Merge pull request #260 from tidymodels/update-snapshots

Update snapshots

Author: EmilHvitfeldt

DESCRIPTION

@@ -42,6 +42,7 @@ Suggests:
     janitor,
     knitr,
     modeldata,
+    reticulate,
     rmarkdown,
     sentencepiece,
     spacyr,

tests/testthat/_snaps/R4.3/tokenize_bpe.md

@@ -0,0 +1,10 @@
+# Errors if vocabulary size is set to low.
+
+    Code
+      recipe(~text1, data = test_data) %>% step_tokenize_bpe(text1, vocabulary_size = 10) %>%
+        prep()
+    Condition
+      Error in `step_tokenize_bpe()`:
+      Caused by error in `prep()`:
+      ! `vocabulary_size` of 10 is too small for column `text1` which has a unique character count of 23
+

tests/testthat/_snaps/R4.3/tokenizer-tokenizersbpe.md

@@ -0,0 +1,10 @@
+# Errors if vocabulary size is set to low.
+
+    Code
+      recipe(~text, data = tibble(text = "hello")) %>% step_tokenize(text, engine = "tokenizers.bpe",
+        training_options = list(vocab_size = 2)) %>% prep()
+    Condition
+      Error in `step_tokenize()`:
+      Caused by error in `prep()`:
+      ! `vocabulary_size` of 2 is too small for column `text` which has a unique character count of 4
+

tests/testthat/_snaps/clean_names.md

@@ -64,5 +64,5 @@
       Training data contained 20 data points and 4 incomplete rows.
       
       -- Operations 
-      * Cleaning variable names for: Ozone, Solar.R, Wind, Temp, Month, Day | Trained
+      * Cleaning variable names for: Ozone, Solar.R, Wind, Temp, ... | Trained
 

tests/testthat/_snaps/dummy_hash.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_dummy_hash()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  dummyhash_text_01
+      ! Name collision occurred. The following variable names already exist:
+      * `dummyhash_text_01`
 
 # empty printing
 
@@ -49,8 +49,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_dummy_hash()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_dummy_hash()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/lda.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_lda()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  lda_text_1
+      ! Name collision occurred. The following variable names already exist:
+      * `lda_text_1`
 
 # empty printing
 
@@ -49,8 +49,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_lda()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_lda()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/sequence_onehot.md

@@ -38,8 +38,8 @@
     Condition
       Error in `step_sequence_onehot()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  seq1hot_text_1
+      ! Name collision occurred. The following variable names already exist:
+      * `seq1hot_text_1`
 
 # empty printing
 
@@ -82,8 +82,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_sequence_onehot()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_sequence_onehot()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/textfeature.md

@@ -26,8 +26,8 @@
     Condition
       Error in `step_textfeature()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  textfeature_text_n_words
+      ! Name collision occurred. The following variable names already exist:
+      * `textfeature_text_n_words`
 
 # empty printing
 
@@ -70,17 +70,17 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_tf()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_tf()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 ---
 
     Code
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_textfeature()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_textfeature()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/texthash.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_texthash()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  texthash_text_0001
+      ! Name collision occurred. The following variable names already exist:
+      * `texthash_text_0001`
 
 # empty printing
 
@@ -49,8 +49,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_texthash()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_texthash()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/tf.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_tf()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  tf_text_i
+      ! Name collision occurred. The following variable names already exist:
+      * `tf_text_i`
 
 # empty printing
 
@@ -49,8 +49,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_tf()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_tf()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/tfidf.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_tfidf()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  tfidf_text_i
+      ! Name collision occurred. The following variable names already exist:
+      * `tfidf_text_i`
 
 # Backwards compatibility with 1592690d36581fc5f4952da3e9b02351b31f1a2e
 
@@ -69,8 +69,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_tfidf()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_tfidf()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/_snaps/tokenize_bpe.md

@@ -1,13 +1,3 @@
-# Errors if vocabulary size is set to low.
-
-    Code
-      recipe(~text1, data = test_data) %>% step_tokenize_bpe(text1, vocabulary_size = 10) %>%
-        prep()
-    Condition
-      Error in `step_tokenize_bpe()`:
-      Caused by error in `prep()`:
-      ! `vocabulary_size` of 10 is too small for column `text1` which has a unique character count of 23
-
 # empty printing
 
     Code

tests/testthat/_snaps/tokenizer-tokenizersbpe.md

@@ -14,13 +14,3 @@
       Error:
       ! Invalid index: field name 'pos' not found
 
