These defaults emulate cforest_unbiased() but allow customization.
SL.cforest(Y, X, newX, family, obsWeights, id, ntree = 1000,
mtry = max(floor(ncol(X)/3), 1), mincriterion = 0, teststat = "quad",
testtype = "Univ", replace = F, fraction = 0.632, ...)
Outcome variable
Covariate dataframe
Optional dataframe to predict the outcome
"gaussian" for regression, "binomial" for binary classification
Optional observation-level weights (supported but not tested)
Optional id to group observations from the same unit (not used currently).
Number of trees
Number of randomly selected features per node
See ?cforest_control
See ?cforest_control
See ?cforest_control
See ?cforest_control
See ?cforest_control
Remaining arguments (unused)