EgorKraevTransferwise

Are there any plans to add this? Would be a really big deal for financial applications, among many others

Thanks! Would I not want to convert the one-column dataframe to a column before using it, or will that happen automatically if it passes the assertions?

Sounds good! We're not using SDV at the moment, but might well come back to that in a quarter or two, and if so we'll want to train the models...

Created a PR https://github.com/py-why/dowhy/pull/485

To elaborate, the set A below could be represented via an `outcome_modifiers` init arg and class member in the CausalModel, and adjusting the DML classes to take an additional optional...

The power of the DoWhy approach is in the clean separation between the causal graph and the models/functional relationships chosen to fit the data. I would argue that in that...

Thanks for the detailed answer! We seem to be aligned on the basic point, namely that 'outcome modifiers' is purely a property of the causal graph (parents of Y that...

Please, @amit-sharma could you provide a link to the PR? From what I can see, the line in question is still [there](https://github.com/py-why/dowhy/blob/cf44aab1d2865cd1fe6bd9cf81551f47cff4600e/dowhy/causal_model.py#L249). Also, for the case when both iv and...

I am using the [ERUPT](https://medium.com/building-ibotta/erupt-expected-response-under-proposed-treatments-ff7dd45c84b4) metric on a holdout dataset to compare different models, seems to make sense to me, namely out-of-sample comparison of treatment assignment policies conditioned on the...

How about `estimator.effect_inference(X).population_summary()`?