Model Agnostic Local Attributions

Overview

TheiBreakDown package is a model agnostic tool for explanation of predictions from black boxes ML models. Break Down Table shows contributions of every variable to a final prediction. Break Down Plot presents variable contributions in a concise graphical way. SHAP (Shapley Additive Attributions) values are calculated as average from random Break Down profiles. This package works for binary classifiers as well as regression models.

iBreakDown is a successor of thebreakDown package. It is faster (complexityO(p) instead ofO(p^2)). It supports variable interactions and interactive explanations with D3.js visualizations. It is imported and used to compute model explanations in multiple packages e.g. DALEX,modelStudio,arenar.

Methodology behind theiBreakDown package is described in thearXiv paper andExplanatory Model Analysis book. It is a part ofDrWhy.AI universe.

Installation

# the easiest way to get iBreakDown is to install it from CRAN:install.packages("iBreakDown")# Or the the development version from GitHub:# install.packages("devtools")devtools::install_github("ModelOriented/iBreakDown")

Learn more

Find lots of examples at the website:https://ModelOriented.github.io/iBreakDown.

This version also works withD3:see an example anddemo.

plotD3

Acknowledgments

Work on this package was financially supported by theNCN Opus grant 2016/21/B/ST6/02176.