harrysouthworth/kohonen: Self-organizing Maps for Data Classification

Self-Organizing Maps are cluster analysis, they are searching for groups (clusters) in the data, in such a way that objects belonging to the same cluster are quite similar, whereas objects in different clusters are dissimilar. They are also providing topological informations on the data ; the clusters are organised so that relative distances between groups on the grid reflect dissimilarities between groups in the data. Self-Organizing Maps have been used in several fields: voice recognition, image processing, process control, text analysis, genomic analysis... The package provide various tools for SOM: creation and learning, summary, print methods, groups extraction, plot methods, etc. Numerical and factorial variables are allowed in the data.

Getting started

Package details

AuthorDavid Gohel
MaintainerStephen Kaluzny <spk@insightful.com>
LicenseGNU GENERAL PUBLIC LICENSE Version 2
Version1.0.1
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
install.packages("remotes")
remotes::install_github("harrysouthworth/kohonen")
harrysouthworth/kohonen documentation built on May 17, 2019, 3:03 p.m.