Skip to content

A fast, sparse, parallel implementation of Pseudo-Marginal Inference for Gaussian Process Classification with Large Datasets in R and Rcpp, based on Pseudo-Marginal Bayesian Inference for Gaussian Processes.

License

Notifications You must be signed in to change notification settings

dannyjameswilliams/gpc

Repository files navigation

gpc

Build Status codecov

A fast, sparse, parallel implementation of Pseudo-Marginal Inference for Gaussian Process Classification with Large Datasets, based on Pseudo-Marginal Bayesian Inference for Gaussian Processes.

Authors:

Daniel Williams daniel.williams@bristol.ac.uk

Dom Owens dom.owens@bristol.ac.uk

Jake Spiteri jake.spiteri@bristol.ac.uk

Installation

You can install the released version of gpc from github with:

library(devtools)
install_github("dannyjameswilliams/gpc", build_vignettes = TRUE)

Alternatively, the package can be installed faster without building the vignettes by changing the second argument to FALSE.

Package Contents

The package contains software to efficiently fit a Gaussian process classification (gpc) model, using Rcpp and RcppParallel. We also have included the e-mail spam dataset used for classification.

To see an example of the code, as well as a step-by-step tutorial for its implementation, see the vignette using_gpc, provided as an HTML document you can view in this repository by clicking here, or by running

vignette(package="gpc")

once the package has installed, provided the argument build_vignettes=TRUE was specified.

About

A fast, sparse, parallel implementation of Pseudo-Marginal Inference for Gaussian Process Classification with Large Datasets in R and Rcpp, based on Pseudo-Marginal Bayesian Inference for Gaussian Processes.

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published