[skip vbump] update description and news, preping for cran submission (…

…#301)

# Pull Request

<!--- Replace `#nnn` with your issue link for reference. -->

Fixes #nnn

---------

Co-authored-by: Emily de la Rua <emily.de_la_rua@contractors.roche.com>

.Rbuildignore

@@ -37,6 +37,7 @@
 ^staged_dependencies\.yaml$
 ^\.gitlab-ci\.yml$
 ^LICENSE\.md$
+LICENSE
 coverage.*
 ^\.markdownlint\.json$
 .pre-commit-config.yaml

DESCRIPTION

@@ -1,19 +1,23 @@
 Type: Package
 Package: random.cdisc.data
-Title: Create Random SDTM and ADAM Datasets
-Version: 0.3.14.9009
-Date: 2024-03-04
+Title: Create Random ADaM Datasets
+Version: 0.3.15
+Date: 2024-03-26
 Authors@R: c(
-    person("Pawel", "Rucki", , "pawel.rucki@roche.com", role = c("aut", "cre")),
+    person("Pawel", "Rucki", , "pawel.rucki@roche.com", role = "aut"),
     person("Nick", "Paszty", , "npaszty@gene.com", role = "aut"),
     person("Jana", "Stoilova", , "jana.stoilova@roche.com", role = "aut"),
-    person("Joe", "Zhu", , "joe.zhu@roche.com", role = "aut"),
+    person("Joe", "Zhu", , "joe.zhu@roche.com", role = c("aut", "cre")),
+    person("Davide", "Garolini", , "davide.garolini@roche.com", role = "aut"),
+    person("Emily", "de la Rua", , "emily.de_la_rua@contractors.roche.com", role = "aut"),
     person("Christopher", "DiPietrantonio", role = "aut"),
     person("Adrian", "Waddell", , "adrian.waddell@gene.com", role = "aut"),
     person("F. Hoffmann-La Roche AG", role = c("cph", "fnd"))
   )
-Description: Create random CDISC data.
-License: Apache License 2.0 | file LICENSE
+Description: A set of functions to create random Analysis Data Model (ADaM) datasets and cached dataset.
+    ADaM dataset specifications are described by the Clinical Data Interchange Standards Consortium (CDISC) 
+    Analysis Data Model Team.
+License: Apache License 2.0 
 Depends:
     R (>= 3.6)
 Imports:

NAMESPACE

@@ -1,5 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
+export(apply_metadata)
 export(mutate_na)
 export(radab)
 export(radae)
@@ -22,9 +23,13 @@ export(radsub)
 export(radtr)
 export(radtte)
 export(radvs)
+export(rel_var)
 export(replace_na)
 export(rtexp)
 export(rtpois)
+export(sample_fct)
+export(var_relabel)
+export(visit_schedule)
 import(dplyr)
 importFrom(lifecycle,badge)
 importFrom(magrittr,"%>%")

NEWS.md

@@ -1,4 +1,4 @@
-# random.cdisc.data 0.3.14.9009
+# random.cdisc.data 0.3.15
 
 ### New features
 * Asynchronous cached data updates in `rebuild_cached_data` vignette - data is only updated if its (or its dependency's) source file has been updated.

