From 410ea7a5dcf733dd7e76a368d230f9fe4c5e0728 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Tue, 1 Oct 2024 10:00:07 +0200
Subject: [PATCH 01/19] Update `DESCRIPTION` to use latest 'easystats'
 dependencies (#542)

[create-pull-request] automated change

Co-authored-by: IndrajeetPatil <11330453+IndrajeetPatil@users.noreply.github.com>
---
 DESCRIPTION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 67e87fd6c..dbf2318f7 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -33,7 +33,7 @@ BugReports: https://github.com/easystats/datawizard/issues
 Depends:
     R (>= 3.6)
 Imports:
-    insight (>= 0.20.3),
+    insight (>= 0.20.4),
     stats,
     utils
 Suggests:

From 07b20ec0be4b558e69eadb983581a47604419037 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Wed, 2 Oct 2024 07:20:21 +0200
Subject: [PATCH 02/19] Remove Twitter-tag from Authors@R (#545)

Remove Tweitter-tag from Authors@R
---
 DESCRIPTION | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index dbf2318f7..3d1a0081a 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -4,19 +4,19 @@ Title: Easy Data Wrangling and Statistical Transformations
 Version: 0.12.3.4
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
-           comment = c(ORCID = "0000-0003-1995-6531", Twitter = "@patilindrajeets")),
+           comment = c(ORCID = "0000-0003-1995-6531")),
     person("Etienne", "Bacher", , "etienne.bacher@protonmail.com", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-9271-5075")),
     person("Dominique", "Makowski", , "dom.makowski@gmail.com", role = "aut",
-           comment = c(ORCID = "0000-0001-5375-9967", Twitter = "@Dom_Makowski")),
+           comment = c(ORCID = "0000-0001-5375-9967")),
     person("Daniel", "Lüdecke", , "d.luedecke@uke.de", role = "aut",
-           comment = c(ORCID = "0000-0002-8895-3206", Twitter = "@strengejacke")),
+           comment = c(ORCID = "0000-0002-8895-3206")),
     person("Mattan S.", "Ben-Shachar", , "matanshm@post.bgu.ac.il", role = "aut",
            comment = c(ORCID = "0000-0002-4287-4801")),
     person("Brenton M.", "Wiernik", , "brenton@wiernik.org", role = "aut",
-           comment = c(ORCID = "0000-0001-9560-6336", Twitter = "@bmwiernik")),
+           comment = c(ORCID = "0000-0001-9560-6336")),
     person("Rémi", "Thériault", , "remi.theriault@mail.mcgill.ca", role = "ctb",
-           comment = c(ORCID = "0000-0003-4315-6788", Twitter = "@rempsyc")),
+           comment = c(ORCID = "0000-0003-4315-6788")),
     person("Thomas J.", "Faulkenberry", , "faulkenberry@tarleton.edu", role = "rev"),
     person("Robert", "Garrett", , "rcg4@illinois.edu", role = "rev")
   )

From ea2f16f98927c8265b3302eafbe0298484bc5622 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Wed, 2 Oct 2024 16:32:57 +0200
Subject: [PATCH 03/19] Default values of `to_numeric()` (#547)

Fixes #544
---
 R/to_numeric.R                           | 18 +++++++++---------
 man/datawizard-package.Rd                | 10 +++++-----
 man/to_numeric.Rd                        | 16 ++++++++--------
 tests/testthat/_snaps/data_to_numeric.md |  4 ++--
 tests/testthat/test-data_to_numeric.R    |  8 ++++----
 5 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/R/to_numeric.R b/R/to_numeric.R
index e38e12e80..3e75bccbd 100644
--- a/R/to_numeric.R
+++ b/R/to_numeric.R
@@ -17,11 +17,11 @@
 #' @inheritParams extract_column_names
 #' @inheritParams categorize
 #'
-#' @note By default, `to_numeric()` converts factors into "binary" dummies, i.e.
+#' @note When factors should be converted into multiple "binary" dummies, i.e.
 #' each factor level is converted into a separate column filled with a binary
-#' 0-1 value. If only one column is required, use `dummy_factors = FALSE`. If
-#' you want to preserve the original factor levels (in case these represent
-#' numeric values), use `preserve_levels = TRUE`.
+#' 0-1 value, set `dummy_factors = TRUE`. If you want to preserve the original
+#' factor levels (in case these represent numeric values), use
+#' `preserve_levels = TRUE`.
 #'
 #' @section Selection of variables - `select` argument:
 #' For most functions that have a `select` argument the complete input data
@@ -34,12 +34,12 @@
 #'
 #' @examples
 #' to_numeric(head(ToothGrowth))
-#' to_numeric(head(ToothGrowth), dummy_factors = FALSE)
+#' to_numeric(head(ToothGrowth), dummy_factors = TRUE)
 #'
 #' # factors
 #' x <- as.factor(mtcars$gear)
-#' to_numeric(x, dummy_factors = FALSE)
-#' to_numeric(x, dummy_factors = FALSE, preserve_levels = TRUE)
+#' to_numeric(x)
+#' to_numeric(x, preserve_levels = TRUE)
 #' # same as:
 #' coerce_to_numeric(x)
 #'
@@ -69,7 +69,7 @@ to_numeric.default <- function(x, verbose = TRUE, ...) {
 to_numeric.data.frame <- function(x,
                                   select = NULL,
                                   exclude = NULL,
-                                  dummy_factors = TRUE,
+                                  dummy_factors = FALSE,
                                   preserve_levels = FALSE,
                                   lowest = NULL,
                                   append = FALSE,
@@ -191,7 +191,7 @@ to_numeric.POSIXlt <- to_numeric.Date
 
 #' @export
 to_numeric.factor <- function(x,
-                              dummy_factors = TRUE,
+                              dummy_factors = FALSE,
                               preserve_levels = FALSE,
                               lowest = NULL,
                               verbose = TRUE,
diff --git a/man/datawizard-package.Rd b/man/datawizard-package.Rd
index db38bc334..d389df6ac 100644
--- a/man/datawizard-package.Rd
+++ b/man/datawizard-package.Rd
@@ -33,16 +33,16 @@ Useful links:
 
 Authors:
 \itemize{
-  \item Indrajeet Patil \email{patilindrajeet.science@gmail.com} (\href{https://orcid.org/0000-0003-1995-6531}{ORCID}) (@patilindrajeets)
-  \item Dominique Makowski \email{dom.makowski@gmail.com} (\href{https://orcid.org/0000-0001-5375-9967}{ORCID}) (@Dom_Makowski)
-  \item Daniel Lüdecke \email{d.luedecke@uke.de} (\href{https://orcid.org/0000-0002-8895-3206}{ORCID}) (@strengejacke)
+  \item Indrajeet Patil \email{patilindrajeet.science@gmail.com} (\href{https://orcid.org/0000-0003-1995-6531}{ORCID})
+  \item Dominique Makowski \email{dom.makowski@gmail.com} (\href{https://orcid.org/0000-0001-5375-9967}{ORCID})
+  \item Daniel Lüdecke \email{d.luedecke@uke.de} (\href{https://orcid.org/0000-0002-8895-3206}{ORCID})
   \item Mattan S. Ben-Shachar \email{matanshm@post.bgu.ac.il} (\href{https://orcid.org/0000-0002-4287-4801}{ORCID})
-  \item Brenton M. Wiernik \email{brenton@wiernik.org} (\href{https://orcid.org/0000-0001-9560-6336}{ORCID}) (@bmwiernik)
+  \item Brenton M. Wiernik \email{brenton@wiernik.org} (\href{https://orcid.org/0000-0001-9560-6336}{ORCID})
 }
 
 Other contributors:
 \itemize{
-  \item Rémi Thériault \email{remi.theriault@mail.mcgill.ca} (\href{https://orcid.org/0000-0003-4315-6788}{ORCID}) (@rempsyc) [contributor]
+  \item Rémi Thériault \email{remi.theriault@mail.mcgill.ca} (\href{https://orcid.org/0000-0003-4315-6788}{ORCID}) [contributor]
   \item Thomas J. Faulkenberry \email{faulkenberry@tarleton.edu} [reviewer]
   \item Robert Garrett \email{rcg4@illinois.edu} [reviewer]
 }
diff --git a/man/to_numeric.Rd b/man/to_numeric.Rd
index 7478c9579..634906e4a 100644
--- a/man/to_numeric.Rd
+++ b/man/to_numeric.Rd
@@ -11,7 +11,7 @@ to_numeric(x, ...)
   x,
   select = NULL,
   exclude = NULL,
-  dummy_factors = TRUE,
+  dummy_factors = FALSE,
   preserve_levels = FALSE,
   lowest = NULL,
   append = FALSE,
@@ -107,11 +107,11 @@ either numeric levels or dummy variables. The "counterpart" to convert
 variables into factors is \code{to_factor()}.
 }
 \note{
-By default, \code{to_numeric()} converts factors into "binary" dummies, i.e.
+When factors should be converted into multiple "binary" dummies, i.e.
 each factor level is converted into a separate column filled with a binary
-0-1 value. If only one column is required, use \code{dummy_factors = FALSE}. If
-you want to preserve the original factor levels (in case these represent
-numeric values), use \code{preserve_levels = TRUE}.
+0-1 value, set \code{dummy_factors = TRUE}. If you want to preserve the original
+factor levels (in case these represent numeric values), use
+\code{preserve_levels = TRUE}.
 }
 \section{Selection of variables - \code{select} argument}{
 
@@ -126,12 +126,12 @@ to also include the original variables in the returned data frame.
 
 \examples{
 to_numeric(head(ToothGrowth))
-to_numeric(head(ToothGrowth), dummy_factors = FALSE)
+to_numeric(head(ToothGrowth), dummy_factors = TRUE)
 
 # factors
 x <- as.factor(mtcars$gear)
-to_numeric(x, dummy_factors = FALSE)
-to_numeric(x, dummy_factors = FALSE, preserve_levels = TRUE)
+to_numeric(x)
+to_numeric(x, preserve_levels = TRUE)
 # same as:
 coerce_to_numeric(x)
 
diff --git a/tests/testthat/_snaps/data_to_numeric.md b/tests/testthat/_snaps/data_to_numeric.md
index 42cb00b67..e963890a5 100644
--- a/tests/testthat/_snaps/data_to_numeric.md
+++ b/tests/testthat/_snaps/data_to_numeric.md
@@ -1,7 +1,7 @@
 # convert data frame to numeric
 
     Code
-      to_numeric(head(ToothGrowth))
+      to_numeric(head(ToothGrowth), dummy_factors = TRUE)
     Output
          len supp.OJ supp.VC dose
       1  4.2       0       1  0.5
@@ -27,7 +27,7 @@
 # convert factor to numeric
 
     Code
-      to_numeric(f)
+      to_numeric(f, dummy_factors = TRUE)
     Output
          a c i s t
       1  0 0 0 1 0
diff --git a/tests/testthat/test-data_to_numeric.R b/tests/testthat/test-data_to_numeric.R
index 464c35e8d..816591ac0 100644
--- a/tests/testthat/test-data_to_numeric.R
+++ b/tests/testthat/test-data_to_numeric.R
@@ -1,5 +1,5 @@
 test_that("convert data frame to numeric", {
-  expect_snapshot(to_numeric(head(ToothGrowth)))
+  expect_snapshot(to_numeric(head(ToothGrowth), dummy_factors = TRUE))
   expect_snapshot(to_numeric(head(ToothGrowth), dummy_factors = FALSE))
 })
 
@@ -41,7 +41,7 @@ test_that("convert character to numeric lowest", {
 
 test_that("convert factor to numeric", {
   f <- factor(substring("statistics", 1:10, 1:10))
-  expect_snapshot(to_numeric(f))
+  expect_snapshot(to_numeric(f, dummy_factors = TRUE))
 })
 
 test_that("convert factor to numeric", {
@@ -67,12 +67,12 @@ test_that("convert factor to numeric, dummy factors", {
 test_that("convert factor to numeric, append", {
   data(efc)
   expect_identical(
-    colnames(to_numeric(efc)),
+    colnames(to_numeric(efc, dummy_factors = TRUE)),
     c("c12hour", "e16sex", "e42dep.1", "e42dep.2", "e42dep.3", "e42dep.4", "c172code", "neg_c_7"),
     ignore_attr = TRUE
   )
   expect_identical(
-    colnames(to_numeric(efc, append = TRUE)),
+    colnames(to_numeric(efc, dummy_factors = TRUE, append = TRUE)),
     c(
       "c12hour", "e16sex", "e42dep", "c172code", "neg_c_7", "e42dep_n",
       "e42dep_n.1", "e42dep_n.2", "e42dep_n.3", "e42dep_n.4"

From 77d67f4dcfae2929de382687943e80a380272ab0 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Wed, 2 Oct 2024 18:03:09 +0200
Subject: [PATCH 04/19] categorize() add labels="range" option (#549)

* categorize() add labels="range" option
Fixes #548

* add test, docs

* lintr

* add option to decide on exclusive/inclusive breaks

* docs
---
 R/categorize.R                      | 69 ++++++++++++++++++++++-------
 man/categorize.Rd                   | 27 +++++++++--
 tests/testthat/_snaps/categorize.md | 47 ++++++++++++++++++++
 tests/testthat/test-categorize.R    | 24 ++++++++--
 4 files changed, 144 insertions(+), 23 deletions(-)
 create mode 100644 tests/testthat/_snaps/categorize.md

diff --git a/R/categorize.R b/R/categorize.R
index a6562ab68..9f8dd7505 100644
--- a/R/categorize.R
+++ b/R/categorize.R
@@ -31,10 +31,18 @@
 #'   for numeric variables, the minimum of the original input is preserved. For
 #'   factors, the default minimum is `1`. For `split = "equal_range"`, the
 #'   default minimum is always `1`, unless specified otherwise in `lowest`.
+#' @param breaks Character, indicating whether breaks for categorizing data are
+#'   `"inclusive"` (values indicate the _upper_ bound of the _previous_ group or
+#'   interval) or `"exclusive"` (values indicate the _lower_ bound of the _next_
+#'   group or interval to begin). Use `labels = "range"` to make this behaviour
+#'   easier to see.
 #' @param labels Character vector of value labels. If not `NULL`, `categorize()`
 #'   will returns factors instead of numeric variables, with `labels` used
-#'   for labelling the factor levels. Can also be `"mean"` or `"median"` for a
-#'   factor with labels as the mean/median of each groups.
+#'   for labelling the factor levels. Can also be `"mean"`, `"median"`,
+#'   `"range"` or `"observed"` for a factor with labels as the mean/median,
+#'   the requested range (even if not all values of that range are present in
+#'   the data) or observed range (range of the actual recoded values) of each
+#'   group. See 'Examples'.
 #' @param append Logical or string. If `TRUE`, recoded or converted variables
 #'   get new column names and are appended (column bind) to `x`, thus returning
 #'   both the original and the recoded variables. The new columns get a suffix,
@@ -53,7 +61,7 @@
 #'
 #' # Splits and breaks (cut-off values)
 #'
-#' Breaks are in general _exclusive_, this means that these values indicate
+#' Breaks are by default _exclusive_, this means that these values indicate
 #' the lower bound of the next group or interval to begin. Take a simple
 #' example, a numeric variable with values from 1 to 9. The median would be 5,
 #' thus the first interval ranges from 1-4 and is recoded into 1, while 5-9
@@ -63,6 +71,9 @@
 #' from 1 to 3 belong to the first interval and are recoded into 1 (because
 #' the next interval starts at 3.67), 4 to 6 into 2 and 7 to 9 into 3.
 #'
+#' The opposite behaviour can be achieved using `breaks = "inclusive"`, in which
+#' case
+#'
 #' # Recoding into groups with equal size or range
 #'
 #' `split = "equal_length"` and `split = "equal_range"` try to divide the
@@ -119,6 +130,13 @@
 #' x <- sample(1:10, size = 30, replace = TRUE)
 #' categorize(x, "equal_length", n_groups = 3, labels = "mean")
 #' categorize(x, "equal_length", n_groups = 3, labels = "median")
+#'
+#' # cut numeric into groups with the requested range as a label name
+#' # each category has the same range, and labels indicate this range
+#' categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range")
+#' # in this example, each category has the same range, but labels only refer
+#' # to the ranges of the actual values (present in the data) inside each group
+#' categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed")
 #' @export
 categorize <- function(x, ...) {
   UseMethod("categorize")
@@ -142,6 +160,7 @@ categorize.numeric <- function(x,
                                n_groups = NULL,
                                range = NULL,
                                lowest = 1,
+                               breaks = "exclusive",
                                labels = NULL,
                                verbose = TRUE,
                                ...) {
@@ -152,6 +171,9 @@ categorize.numeric <- function(x,
   if (identical(split, "equal_length")) split <- "length"
   if (identical(split, "equal_range")) split <- "range"
 
+  # check for valid values
+  breaks <- match.arg(breaks, c("exclusive", "inclusive"))
+
   # save
   original_x <- x
 
@@ -169,9 +191,9 @@ categorize.numeric <- function(x,
   }
 
   if (is.numeric(split)) {
-    breaks <- split
+    category_splits <- split
   } else {
-    breaks <- switch(split,
+    category_splits <- switch(split,
       median = stats::median(x),
       mean = mean(x),
       length = n_groups,
@@ -182,15 +204,18 @@ categorize.numeric <- function(x,
   }
 
   # complete ranges, including minimum and maximum
-  if (!identical(split, "length")) breaks <- unique(c(min(x), breaks, max(x)))
+  if (!identical(split, "length")) {
+    category_splits <- unique(c(min(x), category_splits, max(x)))
+  }
 
   # recode into groups
   out <- droplevels(cut(
     x,
-    breaks = breaks,
+    breaks = category_splits,
     include.lowest = TRUE,
-    right = FALSE
+    right = identical(breaks, "inclusive")
   ))
+  cut_result <- out
   levels(out) <- 1:nlevels(out)
 
   # fix lowest value, add back into original vector
@@ -201,7 +226,7 @@ categorize.numeric <- function(x,
   original_x[!is.na(original_x)] <- out
 
   # turn into factor?
-  .original_x_to_factor(original_x, x, labels, out, verbose, ...)
+  .original_x_to_factor(original_x, x, cut_result, labels, out, verbose, ...)
 }
 
 
@@ -223,6 +248,7 @@ categorize.data.frame <- function(x,
                                   n_groups = NULL,
                                   range = NULL,
                                   lowest = 1,
+                                  breaks = "exclusive",
                                   labels = NULL,
                                   append = FALSE,
                                   ignore_case = FALSE,
@@ -260,6 +286,7 @@ categorize.data.frame <- function(x,
     n_groups = n_groups,
     range = range,
     lowest = lowest,
+    breaks = breaks,
     labels = labels,
     verbose = verbose,
     ...
@@ -276,6 +303,7 @@ categorize.grouped_df <- function(x,
                                   n_groups = NULL,
                                   range = NULL,
                                   lowest = 1,
+                                  breaks = "exclusive",
                                   labels = NULL,
                                   append = FALSE,
                                   ignore_case = FALSE,
@@ -319,6 +347,7 @@ categorize.grouped_df <- function(x,
       n_groups = n_groups,
       range = range,
       lowest = lowest,
+      breaks = breaks,
       labels = labels,
       select = select,
       exclude = exclude,
@@ -375,20 +404,26 @@ categorize.grouped_df <- function(x,
 }
 
 
-.original_x_to_factor <- function(original_x, x, labels, out, verbose, ...) {
+.original_x_to_factor <- function(original_x, x, cut_result, labels, out, verbose, ...) {
   if (!is.null(labels)) {
     if (length(labels) == length(unique(out))) {
       original_x <- as.factor(original_x)
       levels(original_x) <- labels
-    } else if (length(labels) == 1 && labels %in% c("mean", "median")) {
+    } else if (length(labels) == 1 && labels %in% c("mean", "median", "range", "observed")) {
       original_x <- as.factor(original_x)
       no_na_x <- original_x[!is.na(original_x)]
-      if (labels == "mean") {
-        labels <- stats::aggregate(x, list(no_na_x), FUN = mean, na.rm = TRUE)$x
-      } else {
-        labels <- stats::aggregate(x, list(no_na_x), FUN = stats::median, na.rm = TRUE)$x
-      }
-      levels(original_x) <- insight::format_value(labels, ...)
+      out <- switch(labels,
+        mean = stats::aggregate(x, list(no_na_x), FUN = mean, na.rm = TRUE)$x,
+        median = stats::aggregate(x, list(no_na_x), FUN = stats::median, na.rm = TRUE)$x,
+        # labels basically like what "cut()" returns
+        range = levels(cut_result),
+        # range based on the values that are actually present in the data
+        {
+          temp <- stats::aggregate(x, list(no_na_x), FUN = range, na.rm = TRUE)$x
+          apply(temp, 1, function(i) paste0("(", paste(as.vector(i), collapse = "-"), ")"))
+        }
+      )
+      levels(original_x) <- insight::format_value(out, ...)
     } else if (isTRUE(verbose)) {
       insight::format_warning(
         "Argument `labels` and levels of the recoded variable are not of the same length.",
diff --git a/man/categorize.Rd b/man/categorize.Rd
index 28f823dd4..ca013ce2b 100644
--- a/man/categorize.Rd
+++ b/man/categorize.Rd
@@ -14,6 +14,7 @@ categorize(x, ...)
   n_groups = NULL,
   range = NULL,
   lowest = 1,
+  breaks = "exclusive",
   labels = NULL,
   verbose = TRUE,
   ...
@@ -27,6 +28,7 @@ categorize(x, ...)
   n_groups = NULL,
   range = NULL,
   lowest = 1,
+  breaks = "exclusive",
   labels = NULL,
   append = FALSE,
   ignore_case = FALSE,
@@ -67,10 +69,19 @@ for numeric variables, the minimum of the original input is preserved. For
 factors, the default minimum is \code{1}. For \code{split = "equal_range"}, the
 default minimum is always \code{1}, unless specified otherwise in \code{lowest}.}
 
+\item{breaks}{Character, indicating whether breaks for categorizing data are
+\code{"inclusive"} (values indicate the \emph{upper} bound of the \emph{previous} group or
+interval) or \code{"exclusive"} (values indicate the \emph{lower} bound of the \emph{next}
+group or interval to begin). Use \code{labels = "range"} to make this behaviour
+easier to see.}
+
 \item{labels}{Character vector of value labels. If not \code{NULL}, \code{categorize()}
 will returns factors instead of numeric variables, with \code{labels} used
-for labelling the factor levels. Can also be \code{"mean"} or \code{"median"} for a
-factor with labels as the mean/median of each groups.}
+for labelling the factor levels. Can also be \code{"mean"}, \code{"median"},
+\code{"range"} or \code{"observed"} for a factor with labels as the mean/median,
+the requested range (even if not all values of that range are present in
+the data) or observed range (range of the actual recoded values) of each
+group. See 'Examples'.}
 
 \item{verbose}{Toggle warnings.}
 
@@ -145,7 +156,7 @@ It is basically a wrapper around base R's \code{cut()}, providing a simplified
 and more accessible way to define the interval breaks (cut-off values).
 }
 \section{Splits and breaks (cut-off values)}{
-Breaks are in general \emph{exclusive}, this means that these values indicate
+Breaks are by default \emph{exclusive}, this means that these values indicate
 the lower bound of the next group or interval to begin. Take a simple
 example, a numeric variable with values from 1 to 9. The median would be 5,
 thus the first interval ranges from 1-4 and is recoded into 1, while 5-9
@@ -154,6 +165,9 @@ using \code{split = "quantile"} and \code{n_groups = 3} would define breaks at 3
 and 6.33 (see \code{quantile(1:9, probs = c(1/3, 2/3))}), which means that values
 from 1 to 3 belong to the first interval and are recoded into 1 (because
 the next interval starts at 3.67), 4 to 6 into 2 and 7 to 9 into 3.
+
+The opposite behaviour can be achieved using \code{breaks = "inclusive"}, in which
+case
 }
 
