data/GSS.r

In ZellW/JHU_Shiny: Coursera JHU Shiny Project

library(foreign)
  read.dct <- function(dct, labels.included = "yes") {
      temp <- readLines(dct)
      temp <- temp[grepl("_column", temp)]
      switch(labels.included,
             yes = {
                 pattern <- "_column\\(([0-9]+)\\)\\s+([a-z0-9]+)\\s+(.*)\\s+%([0-9]+)[a-z]\\s+(.*)"
                 classes <- c("numeric", "character", "character", "numeric", "character")
                 N <- 5
                 NAMES <- c("StartPos", "Str", "ColName", "ColWidth", "ColLabel")
             },
             no = {
                 pattern <- "_column\\(([0-9]+)\\)\\s+([a-z0-9]+)\\s+(.*)\\s+%([0-9]+).*"
                 classes <- c("numeric", "character", "character", "numeric")
                 N <- 4
                 NAMES <- c("StartPos", "Str", "ColName", "ColWidth")
             })
      temp_metadata <- setNames(lapply(1:N, function(x) {
          out <- gsub(pattern, paste("\\", x, sep = ""), temp)
          out <- gsub("^\\s+|\\s+$", "", out)
          out <- gsub('\"', "", out, fixed = TRUE)
          class(out) <- classes[x] ; out }), NAMES)
      temp_metadata[["ColName"]] <- make.names(gsub("\\s", "", temp_metadata[["ColName"]]))
      temp_metadata
  }

  read.dat <- function(dat, metadata_var, labels.included = "yes") {
      read.fwf(dat, widths = metadata_var[["ColWidth"]], col.names = metadata_var[["ColName"]])
  }


GSS_dta <- read.dta("/var/www/apps/olds/releases/2015-12-31_03-14/public/system/extracts/4457/Marriage/GSS.dta", convert.dates = TRUE, convert.factors = TRUE, missing.type = FALSE, convert.underscore = FALSE, warn.missing.labels = TRUE)
GSS_metadata <- read.dct("/var/www/apps/olds/releases/2015-12-31_03-14/public/system/extracts/4457/Marriage/GSS.dct")
GSS_ascii <- read.dat("/var/www/apps/olds/releases/2015-12-31_03-14/public/system/extracts/4457/Marriage/GSS.dat", GSS_metadata)
attr(GSS_ascii, "col.label") <- GSS_metadata[["ColLabel"]]
GSS <- GSS_ascii