R/radqlqc.R

@@ -274,12 +274,6 @@ NULL
 #'
 #' @return a dataframe with SDTM questionnaire data
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' qs <- random.cdisc.data:::get_qs_data(adsl, n_assessments = 5L, seed = 1, na_percentage = 0.1)
-#' qs
-#' }
 get_qs_data <- function(adsl,
                         visit_format = "CYCLE",
                         n_assessments = 5L,
@@ -572,23 +566,6 @@ get_qs_data <- function(adsl,
 #'
 #' @return Data frame with new randomly generated dates variable.
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' df <- dplyr::left_join(
-#'   adsl,
-#'   qs,
-#'   by = c("STUDYID", "USUBJID"),
-#'   multiple = "all"
-#' ) |>
-#'   dplyr::mutate(
-#'     AVISIT = VISIT,
-#'     PARAMCD = QSTESTCD,
-#'     AVISITN = VISITNUM
-#'   ) |>
-#'   dplyr::mutate(ADTM = random.cdisc.data:::get_random_dates_between(TRTSDTM, TRTEDTM, AVISITN))
-#' df
-#' }
 get_random_dates_between <- function(from, to, visit_id) {
   min_date <- min(lubridate::as_datetime(from), na.rm = TRUE)
   max_date <- max(lubridate::as_datetime(to), na.rm = TRUE)
@@ -618,12 +595,6 @@ get_random_dates_between <- function(from, to, visit_id) {
 #'
 #' @return `data.frame`
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' adqlqc1 <- random.cdisc.data:::prep_adqlqc(df = qs)
-#' adqlqc1
-#' }
 prep_adqlqc <- function(df) {
   # create PARAMCD from QSTESTCD
   adqlqc <- dplyr::mutate(
@@ -677,12 +648,6 @@ prep_adqlqc <- function(df) {
 #'
 #' @return `data.frame`
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' df_scales <- random.cdisc.data:::calc_scales(df)
-#' df_scales
-#' }
 calc_scales <- function(adqlqc1) {
   # Prep scale data ---------------------------------------------------------
   # parcat2 = scales or global health status
@@ -958,12 +923,6 @@ calc_scales <- function(adqlqc1) {
 #'
 #' @return `data.frame`
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' adqlqc <- random.cdisc.data:::derv_chgcat1(dataset = adqlqc |> dplyr::select(-CHGCAT1))
-#' adqlqc
-#' }
 derv_chgcat1 <- function(dataset) {
   # derivation of CHGCAT1
   check_vars <- c("PARCAT2", "CHG")
@@ -1164,12 +1123,6 @@ derv_chgcat1 <- function(dataset) {
 #'
 #' @return `data.frame`
 #' @keywords internal
-#'
-#' @examples
-#' \dontrun{
-#' compliance_data <- random.cdisc.data:::comp_derv(adqlqc, 80, 2)
-#' compliance_data
-#' }
 comp_derv <- function(dataset, percent, number) {
   # original items data
   orig_data <- filter(

R/radsub.R

@@ -19,12 +19,6 @@
 #'
 #' @return a dataframe with anthropometric measurements for each subject in analysis dataset.
 #' @keywords internal
-#'
-#' @examples
-#' adsl <- radsl(N = 5, seed = 1)
-#'
-#' df_with_measurements <- random.cdisc.data:::h_anthropometrics_by_sex(df = adsl)
-#' df_with_measurements
 h_anthropometrics_by_sex <- function(df,
                                      seed = 1,
                                      id_var = "USUBJID",

R/utils.R

@@ -26,11 +26,11 @@ get_cached_data <- function(dataname) {
 #' @param ... Additional arguments to be passed to `sample`.
 #'
 #' @return A factor of length `N`.
-#' @keywords internal
+#' @export
 #'
 #' @examples
-#' random.cdisc.data:::sample_fct(letters[1:3], 10)
-#' random.cdisc.data:::sample_fct(iris$Species, 10)
+#' sample_fct(letters[1:3], 10)
+#' sample_fct(iris$Species, 10)
 sample_fct <- function(x, N, ...) { # nolint
   checkmate::assert_number(N)
 
