fix: remove unused hyperparameter of ranger (#316)

* fix: remove unused hyperparameter of ranger * ...
mlr-org · Oct 25, 2024 · 3cbc64d · 3cbc64d
1 parent 3a93084
commit 3cbc64d
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 12 deletions.
diff --git a/R/LearnerClassifRanger.R b/R/LearnerClassifRanger.R
@@ -36,17 +36,14 @@ LearnerClassifRanger = R6Class("LearnerClassifRanger",
     #' Creates a new instance of this [R6][R6::R6Class] class.
     initialize = function() {
       ps = ps(
-        # FIXME: only works if predict_type == "se". How to set dependency?
-        alpha                        = p_dbl(default = 0.5, tags = "train"),
         always.split.variables       = p_uty(tags = "train"),
         class.weights                = p_uty(default = NULL, tags = "train"),
         holdout                      = p_lgl(default = FALSE, tags = "train"),
         importance                   = p_fct(c("none", "impurity", "impurity_corrected", "permutation"), tags = "train"),
         keep.inbag                   = p_lgl(default = FALSE, tags = "train"),
-        max.depth                    = p_int(default = NULL, lower = 0L, special_vals = list(NULL), tags = "train"),
+        max.depth                    = p_int(default = NULL, lower = 1L, special_vals = list(NULL), tags = "train"),
         min.bucket                   = p_int(1L, default = 1L, tags = "train"),
         min.node.size                = p_int(1L, default = NULL, special_vals = list(NULL), tags = "train"),
-        minprop                      = p_dbl(default = 0.1, tags = "train"),
         mtry                         = p_int(lower = 1L, special_vals = list(NULL), tags = "train"),
         mtry.ratio                   = p_dbl(lower = 0, upper = 1, tags = "train"),
         num.random.splits            = p_int(1L, default = 1L, tags = "train", depends = quote(splitrule == "extratrees")),
@@ -57,11 +54,10 @@ LearnerClassifRanger = R6Class("LearnerClassifRanger",
         regularization.factor        = p_uty(default = 1, tags = "train"),
         regularization.usedepth      = p_lgl(default = FALSE, tags = "train"),
         replace                      = p_lgl(default = TRUE, tags = "train"),
-        respect.unordered.factors    = p_fct(c("ignore", "order", "partition"), default = "ignore", tags = "train"),
+        respect.unordered.factors    = p_fct(c("ignore", "order", "partition"), tags = "train"),
         sample.fraction              = p_dbl(0L, 1L, tags = "train"),
         save.memory                  = p_lgl(default = FALSE, tags = "train"),
         scale.permutation.importance = p_lgl(default = FALSE, tags = "train", depends = quote(importance == "permutation")),
-        se.method                    = p_fct(c("jack", "infjack"), default = "infjack", tags = "predict"),
         seed                         = p_int(default = NULL, special_vals = list(NULL), tags = c("train", "predict")),
         split.select.weights         = p_uty(default = NULL, tags = "train"),
         splitrule                    = p_fct(c("gini", "extratrees", "hellinger"), default = "gini", tags = "train"),

diff --git a/R/LearnerRegrRanger.R b/R/LearnerRegrRanger.R
@@ -27,15 +27,13 @@ LearnerRegrRanger = R6Class("LearnerRegrRanger",
     #' Creates a new instance of this [R6][R6::R6Class] class.
     initialize = function() {
       ps = ps(
-        alpha                        = p_dbl(default = 0.5, tags = "train", depends = quote(splitrule == "maxstat")),
         always.split.variables       = p_uty(tags = "train"),
         holdout                      = p_lgl(default = FALSE, tags = "train"),
         importance                   = p_fct(c("none", "impurity", "impurity_corrected", "permutation"), tags = "train"),
         keep.inbag                   = p_lgl(default = FALSE, tags = "train"),
-        max.depth                    = p_int(default = NULL, lower = 0L, special_vals = list(NULL), tags = "train"),
+        max.depth                    = p_int(default = NULL, lower = 1L, special_vals = list(NULL), tags = "train"),
         min.bucket                   = p_int(1L, default = 1L, tags = "train"),
         min.node.size                = p_int(1L, default = 5L, special_vals = list(NULL), tags = "train"),
-        minprop                      = p_dbl(default = 0.1, tags = "train", depends = quote(splitrule == "maxstat")),
         mtry                         = p_int(lower = 1L, special_vals = list(NULL), tags = "train"),
         mtry.ratio                   = p_dbl(lower = 0, upper = 1, tags = "train"),
         node.stats                   = p_lgl(default = FALSE, tags = "train"),
@@ -46,7 +44,7 @@ LearnerRegrRanger = R6Class("LearnerRegrRanger",
         regularization.factor        = p_uty(default = 1, tags = "train"),
         regularization.usedepth      = p_lgl(default = FALSE, tags = "train"),
         replace                      = p_lgl(default = TRUE, tags = "train"),
-        respect.unordered.factors    = p_fct(c("ignore", "order", "partition"), default = "ignore", tags = "train"),
+        respect.unordered.factors    = p_fct(c("ignore", "order", "partition"), tags = "train"),
         sample.fraction              = p_dbl(0L, 1L, tags = "train"),
         save.memory                  = p_lgl(default = FALSE, tags = "train"),
         scale.permutation.importance = p_lgl(default = FALSE, tags = "train", depends = quote(importance == "permutation")),

diff --git a/inst/paramtest/test_paramtest_classif.ranger.R b/inst/paramtest/test_paramtest_classif.ranger.R
@@ -18,7 +18,10 @@ test_that("classif.ranger", {
     "status.variable.name", # handled via mlr3
     "classification", # handled via mlr3
     "mtry.ratio", # custom hyperpar
-    "time.interest" # survival only
+    "time.interest", # survival only
+    "alpha", # survival only
+    "minprop", # survival only
+    "se.method" # regression only
   )
 
   ParamTest = run_paramtest(learner, fun, exclude, tag = "train")

diff --git a/inst/paramtest/test_paramtest_regr.ranger.R b/inst/paramtest/test_paramtest_regr.ranger.R
@@ -18,7 +18,9 @@ test_that("regr.ranger", {
     "classification", # handled via mlr3
     "mtry.ratio", # custom hyperpar
     "time.interest", # survival only
-    "quantreg" # handled by predict_type
+    "quantreg", # handled by predict_type
+    "alpha", # survival only
+    "minprop" # survival only
   )
 
   ParamTest = run_paramtest(learner, fun, exclude, tag = "train")