R/ds.na.R

In paularaissa/distStatsClient: Distributed Multiple Imputations

#-------------------------------------- HEADER --------------------------------------------#
#' @title Missing Values of Study Variable
#' @description Computes the missing values of a given study variable.
#' Count all values set as NA or another missing value indicator.
#' @details It is a wrapper for the server side function \code{\link{getNumNa}}.
#' @param x a character, the name of study variable.
#' @param datasources a list of opal object(s) obtained after login in to opal servers;
#' these objects hold also the data assign to R, as \code{data frame}, from opal datasources.
#' @return return a numeric value.
#' @author Paula Raissa Costa e Silva
#' @section Dependencies:
#' \code{\link{getNumNa}}
#' @export
#' @examples {
#' na <- ds.na('D$birth_weight')
#' }
#'

ds.na <- function(x=NULL, datasources=NULL) {

  if(is.null(x)){
    stop("Please provide the name of the input vector", call. = FALSE)
  }

  # if no opal login details are provided look for 'opal' objects in the environment
  if(is.null(datasources)){
    datasources <- findLoginObjects()
  }
  xnames <- extract(x)
  varname <- xnames$elements
  obj2lookfor <- xnames$holders

  if(is.na(obj2lookfor)){
    defined <- isDefined(datasources, varname)
  } else {
    defined <- isDefined(datasources, obj2lookfor)
  }

  # typ <- checkClass(datasources, x)
  # if(typ!='integer' & typ!='numeric'){
  #   message(paste0(x, "is of type ", typ, "!"))
  #   stop("The input vector must be integer or numeric vector", call. = FALSE)
  # }

  #number of studies
  num.sources <- length(datasources)
  result <- list()
  for (i in 1:num.sources) {
    cally <- call("getNumNa", x)
    result <- opal::datashield.aggregate(datasources, cally)
  }

  return(result)

  # total.na <- 0
  # for(node in result) {
  #   total.na <- total.na + node
  # }
  #
  # return(total.na)

}