Update documentation with example data

R/coev_calculate_delta_theta.R

@@ -11,31 +11,27 @@
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' m <- coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
-#' # get delta theta
-#' coev_calculate_delta_theta(m, response = "y", predictor = "x")
+#'   )
+#'
+#' # calculate delta theta
+#' coev_calculate_delta_theta(
+#'   object = fit,
+#'   response = "political_authority",
+#'   predictor = "religious_authority"
+#'   )
 #' }
 coev_calculate_delta_theta <- function(object, response, predictor) {
   # stop if object is not of class coevfit

R/coev_calculate_theta.R

@@ -16,31 +16,29 @@
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' m <- coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
+#'   )
+#'
 #' # calculate theta given intervention values
-#' coev_calculate_theta(m, list(x = NA, y = 0))
+#' coev_calculate_theta(
+#'   object = fit,
+#'   intervention_values = list(
+#'     political_authority = NA,
+#'     religious_authority = 0
+#'     )
+#'   )
 #' }
 coev_calculate_theta <- function(object, intervention_values) {
   # stop if object is not of class coevfit

R/coev_fit.R

@@ -37,7 +37,7 @@
 #'   overdispersion parameters for negative binomial variables (\code{phi}),
 #'   the degrees of freedom parameters for Student t variables (\code{nu}),
 #'   the sigma parameters for Gaussian Processes over locations
-#'   (\code{sigma_dist}), and the rho parameter for Gaussian Processes over
+#'   (\code{sigma_dist}), and the rho parameters for Gaussian Processes over
 #'   locations (\code{rho_dist}). These must be entered with valid prior
 #'   strings, e.g. \code{list(A_offdiag = "normal(0, 2)")}. Invalid prior
 #'   strings will throw an error when the function internally checks the syntax
@@ -52,29 +52,23 @@
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
+#'   )
+#'
+#' # print model summary
+#' summary(fit)
 #' }
 coev_fit <- function(data, variables, id, tree,
                      effects_mat = NULL, dist_mat = NULL,

R/coev_make_stancode.R

@@ -37,7 +37,7 @@
 #'   overdispersion parameters for negative binomial variables (\code{phi}),
 #'   the degrees of freedom parameters for Student t variables (\code{nu}),
 #'   the sigma parameters for Gaussian Processes over locations
-#'   (\code{sigma_dist}), and the rho parameter for Gaussian Processes over
+#'   (\code{sigma_dist}), and the rho parameters for Gaussian Processes over
 #'   locations (\code{rho_dist}). These must be entered with valid prior
 #'   strings, e.g. \code{list(A_offdiag = "normal(0, 2)")}. Invalid prior
 #'   strings will throw an error when the function internally checks the syntax
@@ -51,24 +51,19 @@
 #' @export
 #'
 #' @examples
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'    id = tree$tip.label,
-#'    x = rbinom(n, size = 1, prob = 0.5),
-#'    y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # make stan code
-#' coev_make_stancode(
-#'    data = d,
-#'    variables = list(
-#'        x = "bernoulli_logit",
-#'        y = "ordered_logistic"
-#'    ),
-#'    id = "id",
-#'    tree = tree
-#' )
+#' stan_code <- coev_make_stancode(
+#'   data = authority$data,
+#'   variables = list(
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
+#'   ),
+#'   id = "language",
+#'   tree = authority$phylogeny
+#'   )
+#'
+#' # print Stan code
+#' cat(stan_code)
 coev_make_stancode <- function(data, variables, id, tree,
                                effects_mat = NULL, dist_mat = NULL,
                                prior = NULL, prior_only = FALSE) {