@@ -40,17 +40,14 @@ sample_fct <- function(x, N, ...) { # nolint
 #' Related Variables: Initialize
 #'
 #' Verify and initialize related variable values.
+#' For example, `relvar_init("Alanine Aminotransferase Measurement", "ALT")`.
 #'
 #' @param relvar1 (`list` of `character`)\cr List of n elements.
 #' @param relvar2 (`list` of `character`)\cr List of n elements.
 #'
 #' @return A vector of n elements.
 #'
 #' @keywords internal
-#'
-#' @examples
-#' random.cdisc.data:::relvar_init("Alanine Aminotransferase Measurement", "ALT")
-#' random.cdisc.data:::relvar_init("Alanine Aminotransferase Measurement", "U/L")
 relvar_init <- function(relvar1, relvar2) {
   checkmate::assert_character(relvar1, min.len = 1, any.missing = FALSE)
   checkmate::assert_character(relvar2, min.len = 1, any.missing = FALSE)
@@ -75,7 +72,7 @@ relvar_init <- function(relvar1, relvar2) {
 #' of `var_name` must relate.
 #'
 #' @return `df` with added factor variable `var_name` containing `var_values` corresponding to `related_var`.
-#' @keywords internal
+#' @export
 #'
 #' @examples
 #' # Example with data.frame.
@@ -87,7 +84,7 @@ relvar_init <- function(relvar1, relvar2) {
 #'     levels = params
 #'   )
 #' )
-#' random.cdisc.data:::rel_var(
+#' rel_var(
 #'   df = adlb_df,
 #'   var_name = "PARAMCD",
 #'   var_values = c("A", "B", "C"),
@@ -102,7 +99,7 @@ relvar_init <- function(relvar1, relvar2) {
 #'     levels = params
 #'   )
 #' )
-#' random.cdisc.data:::rel_var(
+#' rel_var(
 #'   df = adlb_tbl,
 #'   var_name = "PARAMCD",
 #'   var_values = c("A", "B", "C"),
@@ -135,11 +132,11 @@ rel_var <- function(df, var_name, related_var, var_values = NULL) {
 #' @inheritParams argument_convention
 #'
 #' @return A factor of length `n_assessments`.
-#' @keywords internal
+#' @export
 #'
 #' @examples
-#' random.cdisc.data:::visit_schedule(visit_format = "WEeK", n_assessments = 10L)
-#' random.cdisc.data:::visit_schedule(visit_format = "CyCLE", n_assessments = 5L, n_days = 2L)
+#' visit_schedule(visit_format = "WEeK", n_assessments = 10L)
+#' visit_schedule(visit_format = "CyCLE", n_assessments = 5L, n_days = 2L)
 visit_schedule <- function(visit_format = "WEEK",
                            n_assessments = 10L,
                            n_days = 5L) {
@@ -173,15 +170,8 @@ visit_schedule <- function(visit_format = "WEEK",
 #' @param value_var (`any`)\cr Variable in `df` containing the value to be retained.
 #' @param event (`expression`)\cr Expression returning a logical value to trigger the retain.
 #' @param outside (`any`)\cr Additional value to retain. Defaults to `NA`.
-#'
+#' @return A vector of values where expression is true.
 #' @keywords internal
-#'
-#' @examples
-#' adlb <- radlb(radsl(N = 10, na_percentage = 0), na_vars = list())
-#' adlb$BASE2 <- random.cdisc.data:::retain(
-#'   df = adlb, value_var = adlb$AVAL,
-#'   event = adlb$ABLFL2 == "Y"
-#' )
 retain <- function(df, value_var, event, outside = NA) {
   indices <- c(1, which(event == TRUE), nrow(df) + 1)
   values <- c(outside, value_var[event == TRUE])
@@ -195,12 +185,13 @@ retain <- function(df, value_var, event, outside = NA) {
 #' @param x (`data.frame`)\cr Data frame containing variables to which labels are applied.
 #' @param ... (`named character`)\cr Name-Value pairs, where name corresponds to a variable
 #' name in `x` and the value to the new variable label.
+#' @return x (`data.frame`)\cr Data frame with labels applied.
 #'
-#' @keywords internal
+#' @export
 #'
 #' @examples
 #' adsl <- radsl()
-#' random.cdisc.data:::var_relabel(adsl,
+#' var_relabel(adsl,
 #'   STUDYID = "Study Identifier",
 #'   USUBJID = "Unique Subject Identifier"
 #' )
@@ -225,16 +216,16 @@ var_relabel <- function(x, ...) {
 #' @param filename (`yaml`)\cr File containing domain metadata.
 #' @param add_adsl (`logical`)\cr Should ADSL data be merged to domain.
 #' @param adsl_filename (`yaml`)\cr File containing ADSL metadata.
+#' @return Data frame with metadata applied.
 #'
-#' @keywords internal
-#'
+#' @export
 #' @examples
 #' seed <- 1
 #' adsl <- radsl(seed = seed)
 #' adsub <- radsub(adsl, seed = seed)
 #' yaml_path <- file.path(path.package("random.cdisc.data"), "inst", "metadata")
-#' adsl <- random.cdisc.data:::apply_metadata(adsl, file.path(yaml_path, "ADSL.yml"), FALSE)
-#' adsub <- random.cdisc.data:::apply_metadata(
+#' adsl <- apply_metadata(adsl, file.path(yaml_path, "ADSL.yml"), FALSE)
+#' adsub <- apply_metadata(
 #'   adsub, file.path(yaml_path, "ADSUB.yml"), TRUE,
 #'   file.path(yaml_path, "ADSL.yml")
 #' )
@@ -250,20 +241,21 @@ apply_metadata <- function(df, filename, add_adsl = TRUE, adsl_filename = "metad
     }
 