 \section{Recoding into groups with equal size or range}{
@@ -217,6 +231,13 @@ categorize(x, "equal_length", n_groups = 3, labels = c("low", "mid", "high"))
 x <- sample(1:10, size = 30, replace = TRUE)
 categorize(x, "equal_length", n_groups = 3, labels = "mean")
 categorize(x, "equal_length", n_groups = 3, labels = "median")
+
+# cut numeric into groups with the requested range as a label name
+# each category has the same range, and labels indicate this range
+categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range")
+# in this example, each category has the same range, but labels only refer
+# to the ranges of the actual values (present in the data) inside each group
+categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed")
 }
 \seealso{
 \itemize{
diff --git a/tests/testthat/_snaps/categorize.md b/tests/testthat/_snaps/categorize.md
new file mode 100644
index 000000000..d08c14c4d
--- /dev/null
+++ b/tests/testthat/_snaps/categorize.md
@@ -0,0 +1,47 @@
+# categorize labelling ranged
+
+    Code
+      categorize(mtcars$mpg, "equal_length", n_groups = 5)
+    Output
+       [1] 3 3 3 3 2 2 1 3 3 2 2 2 2 2 1 1 1 5 5 5 3 2 2 1 2 4 4 5 2 2 1 3
+
+---
+
+    Code
+      categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range")
+    Output
+       [1] [19.8,24.5) [19.8,24.5) [19.8,24.5) [19.8,24.5) [15.1,19.8) [15.1,19.8)
+       [7] [10.4,15.1) [19.8,24.5) [19.8,24.5) [15.1,19.8) [15.1,19.8) [15.1,19.8)
+      [13] [15.1,19.8) [15.1,19.8) [10.4,15.1) [10.4,15.1) [10.4,15.1) [29.2,33.9]
+      [19] [29.2,33.9] [29.2,33.9] [19.8,24.5) [15.1,19.8) [15.1,19.8) [10.4,15.1)
+      [25] [15.1,19.8) [24.5,29.2) [24.5,29.2) [29.2,33.9] [15.1,19.8) [15.1,19.8)
+      [31] [10.4,15.1) [19.8,24.5)
+      Levels: [10.4,15.1) [15.1,19.8) [19.8,24.5) [24.5,29.2) [29.2,33.9]
+
+---
+
+    Code
+      categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed")
+    Output
+       [1] (21-24.4)   (21-24.4)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7)
+       [7] (10.4-15)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7) (15.2-19.7)
+      [13] (15.2-19.7) (15.2-19.7) (10.4-15)   (10.4-15)   (10.4-15)   (30.4-33.9)
+      [19] (30.4-33.9) (30.4-33.9) (21-24.4)   (15.2-19.7) (15.2-19.7) (10.4-15)  
+      [25] (15.2-19.7) (26-27.3)   (26-27.3)   (30.4-33.9) (15.2-19.7) (15.2-19.7)
+      [31] (10.4-15)   (21-24.4)  
+      Levels: (10.4-15) (15.2-19.7) (21-24.4) (26-27.3) (30.4-33.9)
+
+---
+
+    Code
+      categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed",
+      breaks = "inclusive")
+    Output
+       [1] (21-24.4)   (21-24.4)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7)
+       [7] (10.4-15)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7) (15.2-19.7)
+      [13] (15.2-19.7) (15.2-19.7) (10.4-15)   (10.4-15)   (10.4-15)   (30.4-33.9)
+      [19] (30.4-33.9) (30.4-33.9) (21-24.4)   (15.2-19.7) (15.2-19.7) (10.4-15)  
+      [25] (15.2-19.7) (26-27.3)   (26-27.3)   (30.4-33.9) (15.2-19.7) (15.2-19.7)
+      [31] (10.4-15)   (21-24.4)  
+      Levels: (10.4-15) (15.2-19.7) (21-24.4) (26-27.3) (30.4-33.9)
+
diff --git a/tests/testthat/test-categorize.R b/tests/testthat/test-categorize.R
index 0e0b5d317..9ab8eadde 100644
--- a/tests/testthat/test-categorize.R
+++ b/tests/testthat/test-categorize.R
@@ -1,5 +1,5 @@
 set.seed(123)
-d <- sample(1:10, size = 500, replace = TRUE)
+d <- sample.int(10, size = 500, replace = TRUE)
 
 test_that("recode median", {
   expect_identical(categorize(d), ifelse(d >= median(d), 2, 1))
@@ -22,7 +22,7 @@ test_that("recode quantile", {
 })
 
 set.seed(123)
-d <- sample(1:100, size = 1000, replace = TRUE)
+d <- sample.int(100, size = 1000, replace = TRUE)
 
 test_that("recode range", {
   expect_error(categorize(d, split = "range"))
@@ -84,7 +84,7 @@ test_that("recode length", {
 })
 
 set.seed(123)
-x <- sample(1:10, size = 30, replace = TRUE)
+x <- sample.int(10, size = 30, replace = TRUE)
 test_that("recode factor labels", {
   expect_type(categorize(x, "equal_length", n_groups = 3), "double")
   expect_s3_class(categorize(x, "equal_length", n_groups = 3, labels = c("low", "mid", "high")), "factor")
@@ -232,3 +232,21 @@ test_that("categorize regex", {
     categorize(mtcars, select = "mpg")
   )
 })
+
+
+# select helpers ------------------------------
+test_that("categorize labelling ranged", {
+  data(mtcars)
+  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5))
+  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range"))
+  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed"))
+})
+
+test_that("categorize breaks", {
+  data(mtcars)
+  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed", breaks = "inclusive"))
+  expect_error(
+    categorize(mtcars$mpg, "equal_length", n_groups = 5, breaks = "something"),
+    regex = "should be one of"
+  )
+})

From 41aec02ed50f78865d6b9083563c9fa0dc2843d9 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Wed, 2 Oct 2024 18:06:36 +0200
Subject: [PATCH 05/19] typo in comment

---
 tests/testthat/test-categorize.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/testthat/test-categorize.R b/tests/testthat/test-categorize.R
index 9ab8eadde..217797893 100644
--- a/tests/testthat/test-categorize.R
+++ b/tests/testthat/test-categorize.R
@@ -234,7 +234,7 @@ test_that("categorize regex", {
 })
 
 
-# select helpers ------------------------------
+# labelling ranges ------------------------------
 test_that("categorize labelling ranged", {
   data(mtcars)
   expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5))

From c4f3f29b0b8c5ef9016eca93328d46231eb62ff2 Mon Sep 17 00:00:00 2001
From: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
Date: Sun, 6 Oct 2024 12:45:13 +0200
Subject: [PATCH 06/19] Release 0.13.0 (#546)

* Increment version number to 0.13.0

* fix description, remove othe cran comments

* remove deprecated functions and arguments

* forgot to remove one arg

* styler

* update news

* update news

* add correct snapshot test

* requires insight 0.20.5

---------

Co-authored-by: etiennebacher <etienne.bacher@orotonmail.com>
Co-authored-by: Daniel <mail@danielluedecke.de>
---
 DESCRIPTION                         |  5 +--
 NAMESPACE                           |  4 --
 NEWS.md                             | 16 +++++++-
 R/data_partition.R                  |  8 ----
 R/data_select.R                     | 22 ----------
 R/demean.R                          | 19 +--------
 R/descriptives.R                    |  9 +---
 R/extract_column_names.R            | 24 +----------
 R/mean_sd.R                         | 14 +------
 R/means_by_group.R                  | 15 -------
 R/recode_values.R                   | 32 ---------------
 R/rescale_weights.R                 |  9 +---
 R/skewness_kurtosis.R               | 64 -----------------------------
 R/text_format.R                     |  9 ----
 cran-comments.md                    |  7 ----
 man/coef_var.Rd                     |  3 --
 man/data_partition.Rd               |  3 --
 man/demean.Rd                       | 11 ++---
 man/extract_column_names.Rd         | 22 ----------
 man/mean_sd.Rd                      |  5 +--
 man/means_by_group.Rd               | 13 +-----
 man/recode_values.Rd                | 15 -------
 man/rescale_weights.Rd              |  4 +-
 man/skewness.Rd                     |  4 --
 man/text_format.Rd                  | 10 -----
 tests/testthat/_snaps/categorize.md | 19 ++++-----
 tests/testthat/test-categorize.R    |  2 +-
 tests/testthat/test-coef_var.R      |  4 --
 tests/testthat/test-mean_sd.R       |  5 ---
 29 files changed, 40 insertions(+), 337 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 3d1a0081a..f3e7599af 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.12.3.4
+Version: 0.13.0
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
@@ -33,7 +33,7 @@ BugReports: https://github.com/easystats/datawizard/issues
 Depends:
     R (>= 3.6)
 Imports:
-    insight (>= 0.20.4),
+    insight (>= 0.20.5),
     stats,
     utils
 Suggests:
@@ -76,4 +76,3 @@ RoxygenNote: 7.3.2
 Config/testthat/edition: 3
 Config/testthat/parallel: true
 Config/Needs/website: easystats/easystatstemplate
-Remotes: easystats/insight
diff --git a/NAMESPACE b/NAMESPACE
index a08798db1..c435c0cc5 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -220,7 +220,6 @@ export(assign_labels)
 export(categorize)
 export(center)
 export(centre)
-export(change_code)
 export(change_scale)
 export(coef_var)
 export(coerce_to_numeric)
@@ -237,7 +236,6 @@ export(data_codebook)
 export(data_duplicated)
 export(data_extract)
 export(data_filter)
-export(data_find)
 export(data_group)
 export(data_join)
 export(data_match)
@@ -276,8 +274,6 @@ export(empty_columns)
 export(empty_rows)
 export(extract_column_names)
 export(find_columns)
-export(format_text)
-export(get_columns)
 export(kurtosis)
 export(labels_to_levels)
 export(mean_sd)
diff --git a/NEWS.md b/NEWS.md
index 8e329b0fb..f2ade5883 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,16 +1,30 @@
-# datawizard (development)
+# datawizard 0.13.0
 
 BREAKING CHANGES
 
 * `data_rename()` now errors when the `replacement` argument contains `NA` values
   or empty strings (#539).
 
+* Removed deprecated functions `get_columns()`, `data_find()`, `format_text()` (#546).
+
+* Removed deprecated arguments `group` and `na.rm` in multiple functions. Use `by` and `remove_na` instead (#546).
+
+* The default value for the argument `dummy_factors` in `to_numeric()` has
+  changed from `TRUE` to `FALSE` (#544).
+
 CHANGES
 
 * The `pattern` argument in `data_rename()` can also be a named vector. In this
   case, names are used as values for the `replacement` argument (i.e. `pattern`
   can be a character vector using `<new name> = "<old name>"`).
 
+* `categorize()` gains a new `breaks` argument, to decide whether breaks are
+  inclusive or exclusive (#548).
+
+* The `labels` argument in `categorize()` gets two new options, `"range"` and
+  `"observed"`, to use the range of categorized values as labels (i.e. factor
+  levels) (#548).
+
 * Minor additions to `reshape_ci()` to work with forthcoming changes in the
   `{bayestestR}` package.
 
diff --git a/R/data_partition.R b/R/data_partition.R
index 09add9dd7..99f481e18 100644
--- a/R/data_partition.R
+++ b/R/data_partition.R
@@ -15,7 +15,6 @@
 #' @param row_id Character string, indicating the name of the column that
 #'   contains the row-id's.
 #' @param verbose Toggle messages and warnings.
-#' @param group Deprecated. Use `by` instead.
 #'
 #' @return A list of data frames. The list includes one training set per given
 #'   proportion and the remaining data as test set. List elements of training
@@ -50,17 +49,10 @@ data_partition <- function(data,
                            seed = NULL,
                            row_id = ".row_id",
                            verbose = TRUE,
-                           group = NULL,
                            ...) {
   # validation checks
   data <- .coerce_to_dataframe(data)
 
-  ## TODO: remove warning in future release
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
   if (sum(proportion) > 1) {
     insight::format_error("Sum of `proportion` cannot be higher than 1.")
   }
diff --git a/R/data_select.R b/R/data_select.R
index 0f62ba398..db91fc06b 100644
--- a/R/data_select.R
+++ b/R/data_select.R
@@ -38,25 +38,3 @@ data_select <- function(data,
   out <- .replace_attrs(out, a)
   out
 }
-
-
-#' @rdname extract_column_names
-#' @export
-get_columns <- function(data,
-                        select = NULL,
-                        exclude = NULL,
-                        ignore_case = FALSE,
-                        regex = FALSE,
-                        verbose = TRUE,
-                        ...) {
-  insight::format_warning("Function `get_columns()` is deprecated and will be removed in a future release. Please use `data_select()` instead.") # nolint
-  data_select(
-    data,
-    select = select,
-    exclude = exclude,
-    ignore_case = ignore_case,
-    regex = regex,
-    verbose = verbose,
-    ...
-  )
-}
diff --git a/R/demean.R b/R/demean.R
index 94bfc255f..b5363edb6 100644
--- a/R/demean.R
+++ b/R/demean.R
@@ -43,7 +43,6 @@
 #'   attributes to indicate the within- and between-effects. This is only
 #'   relevant when printing `model_parameters()` - in such cases, the
 #'   within- and between-effects are printed in separated blocks.
-#' @param group Deprecated. Use `by` instead.
 #' @inheritParams center
 #'
 #' @return
@@ -285,14 +284,7 @@ demean <- function(x,
                    suffix_demean = "_within",
                    suffix_groupmean = "_between",
                    add_attributes = TRUE,
-                   verbose = TRUE,
-                   group = NULL) {
-  ## TODO: remove warning in future release
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
+                   verbose = TRUE) {
   degroup(
     x = x,
     select = select,
@@ -317,14 +309,7 @@ degroup <- function(x,
                     suffix_demean = "_within",
                     suffix_groupmean = "_between",
                     add_attributes = TRUE,
-                    verbose = TRUE,
-                    group = NULL) {
-  ## TODO: remove warning later
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
+                    verbose = TRUE) {
   # ugly tibbles again...
   x <- .coerce_to_dataframe(x)
 
diff --git a/R/descriptives.R b/R/descriptives.R
index 097934d29..43479f697 100644
--- a/R/descriptives.R
+++ b/R/descriptives.R
@@ -77,7 +77,6 @@ coef_var.default <- function(x, verbose = TRUE, ...) {
 #'   as the nearest endpoint.
 #' @param remove_na Logical. Should `NA` values be removed before computing (`TRUE`)
 #'   or not (`FALSE`, default)?
-#' @param na.rm Deprecated. Please use `remove_na` instead.
 #' @param n If `method = "unbiased"` and both `mu` and `sigma` are provided (not
 #'   computed from `x`), what sample size to use to adjust the computed CV
 #'   for small-sample bias?
@@ -111,13 +110,7 @@ coef_var.default <- function(x, verbose = TRUE, ...) {
 #' @export
 coef_var.numeric <- function(x, mu = NULL, sigma = NULL,
                              method = c("standard", "unbiased", "median_mad", "qcd"),
-                             trim = 0, remove_na = FALSE, n = NULL, na.rm = FALSE, ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    insight::format_warning("Argument `na.rm` is deprecated. Please use `remove_na` instead.")
-    remove_na <- na.rm
-  }
-
+                             trim = 0, remove_na = FALSE, n = NULL, ...) {
   # TODO: Support weights
   if (!missing(x) && all(c(-1, 1) %in% sign(x))) {
     insight::format_error("Coefficient of variation only applicable for ratio scale variables.")
diff --git a/R/extract_column_names.R b/R/extract_column_names.R
index b89173a8c..c245f4bab 100644
--- a/R/extract_column_names.R
+++ b/R/extract_column_names.R
@@ -160,28 +160,6 @@ extract_column_names <- function(data,
   columns
 }
 
-
-#' @rdname extract_column_names
-#' @export
-data_find <- function(data,
-                      select = NULL,
-                      exclude = NULL,
-                      ignore_case = FALSE,
-                      regex = FALSE,
-                      verbose = TRUE,
-                      ...) {
-  insight::format_warning("Function `data_find()` is deprecated and will be removed in a future release. Please use `extract_column_names()` instead.") # nolint
-  extract_column_names(
-    data,
-    select = select,
-    exclude = exclude,
-    ignore_case = ignore_case,
-    regex = regex,
-    verbose = verbose,
-    ...
-  )
-}
-
 #' @rdname extract_column_names
 #' @export
-find_columns <- data_find
+find_columns <- extract_column_names
diff --git a/R/mean_sd.R b/R/mean_sd.R
index d18473d8d..42ce9b523 100644
--- a/R/mean_sd.R
+++ b/R/mean_sd.R
@@ -20,23 +20,13 @@
 #' median_mad(mtcars$mpg)
 #'
 #' @export
-mean_sd <- function(x, times = 1L, remove_na = TRUE, named = TRUE, na.rm = TRUE, ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    insight::format_warning("Argument `na.rm` is deprecated. Please use `remove_na` instead.")
-    remove_na <- na.rm
-  }
+mean_sd <- function(x, times = 1L, remove_na = TRUE, named = TRUE, ...) {
   .centrality_dispersion(x, type = "mean", times = times, remove_na = remove_na, named = named)
 }
 
 #' @export
 #' @rdname mean_sd
-median_mad <- function(x, times = 1L, remove_na = TRUE, constant = 1.4826, named = TRUE, na.rm = TRUE, ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    insight::format_warning("Argument `na.rm` is deprecated. Please use `remove_na` instead.")
-    remove_na <- na.rm
-  }
+median_mad <- function(x, times = 1L, remove_na = TRUE, constant = 1.4826, named = TRUE, ...) {
   .centrality_dispersion(x, type = "median", times = times, remove_na = remove_na, constant = constant, named = named)
 }
 
diff --git a/R/means_by_group.R b/R/means_by_group.R
index ad188f275..39416bb11 100644
--- a/R/means_by_group.R
+++ b/R/means_by_group.R
@@ -19,7 +19,6 @@
 #' @param digits Optional scalar, indicating the amount of digits after decimal
 #' point when rounding estimates and values.
 #' @param ... Currently not used
-#' @param group Deprecated. Use `by` instead.
 #' @inheritParams find_columns
 #'
 #' @return A data frame with information on mean and further summary statistics
@@ -60,14 +59,7 @@ means_by_group.numeric <- function(x,
                                    ci = 0.95,
                                    weights = NULL,
                                    digits = NULL,
-                                   group = NULL,
                                    ...) {
-  ## TODO: remove warning in future release
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
   # validation check for arguments
 
   # "by" must be provided
@@ -139,14 +131,7 @@ means_by_group.data.frame <- function(x,
                                       ignore_case = FALSE,
                                       regex = FALSE,
                                       verbose = TRUE,
-                                      group = NULL,
                                       ...) {
-  ## TODO: remove warning in future release
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
   # evaluate select/exclude, may be select-helpers
   select <- .select_nse(select,
     x,
diff --git a/R/recode_values.R b/R/recode_values.R
index b4570bf44..a8e8d6d3b 100644
--- a/R/recode_values.R
+++ b/R/recode_values.R
@@ -527,35 +527,3 @@ recode_values.data.frame <- function(x,
 
   ok
 }
-
-
-## TODO Deprecate and remove alias later
-
-#' @rdname recode_values
-#' @export
-change_code <- function(x,
-                        select = NULL,
-                        exclude = NULL,
-                        recode = NULL,
-                        default = NULL,
-                        preserve_na = TRUE,
-                        append = FALSE,
-                        ignore_case = FALSE,
-                        regex = FALSE,
-                        verbose = TRUE,
-                        ...) {
-  insight::format_warning("Function `change_code()` is deprecated. Please use `recode_values()` instead.") # nolint
-  recode_values(
-    x,
-    select = select,
-    exclude = exclude,
-    recode = recode,
-    default = default,
-    preserve_na = preserve_na,
-    append = append,
-    ignore_case = ignore_case,
-    regex = regex,
-    verbose = verbose,
-    ...
-  )
-}
diff --git a/R/rescale_weights.R b/R/rescale_weights.R
index 02aab1d2e..60d405c9d 100644
--- a/R/rescale_weights.R
+++ b/R/rescale_weights.R
@@ -20,7 +20,6 @@
 #' @param nest Logical, if `TRUE` and `by` indicates at least two
 #'   group variables, then groups are "nested", i.e. groups are now a
 #'   combination from each group level of the variables in `by`.
-#' @param group Deprecated. Use `by` instead.
 #'
 #' @return `data`, including the new weighting variables: `pweights_a`
 #'   and `pweights_b`, which represent the rescaled design weights to use
@@ -88,13 +87,7 @@
 #'   )
 #' }
 #' @export
-rescale_weights <- function(data, by, probability_weights, nest = FALSE, group = NULL) {
-  ## TODO: remove warning in future release
-  if (!is.null(group)) {
-    by <- group
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-  }
-
+rescale_weights <- function(data, by, probability_weights, nest = FALSE) {
   if (inherits(by, "formula")) {
     by <- all.vars(by)
   }
diff --git a/R/skewness_kurtosis.R b/R/skewness_kurtosis.R
index 6142c59ad..23ced0a04 100644
--- a/R/skewness_kurtosis.R
+++ b/R/skewness_kurtosis.R
@@ -110,15 +110,7 @@ skewness.numeric <- function(x,
                              type = "2",
                              iterations = NULL,
                              verbose = TRUE,
-                             na.rm = TRUE,
                              ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   if (remove_na) x <- x[!is.na(x)]
   n <- length(x)
   out <- (sum((x - mean(x))^3) / n) / (sum((x - mean(x))^2) / n)^1.5
@@ -177,15 +169,7 @@ skewness.matrix <- function(x,
                             remove_na = TRUE,
                             type = "2",
                             iterations = NULL,
-                            na.rm = TRUE,
                             ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   .skewness <- apply(
     x,
     2,
@@ -213,15 +197,7 @@ skewness.data.frame <- function(x,
                                 remove_na = TRUE,
                                 type = "2",
                                 iterations = NULL,
-                                na.rm = TRUE,
                                 ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   .skewness <- lapply(x,
     skewness,
     remove_na = remove_na,
@@ -241,15 +217,7 @@ skewness.default <- function(x,
                              remove_na = TRUE,
                              type = "2",
                              iterations = NULL,
-                             na.rm = TRUE,
                              ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   skewness(
     .factor_to_numeric(x),
     remove_na = remove_na,
@@ -277,15 +245,7 @@ kurtosis.numeric <- function(x,
                              type = "2",
                              iterations = NULL,
                              verbose = TRUE,
-                             na.rm = TRUE,
                              ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   if (remove_na) x <- x[!is.na(x)]
   n <- length(x)
   out <- n * sum((x - mean(x))^4) / (sum((x - mean(x))^2)^2)
@@ -342,15 +302,7 @@ kurtosis.matrix <- function(x,
                             remove_na = TRUE,
                             type = "2",
                             iterations = NULL,
-                            na.rm = TRUE,
                             ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   .kurtosis <- apply(
     x,
     2,
@@ -374,15 +326,7 @@ kurtosis.data.frame <- function(x,
                                 remove_na = TRUE,
                                 type = "2",
                                 iterations = NULL,
-                                na.rm = TRUE,
                                 ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   .kurtosis <- lapply(x,
     kurtosis,
     remove_na = remove_na,
@@ -400,15 +344,7 @@ kurtosis.default <- function(x,
                              remove_na = TRUE,
                              type = "2",
                              iterations = NULL,
-                             na.rm = TRUE,
                              ...) {
-  # TODO: remove deprecated argument later
-  if (!missing(na.rm)) {
-    # TODO: add deprecation warning in a later update
-    insight::format_warning("Argument `na.rm` is deprecated and will be removed in a future release. Please use `remove_na` instead.") # nolint
-    remove_na <- na.rm
-  }
-
   kurtosis(
     .factor_to_numeric(x),
     remove_na = remove_na,
diff --git a/R/text_format.R b/R/text_format.R
index afdf4f861..0fa75bcac 100644
--- a/R/text_format.R
+++ b/R/text_format.R
@@ -42,15 +42,6 @@ text_format <- function(text, sep = ", ", last = " and ", width = NULL, enclose
   text_wrap(text_concatenate(text, sep = sep, last = last, enclose = enclose), width = width)
 }
 
