Add datasets (#19)

Added example datasets and documentation for them including citations.

* Added datasets and testing. Working on documentation.

* Updated data file documentation.

* Slightly updated description of metabolic data to not have a copy-paste of lizard size info.

* Forgot to change format reference name.

* Removed metabolic rate data as it's not set up for DE fitting.

* Removed .rd file for metabolic data.

* Updated vb model to have a y_max parameter pass in as the initial mean estimate of the maximum value in order to avoid intialisation problems.

* Updated example G. recondita data to avoid individuals with <1.5cm growth over observation period.

* Replaced G. recondita with H. triandra data because I forgot I need to not double-up on first paper.

* Removed vB model as it needs fixing on its own branch.

* Removed vb from the switch call in rmot_models.R

* Added P. tenufolium small tree data.

* Updated documentation of data to have correct sample size.

* Forcing update of documentation.

* Finally got the documentation to work.

.gitignore

@@ -61,3 +61,6 @@ src/rmot.dll
 
 # Bugged directory from snapshot package
 tests/testthat/_snaps
+
+# Data prep files
+data-raw/

DESCRIPTION

@@ -43,3 +43,4 @@ Suggests:
     mnormt
 VignetteBuilder: knitr
 Config/testthat/edition: 3
+LazyData: true

R/data.R

@@ -0,0 +1,87 @@
+#' SUSTAIN Salmo trutta data
+#'
+#' A subset of data from the SUSTAIN trout capture-recapture data set
+#' from Moe et al. (2020).
+#' Data prepared by taking a stratified sample of individual IDs based on the
+#' number of observations per individual: 25 individuals with 2 observations,
+#' 15 with 3, 10 with 4. Within the groups a simple random sample
+#' without replacement was used. Data was then transformed and
+#' renamed to match the required structure to act as demonstration for
+#' the package.
+#'
+#' @format ## `Trout_Size_Data`
+#' A data frame with 135 rows and 4 columns:
+#' \describe{
+#'   \item{ind_id}{ID number for individual}
+#'   \item{time}{Years since first capture and tagging of individual.}
+#'   \item{y_obs}{Individual length in centimetres.}
+#'   \item{obs_index}{Index of observations for individual}
+#' }
+#' @source <https://doi.org/10.3897/BDJ.8.e52157>
+"Trout_Size_Data"
+
+#' Skink size data - Lampropholis delicata
+#'
+#' A subset of data from Kar, Nakagawa, and Noble (2024), used to model growth
+#' behaviour in a skink species.
+#' Data was prepared by taking a simple random sample with replacement of 50
+#' individual IDs among individuals with at least 5 observations each. Data was
+#' then transformed to conform to the needs of a model data set in the package.
+#'
+#' @format ## `Lizard_Mass_Data`
+#' A data frame with 336 rows and 4 columns:
+#' \describe{
+#'   \item{ind_id}{ID number for individual}
+#'   \item{time}{Days since first observation.}
+#'   \item{y_obs}{Individual mass in kilograms.}
+#'   \item{obs_index}{Index of observations for individual}
+#' }
+#'
+#' @source \url{https://osf.io/hjkxd/}
+"Lizard_Mass_Data"
+
+#' Protium tenufolium - Barro Colorado Island data
+#'
+#' A subset of data from the Barro Colorado Island long term forest plot
+#' managed by the Smithsonian Tropical Research Institute (Condit et al. 2019).
+#' Data was prepared by taking a simple random sample without replacement of
+#' 30 individual IDs from Protium tenufolium.
+#' The sampling frame was restricted to individuals with individuals under 10cm
+#' for the max observed DBH, 6 observations since 1990. Data was then
+#' transformed and renamed to match the required structure
+#' to act as demonstration for the package.
+#'
+#' @format ## `Small_Tree_Size_Data`
+#' A data frame with 180 rows and 4 columns:
+#' \describe{
+#'   \item{ind_id}{ID number for individual}
+#'   \item{time}{Years since first observation.}
+#'   \item{y_obs}{Individual diameter at breast height (DBH) in centimetres.}
+#'   \item{obs_index}{Index of observations for individual}
+#' }
+#' @references \url{https://doi.org/10.1002/ecy.4140}
+#' @source \url{https://doi.org/10.15146/5xcp-0d46}
+"Small_Tree_Size_Data"
+
+#' Hirtella triandra - Barro Colorado Island data
+#'
+#' A subset of data from the Barro Colorado Island long term forest plot
+#' managed by the Smithsonian Tropical Research Institute (Condit et al. 2019).
+#' Data was prepared by taking a simple random sample without replacement of
+#' 30 individual IDs from Hirtella triandra. The sampling frame was restricted
+#' to individuals with 6 observations since 1990, and a difference between
+#' observed max and min sizes of more than 7cm in order to avoid identifiability
+#' issues. Data was then transformed and renamed to match the required structure
+#' to act as demonstration for the package.
+#'
+#' @format ## `Tree_Size_Data`
+#' A data frame with 180 rows and 4 columns:
+#' \describe{
+#'   \item{ind_id}{ID number for individual}
+#'   \item{time}{Years since first observation.}
+#'   \item{y_obs}{Individual diameter at breast height (DBH) in centimetres.}
+#'   \item{obs_index}{Index of observations for individual}
+#' }
+#' @references \url{https://doi.org/10.1002/ecy.4140}
+#' @source \url{https://doi.org/10.15146/5xcp-0d46}
+"Tree_Size_Data"

