From 4fe86b206bab71be357f5e61d173d925f4e39f8c Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Wed, 22 Jan 2025 16:24:02 -0800 Subject: [PATCH 1/9] don't depend on dev recipes --- DESCRIPTION | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 1e15b34d..3b91dfe0 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -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 LinkingTo: cpp11 VignetteBuilder: From 26c98a2e1ddaca039ddfb5d90be51882159f828c Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Wed, 22 Jan 2025 16:24:21 -0800 Subject: [PATCH 2/9] correctly link to functions in recipes --- R/tf.R | 2 +- R/tfidf.R | 2 +- R/tokenfilter.R | 2 +- R/tokenize_bpe.R | 2 +- R/tokenize_sentencepiece.R | 2 +- man-roxygen/args-recipe.R | 2 +- man/step_clean_levels.Rd | 2 +- man/step_clean_names.Rd | 2 +- man/step_dummy_hash.Rd | 2 +- man/step_lda.Rd | 2 +- man/step_lemma.Rd | 2 +- man/step_ngram.Rd | 2 +- man/step_pos_filter.Rd | 2 +- man/step_sequence_onehot.Rd | 2 +- man/step_stem.Rd | 2 +- man/step_stopwords.Rd | 2 +- man/step_text_normalization.Rd | 2 +- man/step_textfeature.Rd | 2 +- man/step_texthash.Rd | 2 +- man/step_tf.Rd | 4 ++-- man/step_tfidf.Rd | 4 ++-- man/step_tokenfilter.Rd | 4 ++-- man/step_tokenize.Rd | 2 +- man/step_tokenize_bpe.Rd | 4 ++-- man/step_tokenize_sentencepiece.Rd | 4 ++-- man/step_tokenize_wordpiece.Rd | 2 +- man/step_tokenmerge.Rd | 2 +- man/step_untokenize.Rd | 2 +- man/step_word_embeddings.Rd | 2 +- 29 files changed, 34 insertions(+), 34 deletions(-) diff --git a/R/tf.R b/R/tf.R index de8ac572..315b69e5 100644 --- 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 diff --git a/R/tfidf.R b/R/tfidf.R index 50e0c915..680e9c4a 100644 --- 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. diff --git a/R/tokenfilter.R b/R/tokenfilter.R index 70458c40..027eb033 100644 --- 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 #' diff --git a/R/tokenize_bpe.R b/R/tokenize_bpe.R index f7c973db..98b43195 100644 --- 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 #' diff --git a/R/tokenize_sentencepiece.R b/R/tokenize_sentencepiece.R index 0456d410..444e5fe4 100644 --- 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 #' diff --git a/man-roxygen/args-recipe.R b/man-roxygen/args-recipe.R index b59ee0fb..4394ebb0 100644 --- 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 index eff12e58..20b0d5b6 100644 --- a/man/step_clean_levels.Rd +++ b/man/step_clean_levels.Rd @@ -16,7 +16,7 @@ step_clean_levels( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_clean_names.Rd b/man/step_clean_names.Rd index efae42a2..7b9332e6 100644 --- a/man/step_clean_names.Rd +++ b/man/step_clean_names.Rd @@ -16,7 +16,7 @@ step_clean_names( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_dummy_hash.Rd b/man/step_dummy_hash.Rd index 8e3c3345..681c19f9 100644 --- a/man/step_dummy_hash.Rd +++ b/man/step_dummy_hash.Rd @@ -21,7 +21,7 @@ step_dummy_hash( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_lda.Rd b/man/step_lda.Rd index a4a710e4..4a93a052 100644 --- a/man/step_lda.Rd +++ b/man/step_lda.Rd @@ -23,7 +23,7 @@ step_lda( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_lemma.Rd b/man/step_lemma.Rd index 9735a5a2..d809aeac 100644 --- a/man/step_lemma.Rd +++ b/man/step_lemma.Rd @@ -16,7 +16,7 @@ step_lemma( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_ngram.Rd b/man/step_ngram.Rd index 8d20d9d2..fbf77a2e 100644 --- a/man/step_ngram.Rd +++ b/man/step_ngram.Rd @@ -19,7 +19,7 @@ step_ngram( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_pos_filter.Rd b/man/step_pos_filter.Rd index f0f3ae3e..81f2971c 100644 --- a/man/step_pos_filter.Rd +++ b/man/step_pos_filter.Rd @@ -17,7 +17,7 @@ step_pos_filter( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_sequence_onehot.Rd b/man/step_sequence_onehot.Rd index dcbfb7d4..e32573a3 100644 --- a/man/step_sequence_onehot.Rd +++ b/man/step_sequence_onehot.Rd @@ -25,7 +25,7 @@ step_sequence_onehot( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_stem.Rd b/man/step_stem.Rd index 4a22b496..b6db70c4 100644 --- a/man/step_stem.Rd +++ b/man/step_stem.Rd @@ -18,7 +18,7 @@ step_stem( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_stopwords.Rd b/man/step_stopwords.Rd index 7ded7972..f9077af8 100644 --- a/man/step_stopwords.Rd +++ b/man/step_stopwords.Rd @@ -20,7 +20,7 @@ step_stopwords( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_text_normalization.Rd b/man/step_text_normalization.Rd index 0254a093..e01af90d 100644 --- a/man/step_text_normalization.Rd +++ b/man/step_text_normalization.Rd @@ -17,7 +17,7 @@ step_text_normalization( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_textfeature.Rd b/man/step_textfeature.Rd index d7997c42..8ac7b36d 100644 --- a/man/step_textfeature.Rd +++ b/man/step_textfeature.Rd @@ -18,7 +18,7 @@ step_textfeature( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_texthash.Rd b/man/step_texthash.Rd index ee9189ab..3b546696 100644 --- a/man/step_texthash.Rd +++ b/man/step_texthash.Rd @@ -20,7 +20,7 @@ step_texthash( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_tf.Rd b/man/step_tf.Rd index 07e4cfa4..41a21ded 100644 --- a/man/step_tf.Rd +++ b/man/step_tf.Rd @@ -22,7 +22,7 @@ step_tf( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which @@ -53,7 +53,7 @@ normalization". Defaults to 0.5.} \item{res}{The words that will be used to calculate the term frequency will be stored here once this preprocessing step has be trained by -\code{\link[=prep.recipe]{prep.recipe()}}.} +\code{\link[recipes:prep]{recipes::prep.recipe()}}.} \item{prefix}{A character string that will be the prefix to the resulting new variables. See notes below.} diff --git a/man/step_tfidf.Rd b/man/step_tfidf.Rd index 297993c1..6fe75d36 100644 --- a/man/step_tfidf.Rd +++ b/man/step_tfidf.Rd @@ -23,7 +23,7 @@ step_tfidf( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which @@ -46,7 +46,7 @@ until the step is trained by \code{\link[recipes:prep]{recipes::prep.recipe()}}. \item{res}{The words that will be used to calculate the term frequency will be stored here once this preprocessing step has be trained by -\code{\link[=prep.recipe]{prep.recipe()}}.} +\code{\link[recipes:prep]{recipes::prep.recipe()}}.} \item{smooth_idf}{TRUE smooth IDF weights by adding one to document frequencies, as if an extra document was seen containing every term in the diff --git a/man/step_tokenfilter.Rd b/man/step_tokenfilter.Rd index 42f0b858..2ba10163 100644 --- a/man/step_tokenfilter.Rd +++ b/man/step_tokenfilter.Rd @@ -22,7 +22,7 @@ step_tokenfilter( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which @@ -57,7 +57,7 @@ will be applied to each observation of the data set. Defaults to \code{NULL}. All other arguments will be ignored if this argument is used.} \item{res}{The words that will be keep will be stored here once this -preprocessing step has be trained by \code{\link[=prep.recipe]{prep.recipe()}}.} +preprocessing step has be trained by \code{\link[recipes:prep]{recipes::prep.recipe()}}.} \item{skip}{A logical. Should the step be skipped when the recipe is baked by \code{\link[recipes:bake]{recipes::bake.recipe()}}? While all operations are baked diff --git a/man/step_tokenize.Rd b/man/step_tokenize.Rd index 0515caa5..b81cf598 100644 --- a/man/step_tokenize.Rd +++ b/man/step_tokenize.Rd @@ -21,7 +21,7 @@ step_tokenize( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_tokenize_bpe.Rd b/man/step_tokenize_bpe.Rd index cedfe951..b0e88454 100644 --- a/man/step_tokenize_bpe.Rd +++ b/man/step_tokenize_bpe.Rd @@ -19,7 +19,7 @@ step_tokenize_bpe( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which @@ -42,7 +42,7 @@ vocabulary. Defaults to 1000. Highly encouraged to be tuned.