xgboostImpute.R
In VIM: Visualization and Imputation of Missing Values

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 7,
  fig.height=4,
  fig.align = "center"
)

## ----message=FALSE------------------------------------------------------------
library(VIM)
dataset <- sleep[, c("Dream", "NonD", "BodyWgt", "Span")] # dataset with missings
dataset$BodyWgt <- log(dataset$BodyWgt)
dataset$Span <- log(dataset$Span)
aggr(dataset)
str(dataset)

## ----message=FALSE------------------------------------------------------------
imp_xgboost <- xgboostImpute(formula=Dream~BodyWgt,data = dataset)
aggr(imp_xgboost, delimiter = "_imp")


## ----fig.height=5-------------------------------------------------------------
imp_xgboost[, c("Dream", "BodyWgt", "Dream_imp")] |> 
  marginplot(delimiter = "_imp")


## ----message=FALSE------------------------------------------------------------
imp_xgboost <- xgboostImpute(Dream+NonD+Span~BodyWgt,data=dataset)
aggr(imp_xgboost, delimiter = "_imp")


## -----------------------------------------------------------------------------
library(reactable)

data(iris)
df <- iris
colnames(df) <- c("S.Length","S.Width","P.Length","P.Width","Species")
# randomly produce some missing values in the data
set.seed(1)
nbr_missing <- 48
y <- data.frame(row=sample(nrow(iris),size = nbr_missing,replace = FALSE),
                col=sample(rep(1:4,12)))
df[as.matrix(y)]<-NA

aggr(df)
sapply(df, function(x)sum(is.na(x)))

## ----message=FALSE------------------------------------------------------------
imp_xgboost <- xgboostImpute(S.Length + S.Width + P.Length + P.Width ~ Species, df)
aggr(imp_xgboost, delimiter = "imp")


## ----echo=F,warning=F---------------------------------------------------------
results <- cbind("TRUE1" = as.numeric(iris[as.matrix(y[which(y$col==1),])]),
                 "IMPUTED1" = round(as.numeric(imp_xgboost[as.matrix(y[which(y$col==1),])]),2),
                 "TRUE2" = as.numeric(iris[as.matrix(y[which(y$col==2),])]),
                 "IMPUTED2" = round(as.numeric(imp_xgboost[as.matrix(y[which(y$col==2),])]),2),
                 "TRUE3" = as.numeric(iris[as.matrix(y[which(y$col==3),])]),
                 "IMPUTED3" = round(as.numeric(imp_xgboost[as.matrix(y[which(y$col==3),])]),2),
                 "TRUE4" = as.numeric(iris[as.matrix(y[which(y$col==4),])]),
                 "IMPUTED4" = round(as.numeric(imp_xgboost[as.matrix(y[which(y$col==4),])]),2))[1:5,]

reactable(results, columns = list(
    TRUE1 = colDef(name = "True"),
    IMPUTED1 = colDef(name = "Imputed"),
    TRUE2 = colDef(name = "True"),
    IMPUTED2 = colDef(name = "Imputed"),
    TRUE3 = colDef(name = "True"),
    IMPUTED3 = colDef(name = "Imputed"),
    TRUE4 = colDef(name = "True"),
    IMPUTED4 = colDef(name = "Imputed")
  ),
    columnGroups = list(
    colGroup(name = "S.Length", columns = c("TRUE1", "IMPUTED1")),
    colGroup(name = "S.Width", columns = c("TRUE2", "IMPUTED2")),
    colGroup(name = "P.Length", columns = c("TRUE3", "IMPUTED3")),
    colGroup(name = "P.Width", columns = c("TRUE4", "IMPUTED4"))
  ),
  striped = TRUE,
  highlight = TRUE,
  bordered = TRUE
)