evaluate_design

obsidian.experiment.advanced_design.evaluate_design(design, continuous_keys, categorical_keys, subparam_mapping, metrics_to_optimize)

Evaluate a design using the specified quality metrics.

Parameters:

• design – Design DataFrame to evaluate.

• continuous_keys – List of continuous parameter column names.

• categorical_keys – List of categorical column names.

• subparam_mapping – Dict mapping categorical variables to their subparameters (e.g. {'buffer': 'pH', 'sugar': '[Sugar] (%)'}).

• metrics_to_optimize – List of metric names to compute. Valid values are the entries of DEFAULT_METRICS ('D-optimality', 'A-optimality', 'Condition Number', 'Pairwise Distance CV', 'Max Continuous Corr', 'Max Categorical Corr', 'Max Mixed Corr').

Returns:

Computed metric values for the requested metrics only.

Return type:

dict