Skip to content
Very experimental version of the iBreakDown package.
Branch: master
Clone or download
Latest commit 36389d8 Apr 1, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
R
binder
docs
images updated README and pkgdown site with D3 examples Jan 2, 2019
inst
jupyter-notebooks breakDown2 has changed to iBreakDwon Feb 23, 2019
man
misc
tests higher coverage for tests Mar 16, 2019
vignettes
.Rbuildignore
.gitignore refactoring of break down plots Oct 21, 2018
.travis.yml
DESCRIPTION
NAMESPACE
NEWS.md
README.md Update README.md Mar 28, 2019
_pkgdown.yml
breakDown2.Rproj refactoring of break down plots Oct 21, 2018

README.md

CRAN_Status_Badge Total Downloads Build Status Coverage Status Binder

iBreakDown: Model Agnostic Explainers for Individual Predictions

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. 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 fo XAI.

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

Methodology behind the iBreakDown package is described in the [arxiv paper](add link) and VEEDD book.

This version works also with D3! see an example. plotD3

Installation

Install from GitHub

devtools::install_github("ModelOriented/iBreakDown")
You can’t perform that action at this time.