mlr-org · m-muecke · Apr 2, 2025 · Apr 5, 2025
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -9,6 +9,7 @@
 ^Meta$
 ^README\.Rmd$
 ^README\.html$
+^[\.]?air\.toml$
 ^\.Renviron$
 ^\.Rproj\.user$
 ^\.ccache$

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -4,10 +4,6 @@ repos:
   - repo: https://github.com/lorenzwalthert/precommit
     rev: v0.4.3.9008
     hooks:
-      - id: style-files
-        args: [--style_pkg=styler.mlr, --style_fun=mlr_style]
-        additional_dependencies:
-          - mlr-org/styler.mlr
       - id: roxygenize
         additional_dependencies:
         - ClusterR

diff --git a/R/LearnerClust.R b/R/LearnerClust.R
@@ -30,7 +30,8 @@
 #' # get a specific learner from mlr_learners:
 #' learner = lrn("clust.kmeans")
 #' print(learner)
-LearnerClust = R6Class("LearnerClust",
+LearnerClust = R6Class(
+  "LearnerClust",
   inherit = Learner,
   public = list(
     #' @field assignments (`NULL` | `vector()`)\cr

diff --git a/R/LearnerClustAffinityPropagation.R b/R/LearnerClustAffinityPropagation.R
@@ -20,7 +20,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustAP = R6Class("LearnerClustAP",
+LearnerClustAP = R6Class(
+  "LearnerClustAP",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustAgnes.R b/R/LearnerClustAgnes.R
@@ -17,7 +17,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustAgnes = R6Class("LearnerClustAgnes",
+LearnerClustAgnes = R6Class(
+  "LearnerClustAgnes",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -66,7 +67,8 @@ LearnerClustAgnes = R6Class("LearnerClustAgnes",
   private = list(
     .train = function(task) {
       pv = self$param_set$get_values(tags = "train")
-      m = invoke(cluster::agnes,
+      m = invoke(
+        cluster::agnes,
         x = task$data(),
         diss = FALSE,
         .args = remove_named(pv, "k")

diff --git a/R/LearnerClustBICO.R b/R/LearnerClustBICO.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustBICO = R6Class("LearnerClustBICO",
+LearnerClustBICO = R6Class(
+  "LearnerClustBICO",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustBIRCH.R b/R/LearnerClustBIRCH.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustBIRCH = R6Class("LearnerClustBIRCH",
+LearnerClustBIRCH = R6Class(
+  "LearnerClustBIRCH",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustCMeans.R b/R/LearnerClustCMeans.R
@@ -18,29 +18,32 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustCMeans = R6Class("LearnerClustCMeans",
+LearnerClustCMeans = R6Class(
+  "LearnerClustCMeans",
   inherit = LearnerClust,
   public = list(
     #' @description
     #' Creates a new instance of this [R6][R6::R6Class] class.
     initialize = function() {
       param_set = ps(
-        centers = p_uty(
-          tags = c("required", "train"), custom_check = check_centers
-        ),
+        centers = p_uty(tags = c("required", "train"), custom_check = check_centers),
         iter.max = p_int(1L, default = 100L, tags = "train"),
         verbose = p_lgl(default = FALSE, tags = "train"),
         dist = p_fct(levels = c("euclidean", "manhattan"), default = "euclidean", tags = "train"),
         method = p_fct(levels = c("cmeans", "ufcl"), default = "cmeans", tags = "train"),
         m = p_dbl(1, default = 2, tags = "train"),
         rate.par = p_dbl(0, 1, tags = "train", depends = quote(method == "ufcl")),
-        weights = p_uty(default = 1L, tags = "train", custom_check = crate(function(x) {
-          if (test_numeric(x) && all(x > 0) || check_count(x, positive = TRUE)) {
-            TRUE
-          } else {
-            "`weights` must be positive numeric vector or a single positive number"
-          }
-        })),
+        weights = p_uty(
+          default = 1L,
+          tags = "train",
+          custom_check = crate(function(x) {
+            if (test_numeric(x) && all(x > 0) || check_count(x, positive = TRUE)) {
+              TRUE
+            } else {
+              "`weights` must be positive numeric vector or a single positive number"
+            }
+          })
+        ),
         control = p_uty(tags = "train")
       )
 

diff --git a/R/LearnerClustCobweb.R b/R/LearnerClustCobweb.R
@@ -16,7 +16,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustCobweb = R6Class("LearnerClustCobweb",
+LearnerClustCobweb = R6Class(
+  "LearnerClustCobweb",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustDBSCAN.R b/R/LearnerClustDBSCAN.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustDBSCAN = R6Class("LearnerClustDBSCAN",
+LearnerClustDBSCAN = R6Class(
+  "LearnerClustDBSCAN",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustDBSCANfpc.R b/R/LearnerClustDBSCANfpc.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustDBSCANfpc = R6Class("LearnerClustDBSCANfpc",
+LearnerClustDBSCANfpc = R6Class(
+  "LearnerClustDBSCANfpc",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -27,20 +28,28 @@ LearnerClustDBSCANfpc = R6Class("LearnerClustDBSCANfpc",
         scale = p_lgl(default = FALSE, tags = "train"),
         method = p_fct(levels = c("hybrid", "raw", "dist"), tags = "train"),
         seeds = p_lgl(default = TRUE, tags = "train"),
-        showplot = p_uty(default = FALSE, tags = "train", custom_check = crate(function(x) {
-          if (test_flag(x) || test_int(x, lower = 0L, upper = 2L)) {
-            TRUE
-          } else {
-            "`showplot` need to be either logical or integer between 0 and 2"
-          }
-        })),
-        countmode = p_uty(default = NULL, tags = "train", custom_check = crate(function(x) {
-          if (test_integer(x, null.ok = TRUE)) {
-            TRUE
-          } else {
-            "`countmode` need to be NULL or vector of integers"
-          }
-        }))
+        showplot = p_uty(
+          default = FALSE,
+          tags = "train",
+          custom_check = crate(function(x) {
+            if (test_flag(x) || test_int(x, lower = 0L, upper = 2L)) {
+              TRUE
+            } else {
+              "`showplot` need to be either logical or integer between 0 and 2"
+            }
+          })
+        ),
+        countmode = p_uty(
+          default = NULL,
+          tags = "train",
+          custom_check = crate(function(x) {
+            if (test_integer(x, null.ok = TRUE)) {
+              TRUE
+            } else {
+              "`countmode` need to be NULL or vector of integers"
+            }
+          })
+        )
       )
 
       param_set$set_values(MinPts = 5L, scale = FALSE, seeds = TRUE, showplot = FALSE, countmode = NULL)

diff --git a/R/LearnerClustDiana.R b/R/LearnerClustDiana.R
@@ -17,7 +17,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustDiana = R6Class("LearnerClustDiana",
+LearnerClustDiana = R6Class(
+  "LearnerClustDiana",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -47,7 +48,8 @@ LearnerClustDiana = R6Class("LearnerClustDiana",
   private = list(
     .train = function(task) {
       pv = self$param_set$get_values(tags = "train")
-      m = invoke(cluster::diana,
+      m = invoke(
+        cluster::diana,
         x = task$data(),
         diss = FALSE,
         .args = remove_named(pv, "k")

diff --git a/R/LearnerClustEM.R b/R/LearnerClustEM.R
@@ -17,7 +17,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustEM = R6Class("LearnerClustEM",
+LearnerClustEM = R6Class(
+  "LearnerClustEM",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustFanny.R b/R/LearnerClustFanny.R
@@ -20,7 +20,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustFanny = R6Class("LearnerClustFanny",
+LearnerClustFanny = R6Class(
+  "LearnerClustFanny",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustFarthestFirst.R b/R/LearnerClustFarthestFirst.R
@@ -16,7 +16,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustFarthestFirst = R6Class("LearnerClustFF",
+LearnerClustFarthestFirst = R6Class(
+  "LearnerClustFF",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustFeatureless.R b/R/LearnerClustFeatureless.R
@@ -12,7 +12,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustFeatureless = R6Class("LearnerClustFeatureless",
+LearnerClustFeatureless = R6Class(
+  "LearnerClustFeatureless",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -68,11 +69,14 @@ LearnerClustFeatureless = R6Class("LearnerClustFeatureless",
 
         # reorder rows so that the max probability corresponds to
         # the selected partition in `partition`
-        prob = do.call(rbind, map(seq_along(partition), function(i) {
-          x = prob[i, , drop = TRUE]
-          pos = which_max(x)
-          if (pos == i) x else append(x[-pos], x[pos], after = partition[i] - 1L)
-        }))
+        prob = do.call(
+          rbind,
+          map(seq_along(partition), function(i) {
+            x = prob[i, , drop = TRUE]
+            pos = which_max(x)
+            if (pos == i) x else append(x[-pos], x[pos], after = partition[i] - 1L)
+          })
+        )
       }
 
