R/aps_read_2011.R

In djmorris1989/apsclean: Annual Population Survey Data Wrangling

#' Read APS 2011
#'
#' Reads and performs basic cleaning on the Annual Population Survey 2011
#'
#' @param root Character - the root directory
#' @param file Character - the file path and name
#'
#'
#' @return Returns a data table
#' @export
aps_read_2011 <- function(
  root = c("C:/"),
  file = "Users/User/Documents/Datasets/Annual Population Survey/raw data/apsp_jd11_eul_inclu_smoking.tab"
) {

  data <- data.table::fread(
    paste0(root[1], file),
    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
  )

  data.table::setnames(data, names(data), tolower(names(data)))

  ### keep relevant variables

  weights_vars     <- Hmisc::Cs(pwta14)
  demographic_vars <- Hmisc::Cs(age,sex,govtof,ethukeul)
  family_vars      <- Hmisc::Cs(marsta)
  education_vars   <- Hmisc::Cs(qual_1,qual_2,qual_3,qual_4,qual_5,qual_6,qual_7,qual_8,qual_9,qual_10,qual_11,qual_12,
                                qual_13,qual_14,qual_15,qual_16,qual_17,qual_18,qual_19,qual_20,qual_21,qual_22,qual_23,
                                qual_24,qual_25,qual_26,qual_27,qual_28,qual_29,qual_30,qual_31)
  work_vars        <- Hmisc::Cs(inecac05,grsswk,ftptwk,ttachr,ttushr,illwk,illoff)
  health_vars      <- Hmisc::Cs(cigsmk1)
  other_vars       <- Hmisc::Cs(refwkm)

  names <- c(demographic_vars,family_vars,education_vars,work_vars,health_vars,weights_vars,other_vars)
  names <- tolower(names)

  data <- data[ ,names, with=F]

  ### tidy data

  data <- rename(data,
                 c("month" = "refwkm"),
                 c("smoker" = "cigsmk1"),
                 c("pwt" = "pwta14")
                 #c("piwt" = "piwta18")
  )

  # date variables

  data$quarter <- recode(as.character(data$month),
                         "1" = "1" ,
                         "2" = "1" ,
                         "3" = "1" ,
                         "4" = "2" ,
                         "5" = "2" ,
                         "6" = "2" ,
                         "7" = "3" ,
                         "8" = "3" ,
                         "9" = "3" ,
                         "10" = "4" ,
                         "11" = "4" ,
                         "12" = "4" )

  data$year <- 2011

  return(data)
}