add extra waves of LFS longitudinal data

DESCRIPTION

@@ -15,7 +15,7 @@ Description: Reads in raw Labour Force Survey data obtained under the End User L
 License: GPL-3
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.3.0
+RoxygenNote: 7.3.2
 Depends: 
     R (>= 3.6.1)
 Imports:

NAMESPACE

@@ -41,6 +41,14 @@ export(lfs_read_2020)
 export(lfs_read_2021)
 export(lfs_read_2022)
 export(lfs_read_2023)
+export(lfs_read_5q_2012)
+export(lfs_read_5q_2013)
+export(lfs_read_5q_2014)
+export(lfs_read_5q_2015)
+export(lfs_read_5q_2016)
+export(lfs_read_5q_2017)
+export(lfs_read_5q_2018)
+export(lfs_read_5q_2019)
 export(lfs_read_5q_2020)
 export(lfs_read_5q_2021)
 export(lfs_read_5q_2022)

R/lfs_read_5q_2012.R

@@ -0,0 +1,156 @@
+#' Read LFS 2012 longitudinal
+#'
+#' Reads and performs basic cleaning on the Labour Force Survey five-quarter longitudinal
+#' data with a 1st wave that began in calendar year 2012.
+#'
+#' @param root Character - the root directory
+#' @param file Character - the file path and name
+#'
+#'
+#' @return Returns a data table
+#' @export
+lfs_read_5q_2012 <- function(
+    root = c("X:/"),
+    file = "HAR_PR/PR/LFS/Data/longitudinal/tab/"
+) {
+
+  path <- here::here(paste0(root[1], file))
+
+  cat(crayon::yellow("Reading LFS 2012:\n"))
+
+  ###### Read in each quarter
+  cat(crayon::green("\tJan-Mar 2012 to Jan-Mar 2013"))
+  data.q1 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_jm12-jm13_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tApr-Jun 2012 to Apr-Jun 2013"))
+  data.q2 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_aj12-aj13_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tJul-Sep 2012 to Jul-Sep 2013"))
+  data.q3 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_js12-js13_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tOct-Dec 2012 to Oct-Dec 2013"))
+  data.q4 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_od12-od13_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+  ###### group data tables into a list and initialize a list to store cleaned data tables in
+
+  data.list <- list(data.q1, data.q2, data.q3, data.q4)
+
+  clean.data.list <- list()
+
+  ##### loop the cleaning function over the four quarters
+  for (l in c(1:4)) {
+    data <- data.list[[l]]
+
+    setnames(data, names(data), tolower(names(data)))
+
+    setnames(data,
+             c("lgwt17","hiqul11d1","hiqul11d2","hiqul11d3","hiqul11d4","hiqul11d5"),
+             c("lgwt22","hiqul22d1","hiqul22d2","hiqul22d3","hiqul22d4","hiqul22d5"))
+
+    id_weights_vars  <- Hmisc::Cs(persid, lgwt22)
+
+    demographic_vars <- Hmisc::Cs(sex,
+                                  age1, age2, age3, age4, age5)
+
+    education_vars   <- Hmisc::Cs(hiqul22d1, hiqul22d2, hiqul22d3, hiqul22d4, hiqul22d5)
+
+    empstat_vars        <- Hmisc::Cs(ilodefr1, ilodefr2, ilodefr3, ilodefr4, ilodefr5,
+                                     incac051, incac052, incac053, incac054, incac055)
+
+    #health_vars      <- Hmisc::Cs(disea1, disea2, disea3, disea4, disea5,
+    #                              illoff1, illoff2, illoff3, illoff4, illoff5)
+
+    #benefit_vars     <- Hmisc::Cs(clims141, clims142, clims143, clims144, clims145,
+    #                              benfts1, benfts2, benfts3, benfts4, benfts5,
+    #                              ooben1, ooben2, ooben3, ooben4, ooben5)
+
+    work_vars     <- Hmisc::Cs(ttushr1, ttushr2, ttushr3, ttushr4, ttushr5,
+                               grsswk1, grsswk2, grsswk3, grsswk4, grsswk5)
+
+    names <- c(id_weights_vars, demographic_vars, education_vars, empstat_vars,
+               work_vars)
+
+    data <- data[ ,names, with=F]
+
+    data$quarter <- l
+    data$year <- 2012
+
+    clean.data.list[[l]] <- data
+  }
+
+  ### combine quarters into a single data table
+
+  data <- rbind(clean.data.list[[1]],
+                clean.data.list[[2]],
+                clean.data.list[[3]],
+                clean.data.list[[4]], fill=TRUE)
+
+  ### generate missing values for variables not in this year
+
+  data[, etukeul1 := NA]
+  data[, etukeul2 := NA]
+  data[, etukeul3 := NA]
+  data[, etukeul4 := NA]
+  data[, etukeul5 := NA]
+
+  data[, govtof21 := NA]
+  data[, govtof22 := NA]
+  data[, govtof23 := NA]
+  data[, govtof24 := NA]
+  data[, govtof25 := NA]
+
+  data[, disea1 := NA]
+  data[, disea2 := NA]
+  data[, disea3 := NA]
+  data[, disea4 := NA]
+  data[, disea5 := NA]
+
+  data[, illoff1 := NA]
+  data[, illoff2 := NA]
+  data[, illoff3 := NA]
+  data[, illoff4 := NA]
+  data[, illoff5 := NA]
+
+  data[, clims141 := NA]
+  data[, clims142 := NA]
+  data[, clims143 := NA]
+  data[, clims144 := NA]
+  data[, clims145 := NA]
+
+  data[, benfts1 := NA]
+  data[, benfts2 := NA]
+  data[, benfts3 := NA]
+  data[, benfts4 := NA]
+  data[, benfts5 := NA]
+
+  data[, ooben1 := NA]
+  data[, ooben2 := NA]
+  data[, ooben3 := NA]
+  data[, ooben4 := NA]
+  data[, ooben5 := NA]
+
+  return(data)
+}

