interpretml / slicer Goto Github PK

This is a bigger issue centered on how to do Alias objects with sparse representations, but right now SHAP explanations often need per-row feature names and output names, but since Alias does not support this we use Obj instead and manually handle feature name or output name lookup. This issue is here to document this for future work.

the title says it all. Right now we need to convert things to lists...