Merge pull request #44 from Big-Life-Lab/PBC-database

Add PBC database as demostration data

.Rbuildignore

@@ -1,3 +1,5 @@
+^CONTRIBUTING\.md$
+^path$
 ^renv$
 ^renv\.lock$
 ^.*\.Rproj$
@@ -6,3 +8,5 @@
 ^docs$
 ^pkgdown$
 ^\.github$
+^data-raw$
+^path/to/venv/

.gitignore

@@ -5,3 +5,5 @@
 # Mac
 .DS_Store
 inst/doc
+
+*.code-workspace

DESCRIPTION

@@ -3,10 +3,11 @@ Type: Package
 Title: Contains functions to interface with variable details sheets, including recoding variables and converting them to PMML
 Version: 0.1.0
 Authors@R: c(
-    person(given = "Yulric", family = "Sequeira", role = c("aut"), email = "ysequeira@ohri.ca"),
-    person(given = "Luke",family = "Bailey", email = "lbailey@toh.ca", role = c("aut")),
-    person(given = "Rostyslav", family = "Vyuha", role = c("aut","cre"), email = "rvyuha@toh.ca"))
-Maintainer: Rostyslav Vyuha <rvyuha@toh.ca>
+    person("Yulric", "Sequeira", email = "ysequeira@ohri.ca", role = c("aut", "cre")),
+    person("Luke", "Bailey", role = c("aut")),
+    person("Rostyslav", role = c("aut"))
+    )
+Maintainer: Yulric Sequeria <ysequeira@ohri.ca>
 Description: Recode and harmonize data using variable and details sheets.
 Depends:
     R (>= 3.1.0)
@@ -24,12 +25,13 @@ URL: https://github.com/Big-Life-Lab/recodeflow
 BugReports: https://github.com/Big-Life-Lab/recodeflow/issues
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.2
 Suggests: 
     DT,
     kableExtra,
     knitr,
     rmarkdown,
+    readr,
     testthat (>= 3.0.0)
 Config/testthat/edition: 3
 VignetteBuilder: knitr

R/data.R

@@ -0,0 +1,88 @@
+#' The pbc dataset
+#'
+#' @format A data frame with 418 observations and 20 variables.
+#' \describe{
+#'  \item{id}{case number}
+#'  \item{time}{number of days between registration and the earlier of death, transplantation, or study analysis time}
+#'  \item{status}{status at endpoint, 0/1/2 for censored, transplant, dead}
+#'  \item{trt}{1/2/NA for D-penicillamine, placebo, or not randomized}
+#'  \item{age}{age in years}
+#'  \item{sex}{m/f}
+#'  \item{ascites}{presence of ascites}
+#'  \item{hepato}{presence of hepatomegaly or enlarged liver}
+#'  \item{spiders}{blood vessel malformations in the skin}
+#'  \item{edema}{0 no edema, 0.5 untreated or successfully treated, 1 edema despite diuretic therapy}
+#'  \item{bili}{serum bilirubin (mg/dl)}
+#'  \item{chol}{serum cholesterol (mg/dl)}
+#'  \item{albumin}{serum albumin (g/dl)}
+#'  \item{copper}{urine copper (ug/day)}
+#'  \item{alk.phos}{alkaline phosphotase (U/liter)}
+#'  \item{ast}{aspartate aminotransferase (U/ml)}
+#'  \item{trig}{triglycerides (mg/dl)}
+#'  \item{platelet}{platelet count}
+#'  \item{protime}{standardised blood clotting time}
+#'  \item{stage}{histologic stage of disease (1, 2, 3, or 4)}
+#' }
+#' @source {https://cran.r-project.org/web/packages/survival/survival.pdf}
+"pbc"
+
+#' Metadata for the pbc dataset using the DCIM standard
+#'
+#' @format A list containing DCMI metadata:
+#' \describe{
+#' \item{title}{title}
+#' \item{creator}{creator}
+#' \item{subject}{subject}
+#' \item{description}{description}
+#' \item{publisher}{publisher}
+#' \item{date}{date}
+#' \item{type}{type}
+#' \item{format}{format}
+#' \item{identifier}{identifier}
+#' \item{source}{source}
+#' \item{language}{language}
+#' \item{rights}{rights}
+#' \item{references}{references}
+#' }
+"pbc_metadata"
+
+#' Variables sheet for the pbc dataset
+#'
+#' @format A data frame with 24 rows and 11 columns:
+#' \describe{
+#' \item{variable}{variable name}
+#' \item{label}{variable label}
+#' \item{labelLong}{variable label long}
+#' \item{subject}{subject}
+#' \item{section}{section}
+#' \item{variableType}{variable type}
+#' \item{databaseStart}{database start}
+#' \item{units}{units}
+#' \item{variableStart}{variable start}
+#' \item{notes}{logical indicating presence of notes}
+#' \item{description}{logical indicating presence of description}
+#' }
+"pbc_variables"
+
+#' Variable details sheet for the pbc dataset
+#'
+#' @format A data frame with 69 rows and 16 columns:
+#' \describe{
+#' \item{variable}{variable name}
+#' \item{dummyVariable}{dummy variable name}
+#' \item{typeEnd}{end type}
+#' \item{databaseStart}{database start}
+#' \item{variableStart}{variable start}
+#' \item{typeStart}{start type}
+#' \item{recEnd}{record end}
+#' \item{recStart}{record start}
+#' \item{catLabel}{category label}
+#' \item{catLabelLong}{category long label}
+#' \item{nubValidCat}{number of valid categories (numeric)}
+#' \item{units}{logical indicating presence of units}
+#' \item{notes}{logical indicating presence of notes}
+#' \item{catStartLabel}{category start label}
+#' \item{variableStartShortLabel}{variable start short label}
+#' \item{variableStartLabel}{variable start label}
+#' }
+"pbc_variable_details"

