gemseo_mlearning / adaptive

gemseo_mlearning.adaptive.distributions

• kriging_distribution
• regressor_distribution

The distributions of machine learning algorithms.

gemseo_mlearning.adaptive.distributions.get_regressor_distribution(regression_algorithm, use_bootstrap=True, use_loo=False, size=None)

Return the distribution of a regression algorithm.

Parameters:

• regression_algorithm (MLRegressionAlgo) – The regression algorithm.

• bootstrap – Whether to use bootstrap for resampling. If False, use cross-validation.

• use_loo (bool) –

  Whether to use leave-one-out resampling when use_bootstrap is False. If False, use parameterized cross-validation.

  By default it is set to False.

• size (int | None) – The size of the resampling set, i.e. the number of times the regression algorithm is rebuilt. If None, use the default size for bootstrap (MLAlgoSampler.N_BOOTSTRAP) and cross-validation (MLAlgoSampler.N_FOLDS). This argument does not apply to leave-one-out.

• use_bootstrap (bool) –

  By default it is set to True.

Returns:

The distribution of the regression algorithm.

Return type:

MLRegressorDistribution