timbR: Tree interpretation methods based on ranger

Björn-Hergen Laabs

Introduction

timbR is a collection of methods for the interpretation of random forests trained by ranger.

In version 1.0 most representaive trees can be selected based on four different tree based distance measures.

Installation

R version

To install the timbR R package, run

install.packaged("devtools")
library(devtools)
devtools::install_github("imbs-hl/timbR")

If you find any bugs, or if you experience any crashes, please report to us.

Please cite our paper if you use ranger.

References

• Laabs, B.-H., Westenberger, A., König, I. R. (2020) Identification of representative trees in random forests based on a new tree-based distance measure. Unpublished
• Bannerjee, M., Ding, Y., Noone, A.-M. (2012) Identifying representative trees from ensembles. Stat in Med 31:1601-16.