summary_table#

scio.eval.summary_table(evals, *, scores_and_layers=None, keep=None, oods_title=None, metrics=None, baseline=None)[source]#

Print scores evaluation results summary in rich table.

Parameters:

  • evals (NDArray[np.floating]) – Result from a compute_metrics() call. Shape is (n_scores, n_ood_sets, n_metrics).

  • scores_and_layers (Iterable[ScoreClassifAndLayers | str], optional) – See fit_scores() for ScoreClassifAndLayers elements. Used only for row headers.

  • keep (ArrayLike, optional) –

    If provided, the table is restricted to the corresponding scores. In this case, it must be a \(1\)D array of integer indexes, or a boolean mask. Using integer indexes allows arbitrary reordering of the scores.

    Note that if baseline is provided, the advanced highlighting is applied before the keep restriction. Use the output of a topk_evals() call to show only the best performing scores.

  • oods_title (Iterable[str], optional) – See compute_confidence(). Used only for column headers.

  • metrics (Iterable[BaseDiscriminativePower], optional) – Metrics used to compute evals in compute_metrics(). For highlight purposes, elements should take values in \([0, 1]\) and be to maximize. Used only for table title.

  • baseline (int, optional) – The index of the baseline score, for advanced highlighting.

On this page