CORElearn: Classification, Regression and Feature Evaluation

The package is a port of stand-alone C++ software to R. It contains several machine learning model learning techniques in classification and regression, for example classification and regression trees with optional constructive induction and models in the leafs, random forests, kNN, naive Bayes, and locally weighted regression. It is especially strong in feature evaluation where it contains several variants of Relief algorithm and many impurity based attribute evaluation functions, e.g., Gini, information gain, MDL, DKM. Its additional strength is OrdEval algorithm and its visualization used for evaluation of data sets with ordinal features and class. Several algorithms support parallel multithreaded execution via OpenMP. The top-level documentation is reachable through ?CORElearn.

Version: 0.9.45
Imports: cluster, rpart, stats
Suggests: lattice, MASS, rpart.plot
Published: 2015-01-27
Author: Marko Robnik-Sikonja and Petr Savicky with contributions from John Adeyanju Alao
Maintainer: "Marko Robnik-Sikonja" <marko.robnik at>
License: GPL-3
NeedsCompilation: yes
Materials: ChangeLog
In views: MachineLearning
CRAN checks: CORElearn results


Reference manual: CORElearn.pdf
Package source: CORElearn_0.9.45.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X Snow Leopard binaries: r-release: CORElearn_0.9.45.tgz, r-oldrel: CORElearn_0.9.45.tgz
OS X Mavericks binaries: r-release: CORElearn_0.9.45.tgz
Old sources: CORElearn archive

Reverse dependencies:

Reverse imports: AppliedPredictiveModeling, semiArtificial