Learn R Programming

emil (version 2.0.2)

fit_cforest: Fit conditional inference forest

Description

A cforest is a random forest based on conditional inference trees, using the implementation in the party package. These trees can be used for classification, regression or survival analysis, but only the survival part has been properly tested so far.

Usage

fit_cforest(x, y, formula = y ~ ., ctrl_fun = party::cforest_unbiased, ...)

Arguments

x
Dataset, observations as rows and descriptors as columns.
y
Responses.
formula
Formula linking response to descriptors.
ctrl_fun
Which control function to use, see cforest_control.
...
Sent to the function specified by ctrl_fun.

Value

Details

The parameters to cforest are set using a cforest_control object. You should read the documentation as the default values are chosen for technical reasons, not predictive performance! Pay special attention to mtry which is set very low by default.

See Also

emil, predict_cforest, modeling_procedure