Merge branch 'main' of https://github.com/jospueyo/janitor

DESCRIPTION

@@ -53,4 +53,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.0

NEWS.md

@@ -28,7 +28,7 @@ These are all minor breaking changes resulting from enhancements and are not exp
 
 * Remove dplyr verbs superseded in dplyr 1.0.0 (#547, @olivroy)
 
-* Restyle the package and vignettes according to the [tidyverse style guide](style.tidyverse.org) (#548, olivroy)
+* Restyle the package and vignettes according to the [tidyverse style guide](https://style.tidyverse.org) (#548, olivroy)
 
 # janitor 2.2.0 (2023-02-02)
 

R/adorn_ns.R

@@ -1,14 +1,25 @@
 #' Add underlying Ns to a tabyl displaying percentages.
 #'
-#' This function adds back the underlying Ns to a `tabyl` whose percentages were calculated using `adorn_percentages()`, to display the Ns and percentages together.  You can also call it on a non-tabyl data.frame to which you wish to append Ns.
+#' This function adds back the underlying Ns to a `tabyl` whose percentages were
+#' calculated using [adorn_percentages()], to display the Ns and percentages together.
+#' You can also call it on a non-tabyl data.frame to which you wish to append Ns.
 #'
-#' @param dat a data.frame of class `tabyl` that has had `adorn_percentages` and/or `adorn_pct_formatting` called on it.  If given a list of data.frames, this function will apply itself to each data.frame in the list (designed for 3-way `tabyl` lists).
-#' @param position should the N go in the front, or in the rear, of the percentage?
-#' @param ns the Ns to append.  The default is the "core" attribute of the input tabyl `dat`, where the original Ns of a two-way `tabyl` are stored.  However, if your Ns are stored somewhere else, or you need to customize them beyond what can be done with `format_func`, you can supply them here.
-#' @param format_func a formatting function to run on the Ns.  Consider defining with [base::format()].
-#' @param ... columns to adorn.  This takes a tidyselect specification.  By default, all columns are adorned except for the first column and columns not of class `numeric`, but this allows you to manually specify which columns should be adorned, for use on a data.frame that does not result from a call to `tabyl`.
+#' @param dat A data.frame of class `tabyl` that has had `adorn_percentages` and/or
+#'   `adorn_pct_formatting` called on it.  If given a list of data.frames,
+#'   this function will apply itself to each data.frame in the list (designed for 3-way `tabyl` lists).
+#' @param position Should the N go in the front, or in the rear, of the percentage?
+#' @param ns The Ns to append.  The default is the "core" attribute of the input tabyl
+#'   `dat`, where the original Ns of a two-way `tabyl` are stored. However, if your Ns
+#'   are stored somewhere else, or you need to customize them beyond what can be done
+#'   with `format_func`, you can supply them here.
+#' @param format_func A formatting function to run on the Ns. Consider defining
+#'   with [base::format()].
+#' @param ... Columns to adorn. This takes a tidyselect specification.  By default,
+#'   all columns are adorned except for the first column and columns not of class
+#'   `numeric`, but this allows you to manually specify which columns should be adorned,
+#'   for use on a data.frame that does not result from a call to `tabyl`.
 #'
-#' @return a data.frame with Ns appended
+#' @return A `data.frame` with Ns appended
 #' @export
 #' @examples
 #' mtcars %>%

R/adorn_percentages.R

@@ -1,13 +1,21 @@
 #' Convert a data.frame of counts to percentages.
 #'
-#' This function defaults to excluding the first column of the input data.frame, assuming that it contains a descriptive variable, but this can be overridden by specifying the columns to adorn in the `...` argument.
+#' This function defaults to excluding the first column of the input data.frame,
+#' assuming that it contains a descriptive variable, but this can be overridden
+#' by specifying the columns to adorn in the `...` argument.
 #'
-#' @param dat a `tabyl` or other data.frame with a tabyl-like layout.  If given a list of data.frames, this function will apply itself to each data.frame in the list (designed for 3-way `tabyl` lists).
-#' @param denominator the direction to use for calculating percentages.  One of "row", "col", or "all".
-#' @param na.rm should missing values (including NaN) be omitted from the calculations?
-#' @param ... columns to adorn.  This takes a tidyselect specification.  By default, all numeric columns (besides the initial column, if numeric) are adorned, but this allows you to manually specify which columns should be adorned, for use on a data.frame that does not result from a call to `tabyl`.
+#' @param dat A `tabyl` or other data.frame with a tabyl-like layout.
+#'   If given a list of data.frames, this function will apply itself to each
+#'   `data.frame` in the list (designed for 3-way `tabyl` lists).
+#' @param denominator The direction to use for calculating percentages.
+#'   One of "row", "col", or "all".
+#' @param na.rm should missing values (including `NaN`) be omitted from the calculations?
+#' @param ... columns to adorn. This takes a <[`tidy-select`][dplyr::dplyr_tidy_select]>
+#'   specification. By default, all numeric columns (besides the initial column, if numeric)
+#'   are adorned, but this allows you to manually specify which columns should
+#'   be adorned, for use on a `data.frame` that does not result from a call to [tabyl()].
 #'
-#' @return Returns a data.frame of percentages, expressed as numeric values between 0 and 1.
+#' @return A `data.frame` of percentages, expressed as numeric values between 0 and 1.
 #' @export
 #' @examples
 #'

