Merge branch 'main' of https://github.com/UCD-SERG/serodynamics into Kwan_2025

# Conflicts:
#	.Rbuildignore
#	.gitignore
#	DESCRIPTION
#	NEWS.md
#	tests/testthat/_snaps/run_mod/nostrat-curve-params.csv
#	tests/testthat/_snaps/run_mod/sim-strat-curve-params.csv
#	tests/testthat/_snaps/run_mod/strat-curve-params.csv

Author: Kwan-Jenny

.Rbuildignore

@@ -22,4 +22,7 @@
 ^\.project$
 ^\.settings$
 ^\.lintr\.R$
+^_extensions$
+^vignettes/\.quarto$
+^vignettes/*_files$
 

.gitignore

@@ -21,4 +21,5 @@ serodynamics*.tgz
 
 inst/doc
 docs
+**/.quarto/
 

.lintr.R

@@ -1,7 +1,7 @@
 
 
-undesirable_functions <- 
-  lintr::default_undesirable_functions |> 
+undesirable_functions <-
+  lintr::default_undesirable_functions |>
   lintr::modify_defaults(
 
     # following https://github.com/r-lib/devtools/blob/2aa51ef/.lintr.R:
@@ -25,25 +25,26 @@ undesirable_functions <-
       "\nSee:\n",
       "<https://r-pkgs.org/code.html#sec-code-r-landscape> and\n",
       "<https://r-pkgs.org/testing-design.html#sec-testing-design-self-contained>",
-      "\nfor more details"
+      "\nfor more details."
     ),
 
-    structure = NULL
-    # see https://github.com/r-lib/lintr/pull/2227 and 
+    structure = NULL,
+    browser = NULL
+    # see https://github.com/r-lib/lintr/pull/2227 and
     # rebuttal https://github.com/r-lib/lintr/pull/2227#issuecomment-1800302675
 
   )
 
 # define snake_case with uppercase acronyms allowed;
 # see https://github.com/r-lib/lintr/issues/2844 for details:
 withr::local_package("rex")
-snake_case_ACRO = rex::rex(
+snake_case_ACROs1 <- rex::rex(
   start,
   maybe("."),
-  some_of(lower, digit) %or% some_of(upper, digit),
+  list(some_of(upper), maybe("s"), zero_or_more(digit)) %or% list(some_of(lower), zero_or_more(digit)),
   zero_or_more(
     "_",
-    some_of(lower, digit) %or% some_of(upper, digit)
+    list(some_of(upper), maybe("s"), zero_or_more(digit)) %or% list(some_of(lower), zero_or_more(digit))
   ),
   end
 )
@@ -54,7 +55,7 @@ linters <- lintr::linters_with_defaults(
   lintr::redundant_equals_linter(),
   lintr::pipe_consistency_linter(pipe = "|>"),
   lintr::object_name_linter(
-    regexes = c(snake_case_ACRO = snake_case_ACRO)
+    regexes = c(snake_case_ACROs1 = snake_case_ACROs1)
   ),
   lintr::undesirable_function_linter(
     fun = undesirable_functions,
@@ -64,9 +65,19 @@ linters <- lintr::linters_with_defaults(
 
 # prevent warnings from lintr::read_settings:
 rm(undesirable_functions)
-rm(snake_case_ACRO)
+rm(snake_case_ACROs1)
 exclusions <- list(
   `data-raw` = list(
     pipe_consistency_linter = Inf
+  ),
+  vignettes = list(
+    undesirable_function_linter = Inf
+  ),
+  "inst/analyses" = list(
+    undesirable_function_linter = Inf
+  ),
+  "tests/testthat.R" = list(
+    undesirable_function_linter = Inf
   )
+  
 )

DESCRIPTION

@@ -5,7 +5,7 @@ Authors@R: c(
     person("Peter", "Teunis", , "p.teunis@emory.edu", role = c("aut", "cph"),
            comment = "Author of the method and original code."),
     person("Samuel", "Schildhauer", , "sschildhauer@ucdavis.edu", role = c("aut", "cre")),
-    person("Kwan Ho", "Lee", role = "ctb"),
+    person("Kwan Ho", "Lee", , "ksjlee@ucdavis.edu", role = "ctb"),
     person("Kristen", "Aiemjoy", , "kaiemjoy@ucdavis.edu", role = "aut"),
     person("Douglas Ezra", "Morrison", , "demorrison@ucdavis.edu", role = "aut")
   )
@@ -48,7 +48,8 @@ Suggests:
     rmarkdown,
     magrittr,
     ssdtools,
-    rex
+    rex,
+    quarto
 Language: en-US
 Config/testthat/edition: 3
 Config/needs/test: 
@@ -67,4 +68,4 @@ Remotes:
 Depends: 
     R (>= 4.1.0)
 LazyData: true
-VignetteBuilder: knitr
+VignetteBuilder: knitr, quarto

