ClassificationSplitMetric
Classification analogue of SplitMetric: scores a candidate split using the leaf's per-class counts. Higher is better; returns 0 when the split has no signal (one side empty, or zero impurity reduction).
Ships GiniReduction and InformationGain only; other criteria can land here when consumers ask for them.
Inheritors
Functions
Link copied to clipboard
abstract fun score(total: ClassCountsResult, pos: ClassCountsResult, neg: ClassCountsResult): Double
Score a candidate split given the leaf's total / pos / neg class counts.
score
abstract fun score(total: ClassCountsResult, pos: ClassCountsResult, neg: ClassCountsResult): Double(source)
Score a candidate split given the leaf's total / pos / neg class counts.