Is there a way to pass parameters to the predict call when using resampling in mlr? E.g. predict.coxph has an extra parameter "reference", which i want to change when using resampling, but extra-parameters for resampling seem to be for the learner only.
I have for now just extracted the models and the test data from the resampling object and apply the prediction myself, but that seems clumsy somehow.
Is there a better solution? Thanks!