Merge branch 'master' into fix-stop-vs-abort-inconsistency

Author: utkarshpawade

.github/workflows/test-coverage.yaml

@@ -7,7 +7,9 @@ on:
 
 name: test-coverage.yaml
 
-permissions: read-all
+permissions:
+  contents: read
+  id-token: write
 
 jobs:
   test-coverage:
@@ -45,7 +47,7 @@ jobs:
           files: ./cobertura.xml
           plugins: noop
           disable_search: true
-          token: ${{ secrets.CODECOV_TOKEN }}
+          use_oidc: true
 
       - name: Show testthat output
         if: always()
@@ -56,7 +58,7 @@ jobs:
 
       - name: Upload test results
         if: failure()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: coverage-test-failures
           path: ${{ runner.temp }}/package

DESCRIPTION

@@ -30,10 +30,11 @@ SystemRequirements: pandoc (>= 1.12.3), pandoc-citeproc
 Depends:
     R (>= 4.1.0)
 Imports:
-    dplyr (>= 0.8.0),
+    dplyr (>= 1.0.0),
     ggplot2 (>= 3.4.0),
     ggridges (>= 0.5.5),
     glue,
+    lifecycle,
     posterior,
     reshape2,
     rlang (>= 0.3.0),

NAMESPACE

@@ -226,3 +226,6 @@ importFrom(dplyr,top_n)
 importFrom(dplyr,ungroup)
 importFrom(dplyr,vars)
 importFrom(ggplot2,"%+replace%")
+importFrom(lifecycle,deprecate_warn)
+importFrom(lifecycle,deprecated)
+importFrom(lifecycle,is_present)

NEWS.md

@@ -1,6 +1,12 @@
 # bayesplot (development version)
 
 * Standardize input validation errors in `ppc_km_overlay()` and interpolation helpers to use `rlang::abort()` for consistent error handling.
+* Fix assignment-in-call bug in `mcmc_rank_ecdf()` (#).
+* Replaced deprecated `dplyr` and `tidyselect` functions (`top_n`, `one_of`, `group_indices`) with their modern equivalents to ensure future compatibility. (#431)
+* Documentation added for all exported `*_data()` functions (#209)
+* Improved documentation for `binwidth`, `bins`, and `breaks` arguments to clarify they are passed to `ggplot2::geom_area()` and `ggdist::stat_dots()` in addition to `ggplot2::geom_histogram()`
+* Improved documentation for `freq` argument to clarify it applies to frequency polygons in addition to histograms
+* Fixed test in `test-ppc-distributions.R` that incorrectly used `ppc_dens()` instead of `ppd_dens()` when testing PPD functions
 * New functions `mcmc_dots` and `mcmc_dots_by_chain` for dot plots of MCMC draws by @behramulukir (#402)
 * Default to `quantiles=100` for all dot plots by @behramulukir (#402)
 

R/bayesplot-helpers.R

@@ -446,19 +446,28 @@ plot_bg <- function(on = TRUE, ...) {
 
 #' @rdname bayesplot-helpers
 #' @export
-#' @param color,size Passed to [ggplot2::element_line()].
-#'
-grid_lines <- function(color = "gray50", size = 0.2) {
+#' @param color,linewidth Passed to [ggplot2::element_line()].
+#' @param size `r lifecycle::badge("deprecated")` Use `linewidth` instead.
+#'
+grid_lines <- function(color = "gray50", linewidth = 0.2, size = deprecated()) {
+  if (lifecycle::is_present(size)) {
+    lifecycle::deprecate_warn(
+      "1.16.0",
+      "grid_lines(size)",
+      "grid_lines(linewidth)"
+    )
+    linewidth <- size
+  }
   theme(
-    panel.grid.major = element_line(color = color, linewidth = size),
-    panel.grid.minor = element_line(color = color, linewidth = size * 0.5)
+    panel.grid.major = element_line(color = color, linewidth = linewidth),
+    panel.grid.minor = element_line(color = color, linewidth = linewidth * 0.5)
   )
 }
 
