Interactive MLI Composite View

KCH Workflows
1

This worflow will show how to use the interactive views of JavaScript nodes to visualize in a single Composite View a number of Machine Learning Interpretability (MLI) techniques: SHAP explanations, Partial Dependence, Individual Conditional Expectation (ICE) curves and Surrogate Decision Tree.

This is a companion discussion topic for the original entry at https://kni.me/w/AIM_-dYRkW3Qq7UO
2

Hey everyone,
this post is able to create an interactive view to explore Shapley Values and ICE curves.
You can see the final result in this video on Twitter:

Cheers
Paolo