Merge branch 'master' into bundle

Author: sebffischer

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: mlr3pipelines
 Title: Preprocessing Operators and Pipelines for 'mlr3'
-Version: 0.5.1-9000
+Version: 0.5.2-9000
 Authors@R:
     c(person(given = "Martin",
              family = "Binder",
@@ -86,7 +86,8 @@ Suggests:
     GenSA,
     methods,
     vtreat,
-    future
+    future,
+    htmlwidgets
 ByteCompile: true
 Encoding: UTF-8
 Config/testthat/edition: 3
@@ -175,6 +176,7 @@ Collate:
     'operators.R'
     'pipeline_bagging.R'
     'pipeline_branch.R'
+    'pipeline_convert_types.R'
     'pipeline_greplicate.R'
     'pipeline_ovr.R'
     'pipeline_robustify.R'

NAMESPACE

@@ -127,6 +127,7 @@ export(mlr_graphs)
 export(mlr_pipeops)
 export(pipeline_bagging)
 export(pipeline_branch)
+export(pipeline_convert_types)
 export(pipeline_greplicate)
 export(pipeline_ovr)
 export(pipeline_robustify)

NEWS.md

@@ -1,4 +1,10 @@
-# mlr3pipelines 0.5.1-9000
+# mlr3pipelines 0.5.2-9000
+
+# mlr3pipelines 0.5.2
+
+* Added new `ppl("convert_types")`.
+* Minor documentation fixes.
+* Test helpers are now available in `inst/`. These are considered experimental and unstable.
 
 * Added marshaling support to `GraphLearner`
 

R/GraphLearner.R

@@ -68,6 +68,7 @@
 #' @family Learners
 #' @export
 #' @examples
+#' \dontshow{ if (requireNamespace("rpart")) \{ }
 #' library("mlr3")
 #'
 #' graph = po("pca") %>>% lrn("classif.rpart")
@@ -86,6 +87,7 @@
 #'
 #' # Feature importance (of principal components):
 #' lr$graph_model$pipeops$classif.rpart$learner_model$importance()
+#' \dontshow{ \} }
 GraphLearner = R6Class("GraphLearner", inherit = Learner,
   public = list(
     initialize = function(graph, id = NULL, param_vals = list(), task_type = NULL, predict_type = NULL, clone_graph = TRUE) {

R/PipeOpBoxCox.R

@@ -48,6 +48,7 @@
 #' Only methods inherited from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @examples
+#' \dontshow{ if (requireNamespace("bestNormalize")) \{ }
 #' library("mlr3")
 #'
 #' task = tsk("iris")
@@ -57,6 +58,7 @@
 #' pop$train(list(task))[[1]]$data()
 #'
 #' pop$state
+#' \dontshow{ \} }
 #' @family PipeOps
 #' @include PipeOpTaskPreproc.R
 #' @template seealso_pipeopslist

R/PipeOpClassifAvg.R

@@ -64,6 +64,7 @@
 #' @export
 #'
 #' @examples
+#' \dontshow{ if (requireNamespace("rpart")) \{ }
 #' \donttest{
 #' library("mlr3")
 #'
@@ -77,6 +78,7 @@
 #'
 #' resample(tsk("iris"), GraphLearner$new(gr), rsmp("holdout"))
 #' }
+#' \dontshow{ \} }
 PipeOpClassifAvg = R6Class("PipeOpClassifAvg",
   inherit = PipeOpEnsemble,
   public = list(

R/PipeOpEncode.R

@@ -5,7 +5,7 @@
 #' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
-#' Encodes columns of type `factor`, `character` and `ordered`.
+#' Encodes columns of type `factor` and `ordered`.
 #'
 #' Possible encodings are `"one-hot"` encoding, as well as encoding according to `stats::contr.helmert()`, `stats::contr.poly()`,
 #' `stats::contr.sum()` and `stats::contr.treatment()`.
@@ -14,6 +14,8 @@
 #'
 #' Use the [`PipeOpTaskPreproc`] `$affect_columns` functionality to only encode a subset of columns, or only encode columns of a certain type.
 #'
+#' `character`-type features can be encoded by converting them `factor` features first, using [`ppl("convert_types", "character", "factor")`][mlr_graphs_convert_types].
+#'
 #' @section Construction:
 #' ```
 #' PipeOpEncode$new(id = "encode", param_vals = list())
@@ -26,7 +28,7 @@
 #' @section Input and Output Channels:
 #' Input and output channels are inherited from [`PipeOpTaskPreproc`].
 #'
-#' The output is the input [`Task`][mlr3::Task] with all affected `factor`, `character` or `ordered` parameters encoded according to the `method`
+#' The output is the input [`Task`][mlr3::Task] with all affected `factor` and `ordered` parameters encoded according to the `method`
 #' parameter.
 #'
 #' @section State:
@@ -78,6 +80,14 @@
 #'
 #' poe$param_set$values$method = "sum"
 #' poe$train(list(task))[[1]]$data()
+#'
+#' # converting character-columns
+#' data_chr = data.table::data.table(x = factor(letters[1:3]), y = letters[1:3])
+#' task_chr = TaskClassif$new("task_chr", data_chr, "x")
+#'
+#' goe = ppl("convert_types", "character", "factor") %>>% po("encode")
+#'
+#' goe$train(task_chr)[[1]]$data()
 PipeOpEncode = R6Class("PipeOpEncode",
   inherit = PipeOpTaskPreprocSimple,
   public = list(

R/PipeOpEncodeLmer.R

@@ -72,6 +72,8 @@
 #' @include PipeOpTaskPreproc.R
 #' @export
 #' @examples
+#' \dontshow{ if (requireNamespace("nloptr")) \{ }
+#' \dontshow{ if (requireNamespace("lme4")) \{ }
 #' library("mlr3")
 #' poe = po("encodelmer")
 #'
@@ -84,6 +86,8 @@
 #' poe$train(list(task))[[1]]$data()
 #'
 #' poe$state
+#' \dontshow{ \} }
+#' \dontshow{ \} }
 PipeOpEncodeLmer = R6Class("PipeOpEncodeLmer",
   inherit = PipeOpTaskPreprocSimple,
   public = list(

R/PipeOpFilter.R

@@ -80,6 +80,8 @@
 #' @include PipeOpTaskPreproc.R
 #' @export
 #' @examples
+#' \dontshow{ if (requireNamespace("mlr3filters")) \{ }
+#' \dontshow{ if (requireNamespace("rpart")) \{ }
 #' library("mlr3")
 #' library("mlr3filters")
 #' \dontshow{data.table::setDTthreads(1)}
@@ -107,6 +109,8 @@
 #' learner = GraphLearner$new(gr)
 #' rr = resample(task, learner, rsmp("holdout"), store_models = TRUE)
 #' rr$learners[[1]]$model$auc$scores
+#' \dontshow{ \} }
+#' \dontshow{ \} }
 PipeOpFilter = R6Class("PipeOpFilter",
   inherit = PipeOpTaskPreprocSimple,
   public = list(

R/PipeOpICA.R

@@ -73,6 +73,7 @@
 #' Only methods inherited from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @examples
+#' \dontshow{ if (requireNamespace("fastICA")) \{ }
 #' library("mlr3")
 #'
 #' task = tsk("iris")
@@ -82,6 +83,7 @@
 #' pop$train(list(task))[[1]]$data()
 #'
 #' pop$state
+#' \dontshow{ \} }
 #' @family PipeOps
 #' @template seealso_pipeopslist
 #' @include PipeOpTaskPreproc.R