- add aggregate_and_document_scale re #1

- update docs

Author: rubenarslan

NAMESPACE

@@ -5,6 +5,7 @@ S3method(summary,labelled)
 S3method(summary,labelled_spss)
 S3method(zap_attributes,data.frame)
 S3method(zap_attributes,default)
+export(aggregate_and_document_scale)
 export(asis_knit_child)
 export(codebook)
 export(codebook_component_scale)

R/codebook.R

@@ -273,6 +273,15 @@ codebook_items <- function(results, indent = "##") {
     cache.path = paste0(knitr::opts_chunk$get("cache.path"), "overview_")
   )
   metadata_table <- codebook_table(results)
+  metadata_table <- dplyr::mutate(metadata_table,
+         name = paste0('<a href="#', safe_name(.data$name), '">',
+                       recursive_escape(.data$name), '</a>'))
+  # bit ugly to suppress warnings here, but necessary for escaping whatever
+  # columns there may be
+  suppressWarnings(
+    metadata_table <- dplyr::mutate_at(metadata_table, dplyr::vars(
+    dplyr::one_of("label", "scale_item_names", "value_labels", "showif")),
+    dplyr::funs(recursive_escape)) )
 
   asis_knit_child(require_file("_codebook_items.Rmd"), options = options)
 }

R/correct_attributes.R

@@ -272,3 +272,46 @@ zap_label.default <- function(x) {
   attr(x, "label") <- NULL
   x
 }
+
+
+
+#' Aggregate variables and remember which variables this were
+#'
+#' The resulting variables will have the attribute `scale_item_names` containing
+#' the basis for aggregation. Its `label` attribute will refer to the common stem of the
+#' aggregated variable names (if any), the number of variables, and the
+#' aggregation function.
+#'
+#' @param items data.frame of the items that should be aggregated
+#' @param fun aggregation function, defaults to rowMeans with na.rm = FALSE
+#' @param stem common stem for the variables, specify if it should not be auto-detected
+#' as the longest common stem of the variable names
+#' @export
+#' @examples
+#' testdf <- data.frame(bfi_neuro_1 = rnorm(20), bfi_neuro_2 = rnorm(20),
+#'                     bfi_neuro_3R = rnorm(20), age = rpois(20, 30))
+#' item_names <- c('bfi_neuro_1', 'bfi_neuro_2', 'bfi_neuro_3R')
+#' testdf$bfi_neuro <- aggregate_and_document_scale(testdf[, item_names])
+#' testdf$bfi_neuro
+aggregate_and_document_scale = function(items, fun = rowMeans, stem = NULL) {
+  new_scale <- fun(items)
+  item_names <- names(items)
+  attributes(new_scale)$scale_item_names <- item_names
+
+  # find longest common stem
+  if (is.null(stem)) {
+    max_len <- min(nchar(item_names))
+    for (l in max_len:0) {
+      stem <- unique(stringr::str_sub(item_names, 1, l))
+      if (length(stem) == 1) break;
+    }
+  }
+  # string trimming for idiots
+  if (nchar(stem)) {
+    stem <- stringr::str_match(stem, "^(.+?)_?$")[, 2]
+  }
+
+  attributes(new_scale)$label <- paste(ncol(items), stem, "items aggregated by",
+                                      deparse(substitute(fun)))
+  new_scale
+}

_pkgdown.yml

@@ -20,6 +20,7 @@ reference:
   - '`detect_scales`'
   - '`compute_reliabilities`'
   - '`rescue_attributes`'
+  - '`aggregate_and_document_scale`'
 - title: Prepare data for non-codebook stuff
   desc: Functions to remove attributes that might confuse other packages
   contents: