Skip to content
Break down ML model predictions with variable attribution (LIME, SHAP, BreakDown)
R Other
  1. R 98.5%
  2. Other 1.5%
Branch: master
Clone or download
Latest commit bdc33e6 Sep 7, 2019

Model Agnostic Local Attributions

Build Status Coverage Status CRAN_Status_Badge Total Downloads


The iBreakDown 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 the breakDown package. It is faster (complexity O(p) instead of O(p^2)). It supports interactions and interactive explainers with D3.js plots.

It is a part of DrWhy.AI collection of tools for XAI.


# the easiest way to get iBreakDown is to install it from CRAN:

# Or the the development version from GitHub:
# install.packages("devtools")

Learn more

Find lots of R examples at iBreakDown website:

Methodology behind the iBreakDown package is described in the arxiv paper and VEEDD book.

This version also works with D3! see an example and demo plotD3


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

You can’t perform that action at this time.