interactPredict: Predict interaction

In karlkumbier/iRF2.0: Iterative Random Forests

Predict interaction

Description

Generate predictions from random forest decision rules corresponding to a signed interaction.

Usage

interactPredict(x, int, read.forest, varnames = NULL, min.nd = 1)

Arguments

x	numeric feature matrix
int	a signed interaction. Formatted as 'X1+_X2+_X3-_...'
read.forest	output of readForest.
varnames	grouping "hyper-features" for RIT search. Features with the same name will be treated as identical for interaction search.
min.nd	minimum leaf node size to extract decision rules from.

Value

a numeric vector of length nrow(x), entries indicating a predicted response for the corresponding observation. Predictions are generated from random forest decision rules using only the features in int.

karlkumbier/iRF2.0 documentation built on April 12, 2025, 1:44 p.m.