AdaBoost Support

[DNCoelho]

Hello,

First of all, thank you very much for developing this amazing tool.

I just wanted to ask if there was any plans to add support to AdaBoost as the title implies.
Or if support is not planned and this is not a too great pain in the ass a quick explanation of how one could go about adding it.

Many thanks in advance.

[slundberg]

Thanks! I don't have plans to add support, but it shouldn't be too hard. TreeExplainer creates a TreeEnsemble object from whatever model type we are trying to explain, and then works with that downstream. So all you would need to do is and add another if statement in the TreeEnsemble constructor similar to the one for gradient boosting: https://github.com/slundberg/shap/blob/4bd41ea9592475370905eadd47f6b4879eeebf49/shap/explainers/tree.py#L433-L443

If you have specific questions let me know and I'll be happy to help.

[DNCoelho]

Tank you for the quick response!

[maxencebrochard]

Hi @DNCoelho,

Did you manage to implement Adaboost? If so, would be very interested :)

Thanks

[hdnh2006]

I left an answer in this link that surely could help.

[slundberg]

@hdnh2006 if you added support for AdaBoost to your version please consider a PR :)