Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How is the method here related to SHAP? #19

Open
haozhenWu opened this issue Feb 28, 2018 · 2 comments
Open

How is the method here related to SHAP? #19

haozhenWu opened this issue Feb 28, 2018 · 2 comments

Comments

@haozhenWu
Copy link

Hi,

I am wondering how are the methods related to SHAP and Individual Conditional Expectation Plot?
Scott M. Lundberg, Su-In Lee, "A Unified Approach to Interpreting Model Predictions", NIPS Proceedings 2017
https://cran.r-project.org/web/packages/ICEbox/ICEbox.pdf

Latest XGBoost also has native support for SHAP:
https://github.com/dmlc/xgboost/blob/master/R-package/R/xgb.plot.shap.R

Thank you,
Haozhen

@lawwu
Copy link

lawwu commented Jul 13, 2018

@haozhenWu thank you for pointing me to SHAP. Looks like it is nicely implemented in python but not yet in R: https://github.com/slundberg/shap

@RossKen
Copy link

RossKen commented Aug 21, 2018

I would also be interested in how this works in comparison to SHAP. More generally, I think it would be really useful to have some documentation that outlines what exactly the explainer is doing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants