In friendly/vcdExtra: 'vcd' Extensions and Additions

knitr::opts_chunk$set(echo = FALSE,
                      message = FALSE)

vcdExtra datasets, by topic

The vcdExtra package contains r nrow(vcdExtra::datasets(package="vcdExtra")) datasets illustrating various methods of categorical data analysis and visualization performed with the package. These have been classified according to the method of analysis and are presented here with links to the help file for each.

library(dplyr)
library(tidyr)
library(readxl)
#library(here)

#setwd(here())
dsets_tagged <- read_excel(here::here("extra", "vcdExtra-datasets.xlsx"), 
                           sheet="vcdExtra-datasets")
#' The `tags` sheet contain the `tag` and a `topic` description
tags <- read_excel(here::here("extra", "vcdExtra-datasets.xlsx"), 
                   sheet="tags")

dsets_tagged <- dsets_tagged |>
  dplyr::select(-Title, -dim) |>
  dplyr::rename(dataset = Item)

#' to invert the table, need to split tags into separate observations
dset_split <- dsets_tagged |>
  tidyr::separate_longer_delim(tags, delim = ";") |>
  dplyr::mutate(tag = stringr::str_trim(tags)) |>
  dplyr::select(-tags)

#' ## collapse the rows for the same tag
tag_dset <- dset_split |>
  arrange(tag) |>
  dplyr::group_by(tag) |>
  dplyr::summarise(datasets = paste(dataset, collapse = "; ")) |> ungroup()

# join with tag descriptions
tag_dset <- tag_dset |>
  left_join(tags, by = "tag") |>
  dplyr::relocate(topic, .after = tag)

add_links <- function(dsets, 
                      sep = "; ") {

  names <- stringr::str_split_1(dsets, sep)
  names <- glue::glue("[{names}](help({names}))")
  glue::glue_collapse(names, sep = sep)
}

tag_dset |>
  dplyr::select(-tag) |>
  dplyr::mutate(datasets = purrr::map(datasets, add_links)) |>
  knitr::kable()