Add tests for factor level ordering issue

tidymodels · Jun 22, 2020 · 6580081 · 6580081
1 parent 23effbb
commit 6580081
Show file tree

Hide file tree

Showing 9 changed files with 43 additions and 0 deletions.
diff --git a/tests/testthat/helper-test-functions.R b/tests/testthat/helper-test-functions.R
@@ -243,3 +243,38 @@ test_multi_minority <- function(step, ...) {
     expect_true(all(max(table(rec1_p2$Species)) == 25))
   })
 }
+
+test_factor_level_memory <- function(step, ...) {
+  # Only checks for two level case
+
+  circle_example_alt_levels <- list()
+  for(i in 1:4) circle_example_alt_levels[[i]] <- circle_example
+
+  # Checking for forgetting levels by majority/minor switching
+  for(i in c(2, 4)){
+    levels(circle_example_alt_levels[[i]]$class) <- rev(levels(circle_example_alt_levels[[i]]$class))
+  }
+
+  # Checking for forgetting levels by alphabetical switching
+  for(i in c(3, 4)){
+    circle_example_alt_levels[[i]]$class <- factor(circle_example_alt_levels[[i]]$class, levels = rev(levels(circle_example_alt_levels[[i]]$class)))
+  }
+
+  test_that("factor levels are not affected by alphabet ordering or class sizes", {
+    for(i in 1:4){
+      rec_p <- recipe(~ ., data = circle_example_alt_levels[[i]]) %>%
+        step(class) %>%
+        prep(training = circle_example_alt_levels[[i]])
+
+      expect_equal(
+        levels(circle_example_alt_levels[[i]]$class), # Original levels
+        rec_p$levels$class$values                     # New levels
+      )
+      expect_equal(
+        levels(circle_example_alt_levels[[i]]$class), # Original levels
+        levels(juice(rec_p)$class)                    # New levels
+      )
+    }
+  })
+
+}
diff --git a/tests/testthat/test-adasyn.R b/tests/testthat/test-adasyn.R
@@ -29,3 +29,4 @@ test_tidy(step_adasyn)
 test_over_ratio(step_adasyn)
 test_multiclass(step_adasyn)
 test_multi_majority(step_adasyn)
+test_factor_level_memory(step_adasyn)
diff --git a/tests/testthat/test-bsmote.R b/tests/testthat/test-bsmote.R
@@ -57,3 +57,4 @@ test_over_ratio(step_bsmote, all_neighbors = TRUE)
 test_multiclass(step_bsmote)
 test_multi_majority(step_bsmote)
 test_multi_majority(step_bsmote, all_neighbors = TRUE)
+test_factor_level_memory(step_bsmote)
diff --git a/tests/testthat/test-downsample.R b/tests/testthat/test-downsample.R
@@ -36,3 +36,4 @@ test_tidy(step_downsample)
 test_under_ratio(step_downsample)
 test_multiclass(step_downsample)
 test_multi_minority(step_downsample)
+test_factor_level_memory(step_downsample)
diff --git a/tests/testthat/test-nearmiss.R b/tests/testthat/test-nearmiss.R
@@ -31,3 +31,4 @@ test_tidy(step_nearmiss)
 test_under_ratio(step_nearmiss)
 test_multiclass(step_nearmiss, rename(iris[-c(1:25, 51:75), ], class = Species))
 test_multi_minority(step_nearmiss)
+test_factor_level_memory(step_nearmiss)
diff --git a/tests/testthat/test-rose.R b/tests/testthat/test-rose.R
@@ -48,3 +48,4 @@ test_na_response(step_rose)
 test_seed(step_rose)
 test_tidy(step_rose)
 test_2_class_only(step_rose)
+test_factor_level_memory(step_rose)
diff --git a/tests/testthat/test-smote.R b/tests/testthat/test-smote.R
@@ -45,3 +45,4 @@ test_tidy(step_smote)
 test_over_ratio(step_smote)
 test_multiclass(step_smote)
 test_multi_majority(step_smote)
+test_factor_level_memory(step_smote)
diff --git a/tests/testthat/test-tomek.R b/tests/testthat/test-tomek.R
@@ -12,3 +12,4 @@ test_character_error(step_tomek)
 test_na_response(step_tomek)
 test_tidy(step_tomek)
 test_2_class_only(step_tomek)
+test_factor_level_memory(step_tomek)
diff --git a/tests/testthat/test-upsample.R b/tests/testthat/test-upsample.R
@@ -37,3 +37,4 @@ test_tidy(step_upsample)
 test_over_ratio(step_upsample)
 test_multiclass(step_upsample)
 test_multi_majority(step_upsample)
+test_factor_level_memory(step_upsample)