R/rmot_models.R

@@ -19,9 +19,7 @@ rmot_model <- function(model=NULL){
                    canham_single_ind = rmot_canham_single_ind(),
                    canham_multi_ind = rmot_canham_multi_ind(),
                    power_single_ind = rmot_power_single_ind(),
-                   power_multi_ind = rmot_power_multi_ind(),
-                   vb_single_ind = rmot_vb_single_ind(),
-                   vb_multi_ind = rmot_vb_multi_ind())
+                   power_multi_ind = rmot_power_multi_ind())
 
   class(output) <- "rmot_object"
 
@@ -128,33 +126,3 @@ rmot_power_multi_ind <- function(){
        y_0_obs = NULL,
        model = "power_multi_ind")
 }
-
-#' Data configuration template for von Bertalanffy growth single individual model
-#' @keywords internal
-#' @noRd
-
-rmot_vb_single_ind <- function(){
-  list(step_size = NULL,
-       n_obs = NULL,
-       y_obs = NULL,
-       obs_index = NULL,
-       time = NULL,
-       y_0_obs = NULL,
-       model = "vb_single_ind")
-}
-
-#' Data configuration template for von Bertalanffy growth single species model
-#' @keywords internal
-#' @noRd
-
-rmot_vb_multi_ind <- function(){
-  list(step_size = NULL,
-       n_obs = NULL,
-       n_ind = NULL,
-       y_obs = NULL,
-       obs_index = NULL,
-       time = NULL,
-       ind_id = NULL,
-       y_0_obs = NULL,
-       model = "vb_multi_ind")
-}

R/rmot_run.R

@@ -22,9 +22,7 @@ rmot_run <- function(model_template, ...) {
          canham_single_ind = rstan::sampling(stanmodels$canham_single_ind, data = model_template, ...),
          canham_multi_ind = rstan::sampling(stanmodels$canham_multi_ind, data = model_template, ...),
          power_single_ind = rstan::sampling(stanmodels$power_single_ind, data = model_template, ...),
-         power_multi_ind = rstan::sampling(stanmodels$power_multi_ind, data = model_template, ...),
-         vb_single_ind = rstan::sampling(stanmodels$vb_single_ind, data = model_template, ...),
-         vb_multi_ind = rstan::sampling(stanmodels$vb_multi_ind, data = model_template, ...))
+         power_multi_ind = rstan::sampling(stanmodels$power_multi_ind, data = model_template, ...))
 
   return(out)
 }

R/stanmodels.R

@@ -1,7 +1,7 @@
 # Generated by rstantools.  Do not edit by hand.
 
 # names of stan models
-stanmodels <- c("canham_multi_ind", "canham_single_ind", "constant_multi_ind", "constant_single_ind", "linear", "power_multi_ind", "power_single_ind", "vb_multi_ind", "vb_single_ind")
+stanmodels <- c("canham_multi_ind", "canham_single_ind", "constant_multi_ind", "constant_single_ind", "linear", "power_multi_ind", "power_single_ind")
 
 # load each stan module
 Rcpp::loadModule("stan_fit4canham_multi_ind_mod", what = TRUE)
@@ -11,8 +11,6 @@ Rcpp::loadModule("stan_fit4constant_single_ind_mod", what = TRUE)
 Rcpp::loadModule("stan_fit4linear_mod", what = TRUE)
 Rcpp::loadModule("stan_fit4power_multi_ind_mod", what = TRUE)
 Rcpp::loadModule("stan_fit4power_single_ind_mod", what = TRUE)
-Rcpp::loadModule("stan_fit4vb_multi_ind_mod", what = TRUE)
-Rcpp::loadModule("stan_fit4vb_single_ind_mod", what = TRUE)
 
 # instantiate each stanmodel object
 stanmodels <- sapply(stanmodels, function(model_name) {