library(brms)
#> Loading required package: Rcpp
#> Loading 'brms' package (version 2.22.0). Useful instructions
#> can be found by typing help('brms'). A more detailed introduction
#> to the package is available through vignette('brms_overview').
#> 
#> Attaching package: 'brms'
#> The following object is masked from 'package:stats':
#> 
#>     ar
library(projpred)
#> This is projpred version 2.9.0.
#> 
#> Attaching package: 'projpred'
#> The following object is masked from 'package:brms':
#> 
#>     do_call
nobsv <- 29
nvars <- 3
set.seed(1235)
x_mat <- matrix(rnorm(nobsv * nvars), nrow = nobsv, ncol = nvars)
x_mat <- cbind(x_mat, x_mat[, 1] * x_mat[, 2],  x_mat[, 1] * x_mat[, 3],  x_mat[, 2] * x_mat[, 3],  x_mat[, 1] * x_mat[, 2] * x_mat[, 3])
b <- c(-3, 1, 2, 3, -1, -2, 4)
dat <- data.frame(y = rnorm(nobsv, mean = x_mat %*% b, sd = 1.5), x_mat)
fitobj <- brm(y ~ X1*X2*X3,
              data = dat,
              seed = 11403,
              silent = 2,
              chains = 4, 
              cores = 4,
              refresh = 0)

vs <- varsel(fitobj, nclusters = 2, nclusters_pred = 3, seed = 457634)
ranking(vs)$fulldata
#> [1] "X1"       "X2"       "X1:X2"    "X3"       "X1:X2:X3" "X2:X3"    "X1:X3"