Xgboost Imputation

Impute missing values based on a random forest model using xgboost::xgboost()

xgboostImpute(
  formula,
  data,
  imp_var = TRUE,
  imp_suffix = "imp",
  verbose = FALSE,
  nrounds = 100,
  objective = NULL,
  ...,
  edit_rules = NULL,
  edit_control = NULL
)

Arguments

formula

model formula for the imputation

data

A data.frame containing the data

imp_var

TRUE/FALSE if a TRUE/FALSE variables for each imputed variable should be created show the imputation status

imp_suffix

suffix used for TF imputation variables

verbose

Show the number of observations used for training and evaluating the RF-Model. This parameter is also passed down to xgboost::xgboost() to show computation status.

nrounds

max number of boosting iterations, argument passed to xgboost::xgboost()

objective

objective for xgboost, argument passed to xgboost::xgboost()

...

Arguments passed to xgboost::xgboost()

edit_rules

Optional model-agnostic validator, applied jointly to the assembled imputed LHS columns after all target fits; see vimpute().

edit_control

Control object or named list; see vimpute_edit_control().

Value

the imputed data set.

See also

Other imputation methods: hotdeck(), impPCA(), imputeCellEM(), imputeCellIRMI(), imputeCellM(), imputeCellMCD(), imputeCellwise(), imputeRobust(), imputeRobustChain(), irmi(), kNN(), matchImpute(), medianSamp(), rangerImpute(), regressionImp(), sampleCat(), vimmi, vimpute()

Examples

data(sleep)
sleepx <- sleep
sleepx$Pred <- as.factor(LETTERS[sleepx$Pred])
sleepx$Pred[1] <- NA
# a numeric and a factor target imputed at once; nrounds = 30 keeps the
# example fast (the default is 100 boosting rounds)
# xgboostImpute() runs on vimpute(), which VIM backs with the suggested
# mlr3 stack -- skip the example where that stack is not installed.
if (requireNamespace("mlr3", quietly = TRUE) &&
    requireNamespace("mlr3learners", quietly = TRUE) &&
    requireNamespace("mlr3pipelines", quietly = TRUE)) {
  imp <- xgboostImpute(Dream + Pred ~ BodyWgt + BrainWgt, data = sleepx, nrounds = 30)
  head(imp)
}
#>    BodyWgt BrainWgt NonD Dream Sleep Span Gest Pred Exp Danger Dream_imp
#> 1 6654.000   5712.0   NA   1.6   3.3 38.6  645    E   5      3      TRUE
#> 2    1.000      6.6  6.3   2.0   8.3  4.5   42    C   1      3     FALSE
#> 3    3.385     44.5   NA   2.2  12.5 14.0   60    A   1      1      TRUE
#> 4    0.920      5.7   NA   1.6  16.5   NA   25    E   2      3      TRUE
#> 5 2547.000   4603.0  2.1   1.8   3.9 69.0  624    C   5      4     FALSE
#> 6   10.550    179.5  9.1   0.7   9.8 27.0  180    D   4      4     FALSE
#>   Pred_imp
#> 1     TRUE
#> 2    FALSE
#> 3    FALSE
#> 4    FALSE
#> 5    FALSE
#> 6    FALSE