R/example_der_function.R

@@ -1,7 +1,7 @@
 #' example_der_fun caluclates chol*bili
 #' @param chol the row value for chol
 #' @param bili the row value for bili
-#' @export
+#' @keywords internal
 example_der_fun <- function(chol, bili){
   # as numeric is used to coerce in case categorical numeric variables are used.
   # Warning either chol or bili being NA will result in NA return

R/recode-with-table.R

@@ -29,7 +29,7 @@
 #'
 #' is_equal(NA,NA)
 #' # TRUE
-#' @export
+#' @keywords internal
 is_equal <- function(v1, v2) {
   same <- (v1 == v2) | (is.na(v1) & is.na(v2))
   # anything compared to NA equals NA
@@ -44,7 +44,7 @@ is_equal <- function(v1, v2) {
 #' Creates new variables by recoding variables in a dataset using the rules
 #' specified in a variables details sheet
 #'
-#' The \href{https://github.com/Big-Life-Lab/recodeflow/blob/master/inst/extdata/PBC-variableDetails.csv}{variable_details}
+#' The \href{https://github.com/Big-Life-Lab/recodeflow/blob/master/inst/extdata/pbc_variable_details.csv}{variable_details}
 #'  dataframe needs the following columns:
 #'  \describe{
 #'   \item{variable}{Name of the new variable created. The name of the new
@@ -523,6 +523,7 @@ recode_call <-
 #' @param variable_being_checked the name of the recoded variable
 #'
 #' @return the data equivalent of variable_being_checked
+#' @keywords internal
 get_data_variable_name <-
   function(data_name,
            data,
@@ -586,6 +587,7 @@ get_data_variable_name <-
 #' @param tables A list of reference tables
 #'
 #' @return Returns recoded and labeled data
+#' @keywords internal
 recode_columns <-
   function(data,
            variables_details_rows_to_process,
@@ -979,7 +981,7 @@ recode_non_derived_variables <- function(
       )
       if (length(else_value) > 0) {
         extra_row <- nrow(log_table) + 1
-        log_table[extra_row , "value_to"] <- else_value
+        log_table[extra_row , "value_to"] <- as.character(else_value)
         log_table[extra_row , "From"] <-
           "else"
         log_table[extra_row , "rows_recoded"] <-
@@ -1009,6 +1011,7 @@ recode_non_derived_variables <- function(
 #'
 #' @return a boolean vector containing true for rows where the
 #' comparison is true
+#' @keywords internal
 compare_value_based_on_interval <-
   function(left_boundary,
            right_boundary,
@@ -1101,6 +1104,7 @@ update_variable_details_based_on_variable_sheet <-
 #' @param var_type the toType of a variable
 #'
 #' @return an appropriately coded tagged NA
+#' @keywords internal
 format_recoded_value <- function(cell_value, var_type) {
   recode_value <- NULL
   if (grepl("NA", cell_value)) {
@@ -1370,6 +1374,7 @@ calculate_custom_function_row_value <-
 #' @param variable_details_row A data frame with a single row which will be
 #' checked
 #' @return A boolean
+#' @keywords internal
 is_derived_var <- function(variable_details_row) {
   derived_var_regex <- "DerivedVar::\\[(.+?)\\]|DerivedVar::\\[\\]"
   return(length(grep(