Skip to contents

Oblique random forest. Calls obliqueRSF::ORSF() from obliqueRSF. Note that obliqueRSF has been superseded by aorsf. We highly recommend you use aorsf to fit oblique random survival forests: see https://github.com/bcjaeger/aorsf or install from CRAN with install.packages('aorsf').

Dictionary

This Learner can be instantiated via the dictionary mlr_learners or with the associated sugar function lrn():

mlr_learners$get("surv.obliqueRSF")
lrn("surv.obliqueRSF")

Meta Information

Parameters

IdTypeDefaultLevelsRange
alphanumeric0.5\((-\infty, \infty)\)
ntreeinteger100\([1, \infty)\)
eval_timesuntyped--
min_events_to_split_nodeinteger5\([1, \infty)\)
min_obs_to_split_nodeinteger10\([1, \infty)\)
min_obs_in_leaf_nodeinteger5\([1, \infty)\)
min_events_in_leaf_nodeinteger1\([1, \infty)\)
nsplitinteger25\([1, \infty)\)
gammanumeric0.5\([1e-16, \infty)\)
max_pval_to_split_nodenumeric0.5\([0, 1]\)
mtryinteger-\([1, \infty)\)
mtry_rationumeric-\([0, 1]\)
dfmaxinteger-\([1, \infty)\)
use.cvlogicalFALSETRUE, FALSE-
verboselogicalTRUETRUE, FALSE-
compute_oob_predictionslogicalFALSETRUE, FALSE-
random_seedinteger-\((-\infty, \infty)\)

Custom mlr3 parameters

  • mtry:

    • This hyperparameter can alternatively be set via the added hyperparameter mtry_ratio as mtry = max(ceiling(mtry_ratio * n_features), 1). Note that mtry and mtry_ratio are mutually exclusive.

Initial parameter values

  • verbose is initialized to FALSE

References

Jaeger BC, Long DL, Long DM, Sims M, Szychowski JM, Min Y, Mcclure LA, Howard G, Simon N (2019). “Oblique random survival forests.” The Annals of Applied Statistics, 13(3). doi:10.1214/19-aoas1261 .

See also

Author

adibender

Super classes

mlr3::Learner -> mlr3proba::LearnerSurv -> LearnerSurvObliqueRSF

Methods

Inherited methods


Method new()

Creates a new instance of this R6 class.

Usage


Method oob_error()

Integrated brier score OOB error extracted from the model slot oob_error. Concordance is also available.

Usage

LearnerSurvObliqueRSF$oob_error()

Returns

numeric().


Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerSurvObliqueRSF$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

learner = mlr3::lrn("surv.obliqueRSF")
print(learner)
#> <LearnerSurvObliqueRSF:surv.obliqueRSF>: Oblique Random Forest
#> * Model: -
#> * Parameters: verbose=FALSE
#> * Packages: mlr3, mlr3proba, mlr3extralearners, obliqueRSF, pracma
#> * Predict Types:  [crank], distr
#> * Feature Types: integer, numeric, factor, ordered
#> * Properties: missings, oob_error

# available parameters:
learner$param_set$ids()
#>  [1] "alpha"                    "ntree"                   
#>  [3] "eval_times"               "min_events_to_split_node"
#>  [5] "min_obs_to_split_node"    "min_obs_in_leaf_node"    
#>  [7] "min_events_in_leaf_node"  "nsplit"                  
#>  [9] "gamma"                    "max_pval_to_split_node"  
#> [11] "mtry"                     "mtry_ratio"              
#> [13] "dfmax"                    "use.cv"                  
#> [15] "verbose"                  "compute_oob_predictions" 
#> [17] "random_seed"