evtree: Evolutionary Learning of Globally Optimal Trees

Commonly used classification and regression tree methods like the CART algorithm are recursive partitioning methods that build the model in a forward stepwise search. Although this approach is known to be an efficient heuristic, the results of recursive tree methods are only locally optimal, as splits are chosen to maximize homogeneity at the next step only. An alternative way to search over the parameter space of trees is to use global optimization methods like evolutionary algorithms. The 'evtree' package implements an evolutionary algorithm for learning globally optimal classification and regression trees in R. CPU and memory-intensive tasks are fully computed in C++ while the 'partykit' package is leveraged to represent the resulting trees in R, providing unified infrastructure for summaries, visualizations, and predictions.

Install the latest version of this package by entering the following in R:
install.packages("evtree")
AuthorThomas Grubinger [aut, cre], Achim Zeileis [aut], Karl-Peter Pfeiffer [aut]
Date of publication2017-04-06 21:46:26 UTC
MaintainerThomas Grubinger <Thomas.Grubinger@scch.at>
LicenseGPL-2 | GPL-3
Version1.0-5

View on CRAN

Files

inst
inst/CITATION
inst/doc
inst/doc/evtree.R
inst/doc/evtree.pdf
inst/doc/evtree.Rnw
tests
tests/Examples
tests/Examples/evtree-Ex.Rout.save
src
src/tree.cpp
src/variable.cpp
src/container.h
src/node.h
src/node.cpp
src/tree.h
src/variable.h
src/container.cpp
NAMESPACE
NEWS
data
data/BBBClub.rda
data/StatlogHeart.RData
data/MAGICGammaTelescope.RData
data/ContraceptiveChoice.RData
data/GermanCredit.RData
R
R/evtree.R R/evtree.control.R R/evtree-internal.R
vignettes
vignettes/results_parameter
vignettes/results_parameter/spam_parameter.RData
vignettes/results_parameter/heart_parameter.RData
vignettes/results_parameter/chessboard44_5_parameter.RData
vignettes/results_parameter/credit_parameter.RData
vignettes/evtree.Rout.save
vignettes/.install_extras
vignettes/results
vignettes/results/dna.RData
vignettes/results/vowel.RData
vignettes/results/servo.RData
vignettes/results/mel0101.RData
vignettes/results/credit.RData
vignettes/results/chessboard44_0.RData
vignettes/results/heart.RData
vignettes/results/bostonhousing.RData
vignettes/results/glass.RData
vignettes/results/contraceptive.RData
vignettes/results/spam.RData
vignettes/results/hdg0202.RData
vignettes/results/pima.RData
vignettes/results/magicgamma.RData
vignettes/results/chessboard44_10.RData
vignettes/results/musk.RData
vignettes/results/hdg0502.RData
vignettes/results/chessboard44_5.RData
vignettes/results/ionosphere.RData
vignettes/results/breastcancer.RData
vignettes/results_j48
vignettes/results_j48/ionosphere_j48.RData
vignettes/results_j48/glass_j48.RData
vignettes/results_j48/pima_j48.RData
vignettes/results_j48/mg3_
vignettes/results_j48/mg4_
vignettes/results_j48/dna_j48.RData
vignettes/results_j48/chessboard44_5_j48.RData
vignettes/results_j48/mg5_
vignettes/results_j48/chessboard44_0_j48.RData
vignettes/results_j48/musk_j48.RData
vignettes/results_j48/credit_j48.RData
vignettes/results_j48/breastcancer_j48.RData
vignettes/results_j48/chessboard44_10_j48.RData
vignettes/results_j48/contraceptive_j48.RData
vignettes/results_j48/magicgamma_j48.RData
vignettes/results_j48/mg2_
vignettes/results_j48/heart_j48.RData
vignettes/results_j48/mg1_
vignettes/results_j48/spam_j48.RData
vignettes/results_j48/vowel_j48.RData
vignettes/evtree.bib
vignettes/evtree.Rnw
MD5
build
build/vignette.rds
DESCRIPTION
man
man/ContraceptiveChoice.Rd man/evtree.Rd man/GermanCredit.Rd man/evtree.control.Rd man/MAGICGammaTelescope.Rd man/BBBClub.Rd man/StatlogHeart.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.