How to use known treatment probabilities in doubly robust learners

@kbattocchi

Hi Keith,

How would you recommend handling a case where we know the true treatment probabilities? I'd prefer to use them to avoid having to fit the model_propensity (in a doubly robust model, say ForestDRLearner).

A few options:

1. Pass the (inverse) probabilities as sample_weight to fit. But then we need to choose something for model_propensity, perhaps just a dummy classifier?
2. Create a trivial model_propensity that takes the probability as a feature and returns the same probability. But then we need some workaround to prevent the model_regression from using the probability as a feature (by DRLearner will always pass X, W to both model_propensity and model_regression). Maybe we can use a sklearn pipeline with transformer for this.

Thanks!
Kyle

Review the ForestDRLearner and DRLearner fit entry points, focusing on model_propensity, model_regression, X, W, and sample_weight. Compare the proposed known-probability approaches and define behavior and tests for supplying probabilities without fitting model_propensity or exposing them to model_regression. No files or tests are named, so repository exploration and maintainer clarification are needed.