kdml: Kernel Distance Metric Learning for Mixed-Type Data

Distance metrics for mixed-type data consisting of continuous, nominal, and ordinal variables. This methodology uses additive and product kernels to calculate similarity functions and metrics, and selects variables relevant to the underlying distance through bandwidth selection via maximum similarity cross-validation. These methods can be used in any distance-based algorithm, such as distance-based clustering. For further details, we refer the reader to Ghashti and Thompson (2024) <<doi:10.48550/arXiv.2306.01890>> for dkps() methodology, and Ghashti (2024) <doi:10.14288/1.0443975> for dkss() methodology.

Version:	1.1.0
Depends:	R (≥ 3.5.0), np
Imports:	MASS, markdown
Suggests:	knitr, rmarkdown
Published:	2024-09-21
DOI:	10.32614/CRAN.package.kdml
Author:	John R. J. Thompson [aut, cre], Jesse S. Ghashti [aut]
Maintainer:	John R. J. Thompson <john.thompson at ubc.ca>
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation:	no
Materials:	README
CRAN checks:	kdml results

Documentation:

Reference manual:	kdml.pdf
Vignettes:	kdml package (source, R code)

Downloads:

Package source:	kdml_1.1.0.tar.gz
Windows binaries:	r-devel: kdml_1.1.0.zip, r-release: kdml_1.1.0.zip, r-oldrel: kdml_1.1.0.zip
macOS binaries:	r-release (arm64): kdml_1.1.0.tgz, r-oldrel (arm64): kdml_1.1.0.tgz, r-release (x86_64): kdml_1.1.0.tgz, r-oldrel (x86_64): kdml_1.1.0.tgz
Old sources:	kdml archive

Linking:

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