sample.gibbs {CRF} | R Documentation |
Generating samples from the distribution
sample.gibbs(
crf,
size,
burn.in = 1000,
start = apply(crf$node.pot, 1, which.max)
)
crf |
The CRF |
size |
The sample size |
burn.in |
The number of samples at the beginning that will be discarded |
start |
An initial configuration |
Approximate sampling using a single-site Gibbs sampler
This function will return a matrix with size
rows and crf$n.nodes
columns,
in which each row is a sampled configuration.
library(CRF)
data(Small)
s <- sample.gibbs(Small$crf, 100)