Penalized Density Estimator

Calls pendensity::pendensity() and the result is coerced to a distr6::Distribution.

Details

Density estimation using penalized B-splines with automatic selection of smoothing parameter.

Dictionary

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

LearnerDensPenalized$new()
mlr_learners$get("dens.pen")
lrn("dens.pen")

Meta Information

• Type: "dens"

• Predict Types: pdf, cdf

• Feature Types: integer, numeric

• Properties: -

• Packages: mlr3 mlr3proba pendensity distr6

References

Schellhase, Christian, Kauermann, Göran (2012). “Density estimation and comparison with a penalized mixture approach.” Computational Statistics, 27(4), 757–777.

See also

Other density estimators: mlr_learners_dens.hist, mlr_learners_dens.kde, mlr_learners_dens.kde_ks, mlr_learners_dens.locfit, mlr_learners_dens.logspline, mlr_learners_dens.mixed, mlr_learners_dens.nonpar, mlr_learners_dens.plug, mlr_learners_dens.spline

Super classes

mlr3::Learner -> mlr3proba::LearnerDens -> LearnerDensPenalized

Methods

Public methods

• LearnerDensPenalized$new()

• LearnerDensPenalized$clone()

Inherited methods

• mlr3::Learner$base_learner()
• mlr3::Learner$configure()
• mlr3::Learner$encapsulate()
• mlr3::Learner$format()
• mlr3::Learner$help()
• mlr3::Learner$predict()
• mlr3::Learner$predict_newdata()
• mlr3::Learner$print()
• mlr3::Learner$reset()
• mlr3::Learner$selected_features()
• mlr3::Learner$train()

---

Method new()

Creates a new instance of this R6 class.

Usage

LearnerDensPenalized$new()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerDensPenalized$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Define the Learner
learner = lrn("dens.pen")
print(learner)
#> 
#> ── <LearnerDensPenalized> (dens.pen): Penalized Density Estimation ─────────────
#> • Model: -
#> • Parameters: list()
#> • Packages: mlr3, mlr3proba, pendensity, and distr6
#> • Predict Types: [pdf] and cdf
#> • Feature Types: integer and numeric
#> • Encapsulation: none (fallback: -)
#> • Properties:
#> • Other settings: use_weights = 'error'

# Define a Task
task = tsk("faithful")

# Create train and test set
ids = partition(task)

# Train the learner on the training ids
learner$train(task, row_ids = ids$train)
#> [1] 1
#> [1] 2
#> [1] 3

print(learner$model)
#> PenDens_gaussian() 

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

# Score the predictions
predictions$score()
#> dens.logloss 
#>     1.819792