Package: pmclust 0.2-2

pmclust: Parallel Model-Based Clustering using Expectation-Gathering-Maximization Algorithm for Finite Mixture Gaussian Model

Aims to utilize model-based clustering (unsupervised) for high dimensional and ultra large data, especially in a distributed manner. The code employs 'pbdMPI' to perform a expectation-gathering-maximization algorithm for finite mixture Gaussian models. The unstructured dispersion matrices are assumed in the Gaussian models. The implementation is default in the single program multiple data programming model. The code can be executed through 'pbdMPI' and MPI' implementations such as 'OpenMPI' and 'MPICH'. See the High Performance Statistical Computing website <https://snoweye.github.io/hpsc/> for more information, documents and examples.

Authors:Wei-Chen Chen [aut, cre], George Ostrouchov [aut]

pmclust_0.2-2.tar.gz

pmclust_0.2-2.tar.gz(r-4.5-noble)pmclust_0.2-2.tar.gz(r-4.4-noble)
pmclust_0.2-2.tgz(r-4.4-emscripten)pmclust_0.2-2.tgz(r-4.3-emscripten)
pmclust.pdf |pmclust.html✨
pmclust/json (API)

# Install 'pmclust' in R:

install.packages('pmclust', repos = c('https://snoweye.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/snoweye/pmclust/issues

Datasets:

.PMC.CT - A Set of Controls in Model-Based Clustering.
.pmclustEnv - Set Global Variables According to the global matrix X.gbd

On CRAN:

26 exports 5 stars 1.18 score 3 dependencies 3 scripts 173 downloads

Last updated 1 years agofrom:1523c5f12e. Checks:OK: 2. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Sep 02 2024
R-4.5-linux-x86_64	OK	Sep 02 2024

Exports:aecm.step apecm.step apecma.step assign.N.sample e.step em.onestep em.step em.update.class generate.basic generate.MixSim get.CLASS get.N.CLASS indep.logL initial.center initial.em initial.RndEM kmeans.step kmeans.update.class m.step mb.print pkmeans pmclust pmclust.reduceK readme set.global set.global.gbd

Dependencies:float MASS pbdMPI

pmclust-guide

Rendered frompmclust-guide.Rnwusingutils::Sweaveon Sep 02 2024.

Last update: 2021-02-09
Started: 2013-07-03

Help page	Topics
Parallel Model-Based Clustering	pmclust-package
Obtain a Set of Random Samples for X.spmd	assign.N.sample
EM-like Steps for GBD	aecm.step apecm.step apecma.step em.step kmeans.step
Generate Examples for Testing	generate.basic
Generate MixSim Examples for Testing	generate.MixSim
Obtain Total Elements for Every Clusters	get.CLASS get.N.CLASS
Independent Function for Log Likelihood	indep.logL
Initialization for EM-like Algorithms	initial.center initial.em initial.RndEM
Print Results of Model-Based Clustering	mb.print
Compute One E-step and Log Likelihood Based on Current Parameters	e.step
Compute One M-Step Based on Current Posterior Probabilities	m.step
One EM Step for GBD	em.onestep
Parallel Model-Based Clustering and Parallel K-means Algorithm	pkmeans pmclust
Functions for Printing or Summarizing Objects According to Classes	print.pkmeans print.pmclust
Read Me First Function	CHECK CLASS.spmd COMM.RANK COMM.SIZE p.times.logtwopi readme SAVE.iter SAVE.param U.spmd W.spmd W.spmd.rowSums Z.colSums Z.spmd
Set Global Variables According to the global matrix X.gbd (X.spmd)	.pmclustEnv set.global set.global.gbd X.gbd X.spmd
A Set of Controls in Model-Based Clustering.	.PMC.CT CONTROL
A Set of Parameters in Model-Based Clustering.	ETA MU PARAM PARAM.org SIGMA
Update CLASS.spmd Based on the Final Iteration	em.update.class kmeans.update.class

Package: pmclust 0.2-2

pmclust: Parallel Model-Based Clustering using Expectation-Gathering-Maximization Algorithm for Finite Mixture Gaussian Model

pmclust-guide

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)