inverse of plot_missing? about dataexplorer HOT 2 CLOSED

profile_non_missing <- function(data) {
  ## Declare variable first to pass R CMD check
  feature <- num_missing <- pct_missing <- group <- NULL
  ## Check if input is data.table
  is_data_table <- is.data.table(data)
  ## Detect input data class
  data_class <- class(data)
  ## Set data to data.table
  if (!is_data_table) data <- data.table(data)
  ## Extract missing value distribution
  missing_value <- data.table(
    "feature" = names(data),
    "num_missing" = sapply(data, function(x) {sum(!is.na(x))})
  )
  missing_value[, feature := factor(feature, levels = feature[order(-rank(num_missing))])]
  missing_value[, pct_missing := num_missing / nrow(data)][]
  ## Set data class back to original
  if (!is_data_table) class(missing_value) <- data_class
  
  missing_value
}

plot_missing2 <- function(data,
                         group = list("Good" = 0.05, "OK" = 0.4, "Bad" = 0.8, "Remove" = 1),
                         missing_only = FALSE,
                         geom_label_args = list(),
                         title = NULL,
                         ggtheme = theme_gray(),
                         theme_config = list("legend.position" = c("bottom"))) {
  ## Declare variable first to pass R CMD check
  num_missing <- pct_missing <- Band <- NULL
  ## Profile missing values
  missing_value <- data.table(profile_non_missing(data))
  if (missing_only) missing_value <- missing_value[num_missing > 0]
  ## Sort group based on value
  group <- group[sort.list(unlist(group))]
  invisible(lapply(seq_along(group), function(i) {
    if (i == 1) {
      missing_value[pct_missing <= group[[i]], Band := names(group)[i]]
    } else {
      missing_value[pct_missing > group[[i-1]] & pct_missing <= group[[i]], Band := names(group)[i]]
    }
  }))
  ## Create ggplot object
  output <- ggplot(missing_value, aes_string(x = "feature", y = "num_missing", fill = "Band")) +
    geom_bar(stat = "identity") +
    scale_fill_discrete("Band") +
    coord_flip() +
    xlab("Features") + ylab("Non-Missing Rows") +
    guides(fill = guide_legend(override.aes = aes(label = "")))
  geom_label_args_list <- list("mapping" = aes(label = paste0(round(100 * pct_missing, 2), "%")))
  output <- output +
    do.call("geom_label", c(geom_label_args_list, geom_label_args))
  ## Plot object
  class(output) <- c("single", class(output))
  plotDataExplorer(
    plot_obj = output,
    title = title,
    ggtheme = ggtheme,
    theme_config = theme_config
  )
}

library(data.table)
library(ggplot2)
library(DataExplorer)
plot_missing2(airquality, group = list("Remove" = 0.05, "Bad" = 0.4, "OK" = 0.8, "Good" = 1))