} \item{options}{A list of options passed to the tokenizer.} \item{res}{The fitted \code{\link[tokenizers.bpe:bpe]{tokenizers.bpe::bpe()}} model tokenizer will be stored -here once this preprocessing step has be trained by \code{\link[=prep.recipe]{prep.recipe()}}.} +here once this preprocessing step has be trained by \code{\link[recipes:prep]{recipes::prep.recipe()}}.} \item{skip}{A logical. Should the step be skipped when the recipe is baked by \code{\link[recipes:bake]{recipes::bake.recipe()}}? While all operations are baked diff --git a/man/step_tokenize_sentencepiece.Rd b/man/step_tokenize_sentencepiece.Rd index 5c48788b..4037646c 100644 --- a/man/step_tokenize_sentencepiece.Rd +++ b/man/step_tokenize_sentencepiece.Rd @@ -19,7 +19,7 @@ step_tokenize_sentencepiece( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which @@ -43,7 +43,7 @@ vocabulary. Defaults to 1000. Highly encouraged to be tuned.} \item{res}{The fitted \code{\link[sentencepiece:sentencepiece]{sentencepiece::sentencepiece()}} model tokenizer will be stored here once this preprocessing step has be trained by -\code{\link[=prep.recipe]{prep.recipe()}}.} +\code{\link[recipes:prep]{recipes::prep.recipe()}}.} \item{skip}{A logical. Should the step be skipped when the recipe is baked by \code{\link[recipes:bake]{recipes::bake.recipe()}}? While all operations are baked diff --git a/man/step_tokenize_wordpiece.Rd b/man/step_tokenize_wordpiece.Rd index 72295135..a9e95926 100644 --- a/man/step_tokenize_wordpiece.Rd +++ b/man/step_tokenize_wordpiece.Rd @@ -19,7 +19,7 @@ step_tokenize_wordpiece( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_tokenmerge.Rd b/man/step_tokenmerge.Rd index f39cb657..8b6b0af8 100644 --- a/man/step_tokenmerge.Rd +++ b/man/step_tokenmerge.Rd @@ -18,7 +18,7 @@ step_tokenmerge( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_untokenize.Rd b/man/step_untokenize.Rd index 8d03841c..e8cd4c76 100644 --- a/man/step_untokenize.Rd +++ b/man/step_untokenize.Rd @@ -17,7 +17,7 @@ step_untokenize( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which diff --git a/man/step_word_embeddings.Rd b/man/step_word_embeddings.Rd index f56c0b0a..bf717dfc 100644 --- a/man/step_word_embeddings.Rd +++ b/man/step_word_embeddings.Rd @@ -21,7 +21,7 @@ step_word_embeddings( ) } \arguments{ -\item{recipe}{A \link{recipe} object. The step will be added to the +\item{recipe}{A \link[recipes:recipe]{recipes::recipe} object. The step will be added to the sequence of operations for this recipe.} \item{...}{One or more selector functions to choose which From 12b047b97668dceb095e9e8adbbf4d3ebbd37cc7 Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:38:15 -0800 Subject: [PATCH 3/9] fix typo in rdname --- R/textfeature.R | 2 +- man/step_textfeature.Rd | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/R/textfeature.R b/R/textfeature.R index 41d4dd4d..e5c3fd79 100644 --- a/R/textfeature.R +++ b/R/textfeature.R @@ -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/man/step_textfeature.Rd b/man/step_textfeature.Rd index 8ac7b36d..a81d3c0e 100644 --- a/man/step_textfeature.Rd +++ b/man/step_textfeature.Rd @@ -2,6 +2,7 @@ % Please edit documentation in R/textfeature.R \name{step_textfeature} \alias{step_textfeature} +\alias{tidy.step_textfeature} \title{Calculate Set of Text Features} \usage{ step_textfeature( From 49c875f5a02ead4206e2d94afaecfeaa08633f61 Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:40:36 -0800 Subject: [PATCH 4/9] polish news --- NEWS.