-## TODO Deprecate and remove alias later
-
-#' @rdname text_format
-#' @export
-format_text <- function(text, sep = ", ", last = " and ", width = NULL, enclose = NULL, ...) {
-  insight::format_warning("Function `format_text()` is deprecated and will be removed in a future release. Please use `text_format()` instead.") # nolint
-  text_format(text, sep = sep, last = last, width = width, enclose = enclose, ...)
-}
-
 #' @rdname text_format
 #' @export
 text_fullstop <- function(text) {
diff --git a/cran-comments.md b/cran-comments.md
index 2c30d1287..095f22e9a 100644
--- a/cran-comments.md
+++ b/cran-comments.md
@@ -9,10 +9,3 @@ We checked 18 reverse dependencies, comparing R CMD check results across CRAN an
  * We saw 0 new problems
  * We failed to check 0 packages
 
-## Other comments
-
-This is a patch release that should (hopefully) fix a failure occurring on macOS
-when building vignettes. This only happens on macOS with R 4.3. We tried to
-reproduce this locally and in CI with the same setup, but we couldn't. Hence, we
-removed all vignettes (except for one "Overview"), they are now only available
-on the website.
diff --git a/man/coef_var.Rd b/man/coef_var.Rd
index 92274ca59..2ff973838 100644
--- a/man/coef_var.Rd
+++ b/man/coef_var.Rd
@@ -19,7 +19,6 @@ distribution_coef_var(x, ...)
   trim = 0,
   remove_na = FALSE,
   n = NULL,
-  na.rm = FALSE,
   ...
 )
 }
@@ -52,8 +51,6 @@ or not (\code{FALSE}, default)?}
 \item{n}{If \code{method = "unbiased"} and both \code{mu} and \code{sigma} are provided (not
 computed from \code{x}), what sample size to use to adjust the computed CV
 for small-sample bias?}
-
-\item{na.rm}{Deprecated. Please use \code{remove_na} instead.}
 }
 \value{
 The computed coefficient of variation for \code{x}.
diff --git a/man/data_partition.Rd b/man/data_partition.Rd
index 68ac05a19..1150b4f28 100644
--- a/man/data_partition.Rd
+++ b/man/data_partition.Rd
@@ -11,7 +11,6 @@ data_partition(
   seed = NULL,
   row_id = ".row_id",
   verbose = TRUE,
-  group = NULL,
   ...
 )
 }
@@ -33,8 +32,6 @@ contains the row-id's.}
 
 \item{verbose}{Toggle messages and warnings.}
 
-\item{group}{Deprecated. Use \code{by} instead.}
-
 \item{...}{Other arguments passed to or from other functions.}
 }
 \value{
diff --git a/man/demean.Rd b/man/demean.Rd
index 8a9a49308..fb4db3a29 100644
--- a/man/demean.Rd
+++ b/man/demean.Rd
@@ -14,8 +14,7 @@ demean(
   suffix_demean = "_within",
   suffix_groupmean = "_between",
   add_attributes = TRUE,
-  verbose = TRUE,
-  group = NULL
+  verbose = TRUE
 )
 
 degroup(
@@ -27,8 +26,7 @@ degroup(
   suffix_demean = "_within",
   suffix_groupmean = "_between",
   add_attributes = TRUE,
-  verbose = TRUE,
-  group = NULL
+  verbose = TRUE
 )
 
 detrend(
@@ -40,8 +38,7 @@ detrend(
   suffix_demean = "_within",
   suffix_groupmean = "_between",
   add_attributes = TRUE,
-  verbose = TRUE,
-  group = NULL
+  verbose = TRUE
 )
 }
 \arguments{
@@ -86,8 +83,6 @@ within- and between-effects are printed in separated blocks.}
 
 \item{verbose}{Toggle warnings and messages.}
 
-\item{group}{Deprecated. Use \code{by} instead.}
-
 \item{center}{Method for centering. \code{demean()} always performs
 mean-centering, while \code{degroup()} can use \code{center = "median"} or
 \code{center = "mode"} for median- or mode-centering, and also \code{"min"}
diff --git a/man/extract_column_names.Rd b/man/extract_column_names.Rd
index 6805d9569..6e658ab33 100644
--- a/man/extract_column_names.Rd
+++ b/man/extract_column_names.Rd
@@ -2,9 +2,7 @@
 % Please edit documentation in R/data_select.R, R/extract_column_names.R
 \name{data_select}
 \alias{data_select}
-\alias{get_columns}
 \alias{extract_column_names}
-\alias{data_find}
 \alias{find_columns}
 \title{Find or get columns in a data frame based on search patterns}
 \usage{
@@ -18,16 +16,6 @@ data_select(
   ...
 )
 
-get_columns(
-  data,
-  select = NULL,
-  exclude = NULL,
-  ignore_case = FALSE,
-  regex = FALSE,
-  verbose = TRUE,
-  ...
-)
-
 extract_column_names(
   data,
   select = NULL,
@@ -38,16 +26,6 @@ extract_column_names(
   ...
 )
 
-data_find(
-  data,
-  select = NULL,
-  exclude = NULL,
-  ignore_case = FALSE,
-  regex = FALSE,
-  verbose = TRUE,
-  ...
-)
-
 find_columns(
   data,
   select = NULL,
diff --git a/man/mean_sd.Rd b/man/mean_sd.Rd
index f0ea239f8..33eeb4bc5 100644
--- a/man/mean_sd.Rd
+++ b/man/mean_sd.Rd
@@ -5,7 +5,7 @@
 \alias{median_mad}
 \title{Summary Helpers}
 \usage{
-mean_sd(x, times = 1L, remove_na = TRUE, named = TRUE, na.rm = TRUE, ...)
+mean_sd(x, times = 1L, remove_na = TRUE, named = TRUE, ...)
 
 median_mad(
   x,
@@ -13,7 +13,6 @@ median_mad(
   remove_na = TRUE,
   constant = 1.4826,
   named = TRUE,
-  na.rm = TRUE,
   ...
 )
 }
@@ -29,8 +28,6 @@ or not (\code{FALSE}, default)?}
 \item{named}{Should the vector be named?
 (E.g., \code{c("-SD" = -1, Mean = 1, "+SD" = 2)}.)}
 
-\item{na.rm}{Deprecated. Please use \code{remove_na} instead.}
-
 \item{...}{Not used.}
 
 \item{constant}{scale factor.}
diff --git a/man/means_by_group.Rd b/man/means_by_group.Rd
index d7a6dfc96..ba2a7d0c8 100644
--- a/man/means_by_group.Rd
+++ b/man/means_by_group.Rd
@@ -8,15 +8,7 @@
 \usage{
 means_by_group(x, ...)
 
-\method{means_by_group}{numeric}(
-  x,
-  by = NULL,
-  ci = 0.95,
-  weights = NULL,
-  digits = NULL,
-  group = NULL,
-  ...
-)
+\method{means_by_group}{numeric}(x, by = NULL, ci = 0.95, weights = NULL, digits = NULL, ...)
 
 \method{means_by_group}{data.frame}(
   x,
@@ -29,7 +21,6 @@ means_by_group(x, ...)
   ignore_case = FALSE,
   regex = FALSE,
   verbose = TRUE,
-  group = NULL,
   ...
 )
 }
@@ -56,8 +47,6 @@ weights are used.}
 \item{digits}{Optional scalar, indicating the amount of digits after decimal
 point when rounding estimates and values.}
 
-\item{group}{Deprecated. Use \code{by} instead.}
-
 \item{select}{Variables that will be included when performing the required
 tasks. Can be either
 \itemize{
diff --git a/man/recode_values.Rd b/man/recode_values.Rd
index 9810c0a2d..baa7afda9 100644
--- a/man/recode_values.Rd
+++ b/man/recode_values.Rd
@@ -4,7 +4,6 @@
 \alias{recode_values}
 \alias{recode_values.numeric}
 \alias{recode_values.data.frame}
-\alias{change_code}
 \title{Recode old values of variables into new values}
 \usage{
 recode_values(x, ...)
@@ -31,20 +30,6 @@ recode_values(x, ...)
   verbose = TRUE,
   ...
 )
-
-change_code(
-  x,
-  select = NULL,
-  exclude = NULL,
-  recode = NULL,
-  default = NULL,
-  preserve_na = TRUE,
-  append = FALSE,
-  ignore_case = FALSE,
-  regex = FALSE,
-  verbose = TRUE,
-  ...
-)
 }
 \arguments{
 \item{x}{A data frame, numeric or character vector, or factor.}
diff --git a/man/rescale_weights.Rd b/man/rescale_weights.Rd
index 4a67d4100..d9651decb 100644
--- a/man/rescale_weights.Rd
+++ b/man/rescale_weights.Rd
@@ -4,7 +4,7 @@
 \alias{rescale_weights}
 \title{Rescale design weights for multilevel analysis}
 \usage{
-rescale_weights(data, by, probability_weights, nest = FALSE, group = NULL)
+rescale_weights(data, by, probability_weights, nest = FALSE)
 }
 \arguments{
 \item{data}{A data frame.}
@@ -21,8 +21,6 @@ sampling) weights of the survey data (level-1-weight).}
 \item{nest}{Logical, if \code{TRUE} and \code{by} indicates at least two
 group variables, then groups are "nested", i.e. groups are now a
 combination from each group level of the variables in \code{by}.}
-
-\item{group}{Deprecated. Use \code{by} instead.}
 }
 \value{
 \code{data}, including the new weighting variables: \code{pweights_a}
diff --git a/man/skewness.Rd b/man/skewness.Rd
index a89d98067..0401e3a40 100644
--- a/man/skewness.Rd
+++ b/man/skewness.Rd
@@ -19,7 +19,6 @@ skewness(x, ...)
   type = "2",
   iterations = NULL,
   verbose = TRUE,
-  na.rm = TRUE,
   ...
 )
 
@@ -31,7 +30,6 @@ kurtosis(x, ...)
   type = "2",
   iterations = NULL,
   verbose = TRUE,
-  na.rm = TRUE,
   ...
 )
 
@@ -61,8 +59,6 @@ errors. If \code{NULL} (default), parametric standard errors are computed.}
 
 \item{verbose}{Toggle warnings and messages.}
 
-\item{na.rm}{Deprecated. Please use \code{remove_na} instead.}
-
 \item{digits}{Number of decimal places.}
 
 \item{test}{Logical, if \code{TRUE}, tests if skewness or kurtosis is
diff --git a/man/text_format.Rd b/man/text_format.Rd
index 5f246731f..14d64b096 100644
--- a/man/text_format.Rd
+++ b/man/text_format.Rd
@@ -2,7 +2,6 @@
 % Please edit documentation in R/text_format.R
 \name{text_format}
 \alias{text_format}
-\alias{format_text}
 \alias{text_fullstop}
 \alias{text_lastchar}
 \alias{text_concatenate}
@@ -20,15 +19,6 @@ text_format(
   ...
 )
 
-format_text(
-  text,
-  sep = ", ",
-  last = " and ",
-  width = NULL,
-  enclose = NULL,
-  ...
-)
-
 text_fullstop(text)
 
 text_lastchar(text, n = 1)
diff --git a/tests/testthat/_snaps/categorize.md b/tests/testthat/_snaps/categorize.md
index d08c14c4d..9ed3c1115 100644
--- a/tests/testthat/_snaps/categorize.md
+++ b/tests/testthat/_snaps/categorize.md
@@ -31,17 +31,16 @@
       [31] (10.4-15)   (21-24.4)  
       Levels: (10.4-15) (15.2-19.7) (21-24.4) (26-27.3) (30.4-33.9)
 
----
+# categorize breaks
 
     Code
-      categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed",
-      breaks = "inclusive")
+      categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range", breaks = "inclusive")
     Output
-       [1] (21-24.4)   (21-24.4)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7)
-       [7] (10.4-15)   (21-24.4)   (21-24.4)   (15.2-19.7) (15.2-19.7) (15.2-19.7)
-      [13] (15.2-19.7) (15.2-19.7) (10.4-15)   (10.4-15)   (10.4-15)   (30.4-33.9)
-      [19] (30.4-33.9) (30.4-33.9) (21-24.4)   (15.2-19.7) (15.2-19.7) (10.4-15)  
-      [25] (15.2-19.7) (26-27.3)   (26-27.3)   (30.4-33.9) (15.2-19.7) (15.2-19.7)
-      [31] (10.4-15)   (21-24.4)  
-      Levels: (10.4-15) (15.2-19.7) (21-24.4) (26-27.3) (30.4-33.9)
+       [1] (19.8,24.5] (19.8,24.5] (19.8,24.5] (19.8,24.5] (15.1,19.8] (15.1,19.8]
+       [7] [10.4,15.1] (19.8,24.5] (19.8,24.5] (15.1,19.8] (15.1,19.8] (15.1,19.8]
+      [13] (15.1,19.8] (15.1,19.8] [10.4,15.1] [10.4,15.1] [10.4,15.1] (29.2,33.9]
+      [19] (29.2,33.9] (29.2,33.9] (19.8,24.5] (15.1,19.8] (15.1,19.8] [10.4,15.1]
+      [25] (15.1,19.8] (24.5,29.2] (24.5,29.2] (29.2,33.9] (15.1,19.8] (15.1,19.8]
+      [31] [10.4,15.1] (19.8,24.5]
+      Levels: [10.4,15.1] (15.1,19.8] (19.8,24.5] (24.5,29.2] (29.2,33.9]
 
diff --git a/tests/testthat/test-categorize.R b/tests/testthat/test-categorize.R
index 217797893..30453d9ad 100644
--- a/tests/testthat/test-categorize.R
+++ b/tests/testthat/test-categorize.R
@@ -244,7 +244,7 @@ test_that("categorize labelling ranged", {
 
 test_that("categorize breaks", {
   data(mtcars)
-  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed", breaks = "inclusive"))
+  expect_snapshot(categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range", breaks = "inclusive"))
   expect_error(
     categorize(mtcars$mpg, "equal_length", n_groups = 5, breaks = "something"),
     regex = "should be one of"
diff --git a/tests/testthat/test-coef_var.R b/tests/testthat/test-coef_var.R
index a55eb7b96..2ae2275cd 100644
--- a/tests/testthat/test-coef_var.R
+++ b/tests/testthat/test-coef_var.R
@@ -29,10 +29,6 @@ test_that("coef_var: argument 'remove_na' works", {
   )
 })
 
-test_that("coef_var: deprecation warning", {
-  expect_warning(coef_var(c(1:10, NA), na.rm = TRUE))
-})
-
 test_that("coef_var: method 'unbiased' needs argument 'n' when sigma and mu are provided", {
   expect_error(
     coef_var(1:10, method = "unbiased", mu = 10, sigma = 20),
diff --git a/tests/testthat/test-mean_sd.R b/tests/testthat/test-mean_sd.R
index e0af8a0f1..3e0829fb1 100644
--- a/tests/testthat/test-mean_sd.R
+++ b/tests/testthat/test-mean_sd.R
@@ -15,8 +15,3 @@ test_that("mean_sd", {
   expect_equal(unname(diff(msd2)), rep(sd(mtcars[["mpg"]]), 6), tolerance = 0.00001)
   expect_named(msd2, c("-3 SD", "-2 SD", "-1 SD", "Mean", "+1 SD", "+2 SD", "+3 SD"))
 })
-
-test_that("deprecation warning for `na.rm`", {
-  expect_warning(mean_sd(c(-1, 0, 1, NA), na.rm = TRUE))
-  expect_warning(median_mad(c(-1, 0, 1, 2, 3, NA), na.rm = TRUE))
-})

From efa7df074d99a4e2f0467a0c35daa024e22cb0c2 Mon Sep 17 00:00:00 2001
From: etiennebacher <etienne.bacher@protonmail.com>
Date: Mon, 7 Oct 2024 21:51:11 +0200
Subject: [PATCH 07/19] Remove "lifecycle" badge, following
 https://github.com/easystats/easystats/issues/432

---
 README.Rmd |   2 +-
 README.md  | 140 ++++++++++++++++++-----------------------------------
 2 files changed, 47 insertions(+), 95 deletions(-)

diff --git a/README.Rmd b/README.Rmd
index ec0d01df7..39b8825ad 100644
--- a/README.Rmd
+++ b/README.Rmd
@@ -19,7 +19,7 @@ library(datawizard)
 
 [![DOI](https://joss.theoj.org/papers/10.21105/joss.04684/status.svg)](https://doi.org/10.21105/joss.04684)
 [![downloads](http://cranlogs.r-pkg.org/badges/datawizard)](https://cran.r-project.org/package=datawizard)
-[![total](https://cranlogs.r-pkg.org/badges/grand-total/datawizard)](https://cranlogs.r-pkg.org/) [![lifecycle](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://lifecycle.r-lib.org/articles/stages.html)
+[![total](https://cranlogs.r-pkg.org/badges/grand-total/datawizard)](https://cranlogs.r-pkg.org/) 
 
 <!-- ***:sparkles: Hockety pockety wockety wack, prepare this data forth and back*** -->
 
diff --git a/README.md b/README.md
index 712449df9..dd046ca12 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,6 @@
 [![DOI](https://joss.theoj.org/papers/10.21105/joss.04684/status.svg)](https://doi.org/10.21105/joss.04684)
 [![downloads](http://cranlogs.r-pkg.org/badges/datawizard)](https://cran.r-project.org/package=datawizard)
 [![total](https://cranlogs.r-pkg.org/badges/grand-total/datawizard)](https://cranlogs.r-pkg.org/)
-[![lifecycle](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://lifecycle.r-lib.org/articles/stages.html)
 
 <!-- ***:sparkles: Hockety pockety wockety wack, prepare this data forth and back*** -->
 <!-- ***Hockety pockety wockety wock, messy data is in shock*** -->
@@ -50,11 +49,11 @@ It covers two aspects of data preparation:
 badge](https://easystats.r-universe.dev/badges/datawizard)](https://easystats.r-universe.dev)
 [![R-CMD-check](https://github.com/easystats/datawizard/workflows/R-CMD-check/badge.svg?branch=main)](https://github.com/easystats/datawizard/actions)
 
-| Type | Source | Command |
-|----|----|----|
-| Release | CRAN | `install.packages("datawizard")` |
+| Type        | Source     | Command                                                                      |
+|-------------|------------|------------------------------------------------------------------------------|
+| Release     | CRAN       | `install.packages("datawizard")`                                             |
 | Development | r-universe | `install.packages("datawizard", repos = "https://easystats.r-universe.dev")` |
-| Development | GitHub | `remotes::install_github("easystats/datawizard")` |
+| Development | GitHub     | `remotes::install_github("easystats/datawizard")`                            |
 
 > **Tip**
 >
@@ -71,9 +70,10 @@ To cite the package, run the following command:
 citation("datawizard")
 To cite package 'datawizard' in publications use:
 
-  Patil et al., (2022). datawizard: An R Package for Easy Data
-  Preparation and Statistical Transformations. Journal of Open Source
-  Software, 7(78), 4684, https://doi.org/10.21105/joss.04684
+  Patil et al., (2022). datawizard: An R Package for Easy
+  Data Preparation and Statistical Transformations. Journal
+  of Open Source Software, 7(78), 4684,
+  https://doi.org/10.21105/joss.04684
 
 A BibTeX entry for LaTeX users is
 
@@ -136,9 +136,6 @@ columns, can be achieved using `extract_column_names()` or
 # find column names matching a pattern
 extract_column_names(iris, starts_with("Sepal"))
 #> [1] "Sepal.Length" "Sepal.Width"
-```
-
-``` r
 
 # return data columns matching a pattern
 data_select(iris, starts_with("Sepal")) |> head()
@@ -156,10 +153,8 @@ It is also possible to extract one or more variables:
 ``` r
 # single variable
 data_extract(mtcars, "gear")
-#>  [1] 4 4 4 3 3 3 3 4 4 4 4 3 3 3 3 3 3 4 4 4 3 3 3 3 3 4 5 5 5 5 5 4
-```
-
-``` r
+#>  [1] 4 4 4 3 3 3 3 4 4 4 4 3 3 3 3 3 3 4 4 4 3 3 3 3 3 4 5 5 5 5 5
+#> [32] 4
 
 # more variables
 head(data_extract(iris, ends_with("Width")))
@@ -220,17 +215,11 @@ x
 #> 1 1 a 5  1
 #> 2 2 b 6  2
 #> 3 3 c 7  3
-```
-
-``` r
 y
 #>   c d   e id
 #> 1 6 f 100  2
 #> 2 7 g 101  3
 #> 3 8 h 102  4
-```
-
-``` r
 
 data_merge(x, y, join = "full")
 #>    a    b c id    d   e
@@ -238,50 +227,32 @@ data_merge(x, y, join = "full")
 #> 1  2    b 6  2    f 100
 #> 2  3    c 7  3    g 101
 #> 4 NA <NA> 8  4    h 102
-```
-
-``` r
 
 data_merge(x, y, join = "left")
 #>   a b c id    d   e
 #> 3 1 a 5  1 <NA>  NA
 #> 1 2 b 6  2    f 100
 #> 2 3 c 7  3    g 101
-```
-
-``` r
 
 data_merge(x, y, join = "right")
 #>    a    b c id d   e
 #> 1  2    b 6  2 f 100
 #> 2  3    c 7  3 g 101
 #> 3 NA <NA> 8  4 h 102
-```
-
-``` r
 
 data_merge(x, y, join = "semi", by = "c")
 #>   a b c id
 #> 2 2 b 6  2
 #> 3 3 c 7  3
-```
-
-``` r
 
 data_merge(x, y, join = "anti", by = "c")
 #>   a b c id
 #> 1 1 a 5  1
-```
-
-``` r
 
 data_merge(x, y, join = "inner")
 #>   a b c id d   e
 #> 1 2 b 6  2 f 100
 #> 2 3 c 7  3 g 101
-```
-
-``` r
 
 data_merge(x, y, join = "bind")
 #>    a    b c id    d   e
@@ -322,17 +293,28 @@ data_to_wide(long_data,
   values_from = "value",
   id_cols = "Row_ID"
 )
-#>    Row_ID          X1          X2          X3         X4          X5
-#> 1       1 -0.08281164 -1.12490028 -0.70632036 -0.7027895  0.07633326
-#> 2       2  1.93468099 -0.87430362  0.96687656  0.2998642 -0.23035595
-#> 3       3 -2.05128979  0.04386162 -0.71016648  1.1494697  0.31746484
-#> 4       4  0.27773897 -0.58397514 -0.05917365 -0.3016415 -1.59268440
-#> 5       5 -1.52596060 -0.82329858 -0.23094342 -0.5473394 -0.18194062
-#> 6       6 -0.26916362  0.11059280  0.69200045 -0.3854041  1.75614174
-#> 7       7  1.23305388  0.36472778  1.35682290  0.2763720  0.11394932
-#> 8       8  0.63360774  0.05370100  1.78872284  0.1518608 -0.29216508
-#> 9       9  0.35271746  1.36867235  0.41071582 -0.4313808  1.75409316
-#> 10     10 -0.56048248 -0.38045724 -2.18785470 -1.8705001  1.80958455
+#>    Row_ID          X1          X2          X3         X4
+#> 1       1 -0.08281164 -1.12490028 -0.70632036 -0.7027895
+#> 2       2  1.93468099 -0.87430362  0.96687656  0.2998642
+#> 3       3 -2.05128979  0.04386162 -0.71016648  1.1494697
+#> 4       4  0.27773897 -0.58397514 -0.05917365 -0.3016415
+#> 5       5 -1.52596060 -0.82329858 -0.23094342 -0.5473394
+#> 6       6 -0.26916362  0.11059280  0.69200045 -0.3854041
+#> 7       7  1.23305388  0.36472778  1.35682290  0.2763720
+#> 8       8  0.63360774  0.05370100  1.78872284  0.1518608
+#> 9       9  0.35271746  1.36867235  0.41071582 -0.4313808
+#> 10     10 -0.56048248 -0.38045724 -2.18785470 -1.8705001
+#>             X5
+#> 1   0.07633326
+#> 2  -0.23035595
+#> 3   0.31746484
+#> 4  -1.59268440
+#> 5  -0.18194062
+#> 6   1.75614174
+#> 7   0.11394932
+#> 8  -0.29216508
+#> 9   1.75409316
+#> 10  1.80958455
 ```
 
