Calculates per-level mean of predicted value vs actual value for a given variable.

In the basic setting, this function is equivalent to doing group-by on variable and calculating mean on predicted and actual. In addition to that it also handles NAs in response and weights automatically.

h2o.predicted_vs_actual_by_variable(object, newdata, predicted, variable)

Arguments

object

A trained supervised H2O model.

newdata

Input frame (can be training/test/.. frame).

predicted

Frame of predictions for the given input frame.

variable

Name of variable to inspect.

Value

H2OTable