prclust: Penalized Regression-Based Clustering Method

Share:

Clustering is unsupervised and exploratory in nature. Yet, it can be performed through penalized regression with grouping pursuit. In this package, we provide two algorithms for fitting the penalized regression-based clustering (PRclust). One algorithm is based on quadratic penalty and difference convex method. Another algorithm is based on difference convex and ADMM, called DC-ADD, which is more efficient. Generalized cross validation was provided to select the tuning parameters. Rand index, adjusted Rand index and Jaccard index were provided to estimate the agreement between estimated cluster memberships and the truth.

Author
Chong Wu, Wei Pan
Date of publication
2016-07-20 00:38:43
Maintainer
Chong Wu <wuxx0845@umn.edu>
License
GPL-2 | GPL-3
Version
1.2

View on CRAN

Man pages

clustStat
External Evaluation of Cluster Results
GCV
Calculate the Generalized Cross-Validation Statistic (GCV)
PRclust
Find the Solution of Penalized Regression-Based Clustering.
prclust-package
Penalized Regression Based Cluster Method
stability
Calculate the stability based statistics

Files in this package

prclust
prclust/src
prclust/src/ADMM_OrignialPRclust2.cpp
prclust/src/RcppExports.cpp
prclust/NAMESPACE
prclust/R
prclust/R/stability.R
prclust/R/RcppExports.R
prclust/R/GCVOrignial.R
prclust/MD5
prclust/DESCRIPTION
prclust/man
prclust/man/PRclust.Rd
prclust/man/clustStat.Rd
prclust/man/stability.Rd
prclust/man/GCV.Rd
prclust/man/prclust-package.Rd