Further updates to data name and and use of PBC data.

.Rd files committed as a reference point.

R/data.R

@@ -1,61 +1,109 @@
-#' Worksheet for pbc dataset
+#' PBC Dataset Collection
+#' @docType data
+#' @name pbc_datasets
 #' @description
-#' The variable and variable_details worksheets that holds metadata for the pbc dataset.
+#' A collection of related datasets containing PBC data and metadata.
 #'
-#' @format A list containing DCMI metadata:
+#' @details
+#' The collection contains four datasets:
 #' \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}
+#' \item{pbc}{Primary Biliary Cirrhosis (PBC) data collected at Mayo Clinic between 1974 and 1984. A data frame with 418 observations and 20 variables including patient characteristics, biochemical measurements, and clinical outcomes.}
+#' \item{pbc_metadata}{DCMI metadata for the PBC database. A list containing the database name and other identification information.}
+#' \item{pbc_variables}{'variables' metadata for the PBC dataset. Metadata for each variable in the PBC data. A data frame with 24 rows and 11 columns.}
+#' \item{pbc_variable_details}{`variable_details` metadata for the PBC dataset. Metadata for variable category or value label in the PBC data. A data frame with 69 rows and 16 columns.}
 #' }
-#' @source \url{https://cran.r-project.org/web/packages/survival/survival.pdf}
-"pbc_data"
+#'
+#' @source The PBC dataset is from the survival package:
+#' \url{https://cran.r-project.org/web/packages/survival/survival.pdf}
+#' 
+#' The metadata (pbc_metadata, pbc_variables, and pbc_variable_details) were created 
+#' specifically for the recodeflow package to demonstrate and test the package functionality.
+NULL
+
+#' @rdname pbc_datasets
+#' @format ## pbc
+#' 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)}
+#' }
+"pbc"
+
+#' @rdname pbc_datasets
+#' @format ## pbc_metadata
+#' 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"
 
-#' @rdname pbc_data
-#' @format A data frame with 24 rows and 11 columns:
+#' @rdname pbc_datasets
+#' @format ## pbc_variables
+#' 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}
+#' \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"
 
-#' @rdname pbc_data
-#' @format A data frame with 69 rows and 16 columns:
+#' @rdname pbc_datasets
+#' @format ## pbc_variable_details
+#' 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}
+#' \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/pbc_worksheets.R

@@ -2,9 +2,9 @@ library(yaml)
 library(readr)
 library(usethis)
 
-# import the pbc_data.yaml file.
-pbc_data <- read_yaml("inst/extdata/pbc_data.yaml")
-usethis::use_data(pbc_data, overwrite = TRUE)
+# import the pbc_metadata.yaml file.
+pbc_metadata <- read_yaml("inst/extdata/pbc_metadata.yaml")
+usethis::use_data(pbc_metadata, overwrite = TRUE)
 
 # import the pbc_variables.csv file.
 pbc_variables <- read_csv("inst/extdata/pbc_variables.csv")

_pkgdown.yml

@@ -56,7 +56,7 @@ reference:
     contents:
     - pbc_variables
     - pbc_variable_details
-  - title: "Metadata"
-    desc: Metadata files
+  - title: "Example data"
+    desc: Data for examples
     contents:
-    - pbc_database
+    - pbc_data

inst/extdata/variable.csv

@@ -0,0 +1,24 @@
+"variable","label","labelLong","subject","section","variableType","databaseStart","units","variableStart"
+"time","time","number of days between registration and the earlier of death, treatment or end of study","study","time","cont","tester1, tester2","days","[time]"
+"status","status","status at end of study","study","status","cat","tester1, tester2","N/A","[status]"
+"trt","treatment","treatment","study","trt","cat","tester1, tester2","N/A","[trt]"
+"age","age","age","demographic","age","cont","tester1, tester2","years","[age]"
+"sex","sex","sex","demographic","sex","cat","tester1, tester2","N/A","[sex]"
+"ascites","ascites","prescence of ascites","physical symptom","ascites","cat","tester1, tester2","N/A","[ascites]"
+"hepato","hepato","prescence of hepatomegaly or enlarged liver","physical symptom","hepato","cat","tester1, tester2","N/A","[hepato]"
+"spiders","spiders","prescence of spiders","physical symptom","spiders","cat","tester1, tester2","N/A","[spiders]"
+"edema","edema","edema","physical symptom","edema","cat","tester1, tester2","N/A","[edema]"
+"bili","bili","bilirunbin concentration (blood)","lab test","bili","cont","tester1, tester2","mg/dl","[bili]"
+"chol","chol","cholestral concentration (blood)","lab test","chol","cont","tester1, tester2","mg/dl","[chol]"
+"albumin","albumin","albumin concentration (blood)","lab test","albumin","cont","tester1, tester2","g/dl","[albumin]"
+"copper","copper","copper concentration (urine)","lab test","copper","cont","tester1, tester2","ug/dl","[copper]"
+"alk.phos","alk.phos","alkaline phosphotase concentration (blood)","lab test","alk.phos","cont","tester1, tester2","U/L","[alk.phos]"
+"ast","ast"," aspartate aminotransferase concentration (blood)","lab test","ast","cont","tester1, tester2","U/L","[ast]"
+"trig","trig","triglycerides concentration (blood)","lab test","trig","cont","tester1, tester2","mg/dl","[trig]"
+"platelet","platelet","platelet count","lab test","platelet","cont","tester1, tester2","N/A","[platelet]"
+"protime","protime","standarized blood clotting time","lab test","protime","cont","tester1, tester2","N/A","[protime]"
+"stage","stage","histologic stage of disease","lab test","stage","cat","tester1, tester2","N/A","[stage]"
+"example_der","example_der","example of dervived function: concentration of cholestral * concentration of bilirunbin","derived","example","cont","tester1, tester2","mg/dl","[example_der]"
+"agegrp5","agegrp5","five year age groups","demographics","age","cat","tester1","years","tester1::agegrp"
+"agegrp10","agegrp10","ten year age groups","demographics","age","cat","tester1, tester2","years","[agegrp]"
+"age_cont","age_cont","continous age created from age groups","demographics","age","cont","tester1, tester2","years","[agegrp]"