PARSE: Model-Based Clustering with Regularization Methods for High-Dimensional Data

Share:

Model-based clustering and identifying informative features based on regularization methods. The package includes three regularization methods - PAirwise Reciprocal fuSE (PARSE) penalty proposed by Wang, Zhou and Hoeting (2016), the adaptive L1 penalty (APL1) and the adaptive pairwise fusion penalty (APFP). Heatmaps are included to shown the identification of informative features.

Author
Lulu Wang, Wen Zhou, Jennifer Hoeting
Date of publication
2016-06-11 09:42:05
Maintainer
Lulu Wang <wanglulu@stat.colostate.edu>
License
CC0
Version
0.1.0

View on CRAN

Man pages

apfp
Model-based Clustering with APFP
apL1
Model-based Clustering with APL1
heatmap_fit
summary plot of globally and pairwise informative variables
nopenalty
Classical Model-based Clustering
parse
Model-based Clustering with PARSE
response2drug
Gene-expression Data for Asthma Disease
summary
summary of the clustering results

Files in this package

PARSE
PARSE/NAMESPACE
PARSE/data
PARSE/data/response2drug.rda
PARSE/R
PARSE/R/apfp.R
PARSE/R/parse_backward.R
PARSE/R/summary_parse_fit.R
PARSE/R/data_response2drug.R
PARSE/R/nopenalty.R
PARSE/R/PARSE_package.R
PARSE/R/additional_fn.R
PARSE/R/parse.R
PARSE/R/apL1.R
PARSE/R/plot_parse_fit.R
PARSE/R/apfp_optim.R
PARSE/MD5
PARSE/DESCRIPTION
PARSE/man
PARSE/man/parse.Rd
PARSE/man/response2drug.Rd
PARSE/man/heatmap_fit.Rd
PARSE/man/apfp.Rd
PARSE/man/apL1.Rd
PARSE/man/summary.Rd
PARSE/man/nopenalty.Rd