Merge pull request #251 from tidymodels/RC-1.0.5

tidymodels · Oct 23, 2023 · 30e607a · 30e607a
2 parents a121d6f + 59e6775
commit 30e607a
Show file tree

Hide file tree

Showing 13 changed files with 113 additions and 56 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: textrecipes
 Title: Extra 'Recipes' for Text Processing
-Version: 1.0.4.9000
+Version: 1.0.5.9000
 Authors@R: c(
     person("Emil", "Hvitfeldt", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-0679-1945")),
@@ -32,6 +32,7 @@ Imports:
     glue
 Suggests: 
     covr,
+    data.table,
     dials (>= 1.2.0),
     hardhat,
     janitor,

diff --git a/NEWS.md b/NEWS.md
@@ -1,7 +1,8 @@
 # textrecipes (development version)
 
-* `step_untokenize()` and `step_normalization()` now returns factors instead of strings.
+# 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/dummy_hash.R b/R/dummy_hash.R
@@ -66,8 +66,20 @@
 #' @seealso [recipes::step_dummy()]
 #' @family Steps for Numeric Variables From Characters
 #'
-#' @examplesIf rlang::is_installed("text2vec")
-#' \dontrun{
+#' @examplesIf all(c("text2vec", "data.table") %in% rownames(installed.packages()))
+#' \dontshow{library(data.table)}
+#' \dontshow{data.table::setDTthreads(2)}
+#' \dontshow{Sys.setenv("OMP_NUM_THREADS" = 1)}
+#' \dontshow{Sys.setenv("OMP_THREAD_LIMIT" = 1)}
+#' \dontshow{Sys.setenv("rsparse_omp_threads" = 1L)}
+#' \dontshow{options(rsparse_omp_threads = 1L)}
+#' \dontshow{library(text2vec)}
+#' \dontshow{Sys.setenv("OMP_NUM_THREADS" = 1)}
+#' \dontshow{Sys.setenv("OMP_THREAD_LIMIT" = 1)}
+#' \dontshow{Sys.setenv("rsparse_omp_threads" = 1L)}
+#' \dontshow{options(rsparse_omp_threads = 1L)}
+#' \dontshow{options("text2vec.mc.cores" = 1)}
+#' 
 #' library(recipes)
 #' library(modeldata)
 #' data(grants)
@@ -82,7 +94,6 @@
 #'
 #' tidy(grants_rec, number = 1)
 #' tidy(grants_obj, number = 1)
-#' }
 #' @export
 step_dummy_hash <-
   function(recipe,

diff --git a/R/lda.R b/R/lda.R
@@ -32,7 +32,10 @@
 #'
 #' @family Steps for Numeric Variables From Tokens
 #'
-#' @examplesIf rlang::is_installed("text2vec")
+#' @examplesIf all(c("text2vec", "data.table") %in% rownames(installed.packages()))
+#' \dontshow{library(data.table)}
+#' \dontshow{data.table::setDTthreads(2)}
+#' \dontshow{Sys.setenv("OMP_THREAD_LIMIT" = 2)}
 #' library(recipes)
 #' library(modeldata)
 #' data(tate_text)

diff --git a/R/texthash.R b/R/texthash.R
@@ -55,7 +55,10 @@
 #'   [step_text_normalization()] to perform text normalization.
 #' @family Steps for Numeric Variables From Tokens
 #'
-#' @examplesIf rlang::is_installed("text2vec")
+#' @examplesIf all(c("text2vec", "data.table") %in% rownames(installed.packages()))
+#' \dontshow{library(data.table)}
+#' \dontshow{data.table::setDTthreads(2)}
+#' \dontshow{Sys.setenv("OMP_THREAD_LIMIT" = 2)}
 #' library(recipes)
 #' library(modeldata)
 #' data(tate_text)

diff --git a/cran-comments.md b/cran-comments.md
@@ -1,6 +1,6 @@
 ## Release Summary
 
-This is the 18th CRAN release of textrecipes. 
+This is the 19th CRAN release of textrecipes. 
 
