[refactor]: separate out convert output processes by model into own files

R/data.R

@@ -3,7 +3,7 @@
 #' Included data set that represents a Report.sso file converted using
 #' convert_output(). This example is from the 2022 Petrale sole stock assessment.
 #'
-#' @format A tibble with 591109 rows and 33 variables:
+#' @format A tibble (\code{tbl_df}, \code{tbl}, \code{data.frame}) with 591109 rows and 33 variables:
 #' \describe{
 #'   \item{label}{Standard name for estimate or value name}
 #'   \item{estimate}{Actual value of the label}
@@ -41,3 +41,178 @@
 #' }
 #'
 "example_data"
+
+#' 2018 Gulf of Alaska Pollock stock assessment output
+#'
+#' Standardized output of the 2018 Gulf of Alaska Pollock stock assessment 
+#' produced from Rceattle including all of the values needed to create 
+#' plots and tables in {stockplotr}. The example can be found and run from the 
+#' Rceattle repository.
+#'
+#' @docType data
+#'
+#' @usage data(pollock)
+#'
+#' @format A tibble (\code{tbl_df}, \code{tbl}, \code{data.frame}) with 9,983 rows and 35 variables:
+#' \describe{
+#'   \item{label}{Standard name for estimate or value name}
+#'   \item{estimate}{Actual value of the label}
+#'   \item{year}{Annual indexing value}
+#'   \item{fleet}{Names of fleets or surveys indexed by the data}
+#'   \item{sex}{Native reference to male, female, unknown, or none}
+#'   \item{area}{Specified areas by the model}
+#'   \item{growth_pattern}{Indexing column of data}
+#'   \item{uncertainty}{Value of uncertainty associated with the label column}
+#'   \item{uncertainty_label}{Uncertainty label or name associated with the label columns}
+#'   \item{module_name}{Name of keyword (SS3) or list indexing in the original model output for tracking purposes}
+#'   \item{time}{Time sometimes referenced in decimals to the year and month}
+#'   \item{era}{"time" for current time series in model; "fore" representing the projected or forecasted years of the model}
+#'   \item{month}{Month factor}
+#'   \item{season}{Season usually associated with year}
+#'   \item{subseason}{Subseason when used}
+#'   \item{birthseas}{Birthseason found in SS3}
+#'   \item{initial}{Initial input value in the model when available associated with the label column}
+#'   \item{likelihood}{Likelihood value for the data point}
+#'   \item{platoon}{Platoon also an SS3 indexing value}
+#'   \item{age}{Age of fish}
+#'   \item{bio_pattern}{Indexing column of data}
+#'   \item{settlement}{Indexing column of data}
+#'   \item{morph}{Indexing column of data}
+#'   \item{type}{Indexing column of data}
+#'   \item{factor}{Indexing column of data}
+#'   \item{part}{Indexing column of data}
+#'   \item{kind}{Indexing column of data}
+#'   \item{nsim}{Indexing column of data}
+#'   \item{bin}{Indexing column of data}
+#'   \item{age_a}{Alternative age column}
+#'   \item{length_bins}{Length bins for composition or other length based data}
+#'   \item{count}{Indexing column of data}
+#'   \item{block}{Indexing column of data}
+#' }
+#'
+#' @keywords datasets
+#'
+#' @references Adams, G. D., Holsman, K. K., Barbeaux, S. J., Dorn, M. W., Ianelli, J. N., Spies, I., … Punt, A. E. (2022)
+#' (\href{https://doi.org/10.1016/j.fishres.2022.106303})
+#'
+#' @source \href{https://github.com/afsc-assessments/Rceattle/blob/main/examples/Fit_2018_GOA_single-species_models.R}{Rceattle Example}
+#'
+#' @examples
+#' data(pollock)
+#' head(pollock)
+#' unique(pollock$label)
+"pollock"
+
+#' SEDAR 55 South Atlantic Vermilion Snapper
+#'
+#' Standardized output of the 2018 South Atlantic Vermilion Snapper stock assessment 
+#' produced from the Beaufort Assessment Model (BAM).
+#'
+#' @docType data
+#'
+#' @usage data(vermilion_snapper)
+#'
+#' @format A tibble (\code{tbl_df}, \code{tbl}, \code{data.frame}) with 35,881 rows and 35 variables:
+#' \describe{
+#'   \item{label}{Standard name for estimate or value name}
+#'   \item{estimate}{Actual value of the label}
+#'   \item{year}{Annual indexing value}
+#'   \item{fleet}{Names of fleets or surveys indexed by the data}
+#'   \item{sex}{Native reference to male, female, unknown, or none}
+#'   \item{area}{Specified areas by the model}
+#'   \item{growth_pattern}{Indexing column of data}
+#'   \item{uncertainty}{Value of uncertainty associated with the label column}
