spuds-package: Spectral Partitioning Using Density Separation

In DavidHofmeyr/spuds: Spectral Partitioning Using Density Separation

Description

Implements the spectral clustering algorithm "SPUDS", introduced in Hofmeyr, D. (2017) "Improving spectral clustering using the asymptotic value of the normalised cut"

Details

The DESCRIPTION file: This package was not yet installed at build time.

Index: This package was not yet installed at build time.
This package provides an implementation of the SPUDS algorithm introduced in Hofmeyr, D. (2017) "Improving spectral clustering using the asymptotic value of the normalised cut". The main function provided in the package is spuds(). The only mandatory argument is a data matrix, all optional arguments are given the default values used in the paper. Details of optional arguments can be seen using the function documentation. A function to simulate data sets like those used in the paper is also provided (spuds_datagen(ndata, nclust, ndimensions)). Publicly available benchmark data sets are also included. Use data(package = 'spuds') to see a list of included data sets.

References

Hofmeyr, D. (2017) Improving spectral clustering using the asymptotic value of the normalised cut, ArXiv preprint, ArXiv 1703.09975.

DavidHofmeyr/spuds documentation built on May 20, 2019, 9:40 a.m.