 ### Empty rows and columns
@@ -352,22 +334,13 @@ tmp
 #> 3  3  3 NA  3
 #> 4 NA NA NA NA
 #> 5  5  5 NA  5
-```
-
-``` r
 
 # indices of empty columns or rows
 empty_columns(tmp)
 #> c 
 #> 3
-```
-
-``` r
 empty_rows(tmp)
 #> [1] 4
-```
-
-``` r
 
 # remove empty columns or rows
 remove_empty_columns(tmp)
@@ -377,18 +350,12 @@ remove_empty_columns(tmp)
 #> 3  3  3  3
 #> 4 NA NA NA
 #> 5  5  5  5
-```
-
-``` r
 remove_empty_rows(tmp)
 #>   a  b  c  d
 #> 1 1  1 NA  1
 #> 2 2 NA NA NA
 #> 3 3  3 NA  3
 #> 5 5  5 NA  5
-```
-
-``` r
 
 # remove empty columns and rows
 remove_empty(tmp)
@@ -409,9 +376,6 @@ table(x)
 #> x
 #>  1  2  3  4  5  6  7  8  9 10 
 #>  2  3  5  3  7  5  5  2 11  7
-```
-
-``` r
 
 # cut into 3 groups, based on distribution (quantiles)
 table(categorize(x, split = "quantile", n_groups = 3))
@@ -445,26 +409,23 @@ summary(swiss)
 #>  Mean   : 41.144   Mean   :19.94   
 #>  3rd Qu.: 93.125   3rd Qu.:21.70   
 #>  Max.   :100.000   Max.   :26.60
-```
-
-``` r
 
