vimpute-mi.R
In VIM: Visualization and Imputation of Missing Values

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>",
                      fig.width = 7, fig.height = 4.5)
run_mice <- requireNamespace("mice", quietly = TRUE)

## ----message = FALSE----------------------------------------------------------
library(VIM)
set.seed(2026)

data(sleep, package = "VIM")
truth <- na.omit(sleep[, c("BodyWgt", "BrainWgt", "NonD", "Sleep", "Span", "Gest")])
truth <- as.data.frame(scale(truth))   # common scale keeps the example compact
nrow(truth)

## -----------------------------------------------------------------------------
amp <- makeMissing(truth, prop = 0.25, mechanism = "MAR",
                   vars = c("Sleep", "Span"), seed = 1)
colSums(is.na(amp))

## -----------------------------------------------------------------------------
mi <- vimpute(amp,
              spec = list(.default = vs_ranger(num.trees = 100)),
              m = 5, sequential = TRUE, nseq = 3, seed = 7, verbose = FALSE)
mi

## ----fig.height = 5.5---------------------------------------------------------
plot(mi)             # chains: mean/sd of the imputed values per iteration

## -----------------------------------------------------------------------------
plot(mi, "density")  # observed (blue, bold) vs per-imputation imputed (red)

## ----eval = run_mice----------------------------------------------------------
fits <- with(mi, lm(Sleep ~ BodyWgt + Span))
pooled <- mice::pool(fits)
summary(pooled)

## ----eval = run_mice----------------------------------------------------------
mids <- vim_as_mids(mi)
class(mids)

## -----------------------------------------------------------------------------
mi_tuned <- vimpute(amp,
                    spec = list(Sleep    = vs_ranger(num.trees = 100, tune = TRUE),
                                .default = vs_ranger(num.trees = 100)),
                    tune_control = vimpute_tune_control(budget = 4, folds = 3),
                    m = 2, sequential = FALSE, seed = 7, verbose = FALSE)
tl <- mi_tuned$tuning_log
tail(tl, 1)[[1]][c("variable", "tuned", "tuned_better", "n_evals", "folds")]

## -----------------------------------------------------------------------------
ov <- overimpute(amp, "Sleep",
                 spec = list(.default = vs_ranger(num.trees = 100)),
                 draws = 5, folds = 3, sequential = FALSE, seed = 3)
ov
plot(ov)

## -----------------------------------------------------------------------------
completed <- vim_complete(mi, 1)
evaluation(truth, completed, where = attr(amp, "where"))