Merge pull request #280 from tidymodels/RC-1.0.7

tidymodels · Jan 24, 2025 · 6c8f451 · 6c8f451
2 parents 435e3fb + b8754ff
commit 6c8f451
Show file tree

Hide file tree

Showing 52 changed files with 94 additions and 90 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: textrecipes
 Title: Extra 'Recipes' for Text Processing
-Version: 1.0.6.9000
+Version: 1.0.7.9000
 Authors@R: c(
     person("Emil", "Hvitfeldt", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-0679-1945")),
@@ -20,7 +20,7 @@ URL: https://github.com/tidymodels/textrecipes,
 BugReports: https://github.com/tidymodels/textrecipes/issues
 Depends: 
     R (>= 3.6),
-    recipes (>= 1.1.0.9000)
+    recipes (>= 1.1.0)
 Imports: 
     cli,
     lifecycle,
@@ -54,8 +54,6 @@ Suggests:
     tokenizers.bpe,
     udpipe,
     wordpiece
-Remotes:
-    tidymodels/recipes
 VignetteBuilder: 
     knitr
 Config/Needs/website: tidyverse/tidytemplate, reticulate

diff --git a/NEWS.md b/NEWS.md
@@ -1,11 +1,17 @@
 # textrecipes (development version)
 
+# textrecipes 1.0.7
+
+## Improvements
+
 * Documentation for tidy methods for all steps has been improved to describe the return value more accurately. (#262)
 
 * Calling `?tidy.step_*()` now sends you to the documentation for `step_*()` where the outcome is documented. (#261)
 
 * `step_textfeatures()` has been made faster and more robust. (#265)
 
+## Bug Fixes
+
 * Fixed bug in `step_clean_levels()` where it would produce NAs for character columns. (#274)
 
 # textrecipes 1.0.6
@@ -17,6 +23,7 @@
 # textrecipes 1.0.5
 
 * `step_untokenize()` and `step_normalization()` now returns factors instead of strings. (#247)
+
 # textrecipes 1.0.4
 
 ## Improvements

diff --git a/R/clean_levels.R b/R/clean_levels.R
@@ -24,7 +24,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `orginal`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/clean_names.R b/R/clean_names.R
@@ -19,7 +19,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/dummy_hash.R b/R/dummy_hash.R
@@ -44,7 +44,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, `num_terms`, `collapse`, and `id`:
 #' 
 #' \describe{

diff --git a/R/lda.R b/R/lda.R
@@ -21,7 +21,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `num_topics`, and `id`:
 #' 
 #' \describe{

diff --git a/R/lemma.R b/R/lemma.R
@@ -23,7 +23,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/ngram.R b/R/ngram.R
@@ -30,7 +30,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/pos_filter.R b/R/pos_filter.R
@@ -25,7 +25,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/sequence_onehot.R b/R/sequence_onehot.R
@@ -38,7 +38,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `vocabulary`, `token`, and `id`:
 #' 
 #' \describe{

diff --git a/R/stem.R b/R/stem.R
@@ -28,7 +28,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `is_custom_stemmer`, and `id`:
 #' 
 #' \describe{

diff --git a/R/stopwords.R b/R/stopwords.R
@@ -34,7 +34,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, `keep`, and `id`:
 #' 
 #' \describe{

diff --git a/R/text_normalization.R b/R/text_normalization.R
@@ -21,7 +21,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `normalization_form`, and `id`:
 #' 
 #' \describe{

diff --git a/R/textfeature.R b/R/textfeature.R
@@ -29,7 +29,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `functions`, and `id`:
 #' 
 #' \describe{
@@ -178,7 +178,7 @@ print.step_textfeature <-
     invisible(x)
   }
 
-#' @rdname step_textfeatures
+#' @rdname step_textfeature 
 #' @usage NULL
 #' @export
 tidy.step_textfeature <- function(x, ...) {

diff --git a/R/texthash.R b/R/texthash.R
@@ -37,7 +37,7 @@
 #'
 #' @details # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #'  columns `terms`, value and `id`:
 #' 
 #' \describe{

diff --git a/R/tf.R b/R/tf.R
@@ -18,7 +18,7 @@
 #' @param vocabulary A character vector of strings to be considered.
 #' @param res The words that will be used to calculate the term frequency will
 #'   be stored here once this preprocessing step has be trained by
-#'   [prep.recipe()].
+#'   [recipes::prep.recipe()].
 #' @template args-prefix
 #' @template args-keep_original_cols
 #' @template args-skip
@@ -54,7 +54,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/tfidf.R b/R/tfidf.R
@@ -12,7 +12,7 @@
 #' @param vocabulary A character vector of strings to be considered.
 #' @param res The words that will be used to calculate the term frequency will
 #'   be stored here once this preprocessing step has be trained by
-#'   [prep.recipe()].
+#'   [recipes::prep.recipe()].
 #' @param smooth_idf TRUE smooth IDF weights by adding one to document
 #'   frequencies, as if an extra document was seen containing every term in the
 #'   collection exactly once. This prevents division by zero.
@@ -51,7 +51,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `token`, `weight`, and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenfilter.R b/R/tokenfilter.R
@@ -21,7 +21,7 @@
 #'   will be applied to each observation of the data set. Defaults to `NULL`.
 #'   All other arguments will be ignored if this argument is used.
 #' @param res The words that will be keep will be stored here once this
-#'   preprocessing step has be trained by [prep.recipe()].
+#'   preprocessing step has be trained by [recipes::prep.recipe()].
 #' @template args-skip
 #' @template args-id
 #'
@@ -44,7 +44,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenize.R b/R/tokenize.R
@@ -182,7 +182,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenize_bpe.R b/R/tokenize_bpe.R
@@ -13,7 +13,7 @@
 #'   vocabulary. Defaults to 1000. Highly encouraged to be tuned.
 #' @param options A list of options passed to the tokenizer.
 #' @param res The fitted [tokenizers.bpe::bpe()] model tokenizer will be stored
-#'   here once this preprocessing step has be trained by [prep.recipe()].
+#'   here once this preprocessing step has be trained by [recipes::prep.recipe()].
 #' @template args-skip
 #' @template args-id
 #'
@@ -23,7 +23,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenize_sentencepiece.R b/R/tokenize_sentencepiece.R
@@ -14,7 +14,7 @@
 #' @param options A list of options passed to the tokenizer.
 #' @param res The fitted [sentencepiece::sentencepiece()] model tokenizer will
 #'   be stored here once this preprocessing step has be trained by
-#'   [prep.recipe()].
+#'   [recipes::prep.recipe()].
 #' @template args-skip
 #' @template args-id
 #'
@@ -28,7 +28,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenize_wordpiece.R b/R/tokenize_wordpiece.R
@@ -22,7 +22,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/tokenmerge.R b/R/tokenmerge.R
@@ -20,7 +20,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms` and `id`:
 #' 
 #' \describe{

diff --git a/R/untokenize.R b/R/untokenize.R
@@ -23,7 +23,7 @@
 #'
 #' # Tidying
 #'
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `value`, and `id`:
 #' 
 #' \describe{

diff --git a/R/word_embeddings.R b/R/word_embeddings.R
@@ -44,7 +44,7 @@
 #'
 #' # Tidying
 #' 
-#' When you [`tidy()`][tidy.recipe()] this step, a tibble is returned with
+#' When you [`tidy()`][recipes::tidy.recipe()] this step, a tibble is returned with
 #' columns `terms`, `embedding_rows`, `aggregation`, and `id`:
 #' 
 #' \describe{

diff --git a/README.Rmd b/README.Rmd
@@ -91,7 +91,7 @@ recipe(~text_var, data = data) %>%
 
 This project is released with a [Contributor Code of Conduct](https://contributor-covenant.org/version/2/0/CODE_OF_CONDUCT.html). By contributing to this project, you agree to abide by its terms.
 
-- For questions and discussions about tidymodels packages, modeling, and machine learning, please [post on RStudio Community](https://community.rstudio.com/new-topic?category_id=15&tags=tidymodels,question).
+- For questions and discussions about tidymodels packages, modeling, and machine learning, please [post on RStudio Community](https://forum.posit.co/new-topic?category_id=15&tags=tidymodels,question).
 
 - If you think you have encountered a bug, please [submit an issue](https://github.com/tidymodels/textrecipes/issues).
 

diff --git a/README.md b/README.md
@@ -115,7 +115,7 @@ By contributing to this project, you agree to abide by its terms.
 
 - For questions and discussions about tidymodels packages, modeling, and
   machine learning, please [post on RStudio
-  Community](https://community.rstudio.com/new-topic?category_id=15&tags=tidymodels,question).
+  Community](https://forum.posit.co/new-topic?category_id=15&tags=tidymodels,question).
 
 - If you think you have encountered a bug, please [submit an
   issue](https://github.com/tidymodels/textrecipes/issues).

diff --git a/cran-comments.md b/cran-comments.md
@@ -1,8 +1,6 @@
 ## Release Summary
 
-This is the 20th CRAN release of textrecipes. 
-
-The package was removed from CRAN because it depended on textfeatures which was removed. This issue has now been fixed.
+This is the 21th CRAN release of textrecipes. 
 
 ## R CMD check results
 

diff --git a/man-roxygen/args-recipe.R b/man-roxygen/args-recipe.R
@@ -1,2 +1,2 @@
-#' @param recipe A [recipe] object. The step will be added to the
+#' @param recipe A [recipes::recipe] object. The step will be added to the
 #'  sequence of operations for this recipe.
diff --git a/man/step_clean_levels.Rd b/man/step_clean_levels.Rd
diff --git a/man/step_clean_names.Rd b/man/step_clean_names.Rd
diff --git a/man/step_dummy_hash.Rd b/man/step_dummy_hash.Rd