SklearnModelAdapter.score#

SklearnModelAdapter.score(X, y, **kwargs)[source]#

Return per-output \(R^2\) scores from the sklearn model.

Parameters:

  • X (Any) – Predictor matrix.

  • y (Any) – Observed outcomes.

  • **kwargs (Any) – Additional keyword arguments forwarded to sklearn.metrics.r2_score(), such as sample_weight. These are not forwarded to the underlying estimator’s score method. multioutput is fixed to "raw_values" so each treated unit receives its own unit_{i}_r2 entry.

Returns:

One unit_{i}_r2 entry per output. Point estimates carry no dispersion entries.

Return type:

pd.Series