Integrating JMP PRO Python Model (NN) with explainable AI SHAP values

Sizemokj — Sat, 10 Jun 2023 20:47:46 GMT

Has anyone successfully connected an integration process in python to take a JMP PRO generated model ( NN ) for example and attempted to run SHAP values on the model?

Any ideas or python code to help get across the line would be greatly appreciated.

Here is some great documentation on SHAP
https://shap.readthedocs.io/en/latest/example_notebooks/overviews/An%20introduction%20to%20explainable%20AI%20with%20Shapley%20values.html

SHAP is model agnostic, I am just trying to figure out the specific code to incorporate JMP Generated models into

shap.KernelExplainer

function :more here https://shap.readthedocs.io/en/latest/example_notebooks/tabular_examples/model_agnostic/Simple%20Kernel%20SHAP.html

SAS VIYA has it already integrated in the software, so I am optimistic we can figure out a solution to get it incorporated into JMP at some point as an add-in.

https://www.sas.com/content/dam/SAS/support/en/sas-global-forum-proceedings/2020/4502-2020.pdf

Thank you!

Re: Integrating JMP PRO Python Model (NN) with explainable AI SHAP values

nick_shelton — Wed, 29 Mar 2023 14:41:13 GMT

Hi @Sizemokj Beginning in JMP Pro v.17, Shapley values are available as an option in the prediction profiler.

https://www.jmp.com/support/help/en/17.0/#page/jmp/prediction-profiler-options.shtml

topic Re: Integrating JMP PRO Python Model (NN) with explainable AI SHAP values in Discussions

Integrating JMP PRO Python Model (NN) with explainable AI SHAP values

Re: Integrating JMP PRO Python Model (NN) with explainable AI SHAP values