Deprecate_alias

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.10.0.3
+Version: 0.10.0.4
 Authors@R: c(
     person("Indrajeet", "Patil", , "[email protected]", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531", Twitter = "@patilindrajeets")),
@@ -69,7 +69,7 @@ Suggests:
     tidyr,
     withr
 Remotes:
-    easystats/modelbased
+    easystats/modelbased, easystats/insight
 VignetteBuilder: 
     knitr
 Encoding: UTF-8

NAMESPACE

@@ -272,7 +272,7 @@ export(distribution_coef_var)
 export(distribution_mode)
 export(empty_columns)
 export(empty_rows)
-export(find_columns)
+export(extract_column_names)
 export(format_text)
 export(get_columns)
 export(kurtosis)

NEWS.md

@@ -1,5 +1,21 @@
 # datawizard 0.10.1
 
+BREAKING CHANGES
+
+* Arguments named `group` or `group_by` are deprecated and will be removed
+  in a future release.
+  Please use `by` instead. This affects the following functions in *datawizard*.
+
+  * `data_partition()`
+  * `demean()` and `degroup()`
+  * `means_by_group()`
+  * `rescale_weights()`
+
+* Following aliases are deprecated and will be removed in a future release:
+
+  * `get_columns()`, use `data_select()` instead.
+  * `data_find()` and `find_columns()`, use `extract_column_names()` instead.
+
 CHANGES
 
 * `recode_into()` is more relaxed regarding checking the type of `NA` values.

R/adjust.R

@@ -25,12 +25,12 @@
 #'   re-added. This avoids the centering around 0 that happens by default
 #'   when regressing out another variable (see the examples below for a
 #'   visual representation of this).
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @inheritParams standardize
 #'
 #' @return A data frame comparable to `data`, with adjusted variables.
 #'
 #' @examplesIf require("bayestestR", quietly = TRUE) && require("rstanarm", quietly = TRUE) && require("gamm4", quietly = TRUE)
 #' adjusted_all <- adjust(attitude)
 #' head(adjusted_all)
 #' adjusted_one <- adjust(attitude, effect = "complaints", select = "rating")

R/assign_labels.R

@@ -14,7 +14,7 @@
 #' `x`, the right-hand side (RHS) the associated value label. Non-matching
 #' labels are omitted.
 #' @param ... Currently not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @inheritSection center Selection of variables - the `select` argument
 #'

R/categorize.R

@@ -45,7 +45,7 @@
 #'   variables are appended with new column names (using the defined suffix) to
 #'   the original data frame.
 #' @param ... not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @inherit data_rename seealso
 #'

R/center.R

@@ -29,7 +29,7 @@
 #'   order, unless a named vector is given. In this case, names are matched
 #'   against the names of the selected variables.
 #' @param ... Currently not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @inheritParams standardize
 #'
 #' @section Selection of variables - the `select` argument:
@@ -118,7 +118,7 @@
     center <- TRUE
   }
 
   args <- .process_std_center(x, weights, robust, verbose, reference, center, scale = NULL)
   dot_args <- list(...)
 
   if (is.null(args)) {
@@ -197,7 +197,7 @@
   )
 
   # process arguments
   args <- .process_std_args(x, select, exclude, weights, append,
     append_suffix = "_c", keep_factors = force, remove_na, reference,
     .center = center, .scale = NULL
   )
@@ -249,7 +249,7 @@
     verbose = verbose
   )
 
   args <- .process_grouped_df(
     x, select, exclude, append,
     append_suffix = "_c",
     reference, weights, keep_factors = force

R/convert_na_to.R

@@ -145,7 +145,7 @@
 #' @param replace_num Value to replace `NA` when variable is of type numeric.
 #' @param replace_char Value to replace `NA` when variable is of type character.
 #' @param replace_fac Value to replace `NA` when variable is of type factor.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @rdname convert_na_to
 #' @export
@@ -160,7 +160,7 @@
                                      regex = FALSE,
                                      verbose = TRUE,
                                      ...) {
   data <- x
   select_nse <- .select_nse(
     select,
     data,

R/convert_to_na.R

@@ -12,7 +12,7 @@
 #' @param drop_levels Logical, for factors, when specific levels are replaced
 #'   by `NA`, should unused levels be dropped?
 #' @param ... Not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @return
 #' `x`, where all values in `na` are converted to `NA`.

