fit_predict: Fit a reward estimation model on features, treatments and outcomes and
return predicted counterfactual rewards for each observation, as well as the
score of the internal estimators.
Description
For categorical treatments, returns the estimated reward under each
treatment observed in the data. For numeric treatments, returns the
estimated reward under each treatment candidate.
Usage
fit_predict(lnr, X, treatments, ...)
Arguments
lnr
The learner or grid to use for estimation
X
The features of the data.
treatments
The treatment applied to each point in the data.
...
Additional arguments depending on the treatment and outcome types.
Refer to the Julia documentation for more information.