+#'   \item{uncertainty_label}{Uncertainty label or name associated with the label columns}
+#'   \item{module_name}{Name of keyword (SS3) or list indexing in the original model output for tracking purposes}
+#'   \item{time}{Time sometimes referenced in decimals to the year and month}
+#'   \item{era}{"time" for current time series in model; "fore" representing the projected or forecasted years of the model}
+#'   \item{month}{Month factor}
+#'   \item{season}{Season usually associated with year}
+#'   \item{subseason}{Subseason when used}
+#'   \item{birthseas}{Birthseason found in SS3}
+#'   \item{initial}{Initial input value in the model when available associated with the label column}
+#'   \item{likelihood}{Likelihood value for the data point}
+#'   \item{platoon}{Platoon also an SS3 indexing value}
+#'   \item{age}{Age of fish}
+#'   \item{bio_pattern}{Indexing column of data}
+#'   \item{settlement}{Indexing column of data}
+#'   \item{morph}{Indexing column of data}
+#'   \item{type}{Indexing column of data}
+#'   \item{factor}{Indexing column of data}
+#'   \item{part}{Indexing column of data}
+#'   \item{kind}{Indexing column of data}
+#'   \item{nsim}{Indexing column of data}
+#'   \item{bin}{Indexing column of data}
+#'   \item{age_a}{Alternative age column}
+#'   \item{length_bins}{Length bins for composition or other length based data}
+#'   \item{count}{Indexing column of data}
+#'   \item{block}{Indexing column of data}
+#' }
+#'
+#' @keywords datasets
+#' 
+#' @references SEDAR (2018)
+#' (\href{https://sedarweb.org/documents/sedar-55-stock-assessment-report-south-atlantic-vermilion-snapper/})
+#'
+#' @examples
+#' data(vermilion_snapper)
+#' head(vermilion_snapper)
+#' unique(vermilion_snapper$label)
+"vermilion_snapper"
+
+#' SS3 Simple stock assessment output
+#'
+#' Standardized output of a generic simple example of SS3 found from the `r4ss` 
+#' repository examples. The raw output is converted to an R readable object 
+#' using `r4ss::ss_output` then standardized using `stockplotr::convert_output()`. 
+#'
+#' @docType data
+#'
+#' @usage data(ss3_simple)
+#'
+#' @format A tibble (\code{tbl_df}, \code{tbl}, \code{data.frame}) with 38,195 rows and 35 variables:
+#' \describe{
+#'   \item{label}{Standard name for estimate or value name}
+#'   \item{estimate}{Actual value of the label}
+#'   \item{year}{Annual indexing value}
+#'   \item{fleet}{Names of fleets or surveys indexed by the data}
+#'   \item{sex}{Native reference to male, female, unknown, or none}
+#'   \item{area}{Specified areas by the model}
+#'   \item{growth_pattern}{Indexing column of data}
+#'   \item{uncertainty}{Value of uncertainty associated with the label column}
+#'   \item{uncertainty_label}{Uncertainty label or name associated with the label columns}
+#'   \item{module_name}{Name of keyword (SS3) or list indexing in the original model output for tracking purposes}
+#'   \item{time}{Time sometimes referenced in decimals to the year and month}
+#'   \item{era}{"time" for current time series in model; "fore" representing the projected or forecasted years of the model}
+#'   \item{month}{Month factor}
+#'   \item{season}{Season usually associated with year}
+#'   \item{subseason}{Subseason when used}
+#'   \item{birthseas}{Birthseason found in SS3}
+#'   \item{initial}{Initial input value in the model when available associated with the label column}
+#'   \item{likelihood}{Likelihood value for the data point}
+#'   \item{platoon}{Platoon also an SS3 indexing value}
+#'   \item{age}{Age of fish}
+#'   \item{bio_pattern}{Indexing column of data}
+#'   \item{settlement}{Indexing column of data}
+#'   \item{morph}{Indexing column of data}
+#'   \item{type}{Indexing column of data}
+#'   \item{factor}{Indexing column of data}
+#'   \item{part}{Indexing column of data}
+#'   \item{kind}{Indexing column of data}
+#'   \item{nsim}{Indexing column of data}
+#'   \item{bin}{Indexing column of data}
+#'   \item{age_a}{Alternative age column}
+#'   \item{length_bins}{Length bins for composition or other length based data}
+#'   \item{count}{Indexing column of data}
+#'   \item{block}{Indexing column of data}
+#' }
+#'
+#' @keywords datasets
+#'
+#' @source \href{https://github.com/r4ss/r4ss/}{r4ss Repository}
+#'
+#' @examples
+#' data(ss3_simple)
+#' head(ss3_simple)
+#' unique(ss3_simple$label)
+"ss3_simple"