R/data_addprefix.R

@@ -1,5 +1,5 @@
 #' @rdname data_rename
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @examples
 #' # Add prefix / suffix to all columns
 #' head(data_addprefix(iris, "NEW_"))

R/data_codebook.R

@@ -22,7 +22,7 @@
 #' @param line_padding For HTML tables, the distance (in pixel) between lines.
 #' @param row_color For HTML tables, the fill color for odd rows.
 #' @inheritParams standardize.data.frame
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @return A formatted data frame, summarizing the content of the data frame.
 #' Returned columns include the column index of the variables in the original
@@ -232,9 +232,9 @@
 
     # add proportions, but not for ranges, since these are always 100%
     if (is_range) {
-      proportions <- ""
+      frq_proportions <- ""
     } else {
-      proportions <- sprintf("%.1f%%", round(100 * (frq / sum(frq)), 1))
+      frq_proportions <- sprintf("%.1f%%", round(100 * (frq / sum(frq)), 1))
     }
 
     # make sure we have not too long rows, e.g. for variables that
@@ -245,9 +245,9 @@
     }
     if (length(frq) > max_values) {
       frq <- frq[1:max_values]
-      proportions <- proportions[1:max_values]
+      frq_proportions <- frq_proportions[1:max_values]
       frq[max_values] <- NA
-      proportions[max_values] <- NA
+      frq_proportions[max_values] <- NA
     }
     if (length(values) > max_values) {
       values <- values[1:max_values]
@@ -273,7 +273,7 @@
       values,
       value_labels,
       frq,
-      proportions,
+      proportions = frq_proportions,
       stringsAsFactors = FALSE
     ))
 
@@ -347,12 +347,12 @@
     x$Prop[x$Prop == "NA" | is.na(x$Prop)] <- ""
     # align only for text format
     if (identical(format, "text")) {
-      x$Prop[x$Prop != ""] <- format(x$Prop[x$Prop != ""], justify = "right")
+      x$Prop[x$Prop != ""] <- format(x$Prop[x$Prop != ""], justify = "right") # nolint
     }
-    x[["N"]][x$Prop != ""] <- sprintf(
+    x[["N"]][x$Prop != ""] <- sprintf( # nolint
       "%s (%s)",
-      as.character(x[["N"]][x$Prop != ""]),
-      x$Prop[x$Prop != ""]
+      as.character(x[["N"]][x$Prop != ""]), # nolint
+      x$Prop[x$Prop != ""] # nolint
     )
     x$Prop <- NULL
   }
@@ -388,7 +388,7 @@
   # since we have each value at its own row, the HTML table contains
   # horizontal borders for each cell/row. We want to remove those borders
   # from rows that actually belong to one variable
-  separator_lines <- which(duplicated(x$.row_id) & x$N == "")
+  separator_lines <- which(duplicated(x$.row_id) & x$N == "") # nolint
   # remove separator lines, as we don't need these for HTML tables
   x <- x[-separator_lines, ]
   # check row IDs, and find odd rows
@@ -405,7 +405,7 @@
   out <- gt::tab_style(
     out,
     style = list(gt::cell_borders(sides = "top", style = "hidden")),
-    locations = gt::cells_body(rows = which(x$ID == ""))
+    locations = gt::cells_body(rows = which(x$ID == "")) # nolint
   )
   # highlight odd rows
   if (!is.null(row_color)) {
@@ -466,5 +466,5 @@
     N = "r"
   )
   align <- align[colnames(x)]
   paste0(unname(align), collapse = "")
 }

R/data_duplicated.R

@@ -7,7 +7,7 @@
 #' values for that row, to help in the decision-making when
 #' selecting which duplicates to keep.
 #'
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @keywords duplicates
 #' @export

R/data_extract.R

@@ -26,7 +26,7 @@
 #' @param verbose Toggle warnings.
 #' @param ... For use by future methods.
 #'
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @details `data_extract()` can be used to select multiple variables or pull a
 #' single variable from a data frame. Thus, the return value is by default not
@@ -134,7 +134,7 @@
   }
 
   # we definitely should have a vector here when name not NULL
   if (!is.null(name)) {
     # if name indicates a variable, extract values for naming now
     if (length(name) == 1L) {
       name <- data[[name]]

R/data_group.R

@@ -6,7 +6,7 @@
 #' grouping information from a grouped data frame.
 #'
 #' @param data A data frame
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @return A grouped data frame, i.e. a data frame with additional information
 #' about the grouping structure saved as attributes.
@@ -41,9 +41,9 @@
     verbose = verbose
   )
   # create grid with combinations of all levels
   grid <- as.data.frame(expand.grid(lapply(data[select], unique)))
   # sort grid
   grid <- grid[do.call(order, grid), , drop = FALSE]
 
