Chris Kennedy

I think the issue would be resolved if the CLI allowed specifying the "stratified_types" argument to [split_dataset](https://github.com/v7labs/darwin-py/blob/master/darwin/dataset/split_manager.py#L78), and I could specify "bounding_box" so that the tag is not also used...

The dataset export is annotatevape / training-data:complete-in-review-1434-may-2nd - are you able to access that? I don't really have capacity to make a sample dataset unfortunately. It has been resolved in...

Thanks, appreciate it. Maybe there is a hack to fit the estimator manually outside of stremr, add the predictions to the data table as a new column with replicated predicted...

I guess longer term perhaps there could be a subset_TRT formula for fitPropensity() to identify the subset of observations used for estimation. Or perhaps if I used an sl3 estimator...

My interpretation of the article is that for the ITT parameter the treatment propensity score (& associated weights) is time-invariant and based on exposure status at t == 0. So...

Thanks a bunch, ok I will give this a try and report back.

I need this kind of method to use mlr3 for EHR-based machine learning - specifically the ability to define training/test/validation sets using date-based splits. Is it possible for me to...

Ah ok, awesome - appreciate the help & fast response 🙏