only in new data flag
topepo opened this issue · comments
Max Kuhn commented
Sort of like skipping in recipes, can we put a flag in adjust_predictions_custom()
to apply it to new data (i.e. not during the model optimization/evaluation cycle)?
I'd like people to avoid exponentiating predictions prior to metric computations. We could add a similar flag to fit.tailor()
that says, "We are in pure new sample prediction mode." We can set that appropriately in tune.
Simon P. Couch commented
Related, maybe duplicate, of #18.