plaid.post.metrics
==================

.. py:module:: plaid.post.metrics

.. autoapi-nested-parse::

   Utility functions for computing and printing metrics for regression problems in PLAID.



Functions
---------

.. autoapisummary::

   plaid.post.metrics.compute_rRMSE_RMSE
   plaid.post.metrics.compute_R2
   plaid.post.metrics.prepare_metrics_for_split
   plaid.post.metrics.pretty_metrics
   plaid.post.metrics.compute_metrics


Module Contents
---------------

.. py:function:: compute_rRMSE_RMSE(metrics: dict, rel_SE_out_scalars: dict, abs_SE_out_scalars: dict, problem_split: dict, out_scalars_names: list[str]) -> None

   Compute and print the relative Root Mean Square Error (rRMSE) for scalar outputs.

   :param metrics: Dictionary to store the computed metrics.
   :type metrics: dict
   :param rel_SE_out_scalars: Dictionary containing relative squared errors for scalar outputs.
   :type rel_SE_out_scalars: dict
   :param abs_SE_out_scalars: Dictionary containing absolute squared errors for scalar outputs.
   :type abs_SE_out_scalars: dict
   :param problem_split: Dictionary specifying how the problem is split.
   :type problem_split: dict
   :param out_scalars_names: List of names of scalar outputs.
   :type out_scalars_names: list[str]


.. py:function:: compute_R2(metrics: dict, r2_out_scalars: dict, problem_split: dict, out_scalars_names: list[str]) -> None

   Compute and print the R-squared (R2) score for scalar outputs.

   :param metrics: Dictionary to store the computed metrics.
   :type metrics: dict
   :param r2_out_scalars: Dictionary containing R2 scores for scalar outputs.
   :type r2_out_scalars: dict
   :param problem_split: Dictionary specifying how the problem is split.
   :type problem_split: dict
   :param out_scalars_names: List of names of scalar outputs.
   :type out_scalars_names: list[str]


.. py:function:: prepare_metrics_for_split(ref_out_specific_scalars: numpy.ndarray, pred_out_specific_scalars: numpy.ndarray, split_indices: list[int], rel_SE_out_specific_scalars: numpy.ndarray, abs_SE_out_specific_scalars: numpy.ndarray) -> float

   Prepare metrics for a specific split and compute the R-squared (R2) score.

   :param ref_out_specific_scalars: Array of reference scalar outputs.
   :type ref_out_specific_scalars: np.ndarray
   :param pred_out_specific_scalars: Array of predicted scalar outputs.
   :type pred_out_specific_scalars: np.ndarray
   :param split_indices: List of indices specifying the split.
   :type split_indices: list[int]
   :param rel_SE_out_specific_scalars: Array to store relative squared errors for scalar outputs.
   :type rel_SE_out_specific_scalars: np.ndarray
   :param abs_SE_out_specific_scalars: Array to store absolute squared errors for scalar outputs.
   :type abs_SE_out_specific_scalars: np.ndarray

   :returns: R-squared (R2) score for the specific split.
   :rtype: float


.. py:function:: pretty_metrics(metrics: dict) -> None

   Prints metrics information in a readable format (pretty print).

   :param metrics: The metrics dictionary to print.
   :type metrics: dict


.. py:function:: compute_metrics(ref_dataset: Union[plaid.Dataset, str, pathlib.Path], pred_dataset: Union[plaid.Dataset, str, pathlib.Path], problem: Union[plaid.ProblemDefinition, str, pathlib.Path], save_file_name: str = 'test_metrics', verbose: bool = False) -> None

   Compute and save evaluation metrics for a given regression problem.

   :param ref_dataset: Reference dataset or path to a reference dataset.
   :type ref_dataset: Dataset | str | Path
   :param pred_dataset: Predicted dataset or path to a predicted dataset.
   :type pred_dataset: Dataset | str | Path
   :param problem: Problem definition or path to a problem definition.
   :type problem: ProblemDefinition | str | Path
   :param save_file_name: Name of the file to save the metrics. Defaults to "test_metrics".
   :type save_file_name: str, optional
   :param verbose: If True, print detailed information during computation.
   :type verbose: bool, optional