Set the hyperparameters of a learner object.

setHyperPars(learner, ..., par.vals = list())

Arguments

learner

(Learner | character(1))
The learner. If you pass a string the learner will be created via makeLearner.

...

(any)
Named (hyper)parameters with new setting. Alternatively these can be passed using the par.vals argument.

par.vals

(list)
Optional list of named (hyper)parameter settings. The arguments in ... take precedence over values in this list.

Value

Learner.

Note

If a named (hyper)parameter can't be found for the given learner, the 3 closest (hyper)parameter names will be output in case the user mistyped.

See also

Examples

cl1 = makeLearner("classif.ksvm", sigma = 1) cl2 = setHyperPars(cl1, sigma = 10, par.vals = list(C = 2)) print(cl1)
#> Learner classif.ksvm from package kernlab #> Type: classif #> Name: Support Vector Machines; Short name: ksvm #> Class: classif.ksvm #> Properties: twoclass,multiclass,numerics,factors,prob,class.weights #> Predict-Type: response #> Hyperparameters: fit=FALSE,sigma=1 #>
# note the now set and altered hyperparameters: print(cl2)
#> Learner classif.ksvm from package kernlab #> Type: classif #> Name: Support Vector Machines; Short name: ksvm #> Class: classif.ksvm #> Properties: twoclass,multiclass,numerics,factors,prob,class.weights #> Predict-Type: response #> Hyperparameters: fit=FALSE,sigma=10,C=2 #>