Description
Model Wrappers for Tree-Based Models.
Description
Bindings for additional tree-based model engines for use with the 'parsnip' package. Models include gradient boosted decision trees with 'LightGBM' (Ke et al, 2017.), conditional inference trees and conditional random forests with 'partykit' (Hothorn and Zeileis, 2015. and Hothorn et al, 2006. <doi:10.1198/106186006X133933>), and accelerated oblique random forests with 'aorsf' (Jaeger et al, 2022 <doi:10.5281/zenodo.7116854>).
README.md
bonsai 
bonsai provides bindings for additional tree-based model engines for use with the parsnip package.
This package is based off of the work done in the treesnip repository by Athos Damiani, Daniel Falbel, and Roel Hogervorst. bonsai is the official CRAN version of the package; new development will reside here.
Installation
You can install the most recent official release of bonsai with:
install.packages("bonsai")
You can install the development version of bonsai from GitHub with:
# install.packages("pak")
pak::pak("tidymodels/bonsai")
Available Engines
The bonsai package provides additional engines for the models in the following table:
| model | engine | mode |
|---|---|---|
| boost_tree | lightgbm | regression |
| boost_tree | lightgbm | classification |
| decision_tree | partykit | regression |
| decision_tree | partykit | classification |
| rand_forest | partykit | regression |
| rand_forest | partykit | classification |
| rand_forest | aorsf | classification |
| rand_forest | aorsf | regression |
Code of Conduct
Please note that the bonsai project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.