L2-Regularized L1-Loss Support Vector Classification Learner

Calls LiblineaR::LiblineaR from package LiblineaR.

Details

Calls LiblineaR::LiblineaR() with type = 3.

Dictionary

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

mlr_learners$get("classif.liblinearl2l1svc")
lrn("classif.liblinearl2l1svc")

Traits

• Packages: LiblineaR

• Predict Types: response

• Feature Types: numeric

• Properties: multiclass, twoclass

Custom mlr3 defaults

• epsilon:

  • Actual default: 0.01

  • Adjusted default: 0.1

  • Reason for change: Param depends on param "type" which is handled internally by choosing the mlr3 learner. The default is set to the actual default of the respective "type".

See also

Dictionary of Learners: mlr3::mlr_learners

Author

be-marc

Super classes

mlr3::Learner -> mlr3::LearnerClassif -> LearnerClassifLiblineaRL2L1SVC

Methods

Public methods

• LearnerClassifLiblineaRL2L1SVC$new()

• LearnerClassifLiblineaRL2L1SVC$clone()

Inherited methods

• mlr3::Learner$format()

• mlr3::Learner$help()

• mlr3::Learner$predict()

• mlr3::Learner$predict_newdata()

• mlr3::Learner$print()

• mlr3::Learner$reset()

• mlr3::Learner$train()

---

Method new()

Creates a new instance of this R6 class.

Usage

LearnerClassifLiblineaRL2L1SVC$new()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerClassifLiblineaRL2L1SVC$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# stop example failing with warning if package not installed
learner = suppressWarnings(mlr3::lrn("classif.liblinearl2l1svc"))
print(learner)
#> <LearnerClassifLiblineaRL2L1SVC:classif.liblinearl2l1svc>
#> * Model: -
#> * Parameters: epsilon=0.1
#> * Packages: LiblineaR
#> * Predict Type: response
#> * Feature types: numeric
#> * Properties: multiclass, twoclass

# available parameters:
learner$param_set$ids()
#> [1] "cost"     "epsilon"  "bias"     "cross"    "verbose"  "wi"       "findC"   
#> [8] "useInitC"