 # after
 summary(standardize(swiss))
-#>    Fertility         Agriculture       Examination         Education      
-#>  Min.   :-2.81327   Min.   :-2.1778   Min.   :-1.69084   Min.   :-1.0378  
-#>  1st Qu.:-0.43569   1st Qu.:-0.6499   1st Qu.:-0.56273   1st Qu.:-0.5178  
-#>  Median : 0.02061   Median : 0.1515   Median :-0.06134   Median :-0.3098  
-#>  Mean   : 0.00000   Mean   : 0.0000   Mean   : 0.00000   Mean   : 0.0000  
-#>  3rd Qu.: 0.66504   3rd Qu.: 0.7481   3rd Qu.: 0.69074   3rd Qu.: 0.1062  
-#>  Max.   : 1.78978   Max.   : 1.7190   Max.   : 2.57094   Max.   : 4.3702  
-#>     Catholic       Infant.Mortality  
-#>  Min.   :-0.9350   Min.   :-3.13886  
-#>  1st Qu.:-0.8620   1st Qu.:-0.61543  
-#>  Median :-0.6235   Median : 0.01972  
-#>  Mean   : 0.0000   Mean   : 0.00000  
-#>  3rd Qu.: 1.2464   3rd Qu.: 0.60337  
-#>  Max.   : 1.4113   Max.   : 2.28566
+#>    Fertility         Agriculture       Examination      
+#>  Min.   :-2.81327   Min.   :-2.1778   Min.   :-1.69084  
+#>  1st Qu.:-0.43569   1st Qu.:-0.6499   1st Qu.:-0.56273  
+#>  Median : 0.02061   Median : 0.1515   Median :-0.06134  
+#>  Mean   : 0.00000   Mean   : 0.0000   Mean   : 0.00000  
+#>  3rd Qu.: 0.66504   3rd Qu.: 0.7481   3rd Qu.: 0.69074  
+#>  Max.   : 1.78978   Max.   : 1.7190   Max.   : 2.57094  
+#>    Education          Catholic       Infant.Mortality  
+#>  Min.   :-1.0378   Min.   :-0.9350   Min.   :-3.13886  
+#>  1st Qu.:-0.5178   1st Qu.:-0.8620   1st Qu.:-0.61543  
+#>  Median :-0.3098   Median :-0.6235   Median : 0.01972  
+#>  Mean   : 0.0000   Mean   : 0.0000   Mean   : 0.00000  
+#>  3rd Qu.: 0.1062   3rd Qu.: 1.2464   3rd Qu.: 0.60337  
+#>  Max.   : 4.3702   Max.   : 1.4113   Max.   : 2.28566
 ```
 
 ### Winsorize
@@ -486,9 +447,6 @@ anscombe
 #> 9  12 12 12  8 10.84 9.13  8.15  5.56
 #> 10  7  7  7  8  4.82 7.26  6.42  7.91
 #> 11  5  5  5  8  5.68 4.74  5.73  6.89
-```
-
-``` r
 
 # after
 winsorize(anscombe)
@@ -540,9 +498,6 @@ head(trees)
 #> 4  10.5     72   16.4
 #> 5  10.7     81   18.8
 #> 6  10.8     83   19.7
-```
-
-``` r
 
 # after
 head(ranktransform(trees))
@@ -575,9 +530,6 @@ x
 #> Mazda RX4     21.0   6  160 110
 #> Mazda RX4 Wag 21.0   6  160 110
 #> Datsun 710    22.8   4  108  93
-```
-
-``` r
 
 data_rotate(x)
 #>      Mazda RX4 Mazda RX4 Wag Datsun 710

From db85541477a95bfd2f56055296fda66bbc61fee1 Mon Sep 17 00:00:00 2001
From: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
Date: Mon, 7 Oct 2024 23:12:55 +0200
Subject: [PATCH 08/19] Do not error when bootstrapping CIs if sample is too
 sparse (#550)

* Do not error when bootstrapping CIs if sample is too sparse

* lint, style

* conditional test

* typo

* style again

* Update NEWS.md
---
 DESCRIPTION                                 |  2 +-
 NEWS.md                                     |  7 +++++++
 R/describe_distribution.R                   | 23 ++++++++++++++++-----
 tests/testthat/test-describe_distribution.R | 13 ++++++++++++
 4 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index f3e7599af..8dd92fb7e 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0
+Version: 0.13.0.1
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NEWS.md b/NEWS.md
index f2ade5883..c28ecc63f 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,10 @@
+# datawizard (development)
+
+BUG FIXES
+
+* `describe_distribution()` no longer errors if the sample was too sparse to compute
+  CIs. Instead, it warns the user and returns `NA` (#550).
+
 # datawizard 0.13.0
 
 BREAKING CHANGES
diff --git a/R/describe_distribution.R b/R/describe_distribution.R
index 41f2a8b83..2e61c1dc3 100644
--- a/R/describe_distribution.R
+++ b/R/describe_distribution.R
@@ -186,11 +186,24 @@ describe_distribution.numeric <- function(x,
   # Confidence Intervals
   if (!is.null(ci)) {
     insight::check_if_installed("boot")
-    results <- boot::boot(
-      data = x,
-      statistic = .boot_distribution,
-      R = iterations,
-      centrality = centrality
+    results <- tryCatch(
+      {
+        boot::boot(
+          data = x,
+          statistic = .boot_distribution,
+          R = iterations,
+          centrality = centrality
+        )
+      },
+      error = function(e) {
+        msg <- conditionMessage(e)
+        if (!is.null(msg) && msg == "sample is too sparse to find TD") {
+          insight::format_warning(
+            "When bootstrapping CIs, sample was too sparse to find TD. Returning NA for CIs."
+          )
+          list(t = c(NA_real_, NA_real_))
+        }
+      }
     )
     out_ci <- bayestestR::ci(results$t, ci = ci, verbose = FALSE)
     out <- cbind(out, data.frame(CI_low = out_ci$CI_low[1], CI_high = out_ci$CI_high[1]))
diff --git a/tests/testthat/test-describe_distribution.R b/tests/testthat/test-describe_distribution.R
index 83d2abb33..dfa7bf617 100644
--- a/tests/testthat/test-describe_distribution.R
+++ b/tests/testthat/test-describe_distribution.R
@@ -286,3 +286,16 @@ test_that("describe_distribution formatting", {
   x <- describe_distribution(iris$Sepal.Width, quartiles = TRUE)
   expect_snapshot(format(x))
 })
+
+# other -----------------------------------
+
+test_that("return NA in CI if sample is too sparse", {
+  skip_if_not_installed("bayestestR")
+  set.seed(123456)
+  expect_warning(
+    res <- describe_distribution(mtcars[mtcars$cyl == "6", ], wt, centrality = "map", ci = 0.95), # nolint
+    "When bootstrapping CIs, sample was too sparse to find TD"
+  )
+  expect_identical(res$CI_low, NA)
+  expect_identical(res$CI_high, NA)
+})

From 9dff2ae6b9d36fe43a72267cccaeb66196519dc7 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Thu, 10 Oct 2024 16:26:02 +0200
Subject: [PATCH 09/19] Allow `:` in select strings (#551)

* Allow : in select strings

* lintr

* fix test

* test. comment

* news item
---
 DESCRIPTION                      |  2 +-
 NEWS.md                          |  6 ++++
 R/extract_column_names.R         | 11 ++++--
 R/select_nse.R                   | 57 +++++++++++++++++++++++++-------
 man/adjust.Rd                    |  6 ++--
 man/assign_labels.Rd             |  6 ++--
 man/categorize.Rd                |  6 ++--
 man/center.Rd                    |  6 ++--
 man/convert_na_to.Rd             |  6 ++--
 man/convert_to_na.Rd             |  6 ++--
 man/data_codebook.Rd             |  6 ++--
 man/data_duplicated.Rd           |  6 ++--
 man/data_extract.Rd              |  6 ++--
 man/data_group.Rd                |  6 ++--
 man/data_peek.Rd                 |  6 ++--
 man/data_relocate.Rd             |  6 ++--
 man/data_rename.Rd               |  6 ++--
 man/data_replicate.Rd            |  6 ++--
 man/data_separate.Rd             |  6 ++--
 man/data_tabulate.Rd             |  6 ++--
 man/data_to_long.Rd              |  6 ++--
 man/data_unique.Rd               |  6 ++--
 man/data_unite.Rd                |  6 ++--
 man/describe_distribution.Rd     |  6 ++--
 man/extract_column_names.Rd      | 11 ++++--
 man/labels_to_levels.Rd          |  6 ++--
 man/means_by_group.Rd            |  6 ++--
 man/normalize.Rd                 |  6 ++--
 man/ranktransform.Rd             |  6 ++--
 man/recode_values.Rd             |  6 ++--
 man/rescale.Rd                   |  6 ++--
 man/reverse.Rd                   |  6 ++--
 man/row_means.Rd                 |  6 ++--
 man/slide.Rd                     |  6 ++--
 man/standardize.Rd               |  6 ++--
 man/to_factor.Rd                 |  6 ++--
 man/to_numeric.Rd                |  6 ++--
 tests/testthat/test-select_nse.R | 21 ++++++++++++
 38 files changed, 217 insertions(+), 83 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 8dd92fb7e..4758f601c 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.1
+Version: 0.13.0.2
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NEWS.md b/NEWS.md
index c28ecc63f..388c5a822 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,5 +1,11 @@
 # datawizard (development)
 
+CHANGES
+
+* The `select` argument, which is available in different functions to select
+  variables, can now also be a character vector with quoted variable names,
+  including a colon to indicate a range of several variables (e.g. `"cyl:gear"`).
+
 BUG FIXES
 
 * `describe_distribution()` no longer errors if the sample was too sparse to compute
diff --git a/R/extract_column_names.R b/R/extract_column_names.R
index c245f4bab..a3d120d3f 100644
--- a/R/extract_column_names.R
+++ b/R/extract_column_names.R
@@ -9,8 +9,10 @@
 #'   tasks. Can be either
 #'
 #'   - a variable specified as a literal variable name (e.g., `column_name`),
-#'   - a string with the variable name (e.g., `"column_name"`), or a character
-#'     vector of variable names (e.g., `c("col1", "col2", "col3")`),
+#'   - a string with the variable name (e.g., `"column_name"`), a character
+#'     vector of variable names (e.g., `c("col1", "col2", "col3")`), or a
+#'     character vector of variable names including ranges specified via `:`
+#'     (e.g., `c("col1:col3", "col5")`),
 #'   - a formula with variable names (e.g., `~column_1 + column_2`),
 #'   - a vector of positive integers, giving the positions counting from the left
 #'     (e.g. `1` or `c(1, 3, 5)`),
@@ -116,7 +118,7 @@
 #' ```
 #'
 #' @examples
-#' # Find columns names by pattern
+#' # Find column names by pattern
 #' extract_column_names(iris, starts_with("Sepal"))
 #' extract_column_names(iris, ends_with("Width"))
 #' extract_column_names(iris, regex("\\."))
@@ -129,6 +131,9 @@
 #' numeric_mean_35 <- function(x) is.numeric(x) && mean(x, na.rm = TRUE) > 3.5
 #' extract_column_names(iris, numeric_mean_35)
 #'
+#' # find range of colum names by range, using character vector
+#' extract_column_names(mtcars, c("cyl:hp", "wt"))
+#'
 #' # rename returned columns for "data_select()"
 #' head(data_select(mtcars, c(`Miles per Gallon` = "mpg", Cylinders = "cyl")))
 #' @export
diff --git a/R/select_nse.R b/R/select_nse.R
index 8f9eba096..5120691a9 100644
--- a/R/select_nse.R
+++ b/R/select_nse.R
@@ -139,6 +139,7 @@
 # Possibilities:
 # - quoted variable name
 # - quoted variable name with ignore case
+# - quoted variable name with colon, to indicate range
 # - character that should be regex-ed on variable names
 # - special word "all" to return all vars
 
@@ -146,31 +147,63 @@
   # use colnames because names() doesn't work for matrices
   columns <- colnames(data)
   if (isTRUE(regex)) {
+    # string is a regular expression
     grep(x, columns)
   } else if (length(x) == 1L && x == "all") {
+    # string is "all" - select all columns
     seq_along(data)
+  } else if (any(grepl(":", x, fixed = TRUE))) {
+    # special pattern, as string (e.g.select = c("cyl:hp", "am")). However,
+    # this will first go into `.eval_call()` and thus only single elements
+    # are passed in `x` - we have never a character *vector* here
+    # check for valid names
+    colon_vars <- unlist(strsplit(x, ":", fixed = TRUE))
+    colon_match <- match(colon_vars, columns)
+    if (anyNA(colon_match)) {
+      .warn_not_found(colon_vars, columns, colon_match, verbose)
+      matches <- NA
+    } else {
+      start_pos <- match(colon_vars[1], columns)
+      end_pos <- match(colon_vars[2], columns)
+      if (!is.na(start_pos) && !is.na(end_pos)) {
+        matches <- start_pos:end_pos
+      } else {
+        matches <- NA
+      }
+    }
+    matches[!is.na(matches)]
   } else if (isTRUE(ignore_case)) {
+    # find columns, case insensitive
     matches <- match(toupper(x), toupper(columns))
     matches[!is.na(matches)]
   } else {
+    # find columns, case sensitive
     matches <- match(x, columns)
-    if (anyNA(matches) && verbose) {
-      insight::format_warning(
-        paste0(
-          "Following variable(s) were not found: ",
-          toString(x[is.na(matches)])
-        ),
-        .misspelled_string(
-          columns,
-          x[is.na(matches)],
-          default_message = "Possibly misspelled?"
-        )
-      )
+    if (anyNA(matches)) {
+      .warn_not_found(x, columns, matches, verbose)
     }
     matches[!is.na(matches)]
   }
 }
 
+# small helper, to avoid duplicated code
+.warn_not_found <- function(x, columns, matches, verbose = TRUE) {
+  if (verbose) {
+    insight::format_warning(
+      paste0(
+        "Following variable(s) were not found: ",
+        toString(x[is.na(matches)])
+      ),
+      .misspelled_string(
+        columns,
+        x[is.na(matches)],
+        default_message = "Possibly misspelled?"
+      )
+    )
+  }
+}
+
+
 # 3 types of symbols:
 # - unquoted variables
 # - objects that need to be evaluated, e.g data_find(iris, i) where
diff --git a/man/adjust.Rd b/man/adjust.Rd
index 64e50d9d3..48b321b8f 100644
--- a/man/adjust.Rd
+++ b/man/adjust.Rd
@@ -43,8 +43,10 @@ out). If \code{NULL} (the default), all variables will be selected.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/assign_labels.Rd b/man/assign_labels.Rd
index cca14cc85..e6fd24252 100644
--- a/man/assign_labels.Rd
+++ b/man/assign_labels.Rd
@@ -38,8 +38,10 @@ labels are omitted.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/categorize.Rd b/man/categorize.Rd
index ca013ce2b..dbecbf5e6 100644
--- a/man/categorize.Rd
+++ b/man/categorize.Rd
@@ -89,8 +89,10 @@ group. See 'Examples'.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/center.Rd b/man/center.Rd
index f143f64b2..4774020ab 100644
--- a/man/center.Rd
+++ b/man/center.Rd
@@ -72,8 +72,10 @@ against the names of the selected variables.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/convert_na_to.Rd b/man/convert_na_to.Rd
index 91121ff94..702e0eb2e 100644
--- a/man/convert_na_to.Rd
+++ b/man/convert_na_to.Rd
@@ -41,8 +41,10 @@ replace \code{NA}.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/convert_to_na.Rd b/man/convert_to_na.Rd
index 2529294b7..fe308d61e 100644
--- a/man/convert_to_na.Rd
+++ b/man/convert_to_na.Rd
@@ -44,8 +44,10 @@ by \code{NA}, should unused levels be dropped?}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_codebook.Rd b/man/data_codebook.Rd
index 4c0f935e7..319f4e5b6 100644
--- a/man/data_codebook.Rd
+++ b/man/data_codebook.Rd
@@ -34,8 +34,10 @@ data_codebook(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_duplicated.Rd b/man/data_duplicated.Rd
index 73c3e8de1..88624c8c8 100644
--- a/man/data_duplicated.Rd
+++ b/man/data_duplicated.Rd
@@ -20,8 +20,10 @@ data_duplicated(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_extract.Rd b/man/data_extract.Rd
index a0cd4e402..0b544e710 100644
--- a/man/data_extract.Rd
+++ b/man/data_extract.Rd
@@ -27,8 +27,10 @@ and data frame extensions (e.g., tibbles).}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_group.Rd b/man/data_group.Rd
index 56f5f314e..9cb55de5d 100644
--- a/man/data_group.Rd
+++ b/man/data_group.Rd
@@ -24,8 +24,10 @@ data_ungroup(data, verbose = TRUE, ...)
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_peek.Rd b/man/data_peek.Rd
index 4f3f88e8a..9524c70ec 100644
--- a/man/data_peek.Rd
+++ b/man/data_peek.Rd
@@ -27,8 +27,10 @@ data_peek(x, ...)
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_relocate.Rd b/man/data_relocate.Rd
index 30e4dbbfe..9949b5d27 100644
--- a/man/data_relocate.Rd
+++ b/man/data_relocate.Rd
@@ -44,8 +44,10 @@ data_remove(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_rename.Rd b/man/data_rename.Rd
index a45095805..2ff779c21 100644
--- a/man/data_rename.Rd
+++ b/man/data_rename.Rd
@@ -56,8 +56,10 @@ will be ignored then).}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_replicate.Rd b/man/data_replicate.Rd
index 35448155d..5a427d570 100644
--- a/man/data_replicate.Rd
+++ b/man/data_replicate.Rd
@@ -27,8 +27,10 @@ column. Note that the variable indicated by \code{expand} must be an integer vec
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_separate.Rd b/man/data_separate.Rd
index 37528d46e..7c951f81c 100644
--- a/man/data_separate.Rd
+++ b/man/data_separate.Rd
@@ -30,8 +30,10 @@ data_separate(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_tabulate.Rd b/man/data_tabulate.Rd
index 2feadf3a9..032c0b989 100644
--- a/man/data_tabulate.Rd
+++ b/man/data_tabulate.Rd
@@ -79,8 +79,10 @@ for printing.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_to_long.Rd b/man/data_to_long.Rd
index 741725d25..73b54219b 100644
--- a/man/data_to_long.Rd
+++ b/man/data_to_long.Rd
@@ -45,8 +45,10 @@ rows and fewer columns after the operation.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_unique.Rd b/man/data_unique.Rd
index 8a45bfc21..a0a70b92a 100644
--- a/man/data_unique.Rd
+++ b/man/data_unique.Rd
@@ -21,8 +21,10 @@ data_unique(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/data_unite.Rd b/man/data_unite.Rd
index ba7710a8a..369fd33d8 100644
--- a/man/data_unite.Rd
+++ b/man/data_unite.Rd
@@ -27,8 +27,10 @@ data_unite(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/describe_distribution.Rd b/man/describe_distribution.Rd
index 369bd9ef6..80b69e115 100644
--- a/man/describe_distribution.Rd
+++ b/man/describe_distribution.Rd
@@ -86,8 +86,10 @@ vector before the mean is computed.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/extract_column_names.Rd b/man/extract_column_names.Rd
index 6e658ab33..3ea5da7dc 100644
--- a/man/extract_column_names.Rd
+++ b/man/extract_column_names.Rd
@@ -43,8 +43,10 @@ find_columns(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
@@ -152,7 +154,7 @@ outer(iris, starts_with("Sep"))
 }\if{html}{\out{</div>}}
 }
 \examples{
-# Find columns names by pattern
+# Find column names by pattern
 extract_column_names(iris, starts_with("Sepal"))
 extract_column_names(iris, ends_with("Width"))
 extract_column_names(iris, regex("\\\\."))
@@ -165,6 +167,9 @@ extract_column_names(iris, starts_with("Sepal"), exclude = contains("Width"))
 numeric_mean_35 <- function(x) is.numeric(x) && mean(x, na.rm = TRUE) > 3.5
 extract_column_names(iris, numeric_mean_35)
 
+# find range of colum names by range, using character vector
+extract_column_names(mtcars, c("cyl:hp", "wt"))
+
 # rename returned columns for "data_select()"
 head(data_select(mtcars, c(`Miles per Gallon` = "mpg", Cylinders = "cyl")))
 }
diff --git a/man/labels_to_levels.Rd b/man/labels_to_levels.Rd
index 8024eb2d3..163eb0eaa 100644
--- a/man/labels_to_levels.Rd
+++ b/man/labels_to_levels.Rd
@@ -33,8 +33,10 @@ allowed.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/means_by_group.Rd b/man/means_by_group.Rd
index ba2a7d0c8..6c06ac3b1 100644
--- a/man/means_by_group.Rd
+++ b/man/means_by_group.Rd
@@ -51,8 +51,10 @@ point when rounding estimates and values.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/normalize.Rd b/man/normalize.Rd
index 4a9a61a68..c325e98fe 100644
--- a/man/normalize.Rd
+++ b/man/normalize.Rd
@@ -71,8 +71,10 @@ the normalized vectors are rescaled to a range from \code{0 + include_bounds} to
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/ranktransform.Rd b/man/ranktransform.Rd
index c23105735..7046db2b5 100644
--- a/man/ranktransform.Rd
+++ b/man/ranktransform.Rd
@@ -39,8 +39,10 @@ details.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/recode_values.Rd b/man/recode_values.Rd
index baa7afda9..dece902f7 100644
--- a/man/recode_values.Rd
+++ b/man/recode_values.Rd
@@ -60,8 +60,10 @@ default value.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/rescale.Rd b/man/rescale.Rd
index 016a6f841..490964777 100644
--- a/man/rescale.Rd
+++ b/man/rescale.Rd
@@ -67,8 +67,10 @@ the input vector (\code{range(x)}).}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/reverse.Rd b/man/reverse.Rd
index 6304dffc6..5767908ff 100644
--- a/man/reverse.Rd
+++ b/man/reverse.Rd
@@ -45,8 +45,10 @@ usually only makes sense when factor levels are numeric, not characters.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/row_means.Rd b/man/row_means.Rd
index c347fc6f1..4d61e8cf2 100644
--- a/man/row_means.Rd
+++ b/man/row_means.Rd
@@ -23,8 +23,10 @@ row_means(
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/slide.Rd b/man/slide.Rd
index ccc6bd7e9..c26943116 100644
--- a/man/slide.Rd
+++ b/man/slide.Rd
@@ -34,8 +34,10 @@ factors or character vectors to numeric values.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/standardize.Rd b/man/standardize.Rd
index 4041f2dc0..fcc8c6ae7 100644
--- a/man/standardize.Rd
+++ b/man/standardize.Rd
@@ -145,8 +145,10 @@ vectors as well.}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/to_factor.Rd b/man/to_factor.Rd
index e035769ec..d544bdaae 100644
--- a/man/to_factor.Rd
+++ b/man/to_factor.Rd
@@ -36,8 +36,10 @@ the values of \code{x} (i.e. as if using \code{as.factor()}).}
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/man/to_numeric.Rd b/man/to_numeric.Rd
index 634906e4a..39f04c3a9 100644
--- a/man/to_numeric.Rd
+++ b/man/to_numeric.Rd
@@ -30,8 +30,10 @@ to_numeric(x, ...)
 tasks. Can be either
 \itemize{
 \item a variable specified as a literal variable name (e.g., \code{column_name}),
-\item a string with the variable name (e.g., \code{"column_name"}), or a character
-vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
 \item a formula with variable names (e.g., \code{~column_1 + column_2}),
 \item a vector of positive integers, giving the positions counting from the left
 (e.g. \code{1} or \code{c(1, 3, 5)}),
diff --git a/tests/testthat/test-select_nse.R b/tests/testthat/test-select_nse.R
index c0195ad94..fb0f6aefb 100644
--- a/tests/testthat/test-select_nse.R
+++ b/tests/testthat/test-select_nse.R
@@ -138,3 +138,24 @@ test_that(".select_nse: works with function and namespace", {
   out <- fun(insight::find_predictors(model, effects = "fixed", flatten = TRUE))
   expect_identical(out, iris["Petal.Width"])
 })
+
+test_that(".select_nse: allow character vector with :", {
+  data(mtcars)
+  out <- data_select(mtcars, c("cyl:hp", "wt", "vs:gear"))
+  expect_named(out, c("cyl", "disp", "hp", "wt", "vs", "am", "gear"))
+  out <- data_select(mtcars, c("cyl:hp", "wta", "vs:gear"))
+  expect_named(out, c("cyl", "disp", "hp", "vs", "am", "gear"))
+  out <- data_select(mtcars, c("hp:cyl", "wta", "vs:gear"))
+  expect_named(out, c("hp", "disp", "cyl", "vs", "am", "gear"))
+  out <- data_select(mtcars, c("cyl:hq", "wt", "vs:gear"))
+  expect_named(out, c("wt", "vs", "am", "gear"))
+
+  expect_warning(
+    center(mtcars, c("cyl:hp", "wta", "vs:gear"), verbose = TRUE),
+    regex = "Did you mean \"wt\""
+  )
+  expect_warning(
+    center(mtcars, c("cyl:hq", "wt", "vs:gear"), verbose = TRUE),
+    regex = "Did you mean one of \"hp\""
+  )
+})

From 8ab24547120f07c4267b716dc9aedaccff8eb782 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Thu, 10 Oct 2024 21:57:27 +0200
Subject: [PATCH 10/19] Rename `drop_na` into `remove_na` in `data_match()`
 (#556)

* Rename drop_na into remove_na?
Fixes #554

* news, desc

* typo
---
 DESCRIPTION                      |  2 +-
 NEWS.md                          |  5 +++++
 R/data_group.R                   |  2 +-
 R/data_match.R                   | 19 ++++++++++++++++---
 man/data_match.Rd                | 14 ++++++++++++--
 tests/testthat/test-data_match.R |  4 ++--
 6 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 4758f601c..20764a09e 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.2
+Version: 0.13.0.5
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NEWS.md b/NEWS.md
index 388c5a822..08e3527b3 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,5 +1,10 @@
 # datawizard (development)
 
+BREAKING CHANGES
+
+* Argument `drop_na` in `data_match()` is deprecated now. Please use `remove_na`
+  instead.
+
 CHANGES
 
 * The `select` argument, which is available in different functions to select
diff --git a/R/data_group.R b/R/data_group.R
index 00a7adf84..538c875c2 100644
--- a/R/data_group.R
+++ b/R/data_group.R
@@ -51,7 +51,7 @@ data_group <- function(data,
       to = my_grid[i, , drop = FALSE],
       match = "and",
       return_indices = TRUE,
-      drop_na = FALSE
+      remove_na = FALSE
     ))
   })
   my_grid[[".rows"]] <- .rows
diff --git a/R/data_match.R b/R/data_match.R
index c03b3f222..6b522a0b8 100644
--- a/R/data_match.R
+++ b/R/data_match.R
@@ -15,7 +15,7 @@
 #' @param return_indices Logical, if `FALSE`, return the vector of rows that
 #'   can be used to filter the original data frame. If `FALSE` (default),
 #'   returns directly the filtered data frame instead of the row indices.
-#' @param drop_na Logical, if `TRUE`, missing values (`NA`s) are removed before
+#' @param remove_na Logical, if `TRUE`, missing values (`NA`s) are removed before
 #'   filtering the data. This is the default behaviour, however, sometimes when
 #'   row indices are requested (i.e. `return_indices=TRUE`), it might be useful
 #'   to preserve `NA` values, so returned row indices match the row indices of
@@ -26,6 +26,7 @@
 #'   character vector (e.g. `c("x > 4", "y == 2")`) or a variable that contains
 #'   the string representation of a logical expression. These might be useful
 #'   when used in packages to avoid defining undefined global variables.
+#' @param drop_na Deprecated, please use `remove_na` instead.
 #'
 #' @return A filtered data frame, or the row indices that match the specified
 #' configuration.
@@ -100,12 +101,24 @@
 #' data_filter(mtcars, fl)
 #' @inherit data_rename seealso
 #' @export
-data_match <- function(x, to, match = "and", return_indices = FALSE, drop_na = TRUE, ...) {
+data_match <- function(x,
+                       to,
+                       match = "and",
+                       return_indices = FALSE,
+                       remove_na = TRUE,
+                       drop_na,
+                       ...) {
   if (!is.data.frame(to)) {
     to <- as.data.frame(to)
   }
   original_x <- x
 
+  ## TODO: remove deprecated argument later
+  if (!missing(drop_na)) {
+    insight::format_warning("Argument `drop_na` is deprecated. Please use `remove_na` instead.")
+    remove_na <- drop_na
+  }
+
   # evaluate
   match <- match.arg(tolower(match), c("and", "&", "&&", "or", "|", "||", "!", "not"))
   match <- switch(match,
@@ -133,7 +146,7 @@ data_match <- function(x, to, match = "and", return_indices = FALSE, drop_na = T
     idx <- vector("numeric", length = 0L)
   } else {
     # remove missings before matching
-    if (isTRUE(drop_na)) {
+    if (isTRUE(remove_na)) {
       x <- x[stats::complete.cases(x), , drop = FALSE]
     }
     idx <- seq_len(nrow(x))
diff --git a/man/data_match.Rd b/man/data_match.Rd
index a57c34768..a209170ab 100644
--- a/man/data_match.Rd
+++ b/man/data_match.Rd
@@ -5,7 +5,15 @@
 \alias{data_filter}
 \title{Return filtered or sliced data frame, or row indices}
 \usage{
-data_match(x, to, match = "and", return_indices = FALSE, drop_na = TRUE, ...)
+data_match(
+  x,
+  to,
+  match = "and",
+  return_indices = FALSE,
+  remove_na = TRUE,
+  drop_na,
+  ...
+)
 
 data_filter(x, ...)
 }
@@ -24,12 +32,14 @@ or \code{"not"} (or \code{"!"}).}
 can be used to filter the original data frame. If \code{FALSE} (default),
 returns directly the filtered data frame instead of the row indices.}
 
-\item{drop_na}{Logical, if \code{TRUE}, missing values (\code{NA}s) are removed before
+\item{remove_na}{Logical, if \code{TRUE}, missing values (\code{NA}s) are removed before
 filtering the data. This is the default behaviour, however, sometimes when
 row indices are requested (i.e. \code{return_indices=TRUE}), it might be useful
 to preserve \code{NA} values, so returned row indices match the row indices of
 the original data frame.}
 
+\item{drop_na}{Deprecated, please use \code{remove_na} instead.}
+
 \item{...}{A sequence of logical expressions indicating which rows to keep,
 or a numeric vector indicating the row indices of rows to keep. Can also be