R/adorn_rounding.R

@@ -1,16 +1,29 @@
 #' Round the numeric columns in a data.frame.
 #'
 #' @description
-#' Can run on any data.frame with at least one numeric column.  This function defaults to excluding the first column of the input data.frame, assuming that it contains a descriptive variable, but this can be overridden by specifying the columns to round in the `...` argument.
+#' Can run on any `data.frame` with at least one numeric column.
+#' This function defaults to excluding the first column of the input data.frame,
+#' assuming that it contains a descriptive variable, but this can be overridden by
+#' specifying the columns to round in the `...` argument.
 #'
-#' If you're formatting percentages, e.g., the result of `adorn_percentages()`, use `adorn_pct_formatting()` instead.  This is a more flexible variant for ad-hoc usage.  Compared to `adorn_pct_formatting()`, it does not multiply by 100 or pad the numbers with spaces for alignment in the results data.frame.   This function retains the class of numeric input columns.
+#' If you're formatting percentages, e.g., the result of [adorn_percentages()],
+#' use [adorn_pct_formatting()] instead.  This is a more flexible variant for ad-hoc usage.
+#' Compared to `adorn_pct_formatting()`, it does not multiply by 100 or pad the
+#' numbers with spaces for alignment in the results `data.frame`.
+#' This function retains the class of numeric input columns.
 #'
-#' @param dat a `tabyl` or other data.frame with similar layout.  If given a list of data.frames, this function will apply itself to each data.frame in the list (designed for 3-way `tabyl` lists).
-#' @param digits how many digits should be displayed after the decimal point?
-#' @param rounding method to use for rounding - either "half to even", the base R default method, or "half up", where 14.5 rounds up to 15.
-#' @param ... columns to adorn.  This takes a tidyselect specification.  By default, all numeric columns (besides the initial column, if numeric) are adorned, but this allows you to manually specify which columns should be adorned, for use on a data.frame that does not result from a call to `tabyl`.
+#' @param dat A `tabyl` or other `data.frame` with similar layout.
+#'   If given a list of data.frames, this function will apply itself to each
+#'   `data.frame` in the list (designed for 3-way `tabyl` lists).
+#' @param digits How many digits should be displayed after the decimal point?
+#' @param rounding Method to use for rounding - either "half to even"
+#'   (the base R default method), or "half up", where 14.5 rounds up to 15.
+#' @param ... Columns to adorn.  This takes a tidyselect specification.
+#'   By default, all numeric columns (besides the initial column, if numeric)
+#'   are adorned, but this allows you to manually specify which columns should
+#'   be adorned, for use on a data.frame that does not result from a call to `tabyl`.
 #'
-#' @return Returns the data.frame with rounded numeric columns.
+#' @return The `data.frame` with rounded numeric columns.
 #' @export
 #' @examples
 #'
@@ -54,7 +67,9 @@ adorn_rounding <- function(dat, digits = 1, rounding = "half to even", ...) {
     }
     numeric_cols <- which(vapply(dat, is.numeric, logical(1)))
     non_numeric_cols <- setdiff(1:ncol(dat), numeric_cols)
-    numeric_cols <- setdiff(numeric_cols, 1) # assume 1st column should not be included so remove it from numeric_cols. Moved up to this line so that if only 1st col is numeric, the function errors
+    # assume 1st column should not be included so remove it from numeric_cols.
+    # Moved up to this line so that if only 1st col is numeric, the function errors
+    numeric_cols <- setdiff(numeric_cols, 1)
 
