Skip to content

Callback

sklearn_optuna.optuna.Callback

Bases: BaseClassWrapper

Wrapper for Optuna callback classes invoked during optimization.

Parameters

Name Type Description Default
callback type

Optuna callback class to instantiate. The class must implement __call__(study, trial) to be invoked at the end of each trial.

 required
**params dict

Parameters to pass to the callback constructor.

 {}

See Also

sklearn_optuna.search.OptunaSearchCV : The main search class that uses callbacks. sklearn_optuna.optuna.Sampler : Wrapper for Optuna samplers.

Examples

>>> from optuna.study import MaxTrialsCallback
>>> callback = Callback(callback=MaxTrialsCallback, n_trials=100)

Source Code

View on GitHub

Show/Hide source 
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
class Callback(BaseClassWrapper):
    """Wrapper for Optuna callback classes invoked during optimization.

    Parameters
    ----------
    callback : type
        Optuna callback class to instantiate. The class must implement
        ``__call__(study, trial)`` to be invoked at the end of each trial.

    **params : dict
        Parameters to pass to the callback constructor.

    See Also
    --------
    sklearn_optuna.search.OptunaSearchCV : The main search class that uses callbacks.
    sklearn_optuna.optuna.Sampler : Wrapper for Optuna samplers.

    Examples
    --------
    >>> from optuna.study import MaxTrialsCallback
    >>> callback = Callback(callback=MaxTrialsCallback, n_trials=100)

    """

    _estimator_name = "callback"
    _estimator_base_class = object

    def __init__(self, callback: type, **params: dict[str, object]) -> None:
        if not isinstance(callback, type):
            raise TypeError(f"callback must be a class, got {type(callback)}")
        BaseClassWrapper.__init__(self, callback=callback, **params)

    def __call__(self, study: optuna.study.Study, trial: optuna.trial.FrozenTrial) -> None:
        """Invoke the callback by instantiating it and calling it.

        Parameters
        ----------
        study : optuna.study.Study
            The study object.

        trial : optuna.trial.FrozenTrial
            The completed trial.

        """
        return self.instance_(study, trial)

Methods

__call__(study, trial)

Invoke the callback by instantiating it and calling it.

Parameters
Name Type Description Default
study Study

The study object.

 required
trial FrozenTrial

The completed trial.

 required
Source Code

View on GitHub

Show/Hide source 
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
def __call__(self, study: optuna.study.Study, trial: optuna.trial.FrozenTrial) -> None:
    """Invoke the callback by instantiating it and calling it.

    Parameters
    ----------
    study : optuna.study.Study
        The study object.

    trial : optuna.trial.FrozenTrial
        The completed trial.

    """
    return self.instance_(study, trial)

Tutorials

The following example notebooks use this component:

  • How to Stop Optimization Early with Callbacks

    Stop unneeded work early by adding Optuna callbacks to your search.

    View · Open in marimo