NEWS.md

@@ -4,8 +4,15 @@
 
 ## New features
 
-
 * Added `plot_predicted_curve()`  (#68)
+* Replacing old data object with new run_mod output (#102)
+* Adding class assignment to run_mod output (#76)
+* Making prep_priors modifiable (#78)
+* Changes to `run_mod()` output:
+  - Taking out `include_subs` as an input option, default will include all
+  individuals
+  - Making a single tbl as output
+  - All other pieces will be attributes.
 * Changes to `run_mod()` (#79):
    - `jags.post` now optionally included in output, as specified by argument
    `with_post`

R/Run_Mod.R

@@ -1,20 +1,20 @@
 #' @title Run Jags Model
 #' @author Sam Schildhauer
 #' @description
-#'  run_mod() takes a data frame and adjustable mcmc inputs to
-#'  [runjags::run.jags()] as an mcmc
-#'  bayesian model to estimate antibody dynamic curve parameters.
+#'  `run_mod()` takes a data frame and adjustable MCMC inputs to
+#'  [runjags::run.jags()] as an MCMC
+#'  Bayesian model to estimate antibody dynamic curve parameters.
 #'  The [rjags::jags.model()] models seroresponse dynamics to an
 #'  infection. The antibody dynamic curve includes the following parameters:
 #'  - y0 = baseline antibody concentration
 #'  - y1 = peak antibody concentration
 #'  - t1 = time to peak
-#'  - r = shape parameter
+#'  - shape = shape parameter
 #'  - alpha = decay rate
 #' @param data A [base::data.frame()] with the following columns.
 #' @param file_mod The name of the file that contains model structure.
 #' @param nchain An [integer] between 1 and 4 that specifies
-#' the number of mcmc chains to be run per jags model.
+#' the number of MCMC chains to be run per jags model.
 #' @param nadapt An [integer] specifying the number of adaptations per chain.
 #' @param nburn An [integer] specifying the number of burn ins before sampling.
 #' @param nmc An [integer] specifying the number of samples in posterior chains.
@@ -26,43 +26,50 @@
 #' should be included as an element of the [list] object returned by `run_mod()`
 #' (see `Value` section below for details).
 #' Note: These objects can be large.
-#' @param include_subs A [logical] value specifying whether posterior
-#' distributions should be included for all subjects. A value of [FALSE] will
-#' only include the predictive distribution.
-#' @returns A [list] containing the following elements:
-#' - `"jags.post"`: a [list] containing one or more [runjags::runjags-class]
-#' objects (one per stratum).
-#' - A [base::data.frame()] titled `curve_params` that contains the posterior
-#' distribution will be exported with the following attributes:
-#'   - `iteration` = number of sampling iterations
-#'   - `chain` = number of mcmc chains run; between 1 and 4
-#'   - `indexid` = "newperson", indicating posterior distribution
-#'   - `antigen_iso` = antibody/antigen type combination being evaluated
-#'   - `alpha` = posterior estimate of decay rate
-#'   - `r` = posterior estimate of shape parameter
-#'   - `t1` = posterior estimate of time to peak
-#'   - `y0` = posterior estimate of baseline antibody concentration
-#'   - `y1` = posterior estimate of peak antibody concentration
-#'   - `stratified variable` = the variable used to stratify jags model
-#' - A [list] of `attributes` that summarize the jags inputs, including:
+#' @returns An `sr_model` class object: a subclass of [dplyr::tbl_df] that
+#' contains MCMC samples from the joint posterior distribution of the model
+#' parameters, conditional on the provided input `data`, 
+#' including the following:
+#'   - `iteration` = Number of sampling iterations
+#'   - `chain` = Number of MCMC chains run; between 1 and 4
+#'   - `Parameter` = Parameter being estimated. Includes the following:
+#'     - `y0` = Posterior estimate of baseline antibody concentration
+#'     - `y1` = Posterior estimate of peak antibody concentration
+#'     - `t1` = Posterior estimate of time to peak
+#'     - `shape` = Posterior estimate of shape parameter
+#'     - `alpha` = Posterior estimate of decay rate
+#'   - `Iso_type` = Antibody/antigen type combination being evaluated
+#'   - `Stratification` = The variable used to stratify jags model
+#'   - `Subject` = ID of subject being evaluated
+#'   - `value` = Estimated value of the parameter
+#' - The following [attributes] are included in the output:
 #'   - `class`: Class of the output object.
 #'   - `nChain`: Number of chains run.
 #'   - `nParameters`: The amount of parameters estimated in the model.
 #'   - `nIterations`: Number of iteration specified.
 #'   - `nBurnin`: Number of burn ins.
-#'   - `nThin`: Thinning number (niter/nmc).
+#'   - `nThin`: Thinning number (niter/nmc)
+#'   - `priors`: A [list] that summarizes the input priors, including:
+#'     - `mu_hyp_param`
+#'     - `prec_hyp_param`
+#'     - `omega_param`
+#'     - `wishdf`
+#'     - `prec_logy_hyp_param`
+#'     - An optional `"jags.post"` attribute, included when argument
+#'   `with_post` = TRUE.
+#' @inheritDotParams prep_priors
 #' @export
 #' @example inst/examples/run_mod-examples.R
 run_mod <- function(data,
-                    file_mod,
+                    file_mod = serodynamics_example("model.jags"),
                     nchain = 4,
                     nadapt = 0,
                     nburn = 0,
                     nmc = 100,
                     niter = 100,
                     strat = NA,
                     with_post = FALSE,
-                    include_subs = FALSE) {
+                    ...) {
   ## Conditionally creating a stratification list to loop through
   if (is.na(strat)) {
     strat_list <- "None"
@@ -97,7 +104,8 @@ run_mod <- function(data,
 