R/lfs_read_5q_2013.R

@@ -0,0 +1,156 @@
+#' Read LFS 2013 longitudinal
+#'
+#' Reads and performs basic cleaning on the Labour Force Survey five-quarter longitudinal
+#' data with a 1st wave that began in calendar year 2013.
+#'
+#' @param root Character - the root directory
+#' @param file Character - the file path and name
+#'
+#'
+#' @return Returns a data table
+#' @export
+lfs_read_5q_2013 <- function(
+    root = c("X:/"),
+    file = "HAR_PR/PR/LFS/Data/longitudinal/tab/"
+) {
+
+  path <- here::here(paste0(root[1], file))
+
+  cat(crayon::yellow("Reading LFS 2013:\n"))
+
+  ###### Read in each quarter
+  cat(crayon::green("\tJan-Mar 2013 to Jan-Mar 2014"))
+  data.q1 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_jm13-jm14_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tApr-Jun 2013 to Apr-Jun 2014"))
+  data.q2 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_aj13-aj14_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tJul-Sep 2013 to Jul-Sep 2014"))
+  data.q3 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_js13-js14_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+
+  cat(crayon::green("\tOct-Dec 2013 to Oct-Dec 2014"))
+  data.q4 <- data.table::fread(
+    paste0(path,"/five_q_longitudinal_od13-od14_eul_lgwt17.tab"), showProgress = FALSE,
+    na.strings = c("NA", "", "-1", "-2", "-6", "-7", "-8", "-9", "-90", "-90.0", "N/A")
+  )
+
+  cat(crayon::yellow("\tdone\n"))
+
+  ###### group data tables into a list and initialize a list to store cleaned data tables in
+
+  data.list <- list(data.q1, data.q2, data.q3, data.q4)
+
+  clean.data.list <- list()
+
+  ##### loop the cleaning function over the four quarters
+  for (l in c(1:4)) {
+    data <- data.list[[l]]
+
+    setnames(data, names(data), tolower(names(data)))
+
+    setnames(data,
+             c("lgwt17","hiqul11d1","hiqul11d2","hiqul11d3","hiqul11d4","hiqul11d5"),
+             c("lgwt22","hiqul22d1","hiqul22d2","hiqul22d3","hiqul22d4","hiqul22d5"))
+
+    id_weights_vars  <- Hmisc::Cs(persid, lgwt22)
+
+    demographic_vars <- Hmisc::Cs(sex,
+                                  age1, age2, age3, age4, age5)
+
+    education_vars   <- Hmisc::Cs(hiqul22d1, hiqul22d2, hiqul22d3, hiqul22d4, hiqul22d5)
+
+    empstat_vars        <- Hmisc::Cs(ilodefr1, ilodefr2, ilodefr3, ilodefr4, ilodefr5,
+                                     incac051, incac052, incac053, incac054, incac055)
+
+    #health_vars      <- Hmisc::Cs(disea1, disea2, disea3, disea4, disea5,
+    #                              illoff1, illoff2, illoff3, illoff4, illoff5)
+
+    #benefit_vars     <- Hmisc::Cs(clims141, clims142, clims143, clims144, clims145,
+    #                              benfts1, benfts2, benfts3, benfts4, benfts5,
+    #                              ooben1, ooben2, ooben3, ooben4, ooben5)
+
+    work_vars     <- Hmisc::Cs(ttushr1, ttushr2, ttushr3, ttushr4, ttushr5,
+                               grsswk1, grsswk2, grsswk3, grsswk4, grsswk5)
+
+    names <- c(id_weights_vars, demographic_vars, education_vars, empstat_vars,
+               work_vars)
+
+    data <- data[ ,names, with=F]
+
+    data$quarter <- l
+    data$year <- 2013
+
+    clean.data.list[[l]] <- data
+  }
+
+  ### combine quarters into a single data table
+
+  data <- rbind(clean.data.list[[1]],
+                clean.data.list[[2]],
+                clean.data.list[[3]],
+                clean.data.list[[4]], fill=TRUE)
+
+  ### generate missing values for variables not in this year
+
+  data[, etukeul1 := NA]
+  data[, etukeul2 := NA]
+  data[, etukeul3 := NA]
+  data[, etukeul4 := NA]
+  data[, etukeul5 := NA]
+
+  data[, govtof21 := NA]
+  data[, govtof22 := NA]
+  data[, govtof23 := NA]
+  data[, govtof24 := NA]
+  data[, govtof25 := NA]
+
+  data[, disea1 := NA]
+  data[, disea2 := NA]
+  data[, disea3 := NA]
+  data[, disea4 := NA]
+  data[, disea5 := NA]
+
+  data[, illoff1 := NA]
+  data[, illoff2 := NA]
+  data[, illoff3 := NA]
+  data[, illoff4 := NA]
+  data[, illoff5 := NA]
+
+  data[, clims141 := NA]
+  data[, clims142 := NA]
+  data[, clims143 := NA]
+  data[, clims144 := NA]
+  data[, clims145 := NA]
+
+  data[, benfts1 := NA]
+  data[, benfts2 := NA]
+  data[, benfts3 := NA]
+  data[, benfts4 := NA]
+  data[, benfts5 := NA]
+
+  data[, ooben1 := NA]
+  data[, ooben2 := NA]
+  data[, ooben3 := NA]
+  data[, ooben4 := NA]
+  data[, ooben5 := NA]
+
+  return(data)
+}