

Returns the meta-data of the created object.

Returns

dict[str, Any]: meta-data of the created object: name, considered states, lower budget states, scale_percentage, seed.

multi_objective_algorithm property writable

multi_objective_algorithm: (
    AbstractMultiObjectiveAlgorithm | None
)

The multi objective algorithm used to transform the data.

runhistory property writable

runhistory: RunHistory

The RunHistory used to transform the data.

get_configurations

get_configurations(
    budget_subset: list | None = None,
) -> ndarray

Returns vector representation of the configurations.

Warning

Instance features are not appended and cost values are not taken into account.

Parameters

budget_subset : list[int|float] | None, defaults to none List of budgets to consider.

Returns

configs_array : np.ndarray

Source code in smac/runhistory/encoder/abstract_encoder.py

def get_configurations(
    self,
    budget_subset: list | None = None,
) -> np.ndarray:
    """Returns vector representation of the configurations.

    Warning
    -------
    Instance features are not
    appended and cost values are not taken into account.

    Parameters
    ----------
    budget_subset : list[int|float] | None, defaults to none
        List of budgets to consider.

    Returns
    -------
    configs_array : np.ndarray
    """
    s_trials = self._get_considered_trials(budget_subset)
    s_config_ids = set(s_trial.config_id for s_trial in s_trials)
    t_trials = self._get_timeout_trials(budget_subset)
    t_config_ids = set(t_trial.config_id for t_trial in t_trials)
    config_ids = s_config_ids | t_config_ids
    configurations = [self.runhistory._ids_config[config_id] for config_id in config_ids]
    configs_array = convert_configurations_to_array(configurations)

    return configs_array

transform

transform(
    budget_subset: list | None = None,
) -> tuple[ndarray, ndarray]

Returns a vector representation of the RunHistory.

Parameters

budget_subset : list | None, defaults to none List of budgets to consider.

Returns

X : np.ndarray Configuration vector and instance features. Y : np.ndarray Cost values.

Source code in smac/runhistory/encoder/abstract_encoder.py

def transform(
    self,
    budget_subset: list | None = None,
) -> tuple[np.ndarray, np.ndarray]:
    """Returns a vector representation of the RunHistory.

    Parameters
    ----------
    budget_subset : list | None, defaults to none
        List of budgets to consider.

    Returns
    -------
    X : np.ndarray
        Configuration vector and instance features.
    Y : np.ndarray
        Cost values.
    """
    logger.debug("Transforming RunHistory into X, y format...")

    considered_trials = self._get_considered_trials(budget_subset)
    X, Y = self._build_matrix(trials=considered_trials, store_statistics=True)

    # Get real TIMEOUT runs
    timeout_trials = self._get_timeout_trials(budget_subset)

    # Use penalization (e.g. PAR10) for EPM training
    store_statistics = True if np.any(np.isnan(self._min_y)) else False
    tX, tY = self._build_matrix(trials=timeout_trials, store_statistics=store_statistics)

    # If we don't have successful runs, we have to return all timeout runs
    if not considered_trials:
        return tX, tY

    # If we do not impute, we also return TIMEOUT data
    X = np.vstack((X, tX))
    Y = np.concatenate((Y, tY))

    logger.debug("Converted %d observations." % (X.shape[0]))
    return X, Y

transform_response_values

transform_response_values(values: ndarray) -> ndarray

Transform the response values by linearly scaling them between zero and one and then using the square root.

Source code in smac/runhistory/encoder/sqrt_scaled_encoder.py

def transform_response_values(self, values: np.ndarray) -> np.ndarray:
    """Transform the response values by linearly scaling them between zero and one and then using the
    square root.
    """
    # Subtract the difference between the percentile and the minimum
    min_y = self._min_y - (self._percentile - self._min_y)

    # Minimal value to avoid numerical issues in the log scaling below
    min_y -= constants.VERY_SMALL_NUMBER

    # Linear scaling: prevent diving by zero
    min_y[np.where(min_y == self._max_y)] *= 1 - 10**-10

    values = (values - min_y) / (self._max_y - min_y)
    values = np.sqrt(values)

    return values