   .rows <- lapply(seq_len(nrow(grid)), function(i) {
     as.integer(data_match(

R/data_partition.R

@@ -2,19 +2,20 @@
 #'
 #' Creates data partitions (for instance, a training and a test set) based on a
 #' data frame that can also be stratified (i.e., evenly spread a given factor)
-#' using the `group` argument.
+#' using the `by` argument.
 #'
 #' @inheritParams data_rename
 #' @param proportion Scalar (between 0 and 1) or numeric vector, indicating the
 #'   proportion(s) of the training set(s). The sum of `proportion` must not be
 #'   greater than 1. The remaining part will be used for the test set.
-#' @param group A character vector indicating the name(s) of the column(s) used
+#' @param by A character vector indicating the name(s) of the column(s) used
 #'   for stratified partitioning.
 #' @param seed A random number generator seed. Enter an integer (e.g. 123) so
 #'   that the random sampling will be the same each time you run the function.
 #' @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
@@ -28,7 +29,7 @@
 #' nrow(out$p_0.9)
 #'
 #' # Stratify by group (equal proportions of each species)
-#' out <- data_partition(iris, proportion = 0.9, group = "Species")
+#' out <- data_partition(iris, proportion = 0.9, by = "Species")
 #' out$test
 #'
 #' # Create multiple partitions
@@ -38,21 +39,28 @@
 #' # Create multiple partitions, stratified by group - 30% equally sampled
 #' # from species in first training set, 50% in second training set and
 #' # remaining 20% equally sampled from each species in test set.
-#' out <- data_partition(iris, proportion = c(0.3, 0.5), group = "Species")
+#' out <- data_partition(iris, proportion = c(0.3, 0.5), by = "Species")
 #' lapply(out, function(i) table(i$Species))
 #'
 #' @inherit data_rename seealso
 #' @export
 data_partition <- function(data,
                            proportion = 0.7,
-                           group = NULL,
+                           by = NULL,
                            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.")
   }
@@ -91,12 +99,12 @@ data_partition <- function(data,
 
   # Create list of data groups. We generally lapply over list of
   # sampled row-id's by group, thus, we even create a list if not grouped.
-  if (is.null(group)) {
+  if (is.null(by)) {
     indices_list <- list(seq_len(nrow(data)))
   } else {
     # else, split by group(s) and extract row-ids per group
     indices_list <- lapply(
-      split(data, data[group]),
+      split(data, data[by]),
       data_extract,
       select = row_id,
       as_data_frame = FALSE
@@ -130,7 +138,7 @@ data_partition <- function(data,
   })
 
   # we need to move all list elements one level higher.
-  if (is.null(group)) {
+  if (is.null(by)) {
     training_sets <- training_sets[[1]]
   } else {
     # for grouped training sets, we need to row-bind all sampled training

R/data_peek.R

@@ -9,7 +9,7 @@
 #' @param width Maximum width of line length to display. If `NULL`, width will
 #' be determined using `options()$width`.
 #' @param ... not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @note To show only specific or a limited number of variables, use the
 #' `select` argument, e.g. `select = 1:5` to show only the first five variables.

R/data_relocate.R

@@ -15,7 +15,7 @@
 #'   character vector, indicating the name of the destination column, or a
 #'   numeric value, indicating the index number of the destination column.
 #'   If `-1`, will be added before or after the last column.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @inheritParams data_rename
 #'
 #' @inherit data_rename seealso
@@ -108,7 +108,7 @@
     }
     where <- min(match(before, data_cols))
     position <- c(setdiff(position, where), where)
   } else if (!is.null(after)) {
     after <- after[after %in% data_cols][1] # Take first that exists (if vector is supplied)
     if (length(after) != 1 || is.na(after)) {
       # guess the misspelled column

R/data_remove.R

@@ -1,4 +1,4 @@
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @rdname data_relocate
 #' @examples
 #' # Remove columns

R/data_replicate.R

@@ -13,7 +13,7 @@
 #' provided in `expand` are removed from the data frame. If `FALSE` and `expand`
 #' contains missing values, the function will throw an error.
 #' @param ... Currently not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @return A dataframe with each row replicated as many times as defined in `expand`.
 #'

R/data_rescale.R

@@ -4,7 +4,7 @@
 #' (change the keying/scoring direction), or to expand a range.
 #'
 #' @inheritParams categorize
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #' @inheritParams standardize.data.frame
 #'
 #' @param to Numeric vector of length 2 giving the new range that the variable

R/data_reverse.R

@@ -12,7 +12,7 @@
 #'   usually only makes sense when factor levels are numeric, not characters.
 #' @param ... Arguments passed to or from other methods.
 #' @inheritParams categorize
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @inheritSection center Selection of variables - the `select` argument
 #'

R/data_select.R

@@ -1,6 +1,6 @@
-#' @rdname find_columns
+#' @rdname extract_column_names
 #' @export
-get_columns <- function(data,
+data_select <- function(data,
                         select = NULL,
                         exclude = NULL,
                         ignore_case = FALSE,
@@ -34,6 +34,22 @@ get_columns <- function(data,
 }
 
 
-#' @rdname find_columns
 #' @export
-data_select <- get_columns
+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,
+    ...
+  )
+}

R/data_separate.R

@@ -42,7 +42,7 @@
 #' @param convert_na Logical, if `TRUE`, character `"NA"` values are converted
 #' into real `NA` values.
 #' @param ... Currently not used.
-#' @inheritParams find_columns
+#' @inheritParams extract_column_names
 #'
 #' @seealso [`data_unite()`]
 #'