bkutlu / iml

iml: interpretable machine learning R package

iml: interpretable machine learning

iml is an R package that interprets the behaviour and explains predictions of machine learning models. It implements model-agnostic interpretability methods - meaning they can be used with any machine learning model.

Currently implemented:

• Feature importance
• Partial dependence plots
• Individual conditional expectation plots (ICE)
• Tree surrogate
• LocalModel: Local Interpretable Model-agnostic Explanations
• Shapley value for explaining single predictions

Read more about the methods in the Interpretable Machine Learning book

Tutorial

Start an interactive notebook tutorial by clicking on the badge:

Installation

The package can be installed directly from CRAN and the develoopment version from github:

# Stable version
install.packages("iml")
# Development version
devtools::install_github("christophM/iml")

News

Changes of the packages can be accessed in the NEWS file shipped with the package.

Examples

First we train a randomForest to predict the Boston median housing value. How does lstat influence the prediction individually and on average? (Partial dependence plot and ICE)

library("iml")
library("randomForest")
data("Boston", package  = "MASS")
rf = randomForest(medv ~ ., data = Boston, ntree = 50)
X =  Boston[which(names(Boston) != "medv")]
model = Predictor$new(rf, data = X, y = Boston$medv)
pdp.obj = Partial$new(model, feature = "lstat")
pdp.obj$plot()

Python Implementation

Referring to https://github.com/datascienceinc/Skater

Funding

This work is funded by the Bavarian State Ministry of Education, Science and the Arts in the framework of the Centre Digitisation.Bavaria (ZD.B)