-grid_lines_y <- function(color = "gray50", size = 0.2) {
+grid_lines_y <- function(color = "gray50", linewidth = 0.2) {
   theme(
-    panel.grid.major.y = element_line(color = color, linewidth = size),
-    panel.grid.minor.y = element_line(color = color, linewidth = size * 0.5)
+    panel.grid.major.y = element_line(color = color, linewidth = linewidth),
+    panel.grid.minor.y = element_line(color = color, linewidth = linewidth * 0.5)
   )
 }
 

R/bayesplot-package.R

@@ -5,6 +5,7 @@
 #'
 #' @import ggplot2 stats rlang
 #' @importFrom dplyr %>% summarise group_by select
+#' @importFrom lifecycle deprecated deprecate_warn is_present
 #'
 #' @description
 #' \if{html}{

R/helpers-gg.R

@@ -24,17 +24,10 @@ geom_ignore <- function(...) {
 
 #' Add new aesthetic mappings to a list of aesthetic mappings
 #'
-#' @param mapping a list of `uneval` aesthetic mappings (created by `aes_()`)
-#' @param ... additional mappings to add, e.g., `color = ~ parameter`
+#' @param mapping a list of `uneval` aesthetic mappings (created by `aes()`)
+#' @param ... additional mappings to add using `.data$` syntax
 #' @return the updated list
 #' @noRd
-modify_aes_ <- function(mapping, ...) {
-  utils::modifyList(mapping, aes_(...))
-}
-
-#' Same as `modify_aes_` but using `aes()` instead of `aes_()` (now deprecated).
-#' Often `...` will need to contain expression of the form `.data$x` to avoid R cmd check warnings
-#' @noRd
 modify_aes <- function(mapping, ...) {
   utils::modifyList(mapping, aes(...))
 }

R/mcmc-diagnostics.R

@@ -18,6 +18,13 @@
 #'
 #' @section Plot Descriptions:
 #' \describe{
+#' \item{`mcmc_rhat_data()`, `mcmc_neff_data()`}{
+#'   Data-preparation back ends for the R-hat and effective sample size plots.
+#'   Users can call these functions directly to obtain the data frame of
+#'   diagnostic values with rating labels and create custom diagnostic
+#'   visualizations with **ggplot2**.
+#' }
+#'
 #' \item{`mcmc_rhat()`, `mcmc_rhat_hist()`}{
 #'   Rhat values as either points or a histogram. Values are colored using
 #'   different shades (lighter is better). The chosen thresholds are somewhat
@@ -70,7 +77,7 @@
 #' (p <- mcmc_acf_bar(x, pars = c("alpha", "beta[1]")))
 #'
 #' # add horiztonal dashed line at 0.5
-#' p + hline_at(0.5, linetype = 2, size = 0.15, color = "gray")
+#' p + hline_at(0.5, linetype = 2, linewidth = 0.15, color = "gray")
 #' }
 #'
 #' # fake rhat values to use for demonstration

R/mcmc-distributions.R

@@ -15,7 +15,7 @@
 #' @param ... For dot plots, optional additional arguments to pass to [ggdist::stat_dots()].
 #' @param alpha Passed to the geom to control the transparency.
 #'
-#' @template return-ggplot
+#' @template return-ggplot-or-data
 #'
 #' @section Plot Descriptions:
 #' \describe{
@@ -48,6 +48,12 @@
 #'    appear in separate facets; in `mcmc_dens_chains()` they appear in the
 #'    same panel and can overlap vertically.
 #'   }
+#'   \item{`mcmc_dens_chains_data()`}{
+#'    Data-preparation back end for `mcmc_dens_chains()`. Users can call this
+#'    function directly to obtain the prepared long-format data frame of MCMC
+#'    draws (with chain information retained) and create custom visualizations
+#'    with **ggplot2**.
+#'   }
 #' }
 #'
 #' @examples
@@ -483,7 +489,7 @@ mcmc_dots_by_chain <- function(
   data <- melt_mcmc(x, value.name = "value")
   n_param <- num_params(data)
 
-  graph <- ggplot(data, aes(x = ~ value)) +
+  graph <- ggplot(data, aes(x = .data$value)) +
     geom_histogram(
       set_hist_aes(freq),
       fill = get_color("mid"),

