EgorKraevTransferwise
EgorKraevTransferwise
When using` FLAML(task="classification")` as a component model in EconML/DoWhy, sometimes it gets called with `y` being a `pd.DataFrame` with a single column, and that throws an error as it only...
I need to do a rolling prediction, that is, for t = T0, T0+1, ..., T1 I need the model to accept the time series up to t and predict...
Most EconML models offer a way to generate a confidence interval for the point estimates of causal impact. What I need is to calculate confidence intervals over subsets of points,...
In case when treatment and IV are discrete, what does `T*Z` in the description of `model_tz_xw` refer to? Firstly, what kind of component model do I need to supply in...
It's great to have tune() methods in some of the model classes (though sadly not all as yet). But they all seem to do tuning via grid search, which is...
Adressing https://github.com/microsoft/EconML/issues/557 Just did ForestDRLearner to see if you agree with the way I'm doing it, will add the others if so. Is there a reason you don't support dowhy...
It's quite hard to guess the 'right' number of trees for a particular estimator, and a full-on hyperparameter search is quite expensive. Would be great to have an early stopping...
That seems rather large, especially as in CausalForestDML the default is `n_estimators=100`, and the ForestDRLearner with n_trees=1000 can take quite a while to fit. Also for example in XGBoost, also...
Can you please provide some tips on tuning DROrthoForest? From its description it sounds like it would be especially useful on larger datasets due to a local component to the...
Hi! First of all, thanks for the wonderful packages econml and dowhy! When trying to follow the example of "Case Study - Customer Segmentation at An Online Media Company -...