Passing return_std to predict

Discussion at discourse and ScikitLearn.jl issue suggested raising an issue here, with background and suggestions copied:

From me @evolbio:
Various Scikitlearn models accept return_std=true when calling predict, for example BayesianRidgeRegressor, see this example. For example, with a BayesianRidgeRegressor or similar machine, I would like to call
y_predict, y_std = predict(machine, X, return_std=true)
I am using MLJ to make calls through ScikitLearn.jl. I have looked through ScikitLearn.jl and MLJScikitLearnInterface.jl and do not see anyway to make this work, but maybe I am missing something simple like the right way to pass additional arguments? Thanks.

and reply from @tlienart:
You’re not missing something, there’s currently no way to pass that argument. It might be good to open an issue at MLJScikitLearnInterface to discuss this (and you could paste what follows).

I doubt that MLJ’s predict signature will be adapted to match this one but I’ll let @ablaom or @samuel_okon discuss that).

What could work is to pass the return_std as a new field of BayesianRidgeRegressor here MLJScikitLearnInterface.jl/linear-regressors.jl at 36882f14321e7e9889aac31447eeed0102eb052f · JuliaAI/MLJScikitLearnInterface.jl · GitHub

then pick that up at predict time here MLJScikitLearnInterface.jl/macros.jl at 36882f14321e7e9889aac31447eeed0102eb052f · JuliaAI/MLJScikitLearnInterface.jl · GitHub

this would also require ScikitLearn.jl to allow passing a return_std=true to predict, that might also require opening an issue there cc @cstjean

Start with src/models/linear-regressors.jl and src/macros.jl at the linked locations to review the suggested model field and predict-time handling. Check the related ScikitLearn.jl issue before proceeding, since passing return_std=true may require support there as well. Done means a BayesianRidgeRegressor or similar model can request return_std through MLJ and receive the prediction and standard deviation.