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/NEWS.md b/NEWS.md index 9a4821c6..87026cb8 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,11 +1,15 @@ # textrecipes (development version) +## 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 From da639dadb51c820bd2cac6bfeb1a5ccfd9faa475 Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:40:40 -0800 Subject: [PATCH 5/9] rerender readme --- NEWS.md | 1 + README.Rmd | 2 +- README.md | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/NEWS.md b/NEWS.md index 87026cb8..d74238e0 100644 --- a/NEWS.md +++ b/NEWS.md @@ -21,6 +21,7 @@ # textrecipes 1.0.5 * `step_untokenize()` and `step_normalization()` now returns factors instead of strings. (#247) + # textrecipes 1.0.4 ## Improvements diff --git a/README.Rmd b/README.Rmd index aca95dd7..5112dc1b 100644 --- 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 index 9531adf1..fbd09c91 100644 --- 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). From 6307375e7f813368559fbf05a9dc38c5e57c8e3f Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:43:21 -0800 Subject: [PATCH 6/9] update cran comments --- cran-comments.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/cran-comments.md b/cran-comments.md index db5b5e76..0a05c6e1 100644 --- 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 From 746a4e4b5a67ef2799c7a01ce8adff6b585a3013 Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:58:55 -0800 Subject: [PATCH 7/9] correctly document link to tidy.recipe --- R/clean_levels.R | 2 +- R/clean_names.R | 2 +- R/dummy_hash.R | 2 +- R/lda.R | 2 +- R/lemma.R | 2 +- R/ngram.R | 2 +- R/pos_filter.R | 2 +- R/sequence_onehot.R | 2 +- R/stem.R | 2 +- R/stopwords.R | 2 +- R/text_normalization.R | 2 +- R/textfeature.R | 2 +- R/texthash.R | 2 +- R/tf.R | 2 +- R/tfidf.R | 2 +- R/tokenfilter.R | 2 +- R/tokenize.R | 2 +- R/tokenize_bpe.R | 2 +- R/tokenize_sentencepiece.R | 2 +- R/tokenize_wordpiece.R | 2 +- R/tokenmerge.R | 2 +- R/untokenize.R | 2 +- R/word_embeddings.R | 2 +- man/step_clean_levels.Rd | 2 +- man/step_clean_names.Rd | 2 +- man/step_dummy_hash.Rd | 2 +- man/step_lda.Rd | 2 +- man/step_lemma.Rd | 2 +- man/step_ngram.Rd | 2 +- man/step_pos_filter.Rd | 2 +- man/step_sequence_onehot.Rd | 2 +- man/step_stem.Rd | 2 +- man/step_stopwords.Rd | 2 +- man/step_text_normalization.Rd | 2 +- man/step_textfeature.Rd | 2 +- man/step_texthash.Rd | 2 +- man/step_tf.Rd | 2 +- man/step_tfidf.Rd | 2 +- man/step_tokenfilter.Rd | 2 +- man/step_tokenize.Rd | 2 +- man/step_tokenize_bpe.Rd | 2 +- man/step_tokenize_sentencepiece.Rd | 2 +- man/step_tokenize_wordpiece.Rd | 2 +- man/step_tokenmerge.Rd | 2 +- man/step_untokenize.Rd | 2 +- man/step_word_embeddings.Rd | 2 +- 46 files changed, 46 insertions(+), 46 deletions(-) diff --git a/R/clean_levels.R b/R/clean_levels.R index 8ab1d8a7..54e39490 100644 --- 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 index 097d6e92..b8112aad 100644 --- 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 index 5f417dec..d8e1fd74 100644 --- 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 index 84b79a81..102bdbb3 100644 --- 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 index e569f2a8..1935fc90 100644 --- 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 index 571f6cf0..0ca47994 100644 --- 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 index 800e1c37..fae24d9f 100644 --- 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 index 71217de4..bd3d390e 100644 --- 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 index 5f43e8a0..f2cfc756 100644 --- 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 index b048c3db..111c71c4 100644 --- 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 