ECoL: Complexity Measures for Supervised Problems

Provides measures to characterize the complexity of classification and regression problems based on aspects that quantify the linearity of the data, the presence of informative feature, the sparsity and dimensionality of the datasets. This package provides bug fixes, generalizations and implementations of many state of the art measures. The measures are described in the papers: Ho and Basu (2002) <doi:10.1109/34.990132> and Lorena et al. (2018) <doi:10.1007/s10994-017-5681-1>.

Version: 0.2.0
Imports: cluster, e1071, FNN, igraph, MASS
Published: 2019-02-26
Author: Luis Garcia [aut, cre], Ana Lorena [aut, ctb]
Maintainer: Luis Garcia <lpfgarcia at icmc.usp.br>
BugReports: https://github.com/lpfgarcia/ECoL/issues
License: MIT + file LICENSE
URL: https://github.com/lpfgarcia/ECoL/
NeedsCompilation: no
Materials: README
CRAN checks: ECoL results

Downloads:

Reference manual: ECoL.pdf
Package source: ECoL_0.2.0.tar.gz
Windows binaries: r-devel: ECoL_0.2.0.zip, r-release: ECoL_0.2.0.zip, r-oldrel: ECoL_0.2.0.zip
OS X binaries: r-release: ECoL_0.2.0.tgz, r-oldrel: ECoL_0.2.0.tgz
Old sources: ECoL archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=ECoL to link to this page.