Merge pull request #939 from mlr-org/version-0.9.0

Version 0.9.0

Author: mb706

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: mlr3pipelines
 Title: Preprocessing Operators and Pipelines for 'mlr3'
-Version: 0.8.0-9000
+Version: 0.9.0
 Authors@R:
     c(person(given = "Martin",
              family = "Binder",

NEWS.md

@@ -1,15 +1,16 @@
-# mlr3pipelines 0.8.0-9000
+# mlr3pipelines 0.9.0
+
 * Breaking change: Removed initialization of `PipeOpImputeConstant`'s `constant` hyperparameter since it was incompatible with other defaults and would lead to not recommended usage (creating an empty level).
-* Fixed a grammatical error in `PipeOp`'s error message wrapper: now correctly says "This happened *in* ...".
+* Removed compatibility for old `paradox` versions pre-1.0.0.
 * Added `empty_level_control` argument to `PipeOpImpute` allowing control over edge cases for `factor`/`ordered` columns.
 * Set new construction argument `empty_level_control` to `"param"` for `PipeOpImputeOOR` and to `"always"` for `PipeOpImputeConstant`.
-* Fix: `PipeOpImputeOOR` now imputes `".MISSING"` for `factor`/`ordered` features with only `NA`s instead of sampling from the feature's levels.
-* Fix: `PipeOpImputeLearner` no longer adds `"factor"` or `"ordered"` levels for these feature types arbitrarily and instead updates levels correctly in certain edge-cases.
-* Fixed the error message for unexpected Multiplicities in the input and output type checking during `PipeOp`s training and prediction.
 * Untrained `PipeOp`s that take `NULL` as input during training now automatically perform training during prediction.
 * `PipeOpImputeConstant`, `PipeOpImputeMode`, `PipeOpImputeOOR`, and `PipeOpImputeLearner` can now handle `factor` or `ordered` features with zero levels.
 * `PipeOpImputeConstant` now gives a more informative error message if `check_levels` is `TRUE` and a new level would be created through imputation.
-* Removed compatibility for old `paradox` versions pre-1.0.0.
+* Fix: `PipeOpImputeOOR` now imputes `".MISSING"` for `factor`/`ordered` features with only `NA`s instead of sampling from the feature's levels.
+* Fix: `PipeOpImputeLearner` no longer adds `"factor"` or `"ordered"` levels for these feature types arbitrarily and instead updates levels correctly in certain edge-cases.
+* Fixed the error message for unexpected Multiplicities in the input and output type checking during `PipeOp`s training and prediction.
+* Fixed a grammatical error in `PipeOp`'s error message wrapper: now correctly says "This happened *in* ...".
 
 # mlr3pipelines 0.8.0
 

R/PipeOpImputeOOR.R

@@ -14,7 +14,7 @@
 #' This type of imputation is especially sensible in the context of tree-based methods, see also
 #' Ding & Simonoff (2010).
 #'
-#' [`Learner`s][mlr3::Learner] expect input [`Task`s][mlr3::Task] to have the same `factor` (or `ordered`) levels during
+#' [`Learner`][mlr3::Learner]s expect input [`Task`][mlr3::Task]s to have the same `factor` (or `ordered`) levels during
 #' training as well as prediction. This `PipeOp` modifies the levels of `factor` and `ordered` features,
 #' and since it may occur that a `factor` or `ordered` feature contains missing values only during prediction, but not
 #' during training, the output `Task` could also have different levels during the two stages.