     if (rlang::dots_n(...) == 0) {
       cols_to_round <- numeric_cols

R/adorn_title.R

@@ -1,13 +1,30 @@
-#' @title Add column name to the top of a two-way tabyl.
+#' Add column name to the top of a two-way tabyl.
 #'
-#' @description
-#' This function adds the column variable name to the top of a `tabyl` for a complete display of information.  This makes the tabyl prettier, but renders the data.frame less useful for further manipulation.
+#' This function adds the column variable name to the top of a `tabyl` for a
+#' complete display of information.  This makes the tabyl prettier, but renders
+#' the `data.frame` less useful for further manipulation.
 #'
-#' @param dat a data.frame of class `tabyl` or other data.frame with a tabyl-like layout.  If given a list of data.frames, this function will apply itself to each data.frame in the list (designed for 3-way `tabyl` lists).
-#' @param placement whether the column name should be added to the top of the tabyl in an otherwise-empty row `"top"` or appended to the already-present row name variable (`"combined"`).  The formatting in the `"top"` option has the look of base R's `table()`; it also wipes out the other column names, making it hard to further use the data.frame besides formatting it for reporting.  The `"combined"` option is more conservative in this regard.
-#' @param row_name (optional) default behavior is to pull the row name from the attributes of the input `tabyl` object.  If you wish to override that text, or if your input is not a `tabyl`, supply a string here.
-#' @param col_name (optional) default behavior is to pull the column_name from the attributes of the input `tabyl` object.  If you wish to override that text, or if your input is not a `tabyl`, supply a string here.
-#' @return the input tabyl, augmented with the column title.  Non-tabyl inputs that are of class `tbl_df` are downgraded to basic data.frames so that the title row prints correctly.
+#' The `placement` argument indicates whether the column name should be added to
+#' the `top` of the tabyl in an otherwise-empty row `"top"` or appended to the
+#' already-present row name variable (`"combined"`). The formatting in the `"top"`
+#' option has the look of base R's `table()`; it also wipes out the other column
+#' names, making it hard to further use the `data.frame` besides formatting it for reporting.
+#' The `"combined"` option is more conservative in this regard.
+#'
+#' @param dat A `data.frame` of class `tabyl` or other `data.frame` with a tabyl-like layout.
+#'   If given a list of data.frames, this function will apply itself to each `data.frame`
+#'   in the list (designed for 3-way `tabyl` lists).
+#' @param placement The title placement, one of `"top"`, or `"combined"`.
+#'   See **Details** for more information.
+#' @param row_name (optional) default behavior is to pull the row name from the
+#'   attributes of the input `tabyl` object.  If you wish to override that text,
+#'   or if your input is not a `tabyl`, supply a string here.
+#' @param col_name (optional) default behavior is to pull the column_name from
+#'   the attributes of the input `tabyl` object.  If you wish to override that text,
+#'   or if your input is not a `tabyl`, supply a string here.
+#' @return The input `tabyl`, augmented with the column title.  Non-tabyl inputs
+#'   that are of class `tbl_df` are downgraded to basic data.frames so that the
+#'   title row prints correctly.
 #'
 #' @export
 #' @examples
@@ -38,12 +55,14 @@ adorn_title <- function(dat, placement = "top", row_name, col_name) {
 
     if (inherits(dat, "tabyl")) {
       if (attr(dat, "tabyl_type") == "one_way") {
-        warning("adorn_title is meant for two-way tabyls, calling it on a one-way tabyl may not yield a meaningful result")
+        warning(
+          "adorn_title is meant for two-way tabyls, calling it on a one-way tabyl may not yield a meaningful result"
+        )
       }
     }
     if (missing(col_name)) {
       if (!inherits(dat, "tabyl")) {
-        stop("When input is not a data.frame of class tabyl, a value must be specified for the col_name argument")
+        stop("When input is not a data.frame of class tabyl, a value must be specified for the col_name argument.")
       }
       col_var <- attr(dat, "var_names")$col
     } else {
@@ -63,13 +82,15 @@ adorn_title <- function(dat, placement = "top", row_name, col_name) {
       if (inherits(dat, "tabyl")) {
         row_var <- attr(dat, "var_names")$row
       } else {
-        row_var <- names(dat)[1] # for non-tabyl input, if no row_name supplied, use first existing name
+        # for non-tabyl input, if no row_name supplied, use first existing name
+        row_var <- names(dat)[1]
       }
     }
 
 
     if (placement == "top") {
-      dat[, ] <- lapply(dat[, ], as.character) # to handle factors, problematic in first column and at bind_rows.
+      # to handle factors, problematic in first column and at bind_rows.
+      dat[, ] <- lapply(dat[, ], as.character)
       # Can't use mutate_all b/c it strips attributes
       top <- dat[1, ]
 
@@ -82,8 +103,10 @@ adorn_title <- function(dat, placement = "top", row_name, col_name) {
       out <- dat
       names(out)[1] <- paste(row_var, col_var, sep = "/")
     }
-    if (inherits(out, "tbl_df")) { # "top" text doesn't print if input (and thus the output) is a tibble
-      out <- as.data.frame(out) # but this prints row numbers, so don't apply to non-tbl_dfs like tabyls
+    # "top" text doesn't print if input (and thus the output) is a tibble
+    if (inherits(out, "tbl_df")) {
+      # but this prints row numbers, so don't apply to non-tbl_dfs like tabyls
+      out <- as.data.frame(out)
     }
     out
   }