From 309e3db8432200db0bdb9970efb99684d3f036a8 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Tue, 24 Oct 2023 12:33:27 +0200
Subject: [PATCH] #382

---
 DESCRIPTION             |  2 +-
 R/binned_residuals.R    | 14 +++++++++++++-
 man/binned_residuals.Rd |  8 +++++++-
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index d72f3909f..cf4108aa7 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: performance
 Title: Assessment of Regression Models Performance
-Version: 0.10.6.1
+Version: 0.10.6.2
 Authors@R: 
     c(person(given = "Daniel",
              family = "Lüdecke",
diff --git a/R/binned_residuals.R b/R/binned_residuals.R
index 355ab63c4..286323968 100644
--- a/R/binned_residuals.R
+++ b/R/binned_residuals.R
@@ -11,6 +11,11 @@
 #' @param n_bins Numeric, the number of bins to divide the data. If
 #'   `n_bins = NULL`, the square root of the number of observations is
 #'   taken.
+#' @param show_dots Logical, if `TRUE`, will show data points in the plot. Set
+#'   to `FALSE` for models with many observations, if generating the plot is too
+#'   time-consuming. By default, `show_dots = NULL`. In this case `binned_residuals()`
+#'   tries to guess whether performance will be poor due to a very large model
+#'   and thus automatically shows or hides dots.
 #' @param ... Currently not used.
 #'
 #' @return A data frame representing the data that is mapped in the accompanying
@@ -57,7 +62,7 @@
 #' }
 #'
 #' @export
-binned_residuals <- function(model, term = NULL, n_bins = NULL, ...) {
+binned_residuals <- function(model, term = NULL, n_bins = NULL, show_dots = NULL, ...) {
   fv <- stats::fitted(model)
   mf <- insight::get_data(model, verbose = FALSE)
 
@@ -67,6 +72,12 @@ binned_residuals <- function(model, term = NULL, n_bins = NULL, ...) {
     pred <- mf[[term]]
   }
 
+  # set default for show_dots, based on "model size"
+  if (is.null(show_dots)) {
+    n <- .safe(insight::n_obs(model))
+    show_dots <- is.null(n) || n <= 1e5
+  }
+
   y <- .recode_to_zero(insight::get_response(model, verbose = FALSE)) - fv
 
   if (is.null(n_bins)) n_bins <- round(sqrt(length(pred)))
@@ -112,6 +123,7 @@ binned_residuals <- function(model, term = NULL, n_bins = NULL, ...) {
   attr(d, "resid_ok") <- resid_ok
   attr(d, "resp_var") <- insight::find_response(model)
   attr(d, "term") <- term
+  attr(d, "show_dots") <- show_dots
 
   d
 }
diff --git a/man/binned_residuals.Rd b/man/binned_residuals.Rd
index ff6fb5784..b8aee666e 100644
--- a/man/binned_residuals.Rd
+++ b/man/binned_residuals.Rd
@@ -4,7 +4,7 @@
 \alias{binned_residuals}
 \title{Binned residuals for binomial logistic regression}
 \usage{
-binned_residuals(model, term = NULL, n_bins = NULL, ...)
+binned_residuals(model, term = NULL, n_bins = NULL, show_dots = NULL, ...)
 }
 \arguments{
 \item{model}{A \code{glm}-object with \emph{binomial}-family.}
@@ -18,6 +18,12 @@ plotted.}
 \code{n_bins = NULL}, the square root of the number of observations is
 taken.}
 
+\item{show_dots}{Logical, if \code{TRUE}, will show data points in the plot. Set
+to \code{FALSE} for models with many observations, if generating the plot is too
+time-consuming. By default, \code{show_dots = NULL}. In this case \code{binned_residuals()}
+tries to guess whether performance will be poor due to a very large model
+and thus automatically shows or hides dots.}
+
 \item{...}{Currently not used.}
 }
 \value{