R/mcmc-intervals.R

@@ -51,6 +51,13 @@
 #'    ridgelines. This plot provides a compact display of (hierarchically)
 #'    related distributions.
 #'   }
+#'   \item{`mcmc_intervals_data()`, `mcmc_areas_data()`, `mcmc_areas_ridges_data()`}{
+#'    Data-preparation back ends for `mcmc_intervals()`, `mcmc_areas()`, and
+#'    `mcmc_areas_ridges()`, respectively. Users can call these functions
+#'    directly to obtain the prepared data frames of posterior interval
+#'    summaries and create custom interval or density-area visualizations
+#'    with **ggplot2**.
+#'   }
 #' }
 #'
 #' @examples
@@ -640,7 +647,7 @@ mcmc_intervals_data <- function(x,
 
     rhat_tbl <- rhat %>%
       mcmc_rhat_data() %>%
-      select(one_of("parameter"),
+      select(all_of("parameter"),
              rhat_value = "value",
              rhat_rating = "rating",
              rhat_description = "description") %>%
@@ -656,7 +663,7 @@ mcmc_intervals_data <- function(x,
 # Don't import `filter`: otherwise, you get a warning when using
 # `devtools::load_all(".")` because stats also has a `filter` function
 
-#' @importFrom dplyr inner_join one_of top_n
+#' @importFrom dplyr inner_join all_of slice_min
 #' @rdname MCMC-intervals
 #' @export
 mcmc_areas_data <- function(x,
@@ -729,14 +736,14 @@ mcmc_areas_data <- function(x,
 
   # Find the density values closest to the point estimate
   point_ests <- intervals %>%
-    select(one_of("parameter", "m"))
+    select(all_of(c("parameter", "m")))
 
   point_centers <- data_inner %>%
     inner_join(point_ests, by = "parameter") %>%
     group_by(.data$parameter) %>%
     mutate(diff = abs(.data$m - .data$x)) %>%
-    dplyr::top_n(1, -.data$diff) %>%
-    select(one_of("parameter", "x", "m")) %>%
+    dplyr::slice_min(order_by = .data$diff, n = 1) %>%
+    select(all_of(c("parameter", "x", "m"))) %>%
     rename(center = "x") %>%
     ungroup()
 
@@ -758,15 +765,15 @@ mcmc_areas_data <- function(x,
   }
 
   data <- dplyr::bind_rows(data_inner, data_outer, points) %>%
-    select(one_of("parameter", "interval", "interval_width",
-                  "x", "density", "scaled_density")) %>%
+    select(all_of(c("parameter", "interval", "interval_width",
+                  "x", "density", "scaled_density"))) %>%
     # Density scaled so the highest in entire dataframe has height 1
     mutate(plotting_density = .data$density / max(.data$density))
 
   if (rlang::has_name(intervals, "rhat_value")) {
     rhat_info <- intervals %>%
-      select(one_of("parameter", "rhat_value",
-                    "rhat_rating", "rhat_description"))
+      select(all_of(c("parameter", "rhat_value",
+                    "rhat_rating", "rhat_description")))
     data <- inner_join(data, rhat_info, by = "parameter")
   }
   data
@@ -817,18 +824,15 @@ compute_column_density <- function(df, group_vars, value_var, ...) {
     syms()
 
   # Tuck away the subgroups to compute densities on into nested dataframes
-  sub_df <- dplyr::select(df, !!! group_cols, !! value_var)
-
   group_df <- df %>%
     dplyr::select(!!! group_cols, !! value_var) %>%
     group_by(!!! group_cols)
 
   by_group <- group_df %>%
-    split(dplyr::group_indices(group_df)) %>%
+    dplyr::group_split() %>%
     lapply(pull, !! value_var)
 
-  nested <- df %>%
-    dplyr::distinct(!!! group_cols) %>%
+  nested <- dplyr::group_keys(group_df) %>%
     mutate(data = by_group)
 
   nested$density <- lapply(nested$data, compute_interval_density, ...)