refactor: allow uft8 in column names by default (#1234)

NEWS.md

@@ -1,5 +1,7 @@
 # mlr3 (development version)
 
+* Column names with UTF-8 characters are now allowed by default.
+The option `mlr3.allow_utf8_names` is removed.
 * BREAKING CHANGE: `Learner$predict_types` is read-only now.
 * docs: Clear up behavior of `Learner$predict_type` after training.
 

R/DataBackendRename.R

@@ -9,7 +9,7 @@ DataBackendRename = R6Class("DataBackendRename", inherit = DataBackend, cloneabl
       assert_character(old, any.missing = FALSE, unique = TRUE)
       assert_subset(old, b$colnames)
       assert_character(new, any.missing = FALSE, len = length(old))
-      assert_names(new, if (allow_utf8_names()) "unique" else "strict")
+      assert_names(new, "unique")
 
       ii = old != new
       old = old[ii]

R/Task.R

@@ -128,13 +128,9 @@ Task = R6Class("Task",
       cn = self$backend$colnames
       rn = self$backend$rownames
 
-      if (allow_utf8_names()) {
-        assert_names(cn, "unique", .var.name = "column names")
-        if (any(grepl("%", cn, fixed = TRUE))) {
-          stopf("Column names may not contain special character '%%'")
-        }
-      } else {
-        assert_names(cn, "strict", .var.name = "column names")
+      assert_names(cn, "unique", .var.name = "column names")
+      if (any(grepl("%", cn, fixed = TRUE))) {
+        stopf("Column names may not contain special character '%%'")
       }
 
       self$col_info = col_info(self$backend)

R/helper.R

@@ -4,11 +4,6 @@ translate_types = function(x) {
   factor(map_values(x, r_types, p_types), levels = p_types)
 }
 
-
-allow_utf8_names = function() {
-  isTRUE(getOption("mlr3.allow_utf8_names"))
-}
-
 get_featureless_learner = function(task_type) {
   if (!is.na(task_type)) {
     id = paste0(task_type, ".featureless")

R/zzz.R

@@ -50,10 +50,6 @@
 #' * `"mlr3.debug"`: If set to `TRUE`, parallelization via \CRANpkg{future} is disabled to simplify
 #'   debugging and provide more concise tracebacks.
 #'   Note that results computed in debug mode use a different seeding mechanism and are **not reproducible**.
-#' * `"mlr3.allow_utf8_names"`: If set to `TRUE`, checks on the feature names are relaxed, allowing
-#'   non-ascii characters in column names. This is an experimental and temporal option to
-#'   pave the way for text analysis, and will likely be removed in a future version of the package.
-#'   analysis.
 #' * `"mlr3.warn_version_mismatch"`: Set to `FALSE` to silence warnings raised during predict if a learner has been
 #'   trained with a different version version of mlr3.
 #'

inst/testthat/helper_autotest.R

@@ -81,8 +81,6 @@ generate_generic_tasks = function(learner, proto) {
 
   # task with non-ascii feature names
   if (p > 0L) {
-    opts = options(mlr3.allow_utf8_names = TRUE)
-    on.exit(options(opts))
     sel = proto$feature_types[list(learner$feature_types), "id", on = "type", with = FALSE, nomatch = NULL][[1L]]
     tasks$utf8_feature_names = proto$clone(deep = TRUE)$select(sel)
     old = sel[1L]

tests/testthat/test_Task.R

@@ -552,15 +552,6 @@ test_that("set_levels", {
 })
 
 test_that("special chars in feature names (#697)", {
-  prev = options(mlr3.allow_utf8_names = FALSE)
-  on.exit(options(prev))
-
-  expect_error(
-    TaskRegr$new("test", data.table(`%^` = 1:3, t = 3:1), target = "t"),
-    "comply"
-  )
-  options(mlr3.allow_utf8_names = TRUE)
-
   expect_error(
     TaskRegr$new("test", data.table(`%asd` = 1:3, t = 3:1), target = "t")
     ,