Merge branch 'master' into website

.lintr

@@ -1,10 +1,10 @@
-linters: with_defaults(
-    # lintr defaults: https://github.com/jimhester/lintr#available-linters
+linters: linters_with_defaults(
+    # lintr defaults: https://lintr.r-lib.org/reference/default_linters.html
     # the following setup changes/removes certain linters
     assignment_linter = NULL, # do not force using <- for assignments
     object_name_linter = object_name_linter(c("snake_case", "CamelCase")), # only allow snake case and camel case object names
     cyclocomp_linter = NULL, # do not check function complexity
     commented_code_linter = NULL, # allow code in comments
-    line_length_linter = line_length_linter(180)
+    line_length_linter = line_length_linter(180L)
     )
 

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: mlr3pipelines
 Title: Preprocessing Operators and Pipelines for 'mlr3'
-Version: 0.5.2-9000
+Version: 0.6.0
 Authors@R:
     c(person(given = "Martin",
              family = "Binder",
@@ -52,7 +52,7 @@ Imports:
     data.table,
     digest,
     lgr,
-    mlr3 (>= 0.19.0),
+    mlr3 (>= 0.20.0),
     mlr3misc (>= 0.9.0),
     paradox,
     R6,
@@ -87,7 +87,8 @@ Suggests:
     methods,
     vtreat,
     future,
-    htmlwidgets
+    htmlwidgets,
+    ranger
 ByteCompile: true
 Encoding: UTF-8
 Config/testthat/edition: 3
@@ -153,6 +154,7 @@ Collate:
     'PipeOpRegrAvg.R'
     'PipeOpRemoveConstants.R'
     'PipeOpRenameColumns.R'
+    'PipeOpRowApply.R'
     'PipeOpScale.R'
     'PipeOpScaleMaxAbs.R'
     'PipeOpScaleRange.R'

NAMESPACE

@@ -92,6 +92,7 @@ export(PipeOpRegrAvg)
 export(PipeOpRemoveConstants)
 export(PipeOpRenameColumns)
 export(PipeOpReplicate)
+export(PipeOpRowApply)
 export(PipeOpScale)
 export(PipeOpScaleMaxAbs)
 export(PipeOpScaleRange)

NEWS.md

@@ -1,4 +1,8 @@
-# mlr3pipelines 0.5.2-9000
+# mlr3pipelines 0.6.1
+
+* New PipeOp `PipeOpRowApply` / `po("rowapply")`
+
+# mlr3pipelines 0.6.0
 
 * Compatibility with new `bbotk` release.
 * Added marshaling support to `GraphLearner`