 ## R CMD check results
 

diff --git a/man/step_dummy_hash.Rd b/man/step_dummy_hash.Rd
diff --git a/man/step_lda.Rd b/man/step_lda.Rd
diff --git a/man/step_texthash.Rd b/man/step_texthash.Rd
diff --git a/revdep/README.md b/revdep/README.md
@@ -1,33 +1,32 @@
 # Platform
 
-|field    |value                                                                                      |
-|:--------|:------------------------------------------------------------------------------------------|
-|version  |R version 4.3.0 (2023-04-21)                                                               |
-|os       |macOS Ventura 13.5                                                                         |
-|system   |aarch64, darwin20                                                                          |
-|ui       |RStudio                                                                                    |
-|language |(EN)                                                                                       |
-|collate  |en_US.UTF-8                                                                                |
-|ctype    |en_US.UTF-8                                                                                |
-|tz       |America/Los_Angeles                                                                        |
-|date     |2023-08-14                                                                                 |
-|rstudio  |2023.09.0-daily+310 Desert Sunflower (desktop)                                             |
-|pandoc   |3.1.1 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/ (via rmarkdown) |
+|field    |value                                              |
+|:--------|:--------------------------------------------------|
+|version  |R version 4.3.1 (2023-06-16)                       |
+|os       |macOS Ventura 13.6                                 |
+|system   |aarch64, darwin20                                  |
+|ui       |X11                                                |
+|language |(EN)                                               |
+|collate  |en_US.UTF-8                                        |
+|ctype    |en_US.UTF-8                                        |
+|tz       |America/Los_Angeles                                |
+|date     |2023-10-17                                         |
+|pandoc   |3.1.3 @ /Users/emilhvitfeldt/miniforge3/bin/pandoc |
 
 # Dependencies
 
 |package      |old        |new        |Δ  |
 |:------------|:----------|:----------|:--|
-|textrecipes  |1.0.3      |1.0.3.9000 |*  |
+|textrecipes  |1.0.4      |1.0.4.9000 |*  |
 |cli          |3.6.1      |3.6.1      |   |
 |clock        |0.7.0      |0.7.0      |   |
 |cpp11        |0.4.6      |0.4.6      |   |
 |data.table   |1.14.8     |1.14.8     |   |
 |diagram      |1.6.5      |1.6.5      |   |
 |digest       |0.6.33     |0.6.33     |   |
-|dplyr        |1.1.2      |1.1.2      |   |
+|dplyr        |1.1.3      |1.1.3      |   |
 |ellipsis     |0.3.2      |0.3.2      |   |
-|fansi        |1.0.4      |1.0.4      |   |
+|fansi        |1.0.5      |1.0.5      |   |
 |future       |1.33.0     |1.33.0     |   |
 |future.apply |1.11.0     |1.11.0     |   |
 |generics     |0.1.3      |0.1.3      |   |
@@ -39,18 +38,18 @@
 |lava         |1.7.2.1    |1.7.2.1    |   |
 |lifecycle    |1.0.3      |1.0.3      |   |
 |listenv      |0.9.0      |0.9.0      |   |
-|lubridate    |1.9.2      |1.9.2      |   |
+|lubridate    |1.9.3      |1.9.3      |   |
 |magrittr     |2.0.3      |2.0.3      |   |
 |numDeriv     |2016.8-1.1 |2016.8-1.1 |   |
 |parallelly   |1.36.0     |1.36.0     |   |
 |pillar       |1.9.0      |1.9.0      |   |
 |pkgconfig    |2.0.3      |2.0.3      |   |
-|prodlim      |2023.03.31 |2023.03.31 |   |
+|prodlim      |2023.08.28 |2023.08.28 |   |
 |progressr    |0.14.0     |0.14.0     |   |
 |purrr        |1.0.2      |1.0.2      |   |
 |R6           |2.5.1      |2.5.1      |   |
 |Rcpp         |1.0.11     |1.0.11     |   |
-|recipes      |1.0.7      |1.0.7      |   |
+|recipes      |1.0.8      |1.0.8      |   |
 |rlang        |1.1.1      |1.1.1      |   |
 |shape        |1.4.6      |1.4.6      |   |
 |SnowballC    |0.7.1      |0.7.1      |   |
@@ -65,8 +64,8 @@
 |tokenizers   |0.3.0      |0.3.0      |   |
 |tzdb         |0.4.0      |0.4.0      |   |
 |utf8         |1.2.3      |1.2.3      |   |
-|vctrs        |0.6.3      |0.6.3      |   |
-|withr        |2.5.0      |2.5.0      |   |
+|vctrs        |0.6.4      |0.6.4      |   |
+|withr        |2.5.1      |2.5.1      |   |
 
