Is there a way to show explain_local without resetting the index?

[hexgnu]

Hey again,

I'm looking at some explain_local for this model I'm working on and wondering if there's a way to get it to show without resetting the index. Mainly because the indexes are important.

ebm_local = ebm.explain_local(X, y) # These have indexes that mean something

show(ebm_local) # Shows 0,1,2,3,4 implying the indexes were reset

Thanks!

[interpret-ml]

Hi @hexgnu,

Good idea! We reset the index right now for engineering simplicity, but we can look into preserving this in the future. Nice to hear that this would be useful for you!

-InterpretML Team

[gianlucahmd]

+1! The use case is pretty simple: I'm using interpretML to classify some datapoints, interpret the decisions of the model and take business decisions based on that. Since it resets the index I struggle going back to check with datapoint a certain prediction was for.

Have you done any progress on this?