index c5040567..5d3149dc 100644 --- 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 index e5c3fd79..841d32f3 100644 --- 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{ diff --git a/R/texthash.R b/R/texthash.R index b05cee87..b9030d1c 100644 --- 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 index 315b69e5..6f62560e 100644 --- a/R/tf.R +++ b/R/tf.R @@ -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 index 680e9c4a..2935d010 100644 --- a/R/tfidf.R +++ b/R/tfidf.R @@ -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 index 027eb033..2a2f0a4e 100644 --- a/R/tokenfilter.R +++ b/R/tokenfilter.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`, and `id`: #' #' \describe{ diff --git a/R/tokenize.R b/R/tokenize.R index 8e24e2d4..86230896 100644 --- 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 index 98b43195..f278b3aa 100644 --- a/R/tokenize_bpe.R +++ b/R/tokenize_bpe.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/tokenize_sentencepiece.R b/R/tokenize_sentencepiece.R index 444e5fe4..3a561293 100644 --- a/R/tokenize_sentencepiece.R +++ b/R/tokenize_sentencepiece.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` and `id`: #' #' \describe{ diff --git a/R/tokenize_wordpiece.R b/R/tokenize_wordpiece.R index 77b356c8..b0f42322 100644 --- 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 index 7835c771..55abba00 100644 --- 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 index 611791fe..86917fb6 100644 --- 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 index ec6da6d3..2de323f4 100644 --- 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/man/step_clean_levels.Rd b/man/step_clean_levels.Rd index 20b0d5b6..5b716609 100644 --- a/man/step_clean_levels.Rd +++ b/man/step_clean_levels.Rd @@ -56,7 +56,7 @@ data to be processed contains novel levels (i.e., not contained in the training set), they are converted to missing. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{orginal}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_clean_names.Rd b/man/step_clean_names.Rd index 7b9332e6..8dd55d6f 100644 --- a/man/step_clean_names.Rd +++ b/man/step_clean_names.Rd @@ -50,7 +50,7 @@ clean variable names so the names consist only of letters, numbers, and the underscore. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_dummy_hash.Rd b/man/step_dummy_hash.Rd index 681c19f9..29912451 100644 --- a/man/step_dummy_hash.Rd +++ b/man/step_dummy_hash.Rd @@ -95,7 +95,7 @@ the name of the variable, followed by the tokens all separated by \code{hash001} - \code{hash101}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, \code{num_terms}, \code{collapse}, and \code{id}: \describe{ diff --git a/man/step_lda.Rd b/man/step_lda.Rd index 4a93a052..dbbd5c8d 100644 --- a/man/step_lda.Rd +++ b/man/step_lda.Rd @@ -70,7 +70,7 @@ to the sequence of existing steps (if any). lda dimension estimates of a text variable. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{num_topics}, and \code{id}: \describe{ diff --git a/man/step_lemma.Rd b/man/step_lemma.Rd index d809aeac..35f313a0 100644 --- a/man/step_lemma.Rd +++ b/man/step_lemma.Rd @@ -57,7 +57,7 @@ lemmatization. Currently using the \code{"spacyr"} engine in \code{\link[=step_t provides lemmatization and works well with \code{step_lemma}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_ngram.Rd b/man/step_ngram.Rd index fbf77a2e..2623da89 100644 --- a/man/step_ngram.Rd +++ b/man/step_ngram.Rd @@ -70,7 +70,7 @@ and \code{num_tokens = 3} then the output will contain all the 1-grams followed the 2-grams followed by all the 3-grams. