Anthony Blaom, PhD

Optionally combine with #177

Thanks for that! It seems some MLJ-specific elements (and particular, Examples) are missing, but this is great improvement. (The full spec is [here](https://alan-turing-institute.github.io/MLJ.jl/dev/adding_models_for_general_use/#Document-strings)). Unfortunately, as BetaML uses DocStringExtensions.jl, this may...

> Hy @ablaom , how can I check how the standard doc "renders" in the user case you have in mind It should suffice to query the ordinary doc string...

@storopoli I guess algorithms that use dictionaries as read-only should be fine. So supplying dictionaries to NaiveBayes.jl should be okay. However, I see that the TextAnalysis version does write to...

As `MLJBase.matrix` is a wrap of `Tables.matrix` @quinnj may want to address this question. As I understand it, the best strategy depends on the table you are converting, information we...

Not familiar with cross_decomposition. Can I think of this as a transformer, like we do PCA?

Continuing the discussion started by @indymnv at https://github.com/alan-turing-institute/MLJ.jl/issues/970: Existing MLJ transformers are documented [here](https://github.com/alan-turing-institute/MLJ.jl/issues/970 ) with the exception of `InteractionTransformer`, which was recently added to MLJModels, but is not documented...

Thanks @indymnv . That's most helpful. PR's for missing items welcome 😉

Thanks for reporting. Are you referring to the field of `fitted_params`? As far as I can tell, this is generated for all model simultaneously (see below) so I'm not sure...

Maybe related to https://github.com/alan-turing-institute/MLJ.jl/issues/757