Learn R Programming

⚠️There's a newer version (0.7) of this package.Take me there.

Modalclust (version 0.3)

Hierarchical Modal Clustering

Description

Perfroms Modal Clustering (MAC) including Hierarchical Modal Clustering (HMAC) along with their parallel implementation (PHMAC) over several processors. These model-based non-parametric clustering techniques can extract clusters in very high dimensions with arbitrary density shapes. By default clustering is performed over several resolutions and the results are summarized as a hierarchical tree. Associated plot functions are also provided. There is a package vignette that provides many examples.

Copy Link

Version

Install

install.packages('Modalclust')

Monthly Downloads

169

Version

0.3

License

GPL-2

Maintainer

Surajit Ray

Last Published

May 2nd, 2012

Functions in Modalclust (0.3)

cta20

Two dimensional data in original and log scale
phmac

Main function for performing Modal Clusters either parallel or serial mode.
oned

One dimensional data with two main clusters
contour.hmac

Plot clusters with different colors for two dimensional data overlayed on the contours of the original data.
choose.cluster

Choosing the cluster which is closest to a specified point
soft.hmac

Plot soft clusters from Modal Clustering output
hmac

Perform Modal Clustering in serial mode only
hard.hmac

Plot clusters with different colors.
findmid

Find the mid point of memberships of each cluster
disc2d

Two and three dimensional data representing two half discs
mydmvnorm

Calculate Density of Multivariate Normal for diagonal covariance
khat.inv

Calculate the smoothing paramters for implementation of Modal Clustering.
plot.hmac

Plots of heierarchical tree for a 'hmac' object
summary

Summary of HMAC output