SL.cforest {SuperLearner} | R Documentation |
cforest (party)
Description
These defaults emulate cforest_unbiased() but allow customization.
Usage
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, ...)
Arguments
Y |
Outcome variable |
X |
Covariate dataframe |
newX |
Optional dataframe to predict the outcome |
family |
"gaussian" for regression, "binomial" for binary classification |
obsWeights |
Optional observation-level weights (supported but not tested) |
id |
Optional id to group observations from the same unit (not used currently). |
ntree |
Number of trees |
mtry |
Number of randomly selected features per node |
mincriterion |
See ?cforest_control |
teststat |
See ?cforest_control |
testtype |
See ?cforest_control |
replace |
See ?cforest_control |
fraction |
See ?cforest_control |
... |
Remaining arguments (unused) |
[Package SuperLearner version 2.0-29 Index]