Merge pull request #93 from Big-Life-Lab/dev

cchsflow 1.8.0

.gitignore

@@ -2,4 +2,4 @@
 .Rhistory
 .RData
 .Ruserdata
-.DS_Store
+*.DS_Store

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: cchsflow
 Type: Package
 Title: Transforming and Harmonizing CCHS Variables
-Version: 1.7.1
-Date: 2020-09-16
+Version: 1.8.0
+Date: 2021-01-22
 Authors@R: c(
     person(given = "Doug",
            family = "Manuel",
@@ -49,6 +49,6 @@ Encoding: UTF-8
 LazyData: true
 URL: https://github.com/Big-Life-Lab/cchsflow
 BugReports: https://github.com/Big-Life-Lab/cchsflow/issues
-RoxygenNote: 7.1.0
+RoxygenNote: 7.1.1
 Suggests: 
     testthat (>= 2.1.0)

NAMESPACE

@@ -4,17 +4,25 @@ export(ALCDTTM)
 export(ALCDTYP)
 export(ALWDDLY)
 export(ALWDWKY)
+export(COPD_Emph_der_fun1)
+export(COPD_Emph_der_fun2)
 export(DPSDPP)
 export(DPSDSF)
 export(GEN_02A2)
+export(LBFA_31A)
+export(LBFA_31A_a)
+export(LBFA_31A_b)
 export(RACDPAL_fun)
 export(adl_fun)
+export(adl_score_5_fun)
 export(age_cat_fun)
 export(binge_drinker_fun)
 export(bmi_fun)
+export(diet_score_fun)
 export(food_insecurity_der)
 export(if_else2)
 export(is_equal)
+export(merge_rec_data)
 export(multiple_conditions_fun1)
 export(multiple_conditions_fun2)
 export(pack_years_fun)
@@ -24,6 +32,8 @@ export(resp_condition_fun1)
 export(resp_condition_fun2)
 export(resp_condition_fun3)
 export(set_data_labels)
+export(smoke_simple_fun)
+export(time_quit_smoking_fun)
 importFrom(dplyr,do)
 importFrom(dplyr,rowwise)
 importFrom(dplyr,select)

NEWS.md

@@ -1,4 +1,40 @@
-# cchsflow 1.7.1 (Latest build)
+# cchsflow 1.8.0
+2021-01-22
+
+## Features
+- New function `merge_rec_data()` that merges and labels transformed CCHS
+datasets.
+
+## Minor improvements
+- Improved support for `tagged_na` in derived variables. Additional
+documentation added for creating derived variables in the [tagged_na](https://big-life-lab.github.io/cchsflow/articles/tagged_na_usage.html)
+article.
+- Updates to labels and variable classification on `variables.csv` and
+`variable_details.csv`.
+
+## New variables
+- [**COPD_Emph_der:**](https://big-life-lab.github.io/reference/COPD_Emph_der_fun1.html)
+derived variable that determines if a respondent has either COPD or Emphysema.
+- [**ADL_score_5:**](https://big-life-lab.github.io/reference/adl_score_5_fun.html)
+derived variable that scores the number of daily tasks that a respondent needs
+help with.
+- [**diet_score:**](https://big-life-lab.github.io/reference/diet_score_fun.html)
+derived variable that scores respondents based on daily consumption of fruit,
+vegetables, and fruit juice.
+- [**smoke_simple:**](https://big-life-lab.github.io/reference/smoke_simple_fun.html)
+derived variable that identifies respondents smoking status.
+- [**time_quit_smoking:**](https://big-life-lab.github.io/reference/time_quit_smoking_fun.html)
+derived variable that estimates approximate time since respondent has quit
+smoking if they are a former smoker.
+- [**LBFA_31A/LBFA_31A_a/LBFA_31A_b:**](https://big-life-lab.github.io/reference/LBFA_31A.html)
+Occupation group. 3 different variables with differing categories were created
+to harmonize between CCHS cycles.
+- **CCC_041:** Fibromyalgia.
+- **CCC_061:** Back problems.
+- **CCC_081:** Migraine headaches.
+- **CCC_290:** Anxiety disorder.
+
+# cchsflow 1.7.1
 2020-09-16
 
