optuna_dashboard.preferential.create_study
- optuna_dashboard.preferential.create_study(*, n_generate, storage=None, sampler=None, study_name=None, load_if_exists=False)
Like
optuna.create_study()
, but for preferential optimization.Example
import optuna from optuna_dashboard.preferential import create_study study = create_study() trial = study.ask()
- Parameters:
n_generate (int) – The number of active trials to keep.
should_generate()
returnsTrue
if the number of trials not reported bad and not skipped are less thann_generate
.storage (str | BaseStorage | None) – Database URL. If this argument is set to None, in-memory storage is used, and the
PreferentialStudy
will not be persistent.sampler (BaseSampler | None) – A sampler object that implements background algorithm for value suggestion. If
None
is specified,PreferentialGPSampler
is used. Please note that most Optuna samplers does not work efficiently for preferential optimization.study_name (str | None) – Study’s name. If this argument is set to None, a unique name is generated automatically.
load_if_exists (bool) – Flag to control the behavior to handle a conflict of study names. In the case where a study named
study_name
already exists in thestorage
, aDuplicatedStudyError
is raised ifload_if_exists
is set toFalse
. Otherwise, the creation of the study is skipped, and the existing one is returned.
- Returns:
A
PreferentialStudy
object.- Return type:
Note
Preferential optimization is an experimental feature (introduced in v0.13.0). The interface may change in newer versions without prior notice.