R/plot_infotables.R

In klarsen1/Information: Data Exploration with Information Theory (Weight-of-Evidence and Information Value)

#' Create bar charts for WOE or NWOE vectors
#' 
#' \code{plot_infotable} creates WOE or NWOE bar charts for one or more variables. 
#' For multi-variable plots, bar charts will be displayed in a grid for comparison. 
#' 
#' @param variables vector of one more variables. For multi-variable plots, bar charts will be displayed in a grid.
#' @param information_object object generated by the information package.
#' @param same_scales if set to TRUE, all plots will have the same limits on the y-axes (default is FALSE).
#' @param show_values if set to TRUE, values will be displayed on the bar chart (default is FALSE).
#' 
#' @export plot_infotables
#' @examples  
#' ##------------------------------------------------------------
#' ## WOE plots
#' ##------------------------------------------------------------
#' library(Information)
#' data(train, package="Information")
#' train <- subset(train, TREATMENT==1)
#' IV <- Information::create_infotables(data=train, y="PURCHASE", parallel=FALSE)
#' 
#' # Plotting a single variable
#' Information::plot_infotables(IV, "N_OPEN_REV_ACTS")
#' 
#' # Plotting multiple variables in a grid for comparison
#' Information::plot_infotables(IV, IV$Summary$Variable[1:4], same_scale=TRUE)
#' 
#' # If the goal is to plot multiple variables individually, as opposed to a comparison-grid, we can
#' # loop through the variable names and create individual plots
#' \dontrun{
#' names <- names(IV$Tables)
#' plots <- list()
#' for (i in 1:length(names)){
#'   plots[[i]] <- plot_infotables(IV, names[i])
#' }
#' # Showing the top 18 variables
#' plots[1:18]
#' }
#' 
#' # We can speed up the creation of the information tables by invoking the parallel option (default)
#' # If we leave ncore as the default, create_infotables() will set ncore to available clusters - 1
#' \dontrun{
#' train <- subset(train, TREATMENT==1)
#' IV <- Information::create_infotables(data=train, y="PURCHASE")
#' }
#' closeAllConnections()

plot_infotables <- function(information_object=NULL, variables=NULL, same_scales=FALSE, show_values=FALSE) {

  if (is.null(information_object)){
    stop("ERROR: an Information object must be provided")
  } else if (length(variables)==0 | is.null(variables)){
     stop("ERROR: at least one variable must be provided")
  } else if (length(variables)==1){
     if (!(variables %in% names(information_object[["Tables"]]))){
       stop(paste0("ERROR: variable ", variables, "not found in the information object"))
     }
     SinglePlot(information_object, variables, show_values = show_values)
  } else{
     MultiPlot(information_object, variables, same_scales = same_scales)
  }
}