pre: Prediction Rule Ensembles

Derives prediction rule ensembles (PREs). Largely follows the procedure for deriving PREs as described in Friedman & Popescu (2008; <doi:10.1214/07-AOAS148>), with several adjustments and improvements. The main function pre() derives a prediction rule ensemble. Functions print(), plot(), coef() and importance() can be used to inspect the generated ensemble. Function predict() generates predicted values. Functions singeplot() and pairplot() depict dependence of the output on specified predictor variables. Function cvpre() performs full cross validation of a pre to calculate the expected prediction error. Functions interact() and bsnullinteract() can be used to assess interaction effects of predictor variables.

Version: 0.2
Depends: R (≥ 3.1.0), partykit, glmnet, MatrixModels, Formula, methods, graphics
Suggests: akima, grid, foreach
Published: 2017-04-26
Author: Marjolein Fokkema [aut, cre]
Maintainer: Marjolein Fokkema <m.fokkema at>
License: GPL-2 | GPL-3
NeedsCompilation: no
Materials: README NEWS
CRAN checks: pre results


Reference manual: pre.pdf
Package source: pre_0.2.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X El Capitan binaries: r-release: pre_0.2.tgz
OS X Mavericks binaries: r-oldrel: pre_0.2.tgz
Old sources: pre archive


Please use the canonical form to link to this page.