Skip to contents

Random forest for classification. Calls randomForestSRC::rfsrc() from randomForestSRC.

Dictionary

This Learner can be instantiated via lrn():

lrn("classif.rfsrc")

Meta Information

  • Task type: “classif”

  • Predict Types: “response”, “prob”

  • Feature Types: “logical”, “integer”, “numeric”, “factor”

  • Required Packages: mlr3, mlr3extralearners, randomForestSRC

Parameters

IdTypeDefaultLevelsRange
ntreeinteger500\([1, \infty)\)
mtryinteger-\([1, \infty)\)
mtry.rationumeric-\([0, 1]\)
nodesizeinteger15\([1, \infty)\)
nodedepthinteger-\([1, \infty)\)
splitrulecharacterginigini, auc, entropy-
nsplitinteger10\([0, \infty)\)
importancecharacterFALSEFALSE, TRUE, none, permute, random, anti-
block.sizeinteger10\([1, \infty)\)
bootstrapcharacterby.rootby.root, by.node, none, by.user-
samptypecharactersworswor, swr-
sampuntyped--
membershiplogicalFALSETRUE, FALSE-
sampsizeuntyped--
sampsize.rationumeric-\([0, 1]\)
na.actioncharacterna.omitna.omit, na.impute-
nimputeinteger1\([1, \infty)\)
proximitycharacterFALSEFALSE, TRUE, inbag, oob, all-
distancecharacterFALSEFALSE, TRUE, inbag, oob, all-
forest.wtcharacterFALSEFALSE, TRUE, inbag, oob, all-
xvar.wtuntyped--
split.wtuntyped--
forestlogicalTRUETRUE, FALSE-
var.usedcharacterFALSEFALSE, all.trees-
split.depthcharacterFALSEFALSE, all.trees, by.tree-
seedinteger-\((-\infty, -1]\)
do.tracelogicalFALSETRUE, FALSE-
get.treeuntyped--
outcomecharactertraintrain, test-
ptn.countinteger0\([0, \infty)\)
coresinteger1\([1, \infty)\)
save.memorylogicalFALSETRUE, FALSE-
perf.typecharacter-gmean, misclass, brier, none-
case.depthlogicalFALSETRUE, FALSE-
marginal.xvaruntypedNULL-

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.

  • sampsize: This hyperparameter can alternatively be set via the added hyperparameter sampsize.ratio as sampsize = max(ceiling(sampsize.ratio * n_obs), 1). Note that sampsize and sampsize.ratio are mutually exclusive.

  • cores: This value is set as the option rf.cores during training and is set to 1 by default.

References

Breiman, Leo (2001). “Random Forests.” Machine Learning, 45(1), 5–32. ISSN 1573-0565, doi:10.1023/A:1010933404324 .

See also

Author

RaphaelS1

Super classes

mlr3::Learner -> mlr3::LearnerClassif -> LearnerClassifRandomForestSRC

Methods

Inherited methods


Method new()

Creates a new instance of this R6 class.


Method importance()

The importance scores are extracted from the model slot importance, returned for 'all'.

Usage

LearnerClassifRandomForestSRC$importance()

Returns

Named numeric().


Method selected_features()

Selected features are extracted from the model slot var.used.

Note: Due to a known issue in randomForestSRC, enabling var.used = "all.trees" causes prediction to fail. Therefore, this setting should be used exclusively for feature selection purposes and not when prediction is required.

Usage

LearnerClassifRandomForestSRC$selected_features()

Returns

character().


Method oob_error()

OOB error extracted from the model slot err.rate.

Usage

LearnerClassifRandomForestSRC$oob_error()

Returns

numeric().


Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerClassifRandomForestSRC$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Define the Learner
learner = lrn("classif.rfsrc", importance = "TRUE")
print(learner)
#> 
#> ── <LearnerClassifRandomForestSRC> (classif.rfsrc): Random Forest ──────────────
#> • Model: -
#> • Parameters: importance=TRUE
#> • Packages: mlr3, mlr3extralearners, and randomForestSRC
#> • Predict Types: [response] and prob
#> • Feature Types: logical, integer, numeric, and factor
#> • Encapsulation: none (fallback: -)
#> • Properties: importance, missings, multiclass, oob_error, selected_features,
#> twoclass, and weights
#> • Other settings: use_weights = 'use'

# Define a Task
task = tsk("sonar")
# Create train and test set
ids = partition(task)

# Train the learner on the training ids
learner$train(task, row_ids = ids$train)

print(learner$model)
#>                          Sample size: 139
#>            Frequency of class labels: M=72, R=67
#>                      Number of trees: 500
#>            Forest terminal node size: 1
#>        Average no. of terminal nodes: 17.654
#> No. of variables tried at each split: 8
#>               Total no. of variables: 60
#>        Resampling used to grow trees: swor
#>     Resample size used to grow trees: 88
#>                             Analysis: RF-C
#>                               Family: class
#>                       Splitting rule: gini *random*
#>        Number of random split points: 10
#>                     Imbalanced ratio: 1.0746
#>                    (OOB) Brier score: 0.15234861
#>         (OOB) Normalized Brier score: 0.60939442
#>                            (OOB) AUC: 0.88557214
#>                       (OOB) Log-loss: 0.47010024
#>                         (OOB) PR-AUC: 0.88389273
#>                         (OOB) G-mean: 0.7520012
#>    (OOB) Requested performance error: 0.23741007, 0.13888889, 0.34328358
#> 
#> Confusion matrix:
#> 
#>           predicted
#>   observed  M  R class.error
#>          M 62 10      0.1389
#>          R 23 44      0.3433
#> 
#>       (OOB) Misclassification rate: 0.2374101
#> 
#> Random-classifier baselines (uniform):
#>    Brier: 0.25   Normalized Brier: 1   Log-loss: 0.69314718
print(learner$importance())
#>         V11         V10          V9         V12         V51         V49 
#> 0.067599411 0.057239465 0.037889476 0.028804850 0.022395125 0.021837913 
#>         V45         V48         V20         V30         V47         V16 
#> 0.020831506 0.019658120 0.019033280 0.017746281 0.017410307 0.016758188 
#>          V4         V28         V52         V36         V37         V32 
#> 0.016082119 0.016001859 0.013656088 0.012972014 0.012704441 0.012521657 
#>         V27         V40         V17         V18         V31         V13 
#> 0.012338326 0.012162557 0.011945741 0.011503208 0.011062606 0.010926955 
#>         V15          V6         V43         V19          V8          V5 
#> 0.010470720 0.009359556 0.009132666 0.008560630 0.008552323 0.008544926 
#>         V34         V23         V26         V21         V44         V14 
#> 0.008415923 0.008267802 0.008144920 0.008138852 0.007399309 0.007307627 
#>         V53         V58         V41         V38         V59          V1 
#> 0.007283823 0.006998183 0.006734628 0.006720811 0.006709906 0.006408192 
#>         V22          V3         V57         V56          V7         V33 
#> 0.006279150 0.005948666 0.005691862 0.005215567 0.004652026 0.004473813 
#>         V60         V42         V50          V2         V39         V55 
#> 0.004346702 0.004213972 0.003947644 0.003942211 0.003327298 0.003038502 
#>         V46         V24         V29         V54         V25         V35 
#> 0.002635236 0.002457247 0.001884243 0.001633071 0.001420752 0.001315825 

# Make predictions for the test rows
predictions = learner$predict(task, row_ids = ids$test)

# Score the predictions
predictions$score()
#> classif.ce 
#>  0.1449275