-# Errors if vocabulary size is set to low.
-
-    Code
-      recipe(~text, data = tibble(text = "hello")) %>% step_tokenize(text, engine = "tokenizers.bpe",
-        training_options = list(vocab_size = 2)) %>% prep()
-    Condition
-      Error in `step_tokenize()`:
-      Caused by error in `prep()`:
-      ! `vocabulary_size` of 2 is too small for column `text` which has a unique character count of 4
-

tests/testthat/_snaps/tokenmerge.md

@@ -5,7 +5,8 @@
     Condition
       Error in `step_tokenmerge()`:
       Caused by error in `prep()`:
-      ! All columns selected for the step should be tokenlist.
+      x All columns selected for the step should be tokenlist.
+      * 2 factor variables found: `text1` and `text2`
 
 # check_name() is used
 
@@ -14,8 +15,8 @@
     Condition
       Error in `step_tokenmerge()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  tokenmerge
+      ! Name collision occurred. The following variable names already exist:
+      * `tokenmerge`
 
 # empty printing
 
@@ -58,8 +59,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_tokenmerge()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_tokenmerge()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 
@@ -74,8 +75,8 @@
       predictor: 2
       
       -- Operations 
-      * Tokenization for: text1, text2
-      * Merging tokens for: text1, text2
+      * Tokenization for: text1 and text2
+      * Merging tokens for: text1 and text2
 
 ---
 
@@ -93,6 +94,6 @@
       Training data contained 4 data points and no incomplete rows.
       
       -- Operations 
-      * Tokenization for: text1, text2 | Trained
-      * Merging tokens for: text1, text2 | Trained
+      * Tokenization for: text1 and text2 | Trained
+      * Merging tokens for: text1 and text2 | Trained
 

tests/testthat/_snaps/word_embeddings.md

@@ -5,8 +5,8 @@
     Condition
       Error in `step_word_embeddings()`:
       Caused by error in `bake()`:
-      ! Name collision occured. The following variable names already exists:
-      i  wordembed_text_d1
+      ! Name collision occurred. The following variable names already exist:
+      * `wordembed_text_d1`
 
 # empty printing
 
@@ -49,8 +49,8 @@
       rec <- prep(rec)
     Condition
       Warning:
-      'keep_original_cols' was added to `step_word_embeddings()` after this recipe was created.
-      Regenerate your recipe to avoid this warning.
+      `keep_original_cols` was added to `step_word_embeddings()` after this recipe was created.
+      i Regenerate your recipe to avoid this warning.
 
 # printing
 

tests/testthat/helper-functions.R

@@ -1,11 +1,7 @@
 skip_if_no_python_or_no_spacy <- function() {
-  if (spacyr::find_spacy_env()) {
+  if (reticulate::py_module_available("spacy")) {
     return(NULL)
-  }
-  spacy_path <- spacyr::find_spacy(ask = FALSE)
-  if (is.null(spacy_path)) {
+  } else {
     testthat::skip("Skip the test as spaCy is not found")
-  } else if (is.na(spacy_path)) {
-    testthat::skip("Skip the test as python is not found")
   }
 }

tests/testthat/test-tokenize_bpe.R

@@ -1,6 +1,8 @@
 library(textrecipes)
 library(recipes)
 
+r_version <- function() paste0("R", getRversion()[, 1:2])
+
 text1 <- c(
   "I would not eat them here or there.",
   "I would not eat them anywhere.",
@@ -122,7 +124,8 @@ test_that("arguments are passed to tokenizers.bpe", {
 
 test_that("Errors if vocabulary size is set to low.", {
   expect_snapshot(
-    error = TRUE,
+    error = TRUE, 
+    variant = r_version(),
     recipe(~text1, data = test_data) %>%
       step_tokenize_bpe(text1, vocabulary_size = 10) %>%
       prep()

tests/testthat/test-tokenizer-tokenizersbpe.R

@@ -1,6 +1,8 @@
 library(textrecipes)
 library(recipes)
 
+r_version <- function() paste0("R", getRversion()[, 1:2])
+
 text1 <- c(
   "I would not eat them here or there.",
   "I would not eat them anywhere.",
@@ -154,6 +156,7 @@ test_that("arguments are passed to tokenizers.bpe", {
 test_that("Errors if vocabulary size is set to low.", {
   expect_snapshot(
     error = TRUE,
+    variant = r_version(),
     recipe(~text, data = tibble(text = "hello")) %>%
       step_tokenize(text,
         engine = "tokenizers.bpe",