Merge branch 'main' into bump-version-requirement

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.17
+Version: 0.13.0.18
 Authors@R: c(
     person("Indrajeet", "Patil", , "[email protected]", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),

R/adjust.R

@@ -30,7 +30,7 @@
 #'
 #' @return A data frame comparable to `data`, with adjusted variables.
 #'
-#' @examplesIf require("bayestestR", quietly = TRUE) && require("rstanarm", quietly = TRUE) && require("gamm4", quietly = TRUE)
+#' @examplesIf all(insight::check_if_installed(c("bayestestR", "rstanarm", "gamm4"), quietly = TRUE))
 #' adjusted_all <- adjust(attitude)
 #' head(adjusted_all)
 #' adjusted_one <- adjust(attitude, effect = "complaints", select = "rating")
@@ -43,7 +43,7 @@
 #' }
 #'
 #' # Generate data
-#' data <- simulate_correlation(n = 100, r = 0.7)
+#' data <- bayestestR::simulate_correlation(n = 100, r = 0.7)
 #' data$V2 <- (5 * data$V2) + 20 # Add intercept
 #'
 #' # Adjust
@@ -75,12 +75,8 @@ adjust <- function(data,
                    ignore_case = FALSE,
                    regex = FALSE,
                    verbose = FALSE) {
-  if (!all(colnames(data) == make.names(colnames(data), unique = TRUE))) {
-    insight::format_warning(
-      "Bad column names (e.g., with spaces) have been detected which might create issues in many functions.",
-      "Please fix it (you can run `names(mydata) <- make.names(names(mydata))` for a quick fix)."
-    )
-  }
+  # make sure column names are syntactically valid
+  .check_dataframe_names(data, action = "error")
 
   # check for formula notation, convert to character vector
   if (inherits(effect, "formula")) {

R/data_rename.R

@@ -1,4 +1,5 @@
 #' @title Rename columns and variable names
+#' @name data_rename
 #'
 #' @description Safe and intuitive functions to rename variables or rows in
 #'   data frames. `data_rename()` will rename column names, i.e. it facilitates
@@ -8,7 +9,7 @@
 #'   possible pipe-workflow.
 #'
 #' @inheritParams extract_column_names
-#' @param data A data frame, or an object that can be coerced to a data frame.
+#' @param data A data frame.
 #' @param replacement Character vector. Can be one of the following:
 #'   - A character vector that indicates the new names of the columns selected
 #'     in `select`. `select` and `replacement` must be of the same length.
@@ -89,6 +90,10 @@ data_rename <- function(data,
                         verbose = TRUE,
                         pattern = NULL,
                         ...) {
+  # check for valid input
+  if (!is.data.frame(data)) {
+    insight::format_error("Argument `data` must be a data frame.")
+  }
   # If the user does data_rename(iris, pattern = "Sepal.Length", "length"),
   # then "length" is matched to select by position while it's the replacement
   # => do the switch manually

R/data_rescale.R

@@ -1,12 +1,13 @@
-#' Rescale Variables to a New Range
+#' @title Rescale Variables to a New Range
+#' @name rescale
 #'
+#' @description
 #' Rescale variables to a new range. Can also be used to reverse-score variables
 #' (change the keying/scoring direction), or to expand a range.
 #'
 #' @inheritParams categorize
 #' @inheritParams extract_column_names
 #' @inheritParams standardize.data.frame
-#'
 #' @param to Numeric vector of length 2 giving the new range that the variable
 #'   will have after rescaling. To reverse-score a variable, the range should
 #'   be given with the maximum value first. See examples.
@@ -27,6 +28,11 @@
 #'
 #' @inheritSection center Selection of variables - the `select` argument
 #'
+#' @seealso See [makepredictcall.dw_transformer()] for use in model formulas.
+#' @family transform utilities
+#'
+#' @return A rescaled object.
+#'
 #' @examples
 #' rescale(c(0, 1, 5, -5, -2))
 #' rescale(c(0, 1, 5, -5, -2), to = c(-5, 5))
@@ -62,14 +68,6 @@
 #' # Specify list of multipliers
 #' d <- data.frame(x = 5:15, y = 5:15)
 #' rescale(d, multiply = list(x = 1.1, y = 0.5))
-#'
-#' @inherit data_rename
-#'
-#' @return A rescaled object.
-#'
-#' @seealso See [makepredictcall.dw_transformer()] for use in model formulas.
-#' @family transform utilities
-#'
 #' @export
 rescale <- function(x, ...) {
   UseMethod("rescale")