 ## Minor improvements

R/adl.R

@@ -70,7 +70,7 @@
 #' 
 #' # To transform ADL_der, use rec_with_table() for each CCHS cycle
 #' # and specify ADL_der, along with the various ADL variables.
-#' # Then by using bind_rows() you can combine ADL_der across cycles.
+#' # Then by using merge_rec_data() you can combine ADL_der across cycles.
 #' 
 #' library(cchsflow)
 #' adl2001 <- rec_with_table(
@@ -89,7 +89,7 @@
 #' 
 #' tail(adl2009_2010)
 #' 
-#' combined_adl <- bind_rows(adl2001, adl2009_2010)
+#' combined_adl <- merge_rec_data(adl2001, adl2009_2010)
 #' 
 #' head(combined_adl)
 #' 
@@ -107,7 +107,6 @@
 #' print(ADL_der)
 #' 
 #' @export
-
 adl_fun <- function (ADL_01, ADL_02, ADL_03, ADL_04, ADL_05) {
   # Check to see if all values are in range
   if_else2((ADL_01 %in% 1:2) & (ADL_02 %in% 1:2) & (ADL_03 %in% 1:2) &
@@ -122,4 +121,107 @@ adl_fun <- function (ADL_01, ADL_02, ADL_03, ADL_04, ADL_05) {
            "NA(b)"
            )
 
-}
+}
+
+#' @title The number of activities of daily living tasks that require help.
+#'
+#' @description A 6 category variable (ADL_score_5) representing the number of
+#'  activities of daily living tasks that require help. This variable tallies
+#'  the number of daily living tasks that a respondent requires help with based
+#'  on various ADL variables that a respondent answered yes or no to. The ADL
+#'  variables used are common across all CCHS cycles from 2001 to 2014.
+#'
+#' @param ADL_01 Needs help preparing meals.
+#' @param ADL_02 Needs help getting to appointments/errands.
+#' @param ADL_03 Needs help doing housework.
+#' @param ADL_04 Needs help doing personal care.
+#' @param ADL_05 Needs help moving inside house.
+#'
+#' @return A derived variable (ADL_score_5) with 6 categories:
+#' \enumerate{
+#'   \item 0 - Needs help with 0 tasks
+#'   \item 1 - Needs help with at least 1 task
+#'   \item 2 - Needs help with at least 2 tasks
+#'   \item 3 - Needs help with at least 3 tasks
+#'   \item 4 - Needs help with at least 4 tasks
+#'   \item 5 - Needs help with at least 5 tasks
+#' }
+#'
+#'
+#' @examples
+#' # Use adl_score_5_fun() to create the variable ADL_score_5 across CCHS 
+#' # cycles adl_score_5_fun() is specified in variable_details.csv along with 
+#' # the CCHS variables and cycles included.
+#'
+#' # To transform ADL_score_5, use rec_with_table() for each CCHS cycle
+#' # and specify ADL_score_5, along with the various ADL variables.
+#' # Then by using merge_rec_data() you can combine ADL_der across cycles.
+#'
+#' library(cchsflow)
+#' adl2001 <- rec_with_table(
+#'   cchs2001_p, c(
+#'     "ADL_01", "ADL_02", "ADL_03", "ADL_04", "ADL_05", "ADL_score_5"
+#'   )
+#' )
+#'
+#' head(adl2001)
+#'
+#' adl2009_2010 <- rec_with_table(
+#'   cchs2009_2010_p, c(
+#'     "ADL_01", "ADL_02", "ADL_03", "ADL_04", "ADL_05", "ADL_score_5"
+#'   )
+#' )
+#'
+#' tail(adl2009_2010)
+#'
+#' combined_adl <- merge_rec_data(adl2001, adl2009_2010)
+#'
+#' head(combined_adl)
+#'
+#' tail(combined_adl)
+#'
+#' # Using adl_score_5_fun() to generate to ADL_score_5 based on user inputted
+#' # values.
+#' # Let's say you do not need help preparing meals, you need help getting to
+#' # appointments or errands, you need help doing housework, do not need help
+#' # doing personal care, and do not need help moving inside the house. Using
+#' # adl_score_5_fun() we can check the number of tasks you need help with
+#'
+#' ADL_score_5 <- adl_score_5_fun(2, 1, 1, 2, 2)
+#'
+#' print(ADL_score_5)
+#'
+#' @export
+adl_score_5_fun <-
+  function(ADL_01, ADL_02, ADL_03, ADL_04, ADL_05) {
+
+    # Create vector of ADL input variables
+    all_adl_vector <- c(ADL_01, ADL_02, ADL_03, ADL_04, ADL_05)
+    # Count the number of missing values in vector
+    count_missing_adl <- sum(all_adl_vector == "NA(b)")
+    # Count the number of not applicable values in vector
+    count_not_applicable_adl <- sum(all_adl_vector == "NA(a)")
+    # Count the number of ADLs that require help (value of 2)
+    count_adl <- sum(all_adl_vector == 2)
+
+
+    # If the individual had missing data for any of the variables then set
+    # the score to missing
+    # If the individual has "not applicable" for any of the variables, then
+    # set the score to "not applicable"
+    # Otherwise set the score for each individual to the count of the number
+    # of tasks they needed help with
+    total_num_adls <- 5
+    ADL_score_5 <-
+      ifelse(
+        count_not_applicable_adl >= 1,
+        "NA(a)",
+        ifelse(
+          count_missing_adl >= 1,
+          "NA(b)",
+          count_adl
+        )
+      )
+
+    return(ADL_score_5)
+  }

