Jeremy Coyle

Not sure what behavior you're expecting here, training and prediction have both different numbers of folds and observations. Validation should stack validation preds but it can only do it for...

So calling `lrnr$train` on any learner is going to be running delayed anyways. See: https://github.com/tlverse/sl3/blob/master/R/Lrnr_base.R#L224 The difference between the two runs is that by default we use `FutureJob`, not `SequentialJob`,...

Hello, Yes, you can pass fitted sl3 objects into the library instead of the unfitted one. Please be aware that by default tmle3 implements cv-tmle and so the fold structure...

Example callouts here: https://github.com/tlverse/tlverse-handbook/blob/master/01-preface.Rmd#L3-L9

Code chunk formatting is via the listings package: https://github.com/tlverse/tlverse-handbook/blob/master/latex_extras/preamble.tex#L82 Options here: https://en.wikibooks.org/wiki/LaTeX/Source_Code_Listings#Settings

Thanks for reporting. Looks like an issue with some of the factor covariate levels not appearing in all strata of REGION. We'll fix the exercise and also the bug. In...

I was under the impression that updates were always fit using observed outcomes and the corresponding likelihood values (so here observed A and p(A=a|W). The update is then applied to...

No parameters have been implemented that support categorical outcomes, but it’d be trivial to implement ATE or TSM generalizations for them. There’s nothing stopping you from fitting a likelihood with...

Thanks for the detailed example. The issue can be solved by changing the NPSEM to specify that the Y likelihood factor is a mean E(Y|A) not a density p(Y|A) as...

`tmle3` trains the `sl3` learners you ask it to train in the `learner_list` argument on the data in the `tmle_task`. You can specify any `sl3` learners you like. If they...