improve tidy documentation

Author: EmilHvitfeldt

DESCRIPTION

@@ -62,5 +62,5 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 SystemRequirements: "GNU make"

NEWS.md

@@ -1,5 +1,7 @@
 # textrecipes (development version)
 
+* Documentation for tidy methods for all steps has been improved to describe the return value more accurately. (#262)
+
 # textrecipes 1.0.6
 
 * textfeatures has been removed from Suggests. (#255)

R/clean_levels.R

@@ -24,9 +24,15 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected), `original` (the original levels) and
-#' `value` (the cleaned levels) is returned.
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `orginal`, `value`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{original}{character, the original levels}
+#'   \item{value}{character, the cleaned levels}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/clean_names.R

@@ -19,9 +19,15 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the new clean variable names) and `value` (the original variable names).
-#'
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the new clean variable names}
+#'   \item{value}{character, the original variable names}
+#'   \item{id}{character, id of this step}
+#' }
+#' 
 #' @template case-weights-not-supported
 #'
 #' @seealso [step_clean_levels()], [recipes::step_factor2string()],

R/dummy_hash.R

@@ -43,11 +43,17 @@
 #' @details
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected), `value` (whether a signed hashing was
-#' performed), `num_terms` (number of terms), and `collapse` (where columns
-#' collapsed).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, `num_terms`, `collapse`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{logical, whether a signed hashing was performed}
+#'   \item{num_terms}{integer, number of terms}
+#'   \item{collapse}{logical, were the columns collapsed}
+#'   \item{id}{character, id of this step}
+#' }
 #' 
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_dummy_hash"

R/lda.R

@@ -21,9 +21,15 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `num_topics` (number of topics).
-#'
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `num_topics`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{num_topics}{integer, number of topics}
+#'   \item{id}{character, id of this step}
+#' }
+#' 
 #' @template case-weights-not-supported
 #'
 #' @source \url{https://arxiv.org/abs/1301.3781}

R/lemma.R

@@ -23,8 +23,13 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/ngram.R

@@ -29,9 +29,14 @@
 #' the 2-grams followed by all the 3-grams.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #' 
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_ngram"

R/pos_filter.R

@@ -25,8 +25,13 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `num_topics` (number of topics).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/sequence_onehot.R

@@ -37,10 +37,16 @@
 #' accordingly. Characters not in the vocabulary will be encoded as 0.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected), `vocabulary` (index) and `token` (text
-#' correspoding to the index).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `vocabulary`, `token`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{vocabulary}{integer, index}
+#'   \item{token}{character, text corresponding to the index}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/stem.R

@@ -27,10 +27,15 @@
 #' therefore not work reliably on ngrams or sentences.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `is_custom_stemmer` (indicate if
-#' custom stemmer was used).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `is_custom_stemmer`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{is_custom_stemmer}{logical, indicate if custom stemmer was used}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/stopwords.R

@@ -33,10 +33,16 @@
 #' these two arguments.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected), `value` (name of stop word list), and
-#' `keep` (whether stop words are removed or kept).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, `keep`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{character, name of stop word list}
+#'   \item{keep}{logical, whether stop words are removed or kept}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/text_normalization.R

@@ -21,9 +21,14 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `normalization_form` (type of
-#' normalization).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `normalization_form`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{normalization_form}{character, type of normalization}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/textfeature.R

@@ -28,10 +28,15 @@
 #' will be thrown.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `functions` (name of feature
-#' functions).
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `functions`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{functions}{character, name of feature functions}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/texthash.R

@@ -37,9 +37,16 @@
 #'
 #' @details # Tidying
 #'
-#'   When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#'   (the selectors or variables selected) and `value` (number of terms).
-#'
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#'  columns `terms`, value and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{logical, is it signed?}
+#'   \item{length}{integer, number of terms}
+#'   \item{id}{character, id of this step}
+#' }
+#' 
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_texthash"
 #' result <- knitr::knit_child("man/rmd/tunable-args.Rmd")

R/tf.R

@@ -54,8 +54,14 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `value` (the weighting scheme).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{character, the weighting scheme}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_tf"

R/tfidf.R

@@ -51,9 +51,15 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected), `token` (name of the tokens),
-#' `weight` (the calculated IDF weight) is returned.
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `token`, `weight`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{token}{character, name of token}
+#'   \item{weight}{numeric, the calculated IDF weight}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template details-prefix
 #'

R/tokenfilter.R

@@ -43,10 +43,16 @@
 #' limit the number of variables created.
 #'
 #' # Tidying
-#'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `value` (number of unique tokens).
-#'
+#' 
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{integer, number of unique tokens}
+#'   \item{id}{character, id of this step}
+#' }
+#' 
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_tokenfilter"
 #' result <- knitr::knit_child("man/rmd/tunable-args.Rmd")

R/tokenize.R

@@ -182,8 +182,14 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected) and `value` (unit of tokenization).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms`, `value`, and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{value}{character, unit of tokenization}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_tokenize"

R/tokenize_bpe.R

@@ -23,8 +23,13 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' ```{r, echo = FALSE, results="asis"}
 #' step <- "step_tokenize_bpe"

R/tokenize_sentencepiece.R

@@ -28,8 +28,13 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'

R/tokenize_wordpiece.R

@@ -22,8 +22,13 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns `terms`
-#' (the selectors or variables selected).
+#' When you [`tidy()`][tidy.recipe()] this step, a tibble is retruned with
+#' columns `terms` and `id`:
+#' 
+#' \describe{
+#'   \item{terms}{character, the selectors or variables selected}
+#'   \item{id}{character, id of this step}
+#' }
 #'
 #' @template case-weights-not-supported
 #'