 # Revdeps
 
diff --git a/tests/testthat/test-dummy_hash.R b/tests/testthat/test-dummy_hash.R
@@ -9,7 +9,8 @@ rec <- recipe(~., data = test_data)
 
 test_that("hashing gives double outputs", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- rec %>%
     step_dummy_hash(sponsor_code)
@@ -30,7 +31,8 @@ test_that("hashing gives double outputs", {
 })
 
 test_that("hashing multiple factors", {
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   res <- rec %>%
     step_dummy_hash(all_nominal_predictors(), num_terms = 12) %>%
@@ -43,7 +45,8 @@ test_that("hashing multiple factors", {
 })
 
 test_that("hashing collapsed multiple factors", {
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   res <- rec %>%
     step_dummy_hash(all_nominal_predictors(), num_terms = 4, collapse = TRUE) %>%
@@ -56,7 +59,8 @@ test_that("hashing collapsed multiple factors", {
 
 test_that("hashing output width changes accordingly with num_terms", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- rec %>%
     step_dummy_hash(sponsor_code, num_terms = 256) %>%
@@ -72,7 +76,8 @@ test_that("hashing output width changes accordingly with num_terms", {
 
 test_that("hashing output width changes accordingly with num_terms", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   signed <- recipe(~., data = test_data) %>%
     step_dummy_hash(all_predictors(), num_terms = 2) %>%
@@ -92,7 +97,8 @@ test_that("hashing output width changes accordingly with num_terms", {
 
 test_that("check_name() is used", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   dat <- test_data
   dat$text <- dat$sponsor_code
@@ -183,7 +189,8 @@ test_that("empty selection tidy method works", {
 
 test_that("keep_original_cols works", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   new_names <- paste0("dummyhash_sponsor_code_", 1:5)
 
@@ -212,7 +219,8 @@ test_that("keep_original_cols works", {
 
 test_that("keep_original_cols - can prep recipes with it missing", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- recipe(~ sponsor_code, data = test_data) %>%
     step_dummy_hash(sponsor_code)
@@ -232,7 +240,8 @@ test_that("keep_original_cols - can prep recipes with it missing", {
 
 test_that("printing", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- rec %>%
     step_dummy_hash(sponsor_code)

diff --git a/tests/testthat/test-lda.R b/tests/testthat/test-lda.R
@@ -9,7 +9,8 @@ rec <- recipe(~ medium + artist, data = tate_text[seq_len(n_rows), ])
 
 test_that("step_lda works as intended", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   n_top <- 10
   rec1 <- rec %>%
@@ -27,7 +28,8 @@ test_that("step_lda works as intended", {
 
 test_that("step_lda works with num_topics argument", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   n_top <- 100
   rec1 <- rec %>%
@@ -42,7 +44,8 @@ test_that("step_lda works with num_topics argument", {
 
 test_that("check_name() is used", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   dat <- tate_text[seq_len(100), ]
   dat$text <- dat$medium
@@ -62,7 +65,8 @@ test_that("check_name() is used", {
 
 test_that("bake method errors when needed non-standard role columns are missing", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   tokenized_test_data <- rec %>%
     step_tokenize(medium) %>%
@@ -126,7 +130,8 @@ test_that("empty selection tidy method works", {
 
 test_that("keep_original_cols works", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   new_names <- paste0("lda_medium_", 1:10)
 
@@ -157,7 +162,8 @@ test_that("keep_original_cols works", {
 
 test_that("keep_original_cols - can prep recipes with it missing", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- recipe(~ medium, data = tate_text[seq_len(n_rows), ]) %>%
     step_tokenize(medium) %>%
@@ -178,7 +184,8 @@ test_that("keep_original_cols - can prep recipes with it missing", {
 
 test_that("printing", {
   skip_if_not_installed("text2vec")
-  skip_on_cran() # because data.table uses all cores by default 
+  skip_if_not_installed("data.table")
+  data.table::setDTthreads(2) # because data.table uses all cores by default 
 
   rec <- rec %>%
     step_tokenize(medium) %>%