data-raw/DATASET_BAM.R

@@ -1,10 +1,12 @@
-## code to prepare `VermilionSnapper` dataset goes here
+## code to prepare `vermilion_snapper` dataset goes here
 # Path to SS3 output file
 EX_REPORT_PATH <- file.path("inst", "extdata", "VermilionSnapper.rdat")
 # Install stockplotr
 pak::local_install(".")
 # Convert output
-VermilionSnapper <- stockplotr::convert_output(EX_REPORT_PATH)
-VermilionSnapper <- subset(VermilionSnapper, year > 1980)
+vermilion_snapper <- stockplotr::convert_output(EX_REPORT_PATH)
+vermilion_snapper <- subset(vermilion_snapper, year > 1980)
 # Save object as rda into raw_data
-usethis::use_data(VermilionSnapper, overwrite = TRUE)
+usethis::use_data(vermilion_snapper, overwrite = TRUE)
+# Overwrite as compressed data
+save(vermilion_snapper, file = "data/vermilion_snapper.rda", compress = "xz", compression_level = 9)

data-raw/DATASET_RCEATTLE.R

@@ -4,7 +4,7 @@ install.packages(c("remotes")) # , "readxl"
 remotes::install_github("afsc-assessments/Rceattle")
 # library(Rceattle)
 # library(readxl)
-Rceattle::data("GOApollock")
+data("GOApollock")
 GOApollock$styr = 1977 # The SAFE model starts at 1970, so change styr to 1970 to run the full time series model (data is in there). I start them all at 1977 because thats the years with overlap.
 pollock_model <- Rceattle::fit_mod(
   data_list = GOApollock,
@@ -20,5 +20,7 @@ pak::local_install(".")
 # Convert output
 # OK not to subset bc small
 pollock <- stockplotr::convert_output(pollock_model)
-# Save object as rda into raw_data
+# Save object as rda into raw_data -- and document
 usethis::use_data(pollock, overwrite = TRUE)
+# Overwrite compressed version
+save(pollock, file = "data/pollock.rda", compress = "xz", compression_level = 9)