     # prepare data for modeline
     longdata <- prep_data(dl_sub)
-    priors <- prep_priors(max_antigens = longdata$n_antigen_isos)
+    priorspec <- prep_priors(max_antigens = longdata$n_antigen_isos,
+                             ...)
 
     # inputs for jags model
     nchains <- nchain # nr of MC chains to run simultaneously
@@ -111,7 +119,7 @@ run_mod <- function(data,
 
     jags_post <- runjags::run.jags(
       model = file_mod,
-      data = c(longdata, priors),
+      data = c(longdata, priorspec),
       inits = initsfunction,
       method = "parallel",
       adapt = nadapt,
@@ -127,13 +135,13 @@ run_mod <- function(data,
     # stratification and will only be included if specified. 
     jags_post_final[[i]] <- jags_post
 
-    # Unpacking and cleaning mcmc output.
+    # Unpacking and cleaning MCMC output.
     jags_unpack <- ggmcmc::ggs(jags_post[["mcmc"]])
 
     # Adding attributes
     mod_atts <- attributes(jags_unpack)
-    # Only keeping necesarry attributes
-    mod_atts <- mod_atts[3:8]
+    # Only keeping necessary attributes
+    mod_atts <- mod_atts[4:8]
 
     # extracting antigen-iso combinations to correctly number
     # then by the order they are estimated by the program.
@@ -169,25 +177,27 @@ run_mod <- function(data,
   jags_out <- jags_out[complete.cases(jags_out), ]
   # Outputting the finalized jags output as a data frame with the
   # jags output results for each stratification rbinded.
-  # Logical argument to include posterior of all subjects or just the
-  # predictive distribution (new person).
-  if (!include_subs) {
-    jags_out <- jags_out |>
-      filter(.data$Subject == "newperson")
-  }
 
