release: 0.13.1 (#758)

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: mlr3
 Title: Machine Learning in R - Next Generation
-Version: 0.13.0-9000
+Version: 0.13.1
 Authors@R:
     c(person(given = "Michel",
              family = "Lang",
@@ -67,7 +67,7 @@ Imports:
     future.apply (>= 1.5.0),
     lgr (>= 0.3.4),
     mlbench,
-    mlr3measures (>= 0.4.0),
+    mlr3measures (>= 0.4.1),
     mlr3misc (>= 0.10.0),
     parallelly,
     palmerpenguins,

NEWS.md

@@ -1,3 +1,13 @@
+# mlr3 0.13.1
+
+* Improved performance for many operations on `ResampleResult` and
+  `BenchmarkResult`.
+* `resample()` and `benchmark()` got a new argument `clone` to control which
+  objects to clone before performing computations.
+* Tasks are checked for infinite values during the conversion from `data.frame`
+  to `Task` in `as_task_classif()` and `as_task_regr()`. A warning is signaled
+  if any column contains infinite values.
+
 # mlr3 0.13.0
 
 * Learners which are capable of resuming/continuing (e.g.,
@@ -87,7 +97,7 @@
   respectively. Note that this behavior will eventually will be the default for
   future releases.
 * Prediction objects generated by `Learner$predict_newdata()` now have row ids
-  starting from 1 instead auto incrementing row ids of the training task.
+  starting from 1 instead auto incremented row ids of the training task.
 * `as.data.table.DictionaryTasks` now returns an additional column `properties`.
 * Added flag `conditions` to `ResampleResult$score()` and
   `BenchmarkResult$score()` to allow to work with failing learners more

R/BenchmarkResult.R

@@ -4,8 +4,8 @@
 #'
 #' @description
 #' This is the result container object returned by [benchmark()].
-#' A [BenchmarkResult] consists of the data row-binded data of multiple
-#' [ResampleResult]s, which can easily be re-constructed.
+#' A [BenchmarkResult] consists of the data of multiple
+#' [ResampleResult]s.
 #'
 #' [BenchmarkResult]s can be visualized via \CRANpkg{mlr3viz}'s `autoplot()` function.
 #'

R/LearnerClassifFeatureless.R

@@ -4,7 +4,7 @@
 #' @include LearnerClassif.R
 #'
 #' @description
-#' A simple [LearnerClassif] which only analyses the labels during train, ignoring all features.
+#' A simple [LearnerClassif] which only analyzes the labels during train, ignoring all features.
 #' Hyperparameter `method` determines the mode of operation during prediction:
 #' \describe{
 #'   \item{mode:}{Predicts the most frequent label. If there are two or more labels tied, randomly selects one per prediction.}

R/LearnerRegrFeatureless.R

@@ -4,7 +4,7 @@
 #' @include LearnerRegr.R
 #'
 #' @description
-#' A simple [LearnerRegr] which only analyses the response during train, ignoring all features.
+#' A simple [LearnerRegr] which only analyzes the response during train, ignoring all features.
 #' If hyperparameter `robust` is `FALSE` (default), constantly predicts `mean(y)` as response
 #' and `sd(y)` as standard error.
 #' If `robust` is `TRUE`, [median()] and [mad()] are used instead of [mean()] and [sd()],

R/worker.R

@@ -61,13 +61,15 @@ learner_train = function(learner, task, row_ids = NULL, mode = "train") {
     train_time = learner$state$train_time + result$elapsed
   }
 
+  proto = task$data(rows = integer())
   learner$state = insert_named(learner$state, list(
     model = result$result,
     log = log,
     train_time = result$elapsed,
     param_vals = learner$param_set$values,
     task_hash = task$hash,
-    data_prototype = task$data(rows = integer()),
+    data_prototype = proto,
+    task_prototype = proto, # deprecated, remove for mlr3learners > 0.5.1
     mlr3_version = packageVersion("mlr3")
   ))