 a string representation of a logical expression (e.g. \code{"x > 4"}), a
diff --git a/tests/testthat/test-data_match.R b/tests/testthat/test-data_match.R
index 75991b4b2..1a40f39fd 100644
--- a/tests/testthat/test-data_match.R
+++ b/tests/testthat/test-data_match.R
@@ -52,7 +52,7 @@ test_that("data_match works with missing data", {
     data.frame(c172code = 1, e16sex = 2),
     match = "not",
     return_indices = TRUE,
-    drop_na = FALSE
+    remove_na = FALSE
   ))
   expect_identical(x1, 41L)
   x1 <- length(data_match(
@@ -60,7 +60,7 @@ test_that("data_match works with missing data", {
     data.frame(c172code = 1, e16sex = 2),
     match = "not",
     return_indices = TRUE,
-    drop_na = TRUE
+    remove_na = TRUE
   ))
   expect_identical(x1, 36L)
 })

From 5ce207b7169a20fdb4168fd83224d836592e6cca Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Fri, 11 Oct 2024 11:43:00 +0200
Subject: [PATCH 11/19] Add `row_count()` to count specific values row-wise
 (#553)

* Draft `row_count()`

* docs, type safe comparisons

* lintr

* apply suggestions

* add test

* fix test

* rename arg

* switch TRUE and FALSE

* update docs

* resolve comment

* comments

* typo
---
 DESCRIPTION                     |   2 +-
 NAMESPACE                       |   1 +
 NEWS.md                         |   2 +
 R/row_count.R                   | 124 ++++++++++++++++++++++++++++++
 man/row_count.Rd                | 132 ++++++++++++++++++++++++++++++++
 pkgdown/_pkgdown.yaml           |   1 +
 tests/testthat/test-row_count.R |  57 ++++++++++++++
 7 files changed, 318 insertions(+), 1 deletion(-)
 create mode 100644 R/row_count.R
 create mode 100644 man/row_count.Rd
 create mode 100644 tests/testthat/test-row_count.R

diff --git a/DESCRIPTION b/DESCRIPTION
index 20764a09e..8fa9eee94 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.5
+Version: 0.13.0.6
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NAMESPACE b/NAMESPACE
index c435c0cc5..1775af562 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -296,6 +296,7 @@ export(reshape_longer)
 export(reshape_wider)
 export(reverse)
 export(reverse_scale)
+export(row_count)
 export(row_means)
 export(row_to_colnames)
 export(rowid_as_column)
diff --git a/NEWS.md b/NEWS.md
index 08e3527b3..da3296536 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -11,6 +11,8 @@ CHANGES
   variables, can now also be a character vector with quoted variable names,
   including a colon to indicate a range of several variables (e.g. `"cyl:gear"`).
 
+* New function `row_count()`, to count specific values row-wise.
+
 BUG FIXES
 
 * `describe_distribution()` no longer errors if the sample was too sparse to compute
diff --git a/R/row_count.R b/R/row_count.R
new file mode 100644
index 000000000..02b1c16dc
--- /dev/null
+++ b/R/row_count.R
@@ -0,0 +1,124 @@
+#' @title Count specific values row-wise
+#' @name row_count
+#' @description `row_count()` mimics base R's `rowSums()`, with sums for a
+#' specific value indicated by `count`. Hence, it is similar to
+#' `rowSums(x == count, na.rm = TRUE)`, but offers some more options, including
+#' strict comparisons. Comparisons using `==` coerce values to atomic vectors,
+#' thus both `2 == 2` and `"2" == 2` are `TRUE`. In `row_count()`, it is also
+#' possible to make "type safe" comparisons using the `allow_coercion` argument,
+#' where `"2" == 2` is not true.
+#'
+#' @param data A data frame with at least two columns, where number of specific
+#' values are counted row-wise.
+#' @param count The value for which the row sum should be computed. May be a
+#' numeric value, a character string (for factors or character vectors), `NA` or
+#' `Inf`.
+#' @param allow_coercion Logical. If `FALSE`, `count` matches only values of same
+#' class (i.e. when `count = 2`, the value `"2"` is not counted and vice versa).
+#' By default, when `allow_coercion = TRUE`, `count = 2` also matches `"2"`. In
+#' order to count factor levels in the data, use `count = factor("level")`. See
+#' 'Examples'.
+#'
+#' @inheritParams extract_column_names
+#' @inheritParams row_means
+#'
+#' @return A vector with row-wise counts of values specified in `count`.
+#'
+#' @examples
+#' dat <- data.frame(
+#'   c1 = c(1, 2, NA, 4),
+#'   c2 = c(NA, 2, NA, 5),
+#'   c3 = c(NA, 4, NA, NA),
+#'   c4 = c(2, 3, 7, 8)
+#' )
+#'
+#' # count all 4s per row
+#' row_count(dat, count = 4)
+#' # count all missing values per row
+#' row_count(dat, count = NA)
+#'
+#' dat <- data.frame(
+#'   c1 = c("1", "2", NA, "3"),
+#'   c2 = c(NA, "2", NA, "3"),
+#'   c3 = c(NA, 4, NA, NA),
+#'   c4 = c(2, 3, 7, Inf)
+#' )
+#' # count all 2s and "2"s per row
+#' row_count(dat, count = 2)
+#' # only count 2s, but not "2"s
+#' row_count(dat, count = 2, allow_coercion = FALSE)
+#'
+#' dat <- data.frame(
+#'   c1 = factor(c("1", "2", NA, "3")),
+#'   c2 = c("2", "1", NA, "3"),
+#'   c3 = c(NA, 4, NA, NA),
+#'   c4 = c(2, 3, 7, Inf)
+#' )
+#' # find only character "2"s
+#' row_count(dat, count = "2", allow_coercion = FALSE)
+#' # find only factor level "2"s
+#' row_count(dat, count = factor("2"), allow_coercion = FALSE)
+#'
+#' @export
+row_count <- function(data,
+                      select = NULL,
+                      exclude = NULL,
+                      count = NULL,
+                      allow_coercion = TRUE,
+                      ignore_case = FALSE,
+                      regex = FALSE,
+                      verbose = TRUE) {
+  # evaluate arguments
+  select <- .select_nse(select,
+    data,
+    exclude,
+    ignore_case = ignore_case,
+    regex = regex,
+    verbose = verbose
+  )
+
+  if (is.null(count)) {
+    insight::format_error("`count` must be a valid value (including `NA` or `Inf`), but not `NULL`.")
+  }
+
+  if (is.null(select) || length(select) == 0) {
+    insight::format_error("No columns selected.")
+  }
+
+  data <- .coerce_to_dataframe(data[select])
+
+  # check if we have a data framme with at least two columns
+  if (nrow(data) < 1) {
+    insight::format_error("`data` must be a data frame with at least one row.")
+  }
+
+  # check if we have a data framme with at least two columns
+  if (ncol(data) < 2) {
+    insight::format_error("`data` must be a data frame with at least two numeric columns.")
+  }
+  # special case: count missing
+  if (is.na(count)) {
+    rowSums(is.na(data))
+  } else {
+    # comparisons in R using == coerce values into a atomic vector, i.e.
+    # 2 == "2" is TRUE. If `allow_coercion = FALSE`, we only want 2 == 2 or
+    # "2" == "2" (i.e. we want exact types to be compared only)
+    if (isFALSE(allow_coercion)) {
+      # we need the "type" of the count-value - we use class() instead of typeof(),
+      # because the latter sometimes returns unsuitable classes/types. compare
+      # typeof(as.Date("2020-01-01")), which returns "double".
+      count_type <- class(count)[1]
+      valid_columns <- vapply(data, inherits, TRUE, what = count_type)
+      # check if any columns left?
+      if (!any(valid_columns)) {
+        insight::format_error("No column has same type as the value provided in `count`. Set `allow_coercion = TRUE` or specify a valid value for `count`.") # nolint
+      }
+      data <- data[valid_columns]
+    }
+    # coerce - we have only valid columns anyway, and we need to coerce factors
+    # to vectors, else comparison with `==` errors.
+    count <- as.vector(count)
+    # finally, count
+    rowSums(data == count, na.rm = TRUE)
+  }
+}
diff --git a/man/row_count.Rd b/man/row_count.Rd
new file mode 100644
index 000000000..7bf54fe5f
--- /dev/null
+++ b/man/row_count.Rd
@@ -0,0 +1,132 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/row_count.R
+\name{row_count}
+\alias{row_count}
+\title{Count specific values row-wise}
+\usage{
+row_count(
+  data,
+  select = NULL,
+  exclude = NULL,
+  count = NULL,
+  allow_coercion = TRUE,
+  ignore_case = FALSE,
+  regex = FALSE,
+  verbose = TRUE
+)
+}
+\arguments{
+\item{data}{A data frame with at least two columns, where number of specific
+values are counted row-wise.}
+
+\item{select}{Variables that will be included when performing the required
+tasks. Can be either
+\itemize{
+\item a variable specified as a literal variable name (e.g., \code{column_name}),
+\item a string with the variable name (e.g., \code{"column_name"}), a character
+vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
+character vector of variable names including ranges specified via \code{:}
+(e.g., \code{c("col1:col3", "col5")}),
+\item a formula with variable names (e.g., \code{~column_1 + column_2}),
+\item a vector of positive integers, giving the positions counting from the left
+(e.g. \code{1} or \code{c(1, 3, 5)}),
+\item a vector of negative integers, giving the positions counting from the
+right (e.g., \code{-1} or \code{-1:-3}),
+\item one of the following select-helpers: \code{starts_with()}, \code{ends_with()},
+\code{contains()}, a range using \code{:} or \code{regex("")}. \code{starts_with()},
+\code{ends_with()}, and  \code{contains()} accept several patterns, e.g
+\code{starts_with("Sep", "Petal")}.
+\item or a function testing for logical conditions, e.g. \code{is.numeric()} (or
+\code{is.numeric}), or any user-defined function that selects the variables
+for which the function returns \code{TRUE} (like: \code{foo <- function(x) mean(x) > 3}),
+\item ranges specified via literal variable names, select-helpers (except
+\code{regex()}) and (user-defined) functions can be negated, i.e. return
+non-matching elements, when prefixed with a \code{-}, e.g. \code{-ends_with("")},
+\code{-is.numeric} or \code{-(Sepal.Width:Petal.Length)}. \strong{Note:} Negation means
+that matches are \emph{excluded}, and thus, the \code{exclude} argument can be
+used alternatively. For instance, \code{select=-ends_with("Length")} (with
+\code{-}) is equivalent to \code{exclude=ends_with("Length")} (no \code{-}). In case
+negation should not work as expected, use the \code{exclude} argument instead.
+}
+
+If \code{NULL}, selects all columns. Patterns that found no matches are silently
+ignored, e.g. \code{extract_column_names(iris, select = c("Species", "Test"))}
+will just return \code{"Species"}.}
+
+\item{exclude}{See \code{select}, however, column names matched by the pattern
+from \code{exclude} will be excluded instead of selected. If \code{NULL} (the default),
+excludes no columns.}
+
+\item{count}{The value for which the row sum should be computed. May be a
+numeric value, a character string (for factors or character vectors), \code{NA} or
+\code{Inf}.}
+
+\item{allow_coercion}{Logical. If \code{FALSE}, \code{count} matches only values of same
+class (i.e. when \code{count = 2}, the value \code{"2"} is not counted and vice versa).
+By default, when \code{allow_coercion = TRUE}, \code{count = 2} also matches \code{"2"}. In
+order to count factor levels in the data, use \code{count = factor("level")}. See
+'Examples'.}
+
+\item{ignore_case}{Logical, if \code{TRUE} and when one of the select-helpers or
+a regular expression is used in \code{select}, ignores lower/upper case in the
+search pattern when matching against variable names.}
+
+\item{regex}{Logical, if \code{TRUE}, the search pattern from \code{select} will be
+treated as regular expression. When \code{regex = TRUE}, select \emph{must} be a
+character string (or a variable containing a character string) and is not
+allowed to be one of the supported select-helpers or a character vector
+of length > 1. \code{regex = TRUE} is comparable to using one of the two
+select-helpers, \code{select = contains("")} or \code{select = regex("")}, however,
+since the select-helpers may not work when called from inside other
+functions (see 'Details'), this argument may be used as workaround.}
+
+\item{verbose}{Toggle warnings.}
+}
+\value{
+A vector with row-wise counts of values specified in \code{count}.
+}
+\description{
+\code{row_count()} mimics base R's \code{rowSums()}, with sums for a
+specific value indicated by \code{count}. Hence, it is similar to
+\code{rowSums(x == count, na.rm = TRUE)}, but offers some more options, including
+strict comparisons. Comparisons using \code{==} coerce values to atomic vectors,
+thus both \code{2 == 2} and \code{"2" == 2} are \code{TRUE}. In \code{row_count()}, it is also
+possible to make "type safe" comparisons using the \code{allow_coercion} argument,
+where \code{"2" == 2} is not true.
+}
+\examples{
+dat <- data.frame(
+  c1 = c(1, 2, NA, 4),
+  c2 = c(NA, 2, NA, 5),
+  c3 = c(NA, 4, NA, NA),
+  c4 = c(2, 3, 7, 8)
+)
+
+# count all 4s per row
+row_count(dat, count = 4)
+# count all missing values per row
+row_count(dat, count = NA)
+
+dat <- data.frame(
+  c1 = c("1", "2", NA, "3"),
+  c2 = c(NA, "2", NA, "3"),
+  c3 = c(NA, 4, NA, NA),
+  c4 = c(2, 3, 7, Inf)
+)
+# count all 2s and "2"s per row
+row_count(dat, count = 2)
+# only count 2s, but not "2"s
+row_count(dat, count = 2, allow_coercion = FALSE)
+
+dat <- data.frame(
+  c1 = factor(c("1", "2", NA, "3")),
+  c2 = c("2", "1", NA, "3"),
+  c3 = c(NA, 4, NA, NA),
+  c4 = c(2, 3, 7, Inf)
+)
+# find only character "2"s
+row_count(dat, count = "2", allow_coercion = FALSE)
+# find only factor level "2"s
+row_count(dat, count = factor("2"), allow_coercion = FALSE)
+
+}
diff --git a/pkgdown/_pkgdown.yaml b/pkgdown/_pkgdown.yaml
index 6e6feb5b2..31ec901d0 100644
--- a/pkgdown/_pkgdown.yaml
+++ b/pkgdown/_pkgdown.yaml
@@ -71,6 +71,7 @@ reference:
       - kurtosis
       - smoothness
       - skewness
+      - row_count
       - row_means
       - weighted_mean
       - mean_sd
diff --git a/tests/testthat/test-row_count.R b/tests/testthat/test-row_count.R
new file mode 100644
index 000000000..0c7d67691
--- /dev/null
+++ b/tests/testthat/test-row_count.R
@@ -0,0 +1,57 @@
+test_that("row_count", {
+  d_mn <- data.frame(
+    c1 = c(1, 2, NA, 4),
+    c2 = c(NA, 2, NA, 5),
+    c3 = c(NA, 4, NA, NA),
+    c4 = c(2, 3, 7, 8)
+  )
+  expect_identical(row_count(d_mn, count = 2), c(1, 2, 0, 0))
+  expect_identical(row_count(d_mn, count = NA), c(2, 0, 3, 1))
+  d_mn <- data.frame(
+    c1 = c("a", "b", NA, "c"),
+    c2 = c(NA, "b", NA, "d"),
+    c3 = c(NA, 4, NA, NA),
+    c4 = c(2, 3, 7, Inf),
+    stringsAsFactors = FALSE
+  )
+  expect_identical(row_count(d_mn, count = "b"), c(0, 2, 0, 0))
+  expect_identical(row_count(d_mn, count = Inf), c(0, 0, 0, 1))
+})
+
+test_that("row_count, errors or messages", {
+  data(iris)
+  expect_error(expect_warning(row_count(iris, select = "abc")), regex = "must be a valid")
+  expect_error(expect_warning(row_count(iris, select = "abc", count = 3)), regex = "No columns")
+  expect_error(row_count(iris[1], count = 3), regex = "with at least")
+  expect_error(row_count(iris[-seq_len(nrow(iris)), , drop = FALSE], count = 2), regex = "one row")
+})
+
+test_that("row_count, allow_coercion match", {
+  d_mn <- data.frame(
+    c1 = c("1", "2", NA, "3"),
+    c2 = c(NA, "2", NA, "3"),
+    c3 = c(NA, 4, NA, NA),
+    c4 = c(2, 3, 7, Inf),
+    stringsAsFactors = FALSE
+  )
+  expect_identical(row_count(d_mn, count = 2, allow_coercion = TRUE), c(1, 2, 0, 0))
+  expect_identical(row_count(d_mn, count = 2, allow_coercion = FALSE), c(1, 0, 0, 0))
+  expect_identical(row_count(d_mn, count = "2", allow_coercion = FALSE), c(0, 2, 0, 0))
+  expect_identical(row_count(d_mn, count = factor("2"), allow_coercion = TRUE), c(1, 2, 0, 0))
+  expect_error(row_count(d_mn, count = factor("2"), allow_coercion = FALSE), regex = "No column has")
+
+  # mix character / factor
+  d_mn <- data.frame(
+    c1 = factor(c("1", "2", NA, "3")),
+    c2 = c("2", "1", NA, "3"),
+    c3 = c(NA, 4, NA, NA),
+    c4 = c(2, 3, 7, Inf),
+    stringsAsFactors = FALSE
+  )
+  expect_identical(row_count(d_mn, count = 2, allow_coercion = TRUE), c(2, 1, 0, 0))
+  expect_identical(row_count(d_mn, count = 2, allow_coercion = FALSE), c(1, 0, 0, 0))
+  expect_identical(row_count(d_mn, count = "2", allow_coercion = FALSE), c(1, 0, 0, 0))
+  expect_identical(row_count(d_mn, count = "2", allow_coercion = TRUE), c(2, 1, 0, 0))
+  expect_identical(row_count(d_mn, count = factor("2"), allow_coercion = FALSE), c(0, 1, 0, 0))
+  expect_identical(row_count(d_mn, count = factor("2"), allow_coercion = TRUE), c(2, 1, 0, 0))
+})

From 213b9d521eaa636b99a15b7a1962e96a5c9b939b Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Fri, 11 Oct 2024 11:50:50 +0200
Subject: [PATCH 12/19] Add `row_sums()` (#552)

* Draft `row_sums()` as complement to `row_means()`

* version
---
 DESCRIPTION                     |   2 +-
 NAMESPACE                       |   1 +
 NEWS.md                         |   3 +
 R/row_means.R                   | 142 ++++++++++++++++++++++----------
 man/row_means.Rd                |  55 +++++++++----
 tests/testthat/test-row_means.R |  11 ++-
 6 files changed, 151 insertions(+), 63 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 8fa9eee94..841bb2573 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.6
+Version: 0.13.0.7
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NAMESPACE b/NAMESPACE
index 1775af562..7e97817b9 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -298,6 +298,7 @@ export(reverse)
 export(reverse_scale)
 export(row_count)
 export(row_means)
+export(row_sums)
 export(row_to_colnames)
 export(rowid_as_column)
 export(rownames_as_column)
diff --git a/NEWS.md b/NEWS.md
index da3296536..679a71a9c 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -11,6 +11,9 @@ CHANGES
   variables, can now also be a character vector with quoted variable names,
   including a colon to indicate a range of several variables (e.g. `"cyl:gear"`).
 
+* New function `row_sums()`, to calculate row sums (optionally with minimum
+  amount of valid values), as complement to `row_means()`.
+
 * New function `row_count()`, to count specific values row-wise.
 
 BUG FIXES
diff --git a/R/row_means.R b/R/row_means.R
index 4d2876c6a..729c800be 100644
--- a/R/row_means.R
+++ b/R/row_means.R
@@ -1,15 +1,16 @@
-#' @title Row means (optionally with minimum amount of valid values)
+#' @title Row means or sums (optionally with minimum amount of valid values)
 #' @name row_means
-#' @description This function is similar to the SPSS `MEAN.n` function and computes
-#' row means from a data frame or matrix if at least `min_valid` values of a row are
-#' valid (and not `NA`).
+#' @description This function is similar to the SPSS `MEAN.n` or `SUM.n`
+#' function and computes row means or row sums from a data frame or matrix if at
+#' least `min_valid` values of a row are valid (and not `NA`).
 #'
-#' @param data A data frame with at least two columns, where row means are applied.
+#' @param data A data frame with at least two columns, where row means or row
+#' sums are applied.
 #' @param min_valid Optional, a numeric value of length 1. May either be
 #' - a numeric value that indicates the amount of valid values per row to
-#'   calculate the row mean;
+#'   calculate the row mean or row sum;
 #' - or a value between `0` and `1`, indicating a proportion of valid values per
-#'   row to calculate the row mean (see 'Details').
+#'   row to calculate the row mean or row sum (see 'Details').
 #' - `NULL` (default), in which all cases are considered.
 #'
 #' If a row's sum of valid values is less than `min_valid`, `NA` will be returned.
@@ -17,21 +18,24 @@
 #' used for rounding mean values. Negative values are allowed (see 'Details').
 #' By default, `digits = NULL` and no rounding is used.
 #' @param remove_na Logical, if `TRUE` (default), removes missing (`NA`) values
-#' before calculating row means. Only applies if `min_valuid` is not specified.
+#' before calculating row means or row sums. Only applies if `min_valid` is not
+#' specified.
 #' @param verbose Toggle warnings.
 #' @inheritParams extract_column_names
 #'
-#' @return A vector with row means for those rows with at least `n` valid values.
+#' @return A vector with row means (for `row_means()`) or row sums (for
+#' `row_sums()`) for those rows with at least `n` valid values.
 #'
-#' @details Rounding to a negative number of `digits` means rounding to a power of
-#' ten, for example `row_means(df, 3, digits = -2)` rounds to the nearest hundred.
-#' For `min_valid`, if not `NULL`, `min_valid` must be a numeric value from `0`
-#' to `ncol(data)`. If a row in the data frame has at least `min_valid`
-#' non-missing values, the row mean is returned. If `min_valid` is a non-integer
-#' value from 0 to 1, `min_valid` is considered to indicate the proportion of
-#' required non-missing values per row. E.g., if `min_valid = 0.75`, a row must
-#' have at least `ncol(data) * min_valid` non-missing values for the row mean
-#' to be calculated. See 'Examples'.
+#' @details Rounding to a negative number of `digits` means rounding to a power
+#' of ten, for example `row_means(df, 3, digits = -2)` rounds to the nearest
+#' hundred. For `min_valid`, if not `NULL`, `min_valid` must be a numeric value
+#' from `0` to `ncol(data)`. If a row in the data frame has at least `min_valid`
+#' non-missing values, the row mean or row sum is returned. If `min_valid` is a
+#' non-integer value from 0 to 1, `min_valid` is considered to indicate the
+#' proportion of required non-missing values per row. E.g., if
+#' `min_valid = 0.75`, a row must have at least `ncol(data) * min_valid`
+#' non-missing values for the row mean or row sum to be calculated. See
+#' 'Examples'.
 #'
 #' @examples
 #' dat <- data.frame(
@@ -49,6 +53,7 @@
 #'
 #' # needs at least 4 non-missing values per row
 #' row_means(dat, min_valid = 4) # 1 valid return value
+#' row_sums(dat, min_valid = 4) # 1 valid return value
 #'
 #' # needs at least 3 non-missing values per row
 #' row_means(dat, min_valid = 3) # 2 valid return values
@@ -61,6 +66,7 @@
 #'
 #' # needs at least 50% of non-missing values per row
 #' row_means(dat, min_valid = 0.5) # 3 valid return values
+#' row_sums(dat, min_valid = 0.5)
 #'
 #' # needs at least 75% of non-missing values per row
 #' row_means(dat, min_valid = 0.75) # 2 valid return values
@@ -84,34 +90,52 @@ row_means <- function(data,
     verbose = verbose
   )
 
-  if (is.null(select) || length(select) == 0) {
-    insight::format_error("No columns selected.")
-  }
+  # prepare data, sanity checks
+  data <- .prepare_row_data(data, select, min_valid, verbose)
 
-  data <- .coerce_to_dataframe(data[select])
+  # calculate row means
+  .row_sums_or_means(data, min_valid, digits, remove_na, fun = "mean")
+}
 
-  # n must be a numeric, non-missing value
-  if (!is.null(min_valid) && (all(is.na(min_valid)) || !is.numeric(min_valid) || length(min_valid) > 1)) {
-    insight::format_error("`min_valid` must be a numeric value of length 1.")
-  }
 
-  # make sure we only have numeric values
-  numeric_columns <- vapply(data, is.numeric, TRUE)
-  if (!all(numeric_columns)) {
-    if (verbose) {
-      insight::format_alert("Only numeric columns are considered for calculation.")
-    }
-    data <- data[numeric_columns]
-  }
+#' @rdname row_means
+#' @export
+row_sums <- function(data,
+                     select = NULL,
+                     exclude = NULL,
+                     min_valid = NULL,
+                     digits = NULL,
+                     ignore_case = FALSE,
+                     regex = FALSE,
+                     remove_na = FALSE,
+                     verbose = TRUE) {
+  # evaluate arguments
+  select <- .select_nse(select,
+    data,
+    exclude,
+    ignore_case = ignore_case,
+    regex = regex,
+    verbose = verbose
+  )
+
+  # prepare data, sanity checks
+  data <- .prepare_row_data(data, select, min_valid, verbose)
+
+  # calculate row sums
+  .row_sums_or_means(data, min_valid, digits, remove_na, fun = "sum")
+}
 
-  # check if we have a data framme with at least two columns
-  if (ncol(data) < 2) {
-    insight::format_error("`data` must be a data frame with at least two numeric columns.")
-  }
 
-  # proceed here if min_valid is not NULL
+# helper ------------------------
+
+# calculate row means or sums
+.row_sums_or_means <- function(data, min_valid, digits, remove_na, fun) {
   if (is.null(min_valid)) {
-    out <- rowMeans(data, na.rm = remove_na)
+    # calculate row means or sums for complete data
+    out <- switch(fun,
+      mean = rowMeans(data, na.rm = remove_na),
+      rowSums(data, na.rm = remove_na)
+    )
   } else {
     # is 'min_valid' indicating a proportion?
     decimals <- min_valid %% 1
@@ -124,9 +148,12 @@ row_means <- function(data,
       insight::format_error("`min_valid` must be smaller or equal to number of columns in data frame.")
     }
 
-    # row means
+    # row means or sums
     to_na <- rowSums(is.na(data)) > ncol(data) - min_valid
-    out <- rowMeans(data, na.rm = TRUE)
+    out <- switch(fun,
+      mean = rowMeans(data, na.rm = TRUE),
+      rowSums(data, na.rm = TRUE)
+    )
     out[to_na] <- NA
   }
 
@@ -137,3 +164,34 @@ row_means <- function(data,
 
   out
 }
+
+
+# check that data is in shape for row means or row sums
+.prepare_row_data <- function(data, select, min_valid, verbose) {
+  if (is.null(select) || length(select) == 0) {
+    insight::format_error("No columns selected.")
+  }
+
+  data <- .coerce_to_dataframe(data[select])
+
+  # n must be a numeric, non-missing value
+  if (!is.null(min_valid) && (all(is.na(min_valid)) || !is.numeric(min_valid) || length(min_valid) > 1)) {
+    insight::format_error("`min_valid` must be a numeric value of length 1.")
+  }
+
+  # make sure we only have numeric values
+  numeric_columns <- vapply(data, is.numeric, TRUE)
+  if (!all(numeric_columns)) {
+    if (verbose) {
+      insight::format_alert("Only numeric columns are considered for calculation.")
+    }
+    data <- data[numeric_columns]
+  }
+
+  # check if we have a data framme with at least two columns
+  if (ncol(data) < 2) {
+    insight::format_error("`data` must be a data frame with at least two numeric columns.")
+  }
+
+  data
+}
diff --git a/man/row_means.Rd b/man/row_means.Rd
index 4d61e8cf2..43d85b5b0 100644
--- a/man/row_means.Rd
+++ b/man/row_means.Rd
@@ -2,7 +2,8 @@
 % Please edit documentation in R/row_means.R
 \name{row_means}
 \alias{row_means}
-\title{Row means (optionally with minimum amount of valid values)}
+\alias{row_sums}
+\title{Row means or sums (optionally with minimum amount of valid values)}
 \usage{
 row_means(
   data,
@@ -15,9 +16,22 @@ row_means(
   remove_na = FALSE,
   verbose = TRUE
 )
+
+row_sums(
+  data,
+  select = NULL,
+  exclude = NULL,
+  min_valid = NULL,
+  digits = NULL,
+  ignore_case = FALSE,
+  regex = FALSE,
+  remove_na = FALSE,
+  verbose = TRUE
+)
 }
 \arguments{
-\item{data}{A data frame with at least two columns, where row means are applied.}
+\item{data}{A data frame with at least two columns, where row means or row
+sums are applied.}
 
 \item{select}{Variables that will be included when performing the required
 tasks. Can be either
@@ -60,9 +74,9 @@ excludes no columns.}
 \item{min_valid}{Optional, a numeric value of length 1. May either be
 \itemize{
 \item a numeric value that indicates the amount of valid values per row to
-calculate the row mean;
+calculate the row mean or row sum;
 \item or a value between \code{0} and \code{1}, indicating a proportion of valid values per
-row to calculate the row mean (see 'Details').
+row to calculate the row mean or row sum (see 'Details').
 \item \code{NULL} (default), in which all cases are considered.
 }
 
@@ -86,28 +100,31 @@ since the select-helpers may not work when called from inside other
 functions (see 'Details'), this argument may be used as workaround.}
 