R/Graph.R

@@ -1,8 +1,7 @@
 #' @title Graph Base Class
-#' @format [R6Class] Graph
 #'
 #' @usage NULL
-#' @format [`R6Class`].
+#' @format [`R6Class`][R6::R6Class].
 #'
 #' @description
 #' A [`Graph`] is a representation of a machine learning pipeline graph. It can be *trained*, and subsequently used for *prediction*.
@@ -19,15 +18,15 @@
 #' ```
 #'
 #' @section Internals:
-#' A [`Graph`] is made up of a list of [`PipeOp`]s, and a [`data.table`] of edges. Both for training and prediction, the [`Graph`]
+#' A [`Graph`] is made up of a list of [`PipeOp`]s, and a [`data.table`][data.table::data.table] of edges. Both for training and prediction, the [`Graph`]
 #' performs topological sorting of the [`PipeOp`]s and executes their respective `$train()` or `$predict()` functions in order, moving
 #' the [`PipeOp`] results along the edges as input to other [`PipeOp`]s.
 #'
 #' @section Fields:
 #' * `pipeops` :: named `list` of [`PipeOp`] \cr
 #'   Contains all [`PipeOp`]s in the [`Graph`], named by the [`PipeOp`]'s `$id`s.
-#' * `edges` :: [`data.table`]  with columns `src_id` (`character`), `src_channel` (`character`), `dst_id` (`character`), `dst_channel` (`character`)\cr
-#'   Table of connections between the [`PipeOp`]s. A [`data.table`]. `src_id` and `dst_id` are `$id`s of [`PipeOp`]s that must be present in
+#' * `edges` :: [`data.table`][data.table::data.table]  with columns `src_id` (`character`), `src_channel` (`character`), `dst_id` (`character`), `dst_channel` (`character`)\cr
+#'   Table of connections between the [`PipeOp`]s. A [`data.table`][data.table::data.table]. `src_id` and `dst_id` are `$id`s of [`PipeOp`]s that must be present in
 #'   the `$pipeops` list. `src_channel` and `dst_channel` must respectively be `$output` and `$input` channel names of the
 #'   respective [`PipeOp`]s.
 #' * `is_trained` :: `logical(1)` \cr
@@ -36,10 +35,10 @@
 #'   Ids of the 'left-hand-side' [`PipeOp`]s that have some unconnected input channels and therefore act as [`Graph`] input layer.
 #' * `rhs` :: `character` \cr
 #'   Ids of the 'right-hand-side' [`PipeOp`]s that have some unconnected output channels and therefore act as [`Graph`] output layer.
-#' * `input` :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`), `op.id` (`character`), `channel.name` (`character`)\cr
+#' * `input` :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`), `op.id` (`character`), `channel.name` (`character`)\cr
 #'   Input channels of the [`Graph`]. For each channel lists the name, input type during training, input type during prediction,
 #'   [`PipeOp`] `$id` of the [`PipeOp`] the channel pertains to, and channel name as the [`PipeOp`] knows it.
-#' * `output` :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`), `op.id` (`character`), `channel.name` (`character`)\cr
+#' * `output` :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`), `op.id` (`character`), `channel.name` (`character`)\cr
 #'   Output channels of the [`Graph`]. For each channel lists the name, output type during training, output type during prediction,
 #'   [`PipeOp`] `$id` of the [`PipeOp`] the channel pertains to, and channel name as the [`PipeOp`] knows it.
 #' * `packages` :: `character`\cr

R/GraphLearner.R

@@ -1,7 +1,7 @@
 #' @title Encapsulate a Graph as a Learner
 #'
 #' @name mlr_learners_graph
-#' @format [`R6Class`] object inheriting from [`mlr3::Learner`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`mlr3::Learner`].
 #'
 #' @description
 #' A [`Learner`][mlr3::Learner] that encapsulates a [`Graph`] to be used in
@@ -337,11 +337,11 @@ GraphLearner = R6Class("GraphLearner", inherit = Learner,
 #'   This parameter is ignored when `validate` is set to `NULL`.
 #'   By default, validation is enabled for the final `PipeOp` in the `Graph`.
 #' @param args_all (`list()`)\cr
-#'  Rarely needed. A named list of parameter values that are passed to all subsequet [`set_validate()`] calls on the individual
+#'  Rarely needed. A named list of parameter values that are passed to all subsequet [`set_validate()`][mlr3::set_validate] calls on the individual
 #'  `PipeOp`s.
 #' @param args (named `list()`)\cr
 #'   Rarely needed.
-#'   A named list of lists, specifying additional argments to be passed to [`set_validate()`] when calling it on the individual
+#'   A named list of lists, specifying additional argments to be passed to [`set_validate()`][mlr3::set_validate] when calling it on the individual
 #'   `PipeOp`s.
 #' @param ... (any)\cr
 #'   Currently unused.

R/LearnerAvg.R

@@ -3,7 +3,7 @@
 #' @usage mlr_learners_classif.avg
 #' @name mlr_learners_avg
 #' @aliases mlr_learners_classif.avg
-#' @format [`R6Class`] object inheriting from [`mlr3::LearnerClassif`]/[`mlr3::Learner`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`mlr3::LearnerClassif`]/[`mlr3::Learner`].
 #'
 #' @description
 #' Computes a weighted average of inputs.
@@ -23,7 +23,7 @@
 #' incoming features.
 #'
 #' @section Parameters:
-#' The parameters are the parameters inherited from [`LearnerClassif`], as well as:
+#' The parameters are the parameters inherited from [`LearnerClassif`][mlr3::LearnerClassif], as well as:
 #'  * `measure` :: [`Measure`][mlr3::Measure] | `character` \cr
 #'    [`Measure`][mlr3::Measure] to optimize for.
 #'    Will be converted to a [`Measure`][mlr3::Measure] in case it is `character`.