-  # Logical argument to keep the raw jags post or not.
+  # Making output a tibble and restructing.
+  jags_out <- dplyr::as_tibble(jags_out)  |>
+    select(!c("Parameter")) |>
+    rename("Parameter" = "Parameter_sub")
+  jags_out <- jags_out[, c("Iteration", "Chain", "Parameter", "Iso_type",
+                           "Stratification", "Subject", "value")]
+  current_atts <- attributes(jags_out) 
+  current_atts <- c(current_atts, mod_atts)
+  attributes(jags_out) <- current_atts
+  
+  # Adding priors
+  jags_out <- jags_out |>
+    structure("priors" = attributes(priorspec)$used_priors)
+  
+  # Conditionally adding jags.post
   if (with_post) {
-    jags_out <- list(
-      "curve_params" = jags_out,
-      "jags.post" = jags_post_final,
-      "attributes" = mod_atts
-    )
-  } else { 
-    jags_out <- list(
-      "curve_params" = jags_out,
-      "attributes" = mod_atts
-    )
-  }
+    jags_out <- jags_out |>
+      structure(jags.post = jags_post_final)
+  } 
+  jags_out <- jags_out |>
+    structure(class = union("sr_model", class(jags_out)))
   jags_out
 }

R/nepal_sees_jags_output.R

@@ -8,15 +8,25 @@
 #' which is the diagnosis type (typhoid or
 #' paratyphoid). Keeping only IDs `"newperson"`, `"sees_npl_1"`, `"sees_npl_2"`.
 #'
-#' @format ## `nepal_sees_jags_output`
-#' A [list] consisting of the following named elements:
-#' \describe{
-#'  \item{curve_params}{A [data.frame] titled `curve_params` that contains the
+#' @format An S3 object of class `sr_model`: A [dplyr::tbl_df] that contains the
 #'   posterior predictive distribution of the person-specific parameters for a
 #'   "new person" with no observed data (`Subject = "newperson"`) and posterior
 #'   distributions of the person-specific parameters for two arbitrarily-chosen
-#'   subjects (`"sees_npl_1"` and `"sees_npl_2"`)}
-#'  \item{attributes}{A [list] of `attributes` that summarize the jags inputs}
+#'   subjects (`"sees_npl_1"` and `"sees_npl_2"`).
+#'   Contains 40,000 `rows`, 7 `columns`, and model `attributes`.
+#' \describe{
+#'  \item{Iteration}{Number of sampling iterations: 500 iterations}
+#'  \item{Chain}{Number of MCMC chains run: 2 chains run}
+#'  \item{Parameter}{Parameter being estimated}
+#'  \item{Iso_type}{Antibody/antigen type combination being evaluated:
+#'  `HlyE_IgA` and `HlyE_IgG`}
+#'  \item{Stratification}{The variable used to stratify jags model: `typhi` and
+#'  `paratyphi`}
+#'  \item{Subject}{ID of subject being evaluated: `newperson`, `sees_npl_1`, 
+#'  `sees_npl_2`}
+#'  \item{value}{Estimated value of the parameter}
+#'  \item{attributes}{A [list] of `attributes` that summarize the jags inputs, 
+#'  priors, and optional jags_post mcmc object}
 #' }
 #' @source reference study: <https://doi.org/10.1016/S2666-5247(22)00114-8>
 "nepal_sees_jags_output"

R/plot_jags_densitydx.R

@@ -32,16 +32,16 @@
 #' @example inst/examples/examples-plot_jags_densitydx.R
 
 plot_jags_dens <- function(data,
-                           iso = unique(data$curve_params$Iso_type),
-                           param = unique(data$curve_params$Parameter_sub),
-                           strat = unique(data$curve_params$Stratification)) {
-  visualize_jags <- data[["curve_params"]]
+                           iso = unique(data$Iso_type),
+                           param = unique(data$Parameter),
+                           strat = unique(data$Stratification)) {
+  
   attributes_jags <- data[["attributes"]]
 
   dens_strat_list <- list()
   for (i in strat) {
 
-    visualize_jags_sub <- visualize_jags |>
+    visualize_jags_sub <- data |>
       dplyr::filter(.data$Stratification == i) |>
       dplyr::filter(.data$Subject == "newperson")
 
@@ -55,12 +55,12 @@ plot_jags_dens <- function(data,
       # Will not loop through parameters, as we may want each to show on the
       # same plot by default.
       visualize_jags_plot <- visualize_jags_plot |>
-        dplyr::filter(.data$Parameter_sub %in% param)
+        dplyr::filter(.data$Parameter %in% param)
 
       visualize_jags_plot <- visualize_jags_plot |>
         # Changing parameter name to reflect the input
         dplyr::mutate(Parameter = paste0("iso = ", j, ", parameter = ",
-                                         .data$Parameter_sub, ", strat = ",
+                                         .data$Parameter, ", strat = ",
                                          i),
                       value = log(.data$value))
       # Assigning attributes, which are needed to run ggs_density