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_pos_filter.Rd b/man/step_pos_filter.Rd index 81f2971c..7e506f06 100644 --- a/man/step_pos_filter.Rd +++ b/man/step_pos_filter.Rd @@ -61,7 +61,7 @@ information look here \url{https://github.com/explosion/spaCy/blob/master/spacy/glossary.py}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_sequence_onehot.Rd b/man/step_sequence_onehot.Rd index e32573a3..bfda777d 100644 --- a/man/step_sequence_onehot.Rd +++ b/man/step_sequence_onehot.Rd @@ -86,7 +86,7 @@ assign an integer to each character in the vocabulary, and will encode accordingly. Characters not in the vocabulary will be encoded as 0. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{vocabulary}, \code{token}, and \code{id}: \describe{ diff --git a/man/step_stem.Rd b/man/step_stem.Rd index b6db70c4..77384282 100644 --- a/man/step_stem.Rd +++ b/man/step_stem.Rd @@ -66,7 +66,7 @@ Note that the stemming will only be done at the end of the word and will therefore not work reliably on ngrams or sentences. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{is_custom_stemmer}, and \code{id}: \describe{ diff --git a/man/step_stopwords.Rd b/man/step_stopwords.Rd index f9077af8..3bd6ff98 100644 --- a/man/step_stopwords.Rd +++ b/man/step_stopwords.Rd @@ -76,7 +76,7 @@ instead of removing thus allowing you to select words with a combination of these two arguments. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, \code{keep}, and \code{id}: \describe{ diff --git a/man/step_text_normalization.Rd b/man/step_text_normalization.Rd index e01af90d..7a8abb56 100644 --- a/man/step_text_normalization.Rd +++ b/man/step_text_normalization.Rd @@ -56,7 +56,7 @@ to the sequence of existing steps (if any). will perform Unicode Normalization on character variables. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{normalization_form}, and \code{id}: \describe{ diff --git a/man/step_textfeature.Rd b/man/step_textfeature.Rd index a81d3c0e..9d67cffb 100644 --- a/man/step_textfeature.Rd +++ b/man/step_textfeature.Rd @@ -72,7 +72,7 @@ as input and return a numeric vector of the same length, otherwise an error will be thrown. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{functions}, and \code{id}: \describe{ diff --git a/man/step_texthash.Rd b/man/step_texthash.Rd index 3b546696..d2c5b3a1 100644 --- a/man/step_texthash.Rd +++ b/man/step_texthash.Rd @@ -88,7 +88,7 @@ the name of the variable, followed by the tokens all separated by \code{hash001} - \code{hash101}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, value and \code{id}: \describe{ diff --git a/man/step_tf.Rd b/man/step_tf.Rd index 41a21ded..b613487e 100644 --- a/man/step_tf.Rd +++ b/man/step_tf.Rd @@ -107,7 +107,7 @@ the name of the variable, followed by the tokens all separated by \code{hash001} - \code{hash101}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_tfidf.Rd b/man/step_tfidf.Rd index 6fe75d36..a557beb2 100644 --- a/man/step_tfidf.Rd +++ b/man/step_tfidf.Rd @@ -110,7 +110,7 @@ the name of the variable, followed by the tokens all separated by \code{hash001} - \code{hash101}. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{token}, \code{weight}, and \code{id}: \describe{ diff --git a/man/step_tokenfilter.Rd b/man/step_tokenfilter.Rd index 2ba10163..ff45edc6 100644 --- a/man/step_tokenfilter.Rd +++ b/man/step_tokenfilter.Rd @@ -90,7 +90,7 @@ It is strongly advised to filter before using \link{step_tf} or \link{step_tfidf limit the number of variables created. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_tokenize.Rd b/man/step_tokenize.Rd index b81cf598..9e6a75c3 100644 --- a/man/step_tokenize.Rd +++ b/man/step_tokenize.Rd @@ -245,7 +245,7 @@ recipe(~ text, data = text_tibble) \%>\% } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_tokenize_bpe.Rd b/man/step_tokenize_bpe.Rd index b0e88454..55dbbe1d 100644 --- a/man/step_tokenize_bpe.Rd +++ b/man/step_tokenize_bpe.Rd @@ -62,7 +62,7 @@ convert a character predictor into a \code{\link[=tokenlist]{token}} variable us Byte Pair Encoding. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_tokenize_sentencepiece.Rd b/man/step_tokenize_sentencepiece.Rd index 4037646c..29c52bb9 100644 --- a/man/step_tokenize_sentencepiece.Rd +++ b/man/step_tokenize_sentencepiece.Rd @@ -68,7 +68,7 @@ compiled code by setting \code{options = list(verbose = TRUE)}. This can reveal sentencepiece ran correctly or not. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_tokenize_wordpiece.Rd b/man/step_tokenize_wordpiece.Rd index a9e95926..c9f2899b 100644 --- a/man/step_tokenize_wordpiece.Rd +++ b/man/step_tokenize_wordpiece.Rd @@ -61,7 +61,7 @@ will convert a character predictor into a \code{\link[=tokenlist]{token}} variab using WordPiece tokenization. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_tokenmerge.Rd b/man/step_tokenmerge.Rd index 8b6b0af8..017e5c48 100644 --- a/man/step_tokenmerge.Rd +++ b/man/step_tokenmerge.Rd @@ -60,7 +60,7 @@ multiple \code{\link[=tokenlist]{token}} variables and combine them into one \code{\link[=tokenlist]{token}} variable. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms} and \code{id}: \describe{ diff --git a/man/step_untokenize.Rd b/man/step_untokenize.Rd index e8cd4c76..ecdd65c3 100644 --- a/man/step_untokenize.Rd +++ b/man/step_untokenize.Rd @@ -59,7 +59,7 @@ vector. This step is calling \code{paste} internally to put the tokens back together to a character. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{value}, and \code{id}: \describe{ diff --git a/man/step_word_embeddings.Rd b/man/step_word_embeddings.Rd index bf717dfc..5504abbf 100644 --- a/man/step_word_embeddings.Rd +++ b/man/step_word_embeddings.Rd @@ -92,7 +92,7 @@ tibble (usually something like "d7"). For example, using the default \code{wordembedding_d1}, \code{wordembedding_d1}, etc. } \section{Tidying}{ -When you \code{\link[=tidy.recipe]{tidy()}} this step, a tibble is returned with +When you \code{\link[recipes:tidy.recipe]{tidy()}} this step, a tibble is returned with columns \code{terms}, \code{embedding_rows}, \code{aggregation}, and \code{id}: \describe{ From 8a17acd73a9442f4eb506bc3967129ae755cc34d Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 15:59:17 -0800 Subject: [PATCH 8/9] Increment version number to 1.0.7 --- DESCRIPTION | 2 +- NEWS.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 4258f6a2..a7b6054e 100644 --- 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 Authors@R: c( person("Emil", "Hvitfeldt", , "emil.hvitfeldt@posit.co", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-0679-1945")), diff --git a/NEWS.md b/NEWS.md index d74238e0..29b749c8 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,4 +1,4 @@ -# textrecipes (development version) +# textrecipes 1.0.7 ## Improvements From b8754ffb69dc2bbf80cd8fed30b1ee8643a548a3 Mon Sep 17 00:00:00 2001 From: Emil Hvitfeldt Date: Thu, 23 Jan 2025 16:14:08 -0800 Subject: [PATCH 9/9] Increment version number to 1.0.7.9000 --- DESCRIPTION | 2 +- NEWS.md | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/DESCRIPTION b/DESCRIPTION index a7b6054e..327ff404 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: textrecipes Title: Extra 'Recipes' for Text Processing -Version: 1.0.7 +Version: 1.0.7.9000 Authors@R: c( person("Emil", "Hvitfeldt", , "emil.hvitfeldt@posit.co", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-0679-1945")), diff --git a/NEWS.md b/NEWS.md index 29b749c8..fcfc1f06 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,3 +1,5 @@ +# textrecipes (development version) + # textrecipes 1.0.7 ## Improvements