def _sample_mo_categorical_index(
self,
study: optuna.study.Study,
trial: optuna.trial.FrozenTrial,
distribution: distributions.CategoricalDistribution,
below: np.ndarray,
above: np.ndarray,
) -> int:
choices = distribution.choices
below = list(map(int, below))
above = list(map(int, above))
upper = len(choices)
size = (self._n_ehvi_candidates,)
weights_below = study._storage.get_trial(trial._trial_id).system_attrs[_WEIGHTS_BELOW_KEY]
counts_below = np.bincount(below, minlength=upper, weights=weights_below)
weighted_below = counts_below + self._prior_weight
weighted_below /= weighted_below.sum()
samples_below = self._sample_from_categorical_dist(weighted_below, size)
log_likelihoods_below = TPESampler._categorical_log_pdf(samples_below, weighted_below)
weights_above = self._weights(len(above))
counts_above = np.bincount(above, minlength=upper, weights=weights_above)
weighted_above = counts_above + self._prior_weight
weighted_above /= weighted_above.sum()
log_likelihoods_above = TPESampler._categorical_log_pdf(samples_below, weighted_above)
return int(
TPESampler._compare(
samples=samples_below, log_l=log_likelihoods_below, log_g=log_likelihoods_above
)[0]
)
def _sample_mo_numerical(
self,
study: optuna.study.Study,
trial: optuna.trial.FrozenTrial,
low: float,
high: float,
below: np.ndarray,
above: np.ndarray,
q: Optional[float] = None,
is_log: bool = False,
) -> float:
if is_log:
low = np.log(low)
high = np.log(high)
below = np.log(below)
above = np.log(above)
size = (self._n_ehvi_candidates,)
weights_below: Callable[[int], np.ndarray]
weights_below = lambda _: np.asarray( # NOQA
study._storage.get_trial(trial._trial_id).system_attrs[_WEIGHTS_BELOW_KEY],
dtype=float,
)
parzen_estimator_parameters_below = _ParzenEstimatorParameters(
self._parzen_estimator_parameters.consider_prior,
self._parzen_estimator_parameters.prior_weight,
self._parzen_estimator_parameters.consider_magic_clip,
self._parzen_estimator_parameters.consider_endpoints,
weights_below,
)
parzen_estimator_below = _ParzenEstimator(
mus=below, low=low, high=high, parameters=parzen_estimator_parameters_below
)
samples_below = self._sample_from_gmm(
parzen_estimator=parzen_estimator_below,
low=low,
high=high,
q=q,
size=size,
)
log_likelihoods_below = self._gmm_log_pdf(
samples=samples_below,
parzen_estimator=parzen_estimator_below,
low=low,
high=high,
q=q,
)
weights_above = self._weights
parzen_estimator_parameters_above = _ParzenEstimatorParameters(
self._parzen_estimator_parameters.consider_prior,
self._parzen_estimator_parameters.prior_weight,
self._parzen_estimator_parameters.consider_magic_clip,
self._parzen_estimator_parameters.consider_endpoints,
weights_above,
)
parzen_estimator_above = _ParzenEstimator(
mus=above, low=low, high=high, parameters=parzen_estimator_parameters_above
)
log_likelihoods_above = self._gmm_log_pdf(
samples=samples_below,
parzen_estimator=parzen_estimator_above,
low=low,
high=high,
q=q,
)
ret = float(
TPESampler._compare(
samples=samples_below, log_l=log_likelihoods_below, log_g=log_likelihoods_above
)[0]
)
return math.exp(ret) if is_log else ret