explainability

Explainability utilities for OpenSTEF.

Tools for feature importance, attribution and model interpretation.

Submodules

openstef_models.explainability.mixins	Mixins for adding explainability features to forecasting models.
openstef_models.explainability.plotters	Visualization tools for model explainability.

Classes

ContributionsMixin()	Mixin for forecasters that can explain per-sample feature contributions.
ContributionsPlotter()	Visualizations for per-timestep feature contributions.
ExplainableForecaster()	Mixin for forecasters that can explain feature importance.
FeatureImportancePlotter(**data)	Creates treemap visualizations of feature importance scores.