R/coev_make_standata.R

@@ -37,7 +37,7 @@
 #'   overdispersion parameters for negative binomial variables (\code{phi}),
 #'   the degrees of freedom parameters for Student t variables (\code{nu}),
 #'   the sigma parameters for Gaussian Processes over locations
-#'   (\code{sigma_dist}), and the rho parameter for Gaussian Processes over
+#'   (\code{sigma_dist}), and the rho parameters for Gaussian Processes over
 #'   locations (\code{rho_dist}). These must be entered with valid prior
 #'   strings, e.g. \code{list(A_offdiag = "normal(0, 2)")}. Invalid prior
 #'   strings will throw an error when the function internally checks the syntax
@@ -51,24 +51,16 @@
 #' @export
 #'
 #' @examples
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'    id = tree$tip.label,
-#'    x = rbinom(n, size = 1, prob = 0.5),
-#'    y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
-#' # make stan code
+#' # make stan data
 #' coev_make_standata(
-#'    data = d,
-#'    variables = list(
-#'        x = "bernoulli_logit",
-#'        y = "ordered_logistic"
-#'    ),
-#'    id = "id",
-#'    tree = tree
-#' )
+#'   data = authority$data,
+#'   variables = list(
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
+#'   ),
+#'   id = "language",
+#'   tree = authority$phylogeny
+#'   )
 coev_make_standata <- function(data, variables, id, tree,
                                effects_mat = NULL, dist_mat = NULL,
                                prior = NULL, prior_only = FALSE) {

R/coev_plot_delta_theta.R

@@ -11,31 +11,23 @@
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' m <- coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
+#'   )
+#'
 #' # plot delta theta values for all effects
-#' coev_plot_delta_theta(m)
+#' coev_plot_delta_theta(fit)
 #' }
 coev_plot_delta_theta <- function(object, variables = NULL, ...) {
   # stop if object is not of class coevfit

R/coev_plot_flowfield.R

@@ -1,41 +1,42 @@
-#' Plot flowfield of expected evolutionary change from a fitted \code{coevfit} object
+#' Plot flowfield of expected evolutionary change from a fitted \code{coevfit}
+#' object
 #'
 #' @param object An object of class \code{coevfit}
-#' @param var1 A character string equal to one of the coevolving variables in the model
-#' @param var2 A character string equal to one of the coevolving variables in the model
-#' @param nullclines Logical (defaults to FALSE); whether to show coloured nullclines
-#' to indicate where each variable is at equilibrium, depending on the state of the other
+#' @param var1 A character string equal to one of the coevolving variables in
+#'   the model
+#' @param var2 A character string equal to one of the coevolving variables in
+#'   the model
+#' @param nullclines Logical (defaults to FALSE); whether to show coloured
+#'   nullclines
+#' to indicate where each variable is at equilibrium, depending on the state of
+#'   the other
 #'
 #' @return A flowfield plot drawn directly to the device
 #' @export
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' m <- coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
-#' # plot flowfield
-#' coev_plot_flowfield(m)
+#'   )
+#'
+#' # plot flow field
+#' coev_plot_flowfield(
+#'   object = fit,
+#'   var1 = "political_authority",
+#'   var2 = "religious_authority"
+#'   )
 #' }
 coev_plot_flowfield <- function(object, var1, var2, nullclines = FALSE) {
   # stop if object is not of class coevfit

R/coev_plot_predictive_check.R

@@ -12,31 +12,23 @@
 #'
 #' @examples
 #' \dontrun{
-#' # simulate data
-#' n <- 20
-#' tree <- ape::rcoal(n)
-#' d <- data.frame(
-#'   id = tree$tip.label,
-#'   x = rbinom(n, size = 1, prob = 0.5),
-#'   y = ordered(sample(1:4, size = n, replace = TRUE))
-#' )
 #' # fit dynamic coevolutionary model
-#' m <- coev_fit(
-#'   data = d,
+#' fit <- coev_fit(
+#'   data = authority$data,
 #'   variables = list(
-#'     x = "bernoulli_logit",
-#'     y = "ordered_logistic"
+#'     political_authority = "ordered_logistic",
+#'     religious_authority = "ordered_logistic"
 #'   ),
-#'   id = "id",
-#'   tree = tree,
+#'   id = "language",
+#'   tree = authority$phylogeny,
 #'   # additional arguments for cmdstanr::sample()
 #'   chains = 4,
 #'   parallel_chains = 4,
-#'   iter_warmup = 500,
 #'   seed = 1
-#' )
+#'   )
+#'
 #' # plot predictive checks for all variables
-#' coev_plot_predictive_check(m)
+#' coev_plot_predictive_check(fit)
 #' }
 coev_plot_predictive_check <- function(object, variables = NULL,
                                        ndraws = NULL) {