RandomForestRegression

@Serializable

@SerialName(value = "RandomForestRegression")

data class RandomForestRegression(val featureSize: Int, val splitCandidates: List<SerializableSplit>, val nbrTrees: Int = 10, val config: RegressionTreeConfig = RegressionTreeConfig(), val bagging: Boolean = true, val randomSeed: Int = 0) : RegressionStatSpec<ForestRegressionResult> (source)

Spec for RandomForestRegressionStat: ensembled VFDT regression forest.

Constructors

constructor(featureSize: Int, splitCandidates: List<SerializableSplit>, nbrTrees: Int = 10, config: RegressionTreeConfig = RegressionTreeConfig(), bagging: Boolean = true, randomSeed: Int = 0)(source)

Oza & Russell Poisson(1) per-tree reweighting.

RegressionTree growth tunables (mtry defaults to ceil(sqrt(p)) when null).

Number of input features.

Trees in the forest.

PRNG seed shared across trees.

Candidate split pool.