R/age-categorical.R

@@ -84,7 +84,8 @@ age_cat_fun <- function(DHHGAGE_cont) {
                               (DHHGAGE_cont %in% 70:74), 14,
                               if_else2(
                                 (DHHGAGE_cont %in% 75:79), 15,
-                                if_else2((DHHGAGE_cont >= 80), 16, NA)
+                                if_else2((DHHGAGE_cont >= 80), 16,
+                                         "NA(b)")
                               )
                             )
                           )

R/bmi.R

@@ -47,7 +47,7 @@
 #'
 #' # To transform the derived BMI variable, use rec_with_table() for each cycle
 #' # and specify HWTGBMI_der, along with height (HWTGHTM) and weight (HWTGWTK).
-#' # Then by using dplyr::bind_rows(), you can combined HWTGBMI_der across
+#' # Then by using merge_rec_data(), you can combined HWTGBMI_der across
 #' # cycles.
 #'
 #' library(cchsflow)
@@ -69,7 +69,7 @@
 #'
 #' tail(bmi2011_2012)
 #'
-#' combined_bmi <- bind_rows(bmi2001, bmi2011_2012)
+#' combined_bmi <- merge_rec_data(bmi2001, bmi2011_2012)
 #' head(combined_bmi)
 #' tail(combined_bmi)
 #'

R/data.R

@@ -58,7 +58,7 @@ NULL
 #' @return \item{cchs2001_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=3359}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=3359}
 #'
 #' @keywords datasets
 #' @examples
@@ -89,7 +89,7 @@ NULL
 #' @return \item{cchs2003_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=4995}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=4995}
 #'
 #' @keywords datasets
 #' @examples
@@ -120,7 +120,7 @@ NULL
 #' @return \item{cchs2005_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=22642}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=22642}
 #'
 #' @keywords datasets
 #' @examples
@@ -151,7 +151,7 @@ NULL
 #' @return \item{cchs2007_2008_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=29539}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=29539}
 #'
 #' @keywords datasets
 #' @examples
@@ -182,7 +182,7 @@ NULL
 #' @return \item{cchs2009_2010_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=67251}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=67251}
 #'
 #' @keywords datasets
 #' @examples
@@ -217,7 +217,7 @@ NULL
 #' @return \item{cchs2010_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=81424}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=81424}
 #'
 #' @keywords datasets
 #' @examples
@@ -248,7 +248,7 @@ NULL
 #' @return \item{cchs2011_2012_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=114112}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=114112}
 #'
 #' @keywords datasets
 #' @examples
@@ -283,7 +283,7 @@ NULL
 #' @return \item{cchs2012_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=135927}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=135927}
 #'
 #' @keywords datasets
 #' @examples
@@ -314,7 +314,7 @@ NULL
 #' @return \item{cchs2013_2014_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=144170}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=144170}
 #'
 #' @keywords datasets
 #' @examples
@@ -349,7 +349,7 @@ NULL
 #' @return \item{cchs2014_p}{a data frame}
 #'
 #' @source
-#'  \url{http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=164081}
+#'  \url{https://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=164081}
 #'
 #' @keywords datasets
 #' @examples