shapFlex
shapFlex copied to clipboard
An R package for computing asymmetric Shapley values to assess causality in any trained machine learning model
Hi, I've tried to extract the pairwise shap interaction returned by the shap.scatter plot. I've noticed that shap_interaction(X_i, X_j) != shap_interaction(X_j, X_i), Thus if we immagine a MxM interaction matrix,...
At present, the package only works with single-outcome regression models. This isn't stated anywhere and, well, the logo seems to imply otherwise. Fix.
I dumped the `adult_dataset` that you mention in ReadMe into a csv and run a [RandomForestClassifier](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html) with almost same settings and calculate shap values from the [SHAP](https://github.com/slundberg/shap) package library in...
Within setup.py, the opening of README.md requires utf-8 encoding. Otherwise installation fails.