knitr::opts_chunk$set( collapse = TRUE, comment = ">", fig.width = 7, fig.height = 7, fig.align = "center" )
The R
package ssgraph is designed for Bayesian structure learning in graphical models using spike-and-slab priors. To speed up the computations, the computationally intensive tasks of the package are implemented in C++
in parallel using OpenMP.
Install ssgraph using
install.packages( "ssgraph" )
First, we install ssgraph
library( ssgraph )
This is a simple example to see the performance of the package for the Gaussian graphical models. First, by using the function bdgraph.sim()
, we simulate 100 observations (n = 100) from a multivariate Gaussian distribution with 8 variables (p = 8) and “scale-free” graph structure, as follows:
set.seed( 10 ) data.sim <- bdgraph.sim( n = 100, p = 8, graph = "scale-free", vis = TRUE ) round( head( data.sim $ data, 4 ), 2 )
Since the generated data are Gaussian, we run ssgraph
function by choosing method = "ggm"
, as follows:
ssgraph.obj <- ssgraph( data = data.sim, method = "ggm", iter = 5000, save = TRUE, verbose = FALSE ) summary( ssgraph.obj )
To compare the result with true graph
compare( data.sim, ssgraph.obj, main = c( "Target", "ssgraph" ), vis = TRUE )
plotroc( ssgraph.obj, data.sim, cut = 200 )
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.