ds <- readr::read_csv("2 Longterm/assigndata.csv", na = c("", "NA"))

library(VarSelLCM)

# Please indicate the number of cores you wan to use for parallelization
nb.CPU <- 4
# clustering without variable selection (about than 10/20 sec on 4 CPU)
clusters <- ds |> select(!mrs_1) |> na.omit() |> 
  mutate(across(is.character, ~ factor(.x))) |> as.data.frame() |> 
  VarSelCluster(
    gvals = 1:5,
    crit.varsel = "BIC",
    vbleSelec = FALSE,
    nbcores = nb.CPU
  )

summary(clusters)

plot(clusters)

plot(x=clusters, y="mdi_1")

plot(x=clusters, y="sex")

print(clusters)

coef(clusters)

VarSelShiny(clusters)

clusters@partitions@zMAP

gtsummary::tbl_summary(tibble(ds |> na.omit(), class=clusters@partitions@zMAP),by=class) |> gtsummary::add_p()