R/NO_OP.R

@@ -1,6 +1,6 @@
 #' @title No-Op Sentinel Used for Alternative Branching
 #'
-#' @format [`R6`] object.
+#' @format [`R6`][R6::R6] object.
 #'
 #' @description
 #' Special data type for no-ops. Distinct from `NULL` for easier debugging

R/PipeOp.R

@@ -4,7 +4,7 @@
 #' @title PipeOp Base Class
 #'
 #' @usage NULL
-#' @format Abstract [`R6Class`].
+#' @format Abstract [`R6Class`][R6::R6Class].
 #'
 #' @description
 #' A [`PipeOp`] represents a transformation of a given "input" into a given "output", with two stages: "training"
@@ -51,9 +51,9 @@
 #' * `param_vals` :: named `list`\cr
 #'   List of hyperparameter settings, overwriting the hyperparameter settings given in `param_set`. The
 #'   subclass should have its own `param_vals` parameter and pass it on to `super$initialize()`. Default `list()`.
-#' * input :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
+#' * input :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
 #'   Sets the `$input` slot of the resulting object; see description there.
-#' * output :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
+#' * output :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
 #'   Sets the `$output` slot of the resulting object; see description there.
 #' * packages :: `character`\cr
 #'   Set of all required packages for the [`PipeOp`]'s `$train` and `$predict` methods. See `$packages` slot.
@@ -92,7 +92,7 @@
 #'   `$train()`, because `private$.train()` may theoretically be executed in a different `R`-session (e.g. for parallelization).
 #'   `$state` should furthermore always be set to something with copy-semantics, since it is never cloned. This is a limitation
 #'   not of [`PipeOp`] or `mlr3pipelines`, but of the way the system as a whole works, together with [`GraphLearner`] and `mlr3`.
-#' * input :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
+#' * input :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
 #'   Input channels of [`PipeOp`]. Column `name` gives the names (and order) of values in the list given to
 #'   `$train()` and `$predict()`. Column `train` is the (S3) class that an input object must conform to during
 #'   training, column `predict` is the (S3) class that an input object must conform to during prediction. Types
@@ -104,7 +104,7 @@
 #'   unpacked and the `.train()` and `.predict()` functions are called multiple times, once for each [`Multiplicity`] element.
 #'   The type enclosed by square brackets indicates that only a [`Multiplicity`] containing values of this type are accepted.
 #'   See [`Multiplicity`] for more information.
-#' * output :: [`data.table`] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
+#' * output :: [`data.table`][data.table::data.table] with columns `name` (`character`), `train` (`character`), `predict` (`character`)\cr
 #'   Output channels of [`PipeOp`], in the order in which they will be given in the list returned by `$train` and
 #'   `$predict` functions. Column `train` is the (S3) class that an output object must conform to during training,
 #'   column `predict` is the (S3) class that an output object must conform to during prediction. The [`PipeOp`] checks

R/PipeOpBoxCox.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_boxcox
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Conducts a Box-Cox transformation on numeric features. The lambda parameter

R/PipeOpBranch.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_branch
-#' @format [`R6Class`] object inheriting from [`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOp`].
 #'
 #' @description
 #' Perform alternative path branching: [`PipeOpBranch`] has multiple output channels

R/PipeOpChunk.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_chunk
-#' @format [`R6Class`] object inheriting from [`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOp`].
 #'
 #' @description
 #' Chunks its input into `outnum` chunks.

R/PipeOpClassBalancing.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_classbalancing
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Both undersamples a [`Task`][mlr3::Task] to keep only a fraction of the rows of the majority class,
@@ -67,7 +67,7 @@
 #'
 #' Uses `task$filter()` to remove rows. When identical rows are added during upsampling, then the `task$row_roles$use` can *not* be used
 #' to duplicate rows because of \[inaudible\]; instead the `task$rbind()` function is used, and
-#' a new [`data.table`] is attached that contains all rows that are being duplicated exactly as many times as they are being added.
+#' a new [`data.table`][data.table::data.table] is attached that contains all rows that are being duplicated exactly as many times as they are being added.
 #'
 #' @section Fields:
 #' Only fields inherited from [`PipeOpTaskPreproc`]/[`PipeOp`].