     if (type == "character" && !is.character(df[[var]])) {
-      df[[var]] <<- as.character(df[[var]])
+      df[[var]] <- as.character(df[[var]])
     } else if (type == "factor" && !is.factor(df[[var]])) {
-      df[[var]] <<- as.factor(df[[var]])
+      df[[var]] <- as.factor(df[[var]])
     } else if (type == "integer" && !is.integer(df[[var]])) {
-      df[[var]] <<- as.integer(df[[var]])
+      df[[var]] <- as.integer(df[[var]])
     } else if (type == "numeric" && !is.numeric(df[[var]])) {
-      df[[var]] <<- as.numeric(df[[var]])
+      df[[var]] <- as.numeric(df[[var]])
     } else if (type == "logical" && !is.logical(df[[var]])) {
-      df[[var]] <<- as.logical(df[[var]])
+      df[[var]] <- as.logical(df[[var]])
     } else if (type == "datetime" && !lubridate::is.POSIXct(df[[var]])) {
-      df[[var]] <<- as.POSIXct(df[[var]])
+      df[[var]] <- as.POSIXct(df[[var]])
     } else if (type == "date" && !lubridate::is.Date(df[[var]])) {
-      df[[var]] <<- as.Date(df[[var]])
+      df[[var]] <- as.Date(df[[var]])
     }
+    return(df)
   }
 
   # remove existing attributes
@@ -306,7 +298,7 @@ apply_metadata <- function(df, filename, add_adsl = TRUE, adsl_filename = "metad
 
   # assign labels to variables
   for (var in metadata_varnames) {
-    apply_type(df, var, metadata_variables[[var]]$type)
+    df <- apply_type(df, var, metadata_variables[[var]]$type)
     attr(df[[var]], "label") <- metadata_variables[[var]]$label
   }
 
@@ -362,6 +354,8 @@ replace_na <- function(v, percentage = 0.05, seed = NULL) {
 #' @inheritParams argument_convention
 #' @param ds (`data.frame`)\cr Any data set.
 #'
+#' @return dataframe without `NA` values.
+#'
 #' @export
 mutate_na <- function(ds, na_vars = NULL, na_percentage = 0.05) {
   if (!is.null(na_vars)) {

inst/WORDLIST

@@ -50,6 +50,7 @@ Pharmacokinetics
 QLQ
 QS
 Repo
+Rua
 SDTM
 SDs
 SMQ
@@ -65,6 +66,7 @@ Xuefeng
 anthropometric
 cdisc
 datetime
+de
 dipietrc
 funder
 metres