Merge branch 'main' into type-checkers

R/cut.R

@@ -139,13 +139,38 @@ prep.step_cut <- function(x, training, info = NULL, ...) {
   )
 }
 
-create_full_breaks <- function(var, breaks) {
+create_full_breaks <- function(var, breaks, call = rlang::caller_env()) {
+  if (!is.numeric(var)) {
+    cli::cli_abort(
+      "{.arg var} must be a numeric vector, not {.obj_type_friendly {var}}.",
+      call = call
+    )
+  }
+
+  if (!is.numeric(breaks)) {
+    cli::cli_abort(
+      "{.arg breaks} must be a numeric vector, not {.obj_type_friendly {breaks}}.",
+      call = call
+    )
+  }
+
+  if (any(is.na(var))) {
+    cli::cli_warn(
+      "{.arg var} contains missing values. These will be ignored in break
+       calculations.",
+      call = call
+    )
+    var <- var[!is.na(var)]
+  }
+
   if (min(var) < min(breaks)) {
     breaks <- c(min(var), breaks)
   }
+
   if (max(var) > max(breaks)) {
     breaks <- c(max(var), breaks)
   }
+
   sort(breaks)
 }
 

tests/testthat/test-cut.R

@@ -172,6 +172,28 @@ test_that("tidy method works", {
   )
 })
 
+test_that("step_cut() provides informative error on missing values", {
+  # Single missing value
+  mtcars_with_na <- mtcars
+  mtcars_with_na[1, "mpg"] <- NA
+
+  expect_warning(
+    recipe(~ ., data = mtcars_with_na) %>%
+      step_cut(mpg, breaks = 20) %>%
+      prep()
+  )
+
+  # Multiple missing values
+  mtcars_with_nas <- mtcars
+  mtcars_with_nas[c(1, 3, 5), "mpg"] <- NA
+
+  expect_warning(
+    recipe(~ ., data = mtcars_with_nas) %>%
+      step_cut(mpg, breaks = 20) %>%
+      prep()
+  )
+})
+
 test_that("breaks argument are type checked", {
   expect_snapshot(
     error = TRUE,
@@ -188,6 +210,7 @@ test_that("breaks argument are type checked", {
   )
 })
 
+
 # Infrastructure ---------------------------------------------------------------
 
 test_that("bake method errors when needed non-standard role columns are missing", {