R/data_rotate.R

@@ -17,6 +17,8 @@
 #'   names.
 #' @param verbose Toggle warnings.
 #'
+#' @inherit data_rename seealso
+#'
 #' @return A (rotated) data frame.
 #'
 #' @examples
@@ -36,7 +38,6 @@
 #' data_rotate(x, colnames = TRUE)
 #' data_rotate(x, colnames = "c")
 #'
-#' @inherit data_rename seealso
 #' @export
 data_rotate <- function(data, rownames = NULL, colnames = FALSE, verbose = TRUE) {
   # copy attributes

R/data_to_long.R

@@ -1,5 +1,7 @@
-#' Reshape (pivot) data from wide to long
+#' @title Reshape (pivot) data from wide to long
+#' @name data_to_long
 #'
+#' @description
 #' This function "lengthens" data, increasing the number of rows and decreasing
 #' the number of columns. This is a dependency-free base-R equivalent of
 #' `tidyr::pivot_longer()`.
@@ -31,6 +33,8 @@
 #' with `tidyr::pivot_longer()`. If both `select` and `cols` are provided, `cols`
 #' is used.
 #'
+#' @inherit data_rename seealso
+#'
 #' @details
 #' Reshaping data into long format usually means that the input data frame is
 #' in _wide_ format, where multiple measurements taken on the same subject are
@@ -58,7 +62,7 @@
 #' @return If a tibble was provided as input, `reshape_longer()` also returns a
 #' tibble. Otherwise, it returns a data frame.
 #'
-#' @examplesIf requireNamespace("psych") && requireNamespace("tidyr")
+#' @examplesIf all(insight::check_if_installed(c("psych", "tidyr"), quietly = TRUE))
 #' wide_data <- setNames(
 #'   data.frame(replicate(2, rnorm(8))),
 #'   c("Time1", "Time2")
@@ -122,7 +126,6 @@
 #'   values_to = "count"
 #' )
 #' head(even_longer_data)
-#' @inherit data_rename
 #' @export
 data_to_long <- function(data,
                          select = "all",

R/select_nse.R

@@ -199,12 +199,11 @@
 
 # small helper, to avoid duplicated code
 .action_if_not_found <- function(
-  x,
-  columns,
-  matches,
-  verbose,
-  ifnotfound
-) {
+    x,
+    columns,
+    matches,
+    verbose,
+    ifnotfound) {
   msg <- paste0(
     "Following variable(s) were not found: ",
     toString(x[is.na(matches)])

R/utils.R

@@ -47,6 +47,29 @@
 }
 
 
+#' Checks dataframes for syntactically valid column names
+#' Argument "action" can be "warning", "error", or "message".
+#'
+#' @keywords internal
+#' @noRd
+.check_dataframe_names <- function(x, action = "warning", verbose = TRUE) {
+  if (verbose && !all(colnames(x) == make.names(colnames(x), unique = TRUE))) {
+    insight::format_alert(
+      "Bad column names (e.g., with spaces) have been detected which might create issues in many functions.",
+      paste0(
+        "We recommend to rename following columns: ",
+        text_concatenate(
+          colnames(x)[colnames(x) != make.names(colnames(x), unique = TRUE)],
+          enclose = "`"
+        )
+      ),
+      "You can run `names(mydata) <- make.names(names(mydata))` or use `janitor::clean_names()` for a quick fix.", # nolint
+      type = action
+    )
+  }
+}
+
+
 #' Fuzzy grep, matches pattern that are close, but not identical
 #' @examples
 #' colnames(iris)

tests/testthat/test-adjust.R

@@ -28,3 +28,13 @@ test_that("adjust regex", {
     adjust(mtcars, select = "mpg")
   )
 })
+
+# select helpers ------------------------------
+test_that("adjust, invalid column names", {
+  data(iris)
+  colnames(iris)[1] <- "I am"
+  expect_error(
+    adjust(iris[c("I am", "Species")], multilevel = FALSE, bayesian = FALSE),
+    regex = "Bad column names"
+  )
+})

tests/testthat/test-data_rename.R

@@ -221,3 +221,11 @@ test_that("Argument `pattern` is deprecated", {
     fixed = TRUE
   )
 })
+
+test_that("works with lists", {
+  result <- list(x = 1, y = 2)
+  expect_error(
+    data_rename(result, select = names(result), replacement = c("a", "b")),
+    regex = "must be a data frame"
+  )
+})