 \item{remove_na}{Logical, if \code{TRUE} (default), removes missing (\code{NA}) values
-before calculating row means. Only applies if \code{min_valuid} is not specified.}
+before calculating row means or row sums. Only applies if \code{min_valid} is not
+specified.}
 
 \item{verbose}{Toggle warnings.}
 }
 \value{
-A vector with row means for those rows with at least \code{n} valid values.
+A vector with row means (for \code{row_means()}) or row sums (for
+\code{row_sums()}) for those rows with at least \code{n} valid values.
 }
 \description{
-This function is similar to the SPSS \code{MEAN.n} function and computes
-row means from a data frame or matrix if at least \code{min_valid} values of a row are
-valid (and not \code{NA}).
+This function is similar to the SPSS \code{MEAN.n} or \code{SUM.n}
+function and computes row means or row sums from a data frame or matrix if at
+least \code{min_valid} values of a row are valid (and not \code{NA}).
 }
 \details{
-Rounding to a negative number of \code{digits} means rounding to a power of
-ten, for example \code{row_means(df, 3, digits = -2)} rounds to the nearest hundred.
-For \code{min_valid}, if not \code{NULL}, \code{min_valid} must be a numeric value from \code{0}
-to \code{ncol(data)}. If a row in the data frame has at least \code{min_valid}
-non-missing values, the row mean is returned. If \code{min_valid} is a non-integer
-value from 0 to 1, \code{min_valid} is considered to indicate the proportion of
-required non-missing values per row. E.g., if \code{min_valid = 0.75}, a row must
-have at least \code{ncol(data) * min_valid} non-missing values for the row mean
-to be calculated. See 'Examples'.
+Rounding to a negative number of \code{digits} means rounding to a power
+of ten, for example \code{row_means(df, 3, digits = -2)} rounds to the nearest
+hundred. For \code{min_valid}, if not \code{NULL}, \code{min_valid} must be a numeric value
+from \code{0} to \code{ncol(data)}. If a row in the data frame has at least \code{min_valid}
+non-missing values, the row mean or row sum is returned. If \code{min_valid} is a
+non-integer value from 0 to 1, \code{min_valid} is considered to indicate the
+proportion of required non-missing values per row. E.g., if
+\code{min_valid = 0.75}, a row must have at least \code{ncol(data) * min_valid}
+non-missing values for the row mean or row sum to be calculated. See
+'Examples'.
 }
 \examples{
 dat <- data.frame(
@@ -125,6 +142,7 @@ row_means(dat, remove_na = TRUE)
 
 # needs at least 4 non-missing values per row
 row_means(dat, min_valid = 4) # 1 valid return value
+row_sums(dat, min_valid = 4) # 1 valid return value
 
 # needs at least 3 non-missing values per row
 row_means(dat, min_valid = 3) # 2 valid return values
@@ -137,6 +155,7 @@ row_means(dat, select = c("c1", "c3"), min_valid = 1)
 
 # needs at least 50\% of non-missing values per row
 row_means(dat, min_valid = 0.5) # 3 valid return values
+row_sums(dat, min_valid = 0.5)
 
 # needs at least 75\% of non-missing values per row
 row_means(dat, min_valid = 0.75) # 2 valid return values
diff --git a/tests/testthat/test-row_means.R b/tests/testthat/test-row_means.R
index 8d0504c69..4db0d7039 100644
--- a/tests/testthat/test-row_means.R
+++ b/tests/testthat/test-row_means.R
@@ -1,4 +1,4 @@
-test_that("row_means", {
+test_that("row_means/sums", {
   d_mn <- data.frame(
     c1 = c(1, 2, NA, 4),
     c2 = c(NA, 2, NA, 5),
@@ -14,14 +14,21 @@ test_that("row_means", {
   expect_equal(row_means(d_mn, min_valid = 2, digits = 1), c(1.5, 2.8, NA, 5.7), tolerance = 1e-1)
   expect_message(row_means(iris), regex = "Only numeric")
   expect_equal(row_means(iris, verbose = FALSE), rowMeans(iris[, 1:4]), tolerance = 1e-3, ignore_attr = TRUE)
+  expect_equal(row_sums(d_mn, min_valid = 4), c(NA, 11, NA, NA), tolerance = 1e-3)
+  expect_equal(row_sums(d_mn, min_valid = 3), c(NA, 11, NA, 17), tolerance = 1e-3)
+  expect_message(row_sums(iris), regex = "Only numeric")
 })
 
-test_that("row_means, errors or messages", {
+test_that("row_means/sums, errors or messages", {
   data(iris)
   expect_error(expect_warning(row_means(iris, select = "abc")), regex = "No columns")
+  expect_error(expect_warning(row_sums(iris, select = "abc")), regex = "No columns")
   expect_error(row_means(iris[1], min_valid = 1), regex = "two numeric")
   expect_error(row_means(iris, min_valid = 1:4), regex = "numeric value")
   expect_error(row_means(iris, min_valid = "a"), regex = "numeric value")
   expect_message(row_means(iris[1:3, ], min_valid = 3), regex = "Only numeric")
   expect_silent(row_means(iris[1:3, ], min_valid = 3, verbose = FALSE))
+  expect_error(row_sums(iris[1], min_valid = 1), regex = "two numeric")
+  expect_message(row_sums(iris[1:3, ], min_valid = 3), regex = "Only numeric")
+  expect_silent(row_sums(iris[1:3, ], min_valid = 3, verbose = FALSE))
 })

From 3f46e31cae70f43588b2cd8bcf0beaf0b5a54d0c Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Sat, 12 Oct 2024 09:05:22 +0200
Subject: [PATCH 13/19] set `trust = TRUE` also for RData files (#557)

* set `trust = TRUE` also for RData files

* fix test

* lintr
---
 DESCRIPTION                     |  2 +-
 NEWS.md                         |  3 +++
 R/data_read.R                   |  4 ++--
 tests/testthat/test-data_read.R | 13 +++++++++++++
 4 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 841bb2573..cc9810def 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.7
+Version: 0.13.0.8
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NEWS.md b/NEWS.md
index 679a71a9c..b5cdf84c0 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -16,6 +16,9 @@ CHANGES
 
 * New function `row_count()`, to count specific values row-wise.
 
+* `data_read()` no longer shows warning about forthcoming breaking changes
+  in upstream packages when reading `.RData` files.
+
 BUG FIXES
 
 * `describe_distribution()` no longer errors if the sample was too sparse to compute
diff --git a/R/data_read.R b/R/data_read.R
index 5137a7735..1306a3f32 100644
--- a/R/data_read.R
+++ b/R/data_read.R
@@ -161,7 +161,7 @@ data_read <- function(path,
   # user may decide whether we automatically detect variable type or not
   if (isTRUE(convert_factors)) {
     if (verbose) {
-      msg <- "Variables where all values have associated labels are now converted into factors. If this is not intended, use `convert_factors = FALSE`."
+      msg <- "Variables where all values have associated labels are now converted into factors. If this is not intended, use `convert_factors = FALSE`." # nolint
       insight::format_alert(msg)
     }
     x[] <- lapply(x, function(i) {
@@ -296,7 +296,7 @@ data_read <- function(path,
   # set up arguments. for RDS, we set trust = TRUE, to avoid warnings
   rio_args <- list(file = path)
   # check if we have RDS, and if so, add trust = TRUE
-  if (file_type == "rds") {
+  if (file_type %in% c("rds", "rdata")) {
     rio_args$trust <- TRUE
   }
   out <- do.call(rio::import, c(rio_args, list(...)))
diff --git a/tests/testthat/test-data_read.R b/tests/testthat/test-data_read.R
index fd4884deb..ac316c706 100644
--- a/tests/testthat/test-data_read.R
+++ b/tests/testthat/test-data_read.R
@@ -154,6 +154,19 @@ test_that("data_read - RDS file, matrix, coercible", {
 })
 
 
+
+# RData -----------------------------------
+
+test_that("data_read - no warning for RData", {
+  withr::with_tempfile("temp_file", fileext = ".RData", code = {
+    data(mtcars)
+    save(mtcars, file = temp_file)
+    expect_silent(data_read(temp_file, verbose = FALSE))
+  })
+})
+
+
+
 # SPSS file -----------------------------------
 
 test_that("data_read - SPSS file", {

From 003e2b80daee0398c6301f10ce3a353ac1efd7ca Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Sat, 19 Oct 2024 16:27:16 +0200
Subject: [PATCH 14/19] `data_read()` preserves class for rds files (#558)

* `data_read()` preserves class for rds files

* desc. news

* fix

* add test

* typo

* Update NEWS.md

---------

Co-authored-by: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
---
 DESCRIPTION                     |  2 +-
 NEWS.md                         |  3 +++
 R/data_read.R                   | 41 +++++++++++++++++----------------
 man/data_read.Rd                | 32 +++++++++++++------------
 tests/testthat/test-data_read.R | 27 ++++++++++++++++++++--
 5 files changed, 67 insertions(+), 38 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index cc9810def..f68a1e2eb 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.8
+Version: 0.13.0.9
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/NEWS.md b/NEWS.md
index b5cdf84c0..8fc8a29ca 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -24,6 +24,9 @@ BUG FIXES
 * `describe_distribution()` no longer errors if the sample was too sparse to compute
   CIs. Instead, it warns the user and returns `NA` (#550).
 
+* `data_read()` preserves variable types when importing files from `rds` or
+  `rdata` format (#558).
+
 # datawizard 0.13.0
 
 BREAKING CHANGES
diff --git a/R/data_read.R b/R/data_read.R
index 1306a3f32..b24a5bdc2 100644
--- a/R/data_read.R
+++ b/R/data_read.R
@@ -15,15 +15,16 @@
 #' for SAS data files.
 #' @param encoding The character encoding used for the file. Usually not needed.
 #' @param convert_factors If `TRUE` (default), numeric variables, where all
-#' values have a value label, are assumed to be categorical and converted
-#' into factors. If `FALSE`, no variable types are guessed and no conversion
-#' of numeric variables into factors will be performed. See also section
-#' 'Differences to other packages'. For `data_write()`, this argument only
-#' applies to the text (e.g. `.txt` or `.csv`) or spreadsheet file formats (like
-#' `.xlsx`). Converting to factors might be useful for these formats because
-#' labelled numeric variables are then converted into factors and exported as
-#' character columns - else, value labels would be lost and only numeric values
-#' are written to the file.
+#' values have a value label, are assumed to be categorical and converted into
+#' factors. If `FALSE`, no variable types are guessed and no conversion of
+#' numeric variables into factors will be performed. For `data_read()`, this
+#' argument only applies to file types with *labelled data*, e.g. files from
+#' SPSS, SAS or Stata. See also section 'Differences to other packages'. For
+#' `data_write()`, this argument only applies to the text (e.g. `.txt` or
+#' `.csv`) or spreadsheet file formats (like `.xlsx`). Converting to factors
+#' might be useful for these formats because labelled numeric variables are then
+#' converted into factors and exported as character columns - else, value labels
+#' would be lost and only numeric values are written to the file.
 #' @param verbose Toggle warnings and messages.
 #' @param ... Arguments passed to the related `read_*()` or `write_*()` functions.
 #'
@@ -65,12 +66,13 @@
 #' @section Differences to other packages that read foreign data formats:
 #' `data_read()` is most comparable to `rio::import()`. For data files from
 #' SPSS, SAS or Stata, which support labelled data, variables are converted into
-#' their most appropriate type. The major difference to `rio::import()` is that
-#' `data_read()` automatically converts fully labelled numeric variables into
-#' factors, where imported value labels will be set as factor levels. If a
-#' numeric variable has _no_ value labels or less value labels than values, it
-#' is not converted to factor. In this case, value labels are preserved as
-#' `"labels"` attribute. Character vectors are preserved. Use
+#' their most appropriate type. The major difference to `rio::import()` is for
+#' data files from SPSS, SAS, or Stata, i.e. file types that support
+#' *labelled data*. `data_read()` automatically converts fully labelled numeric
+#' variables into factors, where imported value labels will be set as factor
+#' levels. If a numeric variable has _no_ value labels or less value labels than
+#' values, it is not converted to factor. In this case, value labels are
+#' preserved as `"labels"` attribute. Character vectors are preserved. Use
 #' `convert_factors = FALSE` to remove the automatic conversion of numeric
 #' variables to factors.
 #'
@@ -105,7 +107,7 @@ data_read <- function(path,
     por = .read_spss(path, encoding, convert_factors, verbose, ...),
     dta = .read_stata(path, encoding, convert_factors, verbose, ...),
     sas7bdat = .read_sas(path, path_catalog, encoding, convert_factors, verbose, ...),
-    .read_unknown(path, file_type, convert_factors, verbose, ...)
+    .read_unknown(path, file_type, verbose, ...)
   )
 
   # tell user about empty columns
@@ -188,7 +190,7 @@ data_read <- function(path,
           value_labels <- NULL
           attr(i, "converted_to_factor") <- TRUE
         } else {
-          # else, fall back to numeric
+          # else, fall back to numeric or factor
           i <- as.numeric(i)
         }
 
@@ -288,7 +290,7 @@ data_read <- function(path,
 }
 
 
-.read_unknown <- function(path, file_type, convert_factors, verbose, ...) {
+.read_unknown <- function(path, file_type, verbose, ...) {
   insight::check_if_installed("rio", reason = paste0("to read files of type '", file_type, "'"))
   if (verbose) {
     insight::format_alert("Reading data...")
@@ -317,6 +319,5 @@ data_read <- function(path,
     }
     out <- tmp
   }
-
-  .post_process_imported_data(out, convert_factors, verbose)
+  out
 }
diff --git a/man/data_read.Rd b/man/data_read.Rd
index 1ae3cea8a..d7d26255b 100644
--- a/man/data_read.Rd
+++ b/man/data_read.Rd
@@ -33,15 +33,16 @@ for SAS data files.}
 \item{encoding}{The character encoding used for the file. Usually not needed.}
 
 \item{convert_factors}{If \code{TRUE} (default), numeric variables, where all
-values have a value label, are assumed to be categorical and converted
-into factors. If \code{FALSE}, no variable types are guessed and no conversion
-of numeric variables into factors will be performed. See also section
-'Differences to other packages'. For \code{data_write()}, this argument only
-applies to the text (e.g. \code{.txt} or \code{.csv}) or spreadsheet file formats (like
-\code{.xlsx}). Converting to factors might be useful for these formats because
-labelled numeric variables are then converted into factors and exported as
-character columns - else, value labels would be lost and only numeric values
-are written to the file.}
+values have a value label, are assumed to be categorical and converted into
+factors. If \code{FALSE}, no variable types are guessed and no conversion of
+numeric variables into factors will be performed. For \code{data_read()}, this
+argument only applies to file types with \emph{labelled data}, e.g. files from
+SPSS, SAS or Stata. See also section 'Differences to other packages'. For
+\code{data_write()}, this argument only applies to the text (e.g. \code{.txt} or
+\code{.csv}) or spreadsheet file formats (like \code{.xlsx}). Converting to factors
+might be useful for these formats because labelled numeric variables are then
+converted into factors and exported as character columns - else, value labels
+would be lost and only numeric values are written to the file.}
 
 \item{verbose}{Toggle warnings and messages.}
 
@@ -118,12 +119,13 @@ versions, use \code{compress = "none"}, for example
 
 \code{data_read()} is most comparable to \code{rio::import()}. For data files from
 SPSS, SAS or Stata, which support labelled data, variables are converted into
-their most appropriate type. The major difference to \code{rio::import()} is that
-\code{data_read()} automatically converts fully labelled numeric variables into
-factors, where imported value labels will be set as factor levels. If a
-numeric variable has \emph{no} value labels or less value labels than values, it
-is not converted to factor. In this case, value labels are preserved as
-\code{"labels"} attribute. Character vectors are preserved. Use
+their most appropriate type. The major difference to \code{rio::import()} is for
+data files from SPSS, SAS, or Stata, i.e. file types that support
+\emph{labelled data}. \code{data_read()} automatically converts fully labelled numeric
+variables into factors, where imported value labels will be set as factor
+levels. If a numeric variable has \emph{no} value labels or less value labels than
+values, it is not converted to factor. In this case, value labels are
+preserved as \code{"labels"} attribute. Character vectors are preserved. Use
 \code{convert_factors = FALSE} to remove the automatic conversion of numeric
 variables to factors.
 }
diff --git a/tests/testthat/test-data_read.R b/tests/testthat/test-data_read.R
index ac316c706..15f1161d3 100644
--- a/tests/testthat/test-data_read.R
+++ b/tests/testthat/test-data_read.R
@@ -141,12 +141,12 @@ test_that("data_read - RDS file, matrix, coercible", {
     httr::stop_for_status(request)
     writeBin(httr::content(request, type = "raw"), temp_file)
 
-    expect_message(expect_message(expect_message({
+    expect_message({
       d <- data_read(
         temp_file,
         verbose = TRUE
       )
-    })), regex = "0 out of 5")
+    })
 
     expect_s3_class(d, "data.frame")
     expect_identical(dim(d), c(2L, 5L))
@@ -155,6 +155,29 @@ test_that("data_read - RDS file, matrix, coercible", {
 
 
 
+# RDS file, preserve class /types -----------------------------------
+
+test_that("data_read - RDS file, preserve class", {
+  withr::with_tempfile("temp_file", fileext = ".rds", code = {
+    request <- httr::GET("https://raw.github.com/easystats/circus/main/data/hiv.rds")
+    httr::stop_for_status(request)
+    writeBin(httr::content(request, type = "raw"), temp_file)
+
+    d <- data_read(temp_file)
+    expect_s3_class(d, "data.frame")
+    expect_identical(
+      sapply(d, class),
+      c(
+        village = "integer", outcome = "integer", distance = "numeric",
+        amount = "numeric", incentive = "integer", age = "integer",
+        hiv2004 = "integer", agecat = "factor"
+      )
+    )
+  })
+})
+
+
+
 # RData -----------------------------------
 
 test_that("data_read - no warning for RData", {

From 5703d853911d5d1d000a4cc20788166e3bd98aae Mon Sep 17 00:00:00 2001
From: "Mattan S. Ben-Shachar" <35330040+mattansb@users.noreply.github.com>
Date: Sun, 3 Nov 2024 10:53:12 +0200
Subject: [PATCH 15/19] Use dev insight

test with changes introduced in https://github.com/easystats/insight/pull/952
---
 DESCRIPTION | 1 +
 1 file changed, 1 insertion(+)

diff --git a/DESCRIPTION b/DESCRIPTION
index f68a1e2eb..8127a2e79 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -76,3 +76,4 @@ RoxygenNote: 7.3.2
 Config/testthat/edition: 3
 Config/testthat/parallel: true
 Config/Needs/website: easystats/easystatstemplate
+Remotes: easystats/insight

From b723df21b3644975bc6e46c44115d8c7b2826f57 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Mon, 4 Nov 2024 22:59:39 +0100
Subject: [PATCH 16/19] Fix snapshot tests (#560)

* Fix snapshot tests
Fixes #559

* update

* pass ... to export_table

* update tests

* pass ...

* update tests

* docs

* Trigger CI

* lintr
---
 DESCRIPTION                            |   2 +-
 R/data_codebook.R                      |   6 +-
 R/data_tabulate.R                      |   9 +-
 R/data_xtabulate.R                     |   3 +-
 R/describe_distribution.R              |   2 +-
 man/data_codebook.Rd                   |   3 +-
 man/data_tabulate.Rd                   |   3 +-
 tests/testthat/_snaps/data_codebook.md | 264 ++++++++++++++++++++++++-
 tests/testthat/test-data_codebook.R    |  32 +--
 9 files changed, 299 insertions(+), 25 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 8127a2e79..a680cfd02 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.9
+Version: 0.13.0.11
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/R/data_codebook.R b/R/data_codebook.R
index 71e2e5828..5dffbf9c2 100644
--- a/R/data_codebook.R
+++ b/R/data_codebook.R
@@ -33,7 +33,8 @@
 #'
 #' @note There are methods to `print()` the data frame in a nicer output, as
 #' well methods for printing in markdown or HTML format (`print_md()` and
-#' `print_html()`).
+#' `print_html()`). The `print()` method for text outputs passes arguments in
+#' `...` to [`insight::export_table()`].
 #'
 #' @examples
 #' data(iris)
@@ -369,7 +370,8 @@ print.data_codebook <- function(x, ...) {
       title = caption,
       empty_line = "-",
       cross = "+",
-      align = .get_codebook_align(x)
+      align = .get_codebook_align(x),
+      ...
     )
   )
 }
diff --git a/R/data_tabulate.R b/R/data_tabulate.R
index e94fc5d55..621fabbb1 100644
--- a/R/data_tabulate.R
+++ b/R/data_tabulate.R
@@ -48,7 +48,8 @@
 #' @note
 #' There are `print_html()` and `print_md()` methods available for printing
 #' frequency or crosstables in HTML and markdown format, e.g.
-#' `print_html(data_tabulate(x))`.
+#' `print_html(data_tabulate(x))`. The `print()` method for text outputs passes
+#' arguments in `...` to [`insight::export_table()`].
 #'
 #' @return A data frame, or a list of data frames, with one frequency table
 #' as data frame per variable.
@@ -522,7 +523,8 @@ print.datawizard_table <- function(x, big_mark = NULL, ...) {
   cat(insight::export_table(
     format(x, big_mark = big_mark, ...),
     cross = "+",
-    missing = "<NA>"
+    missing = "<NA>",
+    ...
   ))
   invisible(x)
 }
@@ -621,7 +623,8 @@ print.datawizard_tables <- function(x, big_mark = NULL, ...) {
       out,
       missing = "<NA>",
       cross = "+",
-      empty_line = "-"
+      empty_line = "-",
+      ...
     ))
   }
 }
diff --git a/R/data_xtabulate.R b/R/data_xtabulate.R
index 08be1eeca..c9595eccf 100644
--- a/R/data_xtabulate.R
+++ b/R/data_xtabulate.R
@@ -198,7 +198,8 @@ print.datawizard_crosstab <- function(x, big_mark = NULL, ...) {
     cross = "+",
     missing = "<NA>",
     caption = caption,
-    empty_line = "-"
+    empty_line = "-",
+    ...
   ))
   invisible(x)
 }
diff --git a/R/describe_distribution.R b/R/describe_distribution.R
index 2e61c1dc3..64f6e29c1 100644
--- a/R/describe_distribution.R
+++ b/R/describe_distribution.R
@@ -513,7 +513,7 @@ print.parameters_distribution <- function(x, digits = 2, ...) {
     ci_brackets = TRUE,
     ...
   )
-  cat(insight::export_table(formatted_table, format = "text", digits = digits))
+  cat(insight::export_table(formatted_table, format = "text", digits = digits, ...))
   invisible(x)
 }
 
diff --git a/man/data_codebook.Rd b/man/data_codebook.Rd
index 319f4e5b6..d5a542be4 100644
--- a/man/data_codebook.Rd
+++ b/man/data_codebook.Rd
@@ -127,7 +127,8 @@ labels, values or value range, frequencies, amount of missing values).
 \note{
 There are methods to \code{print()} the data frame in a nicer output, as
 well methods for printing in markdown or HTML format (\code{print_md()} and
-\code{print_html()}).
+\code{print_html()}). The \code{print()} method for text outputs passes arguments in
+\code{...} to \code{\link[insight:export_table]{insight::export_table()}}.
 }
 \examples{
 data(iris)
diff --git a/man/data_tabulate.Rd b/man/data_tabulate.Rd
index 032c0b989..b28a26ede 100644
--- a/man/data_tabulate.Rd
+++ b/man/data_tabulate.Rd
@@ -167,7 +167,8 @@ frequency tables as data frame. See 'Examples'.
 \note{
 There are \code{print_html()} and \code{print_md()} methods available for printing
 frequency or crosstables in HTML and markdown format, e.g.
-\code{print_html(data_tabulate(x))}.
+\code{print_html(data_tabulate(x))}. The \code{print()} method for text outputs passes
+arguments in \code{...} to \code{\link[insight:export_table]{insight::export_table()}}.
 }
 \section{Crosstables}{
 
diff --git a/tests/testthat/_snaps/data_codebook.md b/tests/testthat/_snaps/data_codebook.md
index c390ba890..8f9b9e7b5 100644
--- a/tests/testthat/_snaps/data_codebook.md
+++ b/tests/testthat/_snaps/data_codebook.md
@@ -139,7 +139,7 @@
 # data_codebook efc
 
     Code
-      data_codebook(efc)
+      print(data_codebook(efc), table_width = Inf)
     Output
       efc (100 rows and 5 variables, 5 shown)
       
@@ -162,10 +162,94 @@
       5  | neg_c_7  | Negative impact with 7 items             | numeric     |   3 (3.0%) |  [7, 28] |                                 |         97
       ---------------------------------------------------------------------------------------------------------------------------------------------
 
+---
+
+    Code
+      print(data_codebook(efc), table_width = "auto", remove_duplicates = FALSE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                                    | Type       
+      ---+----------+------------------------------------------+------------
+      1  | c12hour  | average number of hours of care per week | numeric    
+      ---+----------+------------------------------------------+------------
+      2  | e16sex   | elder's gender                           | numeric    
+         |          |                                          |            
+      ---+----------+------------------------------------------+------------
+      3  | e42dep   | elder's dependency                       | categorical
+         |          |                                          |            
+         |          |                                          |            
+         |          |                                          |            
+      ---+----------+------------------------------------------+------------
+      4  | c172code | carer's level of education               | numeric    
+         |          |                                          |            
+         |          |                                          |            
+      ---+----------+------------------------------------------+------------
+      5  | neg_c_7  | Negative impact with 7 items             | numeric    
+      ----------------------------------------------------------------------
+      
+      ID |   Missings |   Values | Value Labels                    |          N
+      ---+------------+----------+---------------------------------+-----------
+      1  |   2 (2.0%) | [5, 168] |                                 |         98
+      ---+------------+----------+---------------------------------+-----------
+      2  |   0 (0.0%) |        1 | male                            | 46 (46.0%)
+         |            |        2 | female                          | 54 (54.0%)
+      ---+------------+----------+---------------------------------+-----------
+      3  |   3 (3.0%) |        1 | independent                     |  2 ( 2.1%)
+         |            |        2 | slightly dependent              |  4 ( 4.1%)
+         |            |        3 | moderately dependent            | 28 (28.9%)
+         |            |        4 | severely dependent              | 63 (64.9%)
+      ---+------------+----------+---------------------------------+-----------
+      4  | 10 (10.0%) |        1 | low level of education          |  8 ( 8.9%)
+         |            |        2 | intermediate level of education | 66 (73.3%)
+         |            |        3 | high level of education         | 16 (17.8%)
+      ---+------------+----------+---------------------------------+-----------
+      5  |   3 (3.0%) |  [7, 28] |                                 |         97
+      -------------------------------------------------------------------------
+
+---
+
+    Code
+      print(data_codebook(efc), table_width = "auto", remove_duplicates = TRUE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                                    | Type       
+      ---+----------+------------------------------------------+------------
