Merge branch 'master' into add-cmdstanr-to-gha

Author: VisruthSK

.gitignore

@@ -16,3 +16,4 @@ release-prep.R
 
 # vscode/positron/etc settings
 .vscode/*
+Rplots.pdf

NEWS.md

@@ -1,9 +1,11 @@
 # bayesplot (development version)
 
+* Added unit tests for `mcmc_areas_ridges_data()`, `mcmc_parcoord_data()`, and `mcmc_trace_data()`.
+* Added unit tests for `ppc_error_data()` and `ppc_loo_pit_data()` covering output structure, argument handling, and edge cases.
+* Added vignette sections demonstrating `*_data()` companion functions for building custom ggplot2 visualizations (#435)
+* Extract `drop_singleton_values()` helper in `mcmc_nuts_treedepth()` to remove duplicated filtering logic.
 * Eliminate redundant data processing in `mcmc_areas_data()` by reusing the prepared MCMC array for both interval and density computation.
-* Validate equal chain lengths in `validate_df_with_chain()`, reject missing
-  chain labels, and renumber data-frame chain labels internally when converting
-  to arrays.
+* Validate equal chain lengths in `validate_df_with_chain()`, reject missing chain labels, and renumber data-frame chain labels internally when converting to arrays.
 * Added unit tests for previously untested edge cases in `param_range()`, `param_glue()`, and `tidyselect_parameters()` (no-match, partial-match, and negation behavior).
 * Bumped minimum version for `rstantools` from `>= 1.5.0` to `>= 2.0.0` .
 * Use `rlang::warn()` and `rlang::inform()` for selected PPC user messages instead of base `warning()` and `message()`.
@@ -18,7 +20,7 @@
 * Default to `quantiles=100` for all dot plots by @behramulukir (#402)
 * Use `"neff_ratio"` consistently in diagnostic color scale helpers to avoid relying on partial matching of `"neff"`.
 * Replace `expand = c(mult, add)` with `ggplot2::expansion()` helper in scale functions for consistency with ggplot2 >= 3.3.0 style.
-* Replace uses of `geom_bar(stat = "identity")` with the more idiomatic ggplot2 form `geom_col()` 
+* Replace uses of `geom_bar(stat = "identity")` with the more idiomatic ggplot2 form `geom_col()`
 * New function `ppc_rootogram_grouped` for grouped rootogram plots by @behramulukir and @jgabry (#419)
 
 # bayesplot 1.15.0
@@ -35,7 +37,7 @@
 
 # bayesplot 1.14.0
 
-* PPC "avg" functions (`ppc_scatter_avg()`, `ppc_error_scatter_avg()`, etc.) gain a `stat` argument 
+* PPC "avg" functions (`ppc_scatter_avg()`, `ppc_error_scatter_avg()`, etc.) gain a `stat` argument
   to set the averaging function. (Suggestion of #348, @kruschke).
 * `ppc_error_scatter_avg_vs_x(x = some_expression)` labels the x axis with `some_expression`.
 * New quantile dot plot functions `ppc_dots()` and `ppd_dots()` by @behramulukir (#357)
@@ -57,7 +59,7 @@
 
 * Expand checking workflows to more platforms by @andrjohns (#324)
 * Skip tests depending on Suggested dependency rstantools if not installed by @MichaelChirico (#325)
-* Skip tests depending on Suggested dependency gridExtra if not installed by @MichaelChirico (#326) 
+* Skip tests depending on Suggested dependency gridExtra if not installed by @MichaelChirico (#326)
 * Fix missing legends for unobserved levels in rhat and neff plots (#328)
 * Document problems with `ppc_stat` with `stat="mean"` (#329)
 * Ensure rank overlay plot starts at 0 even if not all bins present, thanks @sims1253 (#332)

R/mcmc-diagnostics-nuts.R

@@ -369,11 +369,7 @@ mcmc_nuts_treedepth <- function(x, lp, chain = NULL, ...) {
     yaxis_ticks(FALSE)
 
   violin_lp_data <- data.frame(treedepth, lp = lp$Value)
-
-  # Only keep treedepth values that occur more than once for violin plot
-  value_counts <- table(violin_lp_data$Value)
-  keep_values <- names(value_counts[value_counts > 1])
-  violin_lp_data <- violin_lp_data[violin_lp_data$Value %in% keep_values, ]
+  violin_lp_data <- drop_singleton_values(violin_lp_data, "Value")
 
   violin_lp <-
     ggplot(violin_lp_data, aes(x = factor(.data$Value), y = .data$lp)) +
@@ -382,11 +378,7 @@ mcmc_nuts_treedepth <- function(x, lp, chain = NULL, ...) {
     bayesplot_theme_get()
 
   violin_accept_stat_data <- data.frame(treedepth, as = accept_stat$Value)
-
-  # Only keep treedepth values that occur more than once for violin plot
-  value_counts <- table(violin_accept_stat_data$Value)
-  keep_values <- names(value_counts[value_counts > 1])
-  violin_accept_stat_data <- violin_accept_stat_data[violin_accept_stat_data$Value %in% keep_values, ]
+  violin_accept_stat_data <- drop_singleton_values(violin_accept_stat_data, "Value")
 
   violin_accept_stat <-
     ggplot(violin_accept_stat_data, aes(x = factor(.data$Value), y = .data$as)) +
@@ -572,3 +564,11 @@ chain_violin <-
       alpha = alpha
     )
   }
+
+# Drop rows whose value in `col` appears only once (singletons cannot
+# produce a violin density estimate).
+drop_singleton_values <- function(df, col) {
+  counts <- table(df[[col]])
+  keep <- names(counts[counts > 1])
+  df[df[[col]] %in% keep, ]
+}