copy_chapter() copies a chapter of the mirtverse online book into the
course's chapters/ folder so you can edit it. new_chapter() starts a
blank chapter with the same headings as the book's chapters ("Learning
goals", "Key terms", "Example 1", "Example 2", "Your turn", "In the lab",
"Further reading"). swap_chapter_data() replaces the code that loads an
example's data.
Usage
copy_chapter(id, course = ".", from = NULL, overwrite = FALSE)
new_chapter(
id,
course = ".",
title = NULL,
data_code = NULL,
overwrite = FALSE
)
swap_chapter_data(chapter, chunk = NULL, code)
book_chapters()Arguments
- id
the chapter's id. For
copy_chapter(), one ofbook_chapters()$id; fornew_chapter(), a new id (letters, digits, - and _).- course
the course folder.
- from
where to copy from: A local copy of the book's source folder (
book/in the package's GitHub repository), orNULL(the default) to download the chapter from GitHub.- overwrite
replace an existing file.
copy_chapter()also copies the book's_common.R(packages, chunk options and seed, sourced before each chapter) intochapters/the first time, andcheck_material()runs it before a chapter's chunks.- title
the chapter title.
- data_code
R code that loads the examples' data. It should define
resp, a data frame of scored item responses. Defaults to the LSAT7 data from mirt.- chapter
the chapter's
.Rmdfile.- chunk
the label of the data chunk to replace, for example
"data-dif-1".NULL(the default) replaces everydata-chunk.- code
the new R code for the chunk(s).
Value
copy_chapter() and new_chapter() return the chapter's path,
invisibly. book_chapters() returns a tibble with the id, file and
title of each book chapter.
Details
Each example in a book chapter opens with a chunk labelled
data-<chapter>-<n> that loads its data, and the rest of the example uses
what that chunk defines. To use your own data, rewrite that chunk; the
easiest way is swap_chapter_data().
Examples
book_chapters()
#> # A tibble: 20 × 3
#> id file title
#> <chr> <chr> <chr>
#> 1 measurement 01-measurement.Rmd Measurement, scoring and classical item…
#> 2 irt-models 02-irt-models.Rmd From classical test theory to IRT
#> 3 estimation 03-estimation.Rmd Estimation and comparing models
#> 4 dimensionality 04-dimensionality.Rmd Dimensionality and local independence
#> 5 fit 05-fit.Rmd Item fit, person fit and item quality
#> 6 information 06-information.Rmd Information, precision and reliability
#> 7 scoring 07-scoring.Rmd Scoring people
#> 8 polytomous 08-polytomous.Rmd Polytomous items and open-ended respons…
#> 9 dif 09-dif.Rmd Differential item functioning and fairn…
#> 10 linking 10-linking.Rmd Linking and equating
#> 11 banks-cat 11-banks-cat.Rmd Item banks, test assembly and adaptive …
#> 12 reporting 12-reporting.Rmd Cut scores, reporting and communicating…
#> 13 ml-lens 13-ml-lens.Rmd Machine learning through an IRT lens
#> 14 item-text 14-item-text.Rmd What item text tells us
#> 15 aig 15-aig.Rmd Generating items
#> 16 auto-scoring 16-auto-scoring.Rmd Automated scoring
#> 17 llms 17-llms.Rmd Large language models as a colleague
#> 18 ai-validity 18-ai-validity.Rmd Validity, fairness and governance of AI
#> 19 datasets 90-datasets.Rmd Appendix: the datasets
#> 20 adapting 91-adapting.Rmd Appendix: adapting the book
course <- file.path(tempdir(), "chapter-demo")
ch <- new_chapter("my-week", course, title = "Our own data",
data_code = "resp <- expand.table(LSAT7)")
swap_chapter_data(ch, code = "resp <- expand.table(LSAT6)")
if (FALSE) { # \dontrun{
copy_chapter("dif", course) # downloads from GitHub
} # }