+      1  | c12hour  | average number of hours of care per week | numeric    
+      ---+----------+------------------------------------------+------------
+      2  | e16sex   | elder's gender                           | numeric    
+      ---+----------+------------------------------------------+------------
+      3  | e42dep   | elder's dependency                       | categorical
+      ---+----------+------------------------------------------+------------
+      4  | c172code | carer's level of education               | numeric    
+      ---+----------+------------------------------------------+------------
+      5  | neg_c_7  | Negative impact with 7 items             | numeric    
+      ----------------------------------------------------------------------
+      
+      ID |   Missings |   Values | Value Labels                    |          N
+      ---+------------+----------+---------------------------------+-----------
+      1  |   2 (2.0%) | [5, 168] |                                 |         98
+      ---+------------+----------+---------------------------------+-----------
+      2  |   0 (0.0%) |        1 | male                            | 46 (46.0%)
+         |            |        2 | female                          | 54 (54.0%)
+      ---+------------+----------+---------------------------------+-----------
+      3  |   3 (3.0%) |        1 | independent                     |  2 ( 2.1%)
+         |            |        2 | slightly dependent              |  4 ( 4.1%)
+         |            |        3 | moderately dependent            | 28 (28.9%)
+         |            |        4 | severely dependent              | 63 (64.9%)
+      ---+------------+----------+---------------------------------+-----------
+      4  | 10 (10.0%) |        1 | low level of education          |  8 ( 8.9%)
+         |            |        2 | intermediate level of education | 66 (73.3%)
+         |            |        3 | high level of education         | 16 (17.8%)
+      ---+------------+----------+---------------------------------+-----------
+      5  |   3 (3.0%) |  [7, 28] |                                 |         97
+      -------------------------------------------------------------------------
+
 # data_codebook efc, variable_label_width
 
     Code
-      data_codebook(efc, variable_label_width = 30)
+      print(out, table_width = Inf)
     Output
       efc (100 rows and 5 variables, 5 shown)
       
@@ -189,10 +273,97 @@
       5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%) |  [7, 28] |                                 |         97
       ---------------------------------------------------------------------------------------------------------------------------------
 
+---
+
+    Code
+      print(out, table_width = "auto", remove_duplicates = FALSE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                        | Type        |   Missings
+      ---+----------+------------------------------+-------------+-----------
+      1  | c12hour  | average number of hours of   | numeric     |   2 (2.0%)
+         |          | care per week                |             |           
+      ---+----------+------------------------------+-------------+-----------
+      2  | e16sex   | elder's gender               | numeric     |   0 (0.0%)
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      3  | e42dep   | elder's dependency           | categorical |   3 (3.0%)
+         |          |                              |             |           
+         |          |                              |             |           
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      4  | c172code | carer's level of education   | numeric     | 10 (10.0%)
+         |          |                              |             |           
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%)
+      -----------------------------------------------------------------------
+      
+      ID |   Values | Value Labels                    |          N
+      ---+----------+---------------------------------+-----------
+      1  | [5, 168] |                                 |         98
+         |          |                                 |           
+      ---+----------+---------------------------------+-----------
+      2  |        1 | male                            | 46 (46.0%)
+         |        2 | female                          | 54 (54.0%)
+      ---+----------+---------------------------------+-----------
+      3  |        1 | independent                     |  2 ( 2.1%)
+         |        2 | slightly dependent              |  4 ( 4.1%)
+         |        3 | moderately dependent            | 28 (28.9%)
+         |        4 | severely dependent              | 63 (64.9%)
+      ---+----------+---------------------------------+-----------
+      4  |        1 | low level of education          |  8 ( 8.9%)
+         |        2 | intermediate level of education | 66 (73.3%)
+         |        3 | high level of education         | 16 (17.8%)
+      ---+----------+---------------------------------+-----------
+      5  |  [7, 28] |                                 |         97
+      ------------------------------------------------------------
+
+---
+
+    Code
+      print(out, table_width = "auto", remove_duplicates = TRUE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                        | Type        |   Missings
+      ---+----------+------------------------------+-------------+-----------
+      1  | c12hour  | average number of hours of   | numeric     |   2 (2.0%)
+         |          | care per week                |             |           
+      ---+----------+------------------------------+-------------+-----------
+      2  | e16sex   | elder's gender               | numeric     |   0 (0.0%)
+      ---+----------+------------------------------+-------------+-----------
+      3  | e42dep   | elder's dependency           | categorical |   3 (3.0%)
+      ---+----------+------------------------------+-------------+-----------
+      4  | c172code | carer's level of education   | numeric     | 10 (10.0%)
+      ---+----------+------------------------------+-------------+-----------
+      5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%)
+      -----------------------------------------------------------------------
+      
+      ID |   Values | Value Labels                    |          N
+      ---+----------+---------------------------------+-----------
+      1  | [5, 168] |                                 |         98
+      ---+----------+---------------------------------+-----------
+      2  |        1 | male                            | 46 (46.0%)
+         |        2 | female                          | 54 (54.0%)
+      ---+----------+---------------------------------+-----------
+      3  |        1 | independent                     |  2 ( 2.1%)
+         |        2 | slightly dependent              |  4 ( 4.1%)
+         |        3 | moderately dependent            | 28 (28.9%)
+         |        4 | severely dependent              | 63 (64.9%)
+      ---+----------+---------------------------------+-----------
+      4  |        1 | low level of education          |  8 ( 8.9%)
+         |        2 | intermediate level of education | 66 (73.3%)
+         |        3 | high level of education         | 16 (17.8%)
+      ---+----------+---------------------------------+-----------
+      5  |  [7, 28] |                                 |         97
+      ------------------------------------------------------------
+
 # data_codebook efc, value_label_width
 
     Code
-      data_codebook(efc, variable_label_width = 30, value_label_width = 15)
+      print(out, table_width = Inf)
     Output
       efc (100 rows and 5 variables, 5 shown)
       
@@ -216,6 +387,93 @@
       5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%) |  [7, 28] |                  |         97
       ------------------------------------------------------------------------------------------------------------------
 
+---
+
+    Code
+      print(out, table_width = "auto", remove_duplicates = FALSE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                        | Type        |   Missings
+      ---+----------+------------------------------+-------------+-----------
+      1  | c12hour  | average number of hours of   | numeric     |   2 (2.0%)
+         |          | care per week                |             |           
+      ---+----------+------------------------------+-------------+-----------
+      2  | e16sex   | elder's gender               | numeric     |   0 (0.0%)
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      3  | e42dep   | elder's dependency           | categorical |   3 (3.0%)
+         |          |                              |             |           
+         |          |                              |             |           
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      4  | c172code | carer's level of education   | numeric     | 10 (10.0%)
+         |          |                              |             |           
+         |          |                              |             |           
+      ---+----------+------------------------------+-------------+-----------
+      5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%)
+      -----------------------------------------------------------------------
+      
+      ID |   Values | Value Labels     |          N
+      ---+----------+------------------+-----------
+      1  | [5, 168] |                  |         98
+         |          |                  |           
+      ---+----------+------------------+-----------
+      2  |        1 | male             | 46 (46.0%)
+         |        2 | female           | 54 (54.0%)
+      ---+----------+------------------+-----------
+      3  |        1 | independent      |  2 ( 2.1%)
+         |        2 | slightly...      |  4 ( 4.1%)
+         |        3 | moderately...    | 28 (28.9%)
+         |        4 | severely...      | 63 (64.9%)
+      ---+----------+------------------+-----------
+      4  |        1 | low level of...  |  8 ( 8.9%)
+         |        2 | intermediate...  | 66 (73.3%)
+         |        3 | high level of... | 16 (17.8%)
+      ---+----------+------------------+-----------
+      5  |  [7, 28] |                  |         97
+      ---------------------------------------------
+
+---
+
+    Code
+      print(out, table_width = "auto", remove_duplicates = TRUE)
+    Output
+      efc (100 rows and 5 variables, 5 shown)
+      
+      ID | Name     | Label                        | Type        |   Missings
+      ---+----------+------------------------------+-------------+-----------
+      1  | c12hour  | average number of hours of   | numeric     |   2 (2.0%)
+         |          | care per week                |             |           
+      ---+----------+------------------------------+-------------+-----------
+      2  | e16sex   | elder's gender               | numeric     |   0 (0.0%)
+      ---+----------+------------------------------+-------------+-----------
+      3  | e42dep   | elder's dependency           | categorical |   3 (3.0%)
+      ---+----------+------------------------------+-------------+-----------
+      4  | c172code | carer's level of education   | numeric     | 10 (10.0%)
+      ---+----------+------------------------------+-------------+-----------
+      5  | neg_c_7  | Negative impact with 7 items | numeric     |   3 (3.0%)
+      -----------------------------------------------------------------------
+      
+      ID |   Values | Value Labels     |          N
+      ---+----------+------------------+-----------
+      1  | [5, 168] |                  |         98
+      ---+----------+------------------+-----------
+      2  |        1 | male             | 46 (46.0%)
+         |        2 | female           | 54 (54.0%)
+      ---+----------+------------------+-----------
+      3  |        1 | independent      |  2 ( 2.1%)
+         |        2 | slightly...      |  4 ( 4.1%)
+         |        3 | moderately...    | 28 (28.9%)
+         |        4 | severely...      | 63 (64.9%)
+      ---+----------+------------------+-----------
+      4  |        1 | low level of...  |  8 ( 8.9%)
+         |        2 | intermediate...  | 66 (73.3%)
+         |        3 | high level of... | 16 (17.8%)
+      ---+----------+------------------+-----------
+      5  |  [7, 28] |                  |         97
+      ---------------------------------------------
+
 # data_codebook truncated data
 
     Code
diff --git a/tests/testthat/test-data_codebook.R b/tests/testthat/test-data_codebook.R
index 26a67ccf6..06e9bd2f9 100644
--- a/tests/testthat/test-data_codebook.R
+++ b/tests/testthat/test-data_codebook.R
@@ -19,7 +19,7 @@ test_that("data_codebook NaN and Inf", {
 
   set.seed(123)
   d <- data.frame(
-    x = c(sample(1:15, 100, TRUE), Inf, Inf)
+    x = c(sample.int(15, 100, TRUE), Inf, Inf)
   )
   expect_snapshot(data_codebook(d))
   expect_snapshot(data_codebook(d, range_at = 100))
@@ -38,24 +38,32 @@ test_that("data_codebook iris, select, ID", {
 
 
 test_that("data_codebook efc", {
-  expect_snapshot(data_codebook(efc))
+  expect_snapshot(print(data_codebook(efc), table_width = Inf))
+  expect_snapshot(print(data_codebook(efc), table_width = "auto", remove_duplicates = FALSE))
+  expect_snapshot(print(data_codebook(efc), table_width = "auto", remove_duplicates = TRUE))
 })
 
 
 test_that("data_codebook efc, variable_label_width", {
-  expect_snapshot(data_codebook(efc, variable_label_width = 30))
+  out <- data_codebook(efc, variable_label_width = 30)
+  expect_snapshot(print(out, table_width = Inf))
+  expect_snapshot(print(out, table_width = "auto", remove_duplicates = FALSE))
+  expect_snapshot(print(out, table_width = "auto", remove_duplicates = TRUE))
 })
 
 
 test_that("data_codebook efc, value_label_width", {
-  expect_snapshot(data_codebook(efc, variable_label_width = 30, value_label_width = 15))
+  out <- data_codebook(efc, variable_label_width = 30, value_label_width = 15)
+  expect_snapshot(print(out, table_width = Inf))
+  expect_snapshot(print(out, table_width = "auto", remove_duplicates = FALSE))
+  expect_snapshot(print(out, table_width = "auto", remove_duplicates = TRUE))
 })
 
 
 test_that("data_codebook truncated data", {
   set.seed(123)
   d <- data.frame(
-    a = sample(1:15, 100, TRUE),
+    a = sample.int(15, 100, TRUE),
     b = sample(letters[1:18], 100, TRUE),
     stringsAsFactors = FALSE
   )
@@ -66,7 +74,7 @@ test_that("data_codebook truncated data", {
 test_that("data_codebook mixed numeric lengths", {
   set.seed(123)
   d <- data.frame(
-    a = sample(1:4, 100, TRUE),
+    a = sample.int(4, 100, TRUE),
     b = sample(5:15, 100, TRUE),
     stringsAsFactors = FALSE
   )
@@ -76,7 +84,7 @@ test_that("data_codebook mixed numeric lengths", {
 test_that("data_codebook mixed range_at", {
   set.seed(123)
   d <- data.frame(
-    a = sample(1:4, 100, TRUE),
+    a = sample.int(4, 100, TRUE),
     b = sample(5:15, 100, TRUE),
     stringsAsFactors = FALSE
   )
@@ -87,7 +95,7 @@ test_that("data_codebook mixed range_at", {
 test_that("data_codebook logicals", {
   set.seed(123)
   d <- data.frame(
-    a = sample(1:15, 100, TRUE),
+    a = sample.int(15, 100, TRUE),
     b = sample(letters[1:3], 100, TRUE),
     c = sample(c(TRUE, FALSE), 100, TRUE),
     stringsAsFactors = FALSE
@@ -99,14 +107,14 @@ test_that("data_codebook logicals", {
 test_that("data_codebook labelled data exceptions", {
   set.seed(123)
 
-  f1 <- sample(1:5, 100, TRUE)
+  f1 <- sample.int(5, 100, TRUE)
   f1[f1 == 4] <- NA
   attr(f1, "labels") <- setNames(1:5, c("One", "Two", "Three", "Four", "Five"))
 
-  f2 <- sample(1:5, 100, TRUE)
+  f2 <- sample.int(5, 100, TRUE)
   attr(f2, "labels") <- setNames(c(1:3, 5), c("One", "Two", "Three", "Five"))
 
-  f3 <- sample(1:5, 100, TRUE)
+  f3 <- sample.int(5, 100, TRUE)
   attr(f3, "labels") <- setNames(1:5, c("One", "Two", "Three", "Four", "Five"))
 
   d <- data.frame(f1, f2, f3)
@@ -143,7 +151,7 @@ test_that("data_codebook works with numbers < 1", {
 test_that("data_codebook, big marks", {
   set.seed(123)
   f1 <- factor(sample(c("c", "b", "a"), 1e6, TRUE))
-  f2 <- factor(sample(1:3, 1e6, TRUE))
+  f2 <- factor(sample.int(3, 1e6, TRUE))
   d <- data.frame(f1, f2)
   expect_snapshot(data_codebook(d))
 })

From c0ce69275e0bc81b864d50b333acb916a9f708b7 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Fri, 8 Nov 2024 22:34:19 +0100
Subject: [PATCH 17/19] Trigger CI

---
 DESCRIPTION | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index a680cfd02..ba821b0ba 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.11
+Version: 0.13.0.12
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),

From 9baa22be43af54053d5586323b901951faa4a9a5 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Thu, 21 Nov 2024 10:28:04 +0100
Subject: [PATCH 18/19] Allow `n()` in `data_modify()` (#535)

* Allow `n()` in `data_modify()`

* lintr, styler

* Update NEWS.md

Co-authored-by: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>

* Update R/data_modify.R

Co-authored-by: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>

* comments

* fix test

* update rd

* modify error msg

* error on invalid function

* move news item

---------

Co-authored-by: Etienne Bacher <52219252+etiennebacher@users.noreply.github.com>
---
 NEWS.md                           |  3 ++
 R/data_modify.R                   | 21 +++++++++++--
 man/data_modify.Rd                |  6 +++-
 tests/testthat/test-data_modify.R | 52 +++++++++++++++++++++++++++++++
 4 files changed, 79 insertions(+), 3 deletions(-)

diff --git a/NEWS.md b/NEWS.md
index 8fc8a29ca..663efa310 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -19,6 +19,9 @@ CHANGES
 * `data_read()` no longer shows warning about forthcoming breaking changes
   in upstream packages when reading `.RData` files.
 
+* `data_modify()` now recognizes `n()`, for example to create an index for data groups
+  with `1:n()` (#535).
+
 BUG FIXES
 
 * `describe_distribution()` no longer errors if the sample was too sparse to compute
diff --git a/R/data_modify.R b/R/data_modify.R
index e7744c1f5..3e30b8f68 100644
--- a/R/data_modify.R
+++ b/R/data_modify.R
@@ -22,6 +22,9 @@
 #'   character vector is provided, you may not add further elements to `...`.
 #' - Using `NULL` as right-hand side removes a variable from the data frame.
 #'   Example: `Petal.Width = NULL`.
+#' - For data frames (including grouped ones), the function `n()` can be used to count the
+#'   number of observations and thereby, for instance, create index values by
+#'   using `id = 1:n()` or `id = 3:(n()+2)` and similar.
 #'
 #' Note that newly created variables can be used in subsequent expressions,
 #' including `.at` or `.if`. See also 'Examples'.
@@ -92,7 +95,8 @@
 #'   grouped_efc,
 #'   c12hour_c = center(c12hour),
 #'   c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
-#'   c12hour_z2 = standardize(c12hour)
+#'   c12hour_z2 = standardize(c12hour),
+#'   id = 1:n()
 #' )
 #' head(new_efc)
 #'
@@ -145,6 +149,11 @@ data_modify.default <- function(data, ...) {
 data_modify.data.frame <- function(data, ..., .if = NULL, .at = NULL, .modify = NULL) {
   dots <- eval(substitute(alist(...)))
 
+  # error for data frames with no rows...
+  if (nrow(data) == 0) {
+    insight::format_error("`data` is an empty data frame. `data_modify()` only works for data frames with at least one row.") # nolint
+  }
+
   # check if we have dots, or only at/modify ----
 
   if (length(dots)) {
@@ -201,6 +210,10 @@ data_modify.grouped_df <- function(data, ..., .if = NULL, .at = NULL, .modify =
   # the data.frame method later...
   dots <- match.call(expand.dots = FALSE)[["..."]]
 
+  # error for data frames with no rows...
+  if (nrow(data) == 0) {
+    insight::format_error("`data` is an empty data frame. `data_modify()` only works for data frames with at least one row.") # nolint
+  }
 
   grps <- attr(data, "groups", exact = TRUE)
   grps <- grps[[".rows"]]
@@ -352,8 +365,12 @@ data_modify.grouped_df <- function(data, ..., .if = NULL, .at = NULL, .modify =
   # finally, we can evaluate expression and get values for new variables
   symbol_string <- insight::safe_deparse(symbol)
   if (!is.null(symbol_string) && all(symbol_string == "n()")) {
-    # "special" functions
+    # "special" functions - using "n()" just returns number of rows
     new_variable <- nrow(data)
+  } else if (!is.null(symbol_string) && length(symbol_string) == 1 && grepl("\\bn\\(\\)", symbol_string)) {
+    # "special" functions, like "1:n()" or similar - but not "1:fun()"
+    symbol_string <- str2lang(gsub("n()", "nrow(data)", symbol_string, fixed = TRUE))
+    new_variable <- try(with(data, eval(symbol_string)), silent = TRUE)
   } else {
     # default evaluation of expression
     new_variable <- try(with(data, eval(symbol)), silent = TRUE)
diff --git a/man/data_modify.Rd b/man/data_modify.Rd
index 042962e03..28533ecea 100644
--- a/man/data_modify.Rd
+++ b/man/data_modify.Rd
@@ -30,6 +30,9 @@ type of expression cannot be mixed with other expressions, i.e. if a
 character vector is provided, you may not add further elements to \code{...}.
 \item Using \code{NULL} as right-hand side removes a variable from the data frame.
 Example: \code{Petal.Width = NULL}.
+\item For data frames (including grouped ones), the function \code{n()} can be used to count the
+number of observations and thereby, for instance, create index values by
+using \code{id = 1:n()} or \code{id = 3:(n()+2)} and similar.
 }
 
 Note that newly created variables can be used in subsequent expressions,
@@ -109,7 +112,8 @@ new_efc <- data_modify(
   grouped_efc,
   c12hour_c = center(c12hour),
   c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
-  c12hour_z2 = standardize(c12hour)
+  c12hour_z2 = standardize(c12hour),
+  id = 1:n()
 )
 head(new_efc)
 
diff --git a/tests/testthat/test-data_modify.R b/tests/testthat/test-data_modify.R
index 9bb0a92d6..a7a153c43 100644
--- a/tests/testthat/test-data_modify.R
+++ b/tests/testthat/test-data_modify.R
@@ -353,6 +353,16 @@ test_that("data_modify errors for non df", {
 })
 
 
+test_that("data_modify errors for empty data frames", {
+  data(mtcars)
+  x <- mtcars[1, ]
+  expect_error(
+    data_modify(x[-1, ], new_var = 5),
+    regex = "empty data frame"
+  )
+})
+
+
 test_that("data_modify errors for non df", {
   data(efc)
   a <- "center(c22hour)" # <---------------- error in variable name
@@ -492,6 +502,20 @@ test_that("data_modify works with functions that return character vectors", {
 })
 
 
+test_that("data_modify 1:n() and similar works in (grouped) data frames", {
+  data(mtcars)
+  out <- data_modify(mtcars, Trials = 1:n()) # nolint
+  expect_identical(out$Trials, 1:32)
+  x <- data_group(mtcars, "gear")
+  out <- data_modify(x, Trials = 1:n()) # nolint
+  expect_identical(out$Trials[out$gear == 3], 1:15)
+  expect_identical(out$Trials[out$gear == 4], 1:12)
+  out <- data_modify(x, Trials = 3:(n() + 2))
+  expect_identical(out$Trials[out$gear == 3], 3:17)
+  expect_identical(out$Trials[out$gear == 4], 3:14)
+})
+
+
 test_that("data_modify .if/.at arguments", {
   data(iris)
   d <- iris[1:5, ]
@@ -550,3 +574,31 @@ test_that("data_modify .if/.at arguments", {
   out <- data_modify(d, new_length = Petal.Length * 2, .if = is.numeric, .modify = round)
   expect_equal(out$new_length, c(3, 3, 3, 3, 3), ignore_attr = TRUE)
 })
+
+
+skip_if_not_installed("withr")
+
+withr::with_environment(
+  new.env(),
+  test_that("data_modify 1:n() and similar works in (grouped) data frames inside function calls", {
+    data(mtcars)
+    x <- data_group(mtcars, "gear")
+
+    foo <- function(d) {
+      out <- data_modify(d, Trials = 1:n()) # nolint
+      out$Trials
+    }
+    expect_identical(
+      foo(x),
+      c(
+        1L, 2L, 3L, 1L, 2L, 3L, 4L, 4L, 5L, 6L, 7L, 5L, 6L, 7L, 8L,
+        9L, 10L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 11L, 1L, 2L, 3L,
+        4L, 5L, 12L
+      )
+    )
+  })
+)
+
+test_that("data_modify errors on non-defined function", {
+  expect_error(data_modify(iris, Species = foo()))
+})

From 2741cdc5c86dd2e1f47e45d5bf9db8d5c9db1c91 Mon Sep 17 00:00:00 2001
From: Daniel <mail@danielluedecke.de>
Date: Thu, 21 Nov 2024 19:55:19 +0100
Subject: [PATCH 19/19] Make `standardize()` error messages clearer (#562)

* Warn user for invalif formula

* add tests

* fix tests
---
 DESCRIPTION                              |  2 +-
 R/standardize.models.R                   |  8 ++++++
 tests/testthat/test-standardize_models.R | 32 ++++++++++++++++++++----
 3 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index ba821b0ba..2325c062d 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.12
+Version: 0.13.0.13
 Authors@R: c(
     person("Indrajeet", "Patil", , "patilindrajeet.science@gmail.com", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),
diff --git a/R/standardize.models.R b/R/standardize.models.R
index a92ffe243..cf6062c78 100644
--- a/R/standardize.models.R
+++ b/R/standardize.models.R
@@ -78,6 +78,14 @@ standardize.default <- function(x,
     return(x)
   }
 
+  # check model formula. Some notations don't work when standardizing data
+  insight::formula_ok(
+    x,
+    action = "error",
+    prefix_msg = "Model cannot be standardized.",
+    verbose = verbose
+  )
+
   data_std <- NULL # needed to avoid note
   .standardize_models(x,
     robust = robust, two_sd = two_sd,
diff --git a/tests/testthat/test-standardize_models.R b/tests/testthat/test-standardize_models.R
index 706a4e6e7..d61caf450 100644
--- a/tests/testthat/test-standardize_models.R
+++ b/tests/testthat/test-standardize_models.R
@@ -31,6 +31,29 @@ test_that("standardize | errors", {
 })
 
 
+test_that("standardize | problematic formulas", {
+  data(mtcars)
+  m <- lm(mpg ~ hp, data = mtcars)
+  expect_equal(
+    coef(standardise(m)),
+    c(`(Intercept)` = -3.14935717633686e-17, hp = -0.776168371826586),
+    tolerance = 1e-4
+  )
+
+  colnames(mtcars)[1] <- "1_mpg"
+  m <- lm(`1_mpg` ~ hp, data = mtcars)
+  expect_error(standardise(m), regex = "Looks like")
+
+  # works interactive only
+  # data(mtcars)
+  # m <- lm(mtcars$mpg ~ mtcars$hp)
+  # expect_error(standardise(m), regex = "model formulas")
+
+  m <- lm(mtcars[, 1] ~ hp, data = mtcars)
+  expect_error(standardise(m), regex = "indexed data")
+})
+
+
 # Transformations ---------------------------------------------------------
 test_that("transformations", {
   skip_if_not_installed("effectsize")
@@ -206,15 +229,14 @@ test_that("standardize non-Gaussian response", {
 # variables evaluated in the environment $$$ ------------------------------
 test_that("variables evaluated in the environment", {
   m <- lm(mtcars$mpg ~ mtcars$cyl + am, data = mtcars)
-  w <- capture_warnings(standardize(m))
-  expect_true(any(grepl("mtcars$mpg", w, fixed = TRUE)))
+  w <- capture_error(standardize(m))
+  expect_true(any(grepl("Using `$`", w, fixed = TRUE)))
 
   ## Note:
   # No idea why this is suddenly not giving a warning on older R versions.
   m <- lm(mtcars$mpg ~ mtcars$cyl + mtcars$am, data = mtcars)
-  warns <- capture_warnings(standardize(m))
-  expect_true(any(grepl("mtcars$mpg", warns, fixed = TRUE)))
-  expect_true(any(grepl("No variables", warns, fixed = TRUE)))
+  w <- capture_error(standardize(m))
+  expect_true(any(grepl("Using `$`", w, fixed = TRUE)))
 })