INNER CODE UNIT · Python

tune_pars_TPE_algorithm_optuna

fabsig/GPBoost · python-package/gpboost/engine.py:1249

def tune_pars_TPE_algorithm_optuna(search_space, n_trials, X, y, gp_model = None,
                                max_num_boost_round=1000, early_stopping_rounds=None,
                                metric=None, folds=None, nfold=5,
                                cv_seed=0, tpe_seed=0,
                                params=None, verbose_train=0, verbose_eval=1,
                                use_gp_model_for_validation=True, train_gp_model_cov_pars=True, feval=None,
                                categorical_feature='auto'):
    """Function for choosing tuning parameters using the TPE (Tree-structured Parzen Estimator) algorithm implemented in optuna

    Parameters
    ----------
    search_space : dict
        The range for every parameter over which a search is done.
        The format for every entry of the dict must be 
        'parameter_name': [lower, upper].
        See https://github.com/fabsig/GPBoost/blob/master/docs/Main_parameters.rst#tuning-parameters--hyperparameters-for-the-tree-boosting-part
    n_trials: int
        The number of trials for the TPESampler.

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…