R/PipeOpClassWeights.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_classweights
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Adds a class weight column to the [`Task`][mlr3::Task] that different [`Learner`][mlr3::Learner]s may be

R/PipeOpClassifAvg.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_classifavg
-#' @format [`R6Class`] inheriting from [`PipeOpEnsemble`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] inheriting from [`PipeOpEnsemble`]/[`PipeOp`].
 #'
 #' @description
 #' Perform (weighted) majority vote prediction from classification [`Prediction`][mlr3::Prediction]s by connecting

R/PipeOpColApply.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_colapply
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Applies a function to each column of a task. Use the `affect_columns` parameter inherited from
@@ -39,7 +39,7 @@
 #'   Function to apply to each column of the task.
 #'   The return value should be a `vector` of the same length as the input, i.e., the function vectorizes over the input.
 #'   A typical example would be `as.numeric`.\cr
-#'   The return value can also be a `matrix`, `data.frame`, or [`data.table`].
+#'   The return value can also be a `matrix`, `data.frame`, or [`data.table`][data.table::data.table].
 #'   In this case, the length of the input must match the number of returned rows.
 #'   The names of the resulting features of the output [`Task`][mlr3::Task] is based on the (column) name(s) of the return value of the applicator function,
 #'   prefixed with the original feature name separated by a dot (`.`).

R/PipeOpColRoles.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_colroles
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Changes the column roles of the input [`Task`][mlr3::Task] according to `new_role`.

R/PipeOpCollapseFactors.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_collapsefactors
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Collapses factors of type `factor`, `ordered`: Collapses the rarest factors in the

R/PipeOpCopy.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_copy
-#' @format [`R6Class`] object inheriting from [`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOp`].
 #'
 #' @description
 #' Copies its input `outnum` times. This PipeOp usually not needed,

R/PipeOpDateFeatures.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_datefeatures
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Based on `POSIXct` columns of the data, a set of date related features is computed and added to

R/PipeOpEncode.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_encode
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Encodes columns of type `factor` and `ordered`.

R/PipeOpEncodeImpact.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_encodeimpact
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Encodes columns of type `factor`, `character` and `ordered`.

R/PipeOpEncodeLmer.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_encodelmer
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Encodes columns of type `factor`, `character` and `ordered`.

R/PipeOpEnsemble.R

@@ -1,7 +1,7 @@
 #' @title Ensembling Base Class
 #'
 #' @usage NULL
-#' @format Abstract [`R6Class`] inheriting from [`PipeOp`].
+#' @format Abstract [`R6Class`][R6::R6Class] inheriting from [`PipeOp`].
 #'
 #' @description
 #' Parent class for [`PipeOp`]s that aggregate predictions. Implements the `private$.train()` and `private$.predict()` methods necessary

R/PipeOpFeatureUnion.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_featureunion
-#' @format [`R6Class`] object inheriting from [`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOp`].
 #'
 #' @description
 #' Aggregates features from all input tasks by [cbind()]ing them together into a single

R/PipeOpFilter.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_filter
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Feature filtering using a [`mlr3filters::Filter`] object, see the

R/PipeOpFixFactors.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_fixfactors
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Fixes factors of type `factor`, `ordered`: Makes sure the factor levels

R/PipeOpHistBin.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_histbin
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreprocSimple`]/[`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Splits numeric features into equally spaced bins.

R/PipeOpICA.R

@@ -2,7 +2,7 @@
 #'
 #' @usage NULL
 #' @name mlr_pipeops_ica
-#' @format [`R6Class`] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
+#' @format [`R6Class`][R6::R6Class] object inheriting from [`PipeOpTaskPreproc`]/[`PipeOp`].
 #'
 #' @description
 #' Extracts statistically independent components from data. Only affects numerical features.