       PredictionClust$new(task = task, partition = partition, prob = prob)

diff --git a/R/LearnerClustHDBSCAN.R b/R/LearnerClustHDBSCAN.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustHDBSCAN = R6Class("LearnerClustHDBSCAN",
+LearnerClustHDBSCAN = R6Class(
+  "LearnerClustHDBSCAN",
   inherit = LearnerClust,
   public = list(
     #' @description

diff --git a/R/LearnerClustHclust.R b/R/LearnerClustHclust.R
@@ -15,7 +15,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustHclust = R6Class("LearnerClustHclust",
+LearnerClustHclust = R6Class(
+  "LearnerClustHclust",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -56,12 +57,14 @@ LearnerClustHclust = R6Class("LearnerClustHclust",
   private = list(
     .train = function(task) {
       pv = self$param_set$get_values(tags = "train")
-      dist = invoke(stats::dist,
+      dist = invoke(
+        stats::dist,
         x = task$data(),
         method = pv$d %??% "euclidean",
         .args = self$param_set$get_values(tags = c("train", "dist"))
       )
-      m = invoke(stats::hclust,
+      m = invoke(
+        stats::hclust,
         d = dist,
         .args = self$param_set$get_values(tags = c("train", "hclust"))
       )

diff --git a/R/LearnerClustKKMeans.R b/R/LearnerClustKKMeans.R
@@ -19,7 +19,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustKKMeans = R6Class("LearnerClustKKMeans",
+LearnerClustKKMeans = R6Class(
+  "LearnerClustKKMeans",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -33,10 +34,15 @@ LearnerClustKKMeans = R6Class("LearnerClustKKMeans",
           tags = "train"
         ),
         sigma = p_dbl(
-          0, tags = "train", depends = quote(kernel %in% c("rbfdot", "anovadot", "besseldot", "laplacedot"))
+          0,
+          tags = "train",
+          depends = quote(kernel %in% c("rbfdot", "anovadot", "besseldot", "laplacedot"))
         ),
         degree = p_int(
-          1L, default = 3L, tags = "train", depends = quote(kernel %in% c("polydot", "anovadot", "besseldot"))
+          1L,
+          default = 3L,
+          tags = "train",
+          depends = quote(kernel %in% c("polydot", "anovadot", "besseldot"))
         ),
         scale = p_dbl(0, default = 1, tags = "train", depends = quote(kernel %in% c("polydot", "tanhdot"))),
         offset = p_dbl(default = 1, tags = "train", depends = quote(kernel %in% c("polydot", "tanhdot"))),
@@ -83,11 +89,13 @@ LearnerClustKKMeans = R6Class("LearnerClustKKMeans",
       # kernel product between each new datapoint and itself: rows are identical
       d_xx = matrix(
         rep(diag(kernlab::kernelMatrix(K, as.matrix(data))), each = ncol(d_xc)),
-        ncol = ncol(d_xc), byrow = TRUE
+        ncol = ncol(d_xc),
+        byrow = TRUE
       )
       # kernel product between each center and itself: columns are identical
       d_cc = matrix(
-        rep(diag(kernlab::kernelMatrix(K, as.matrix(c))), each = nrow(d_xc)), nrow = nrow(d_xc)
+        rep(diag(kernlab::kernelMatrix(K, as.matrix(c))), each = nrow(d_xc)),
+        nrow = nrow(d_xc)
       )
       # this is the squared kernel distance to the centers
       d2 = d_xx + d_cc - 2 * d_xc

diff --git a/R/LearnerClustKMeans.R b/R/LearnerClustKMeans.R
@@ -18,7 +18,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustKMeans = R6Class("LearnerClustKMeans",
+LearnerClustKMeans = R6Class(
+  "LearnerClustKMeans",
   inherit = LearnerClust,
   public = list(
     #' @description
@@ -28,7 +29,9 @@ LearnerClustKMeans = R6Class("LearnerClustKMeans",
         centers = p_uty(tags = c("required", "train"), custom_check = check_centers),
         iter.max = p_int(1L, default = 10L, tags = "train"),
         algorithm = p_fct(
-          levels = c("Hartigan-Wong", "Lloyd", "Forgy", "MacQueen"), default = "Hartigan-Wong", tags = "train"
+          levels = c("Hartigan-Wong", "Lloyd", "Forgy", "MacQueen"),
+          default = "Hartigan-Wong",
+          tags = "train"
         ),
         nstart = p_int(1L, default = 1L, tags = "train"),
         trace = p_int(0L, default = 0L, tags = "train")

diff --git a/R/LearnerClustMclust.R b/R/LearnerClustMclust.R
@@ -16,7 +16,8 @@
 #' @export
 #' @template seealso_learner
 #' @template example
-LearnerClustMclust = R6Class("LearnerClustMclust",
+LearnerClustMclust = R6Class(
+  "LearnerClustMclust",
   inherit = LearnerClust,
   public = list(
     #' @description