Anthony Blaom, PhD
Anthony Blaom, PhD
Mmm. It seems integration tests still fail as the test log would otherwise report the flagged issue can be dropped. So there may be a new issue.
It is not possible at present as 1, 2, and 3 are all different: 2 does not generalize to new observations, and 3 outputs probabilistic labels. There are natural differences...
? https://github.com/JuliaRegistries/General/pull/98572
Closing in favour of adding workloads added to component packages. See also https://github.com/JuliaAI/MLJBase.jl/issues/924
No, I think if you want to get probabilisitic predictions for the original (atomic) model, then you need to train the atomic model on the data. You can't eat your...
(After https://github.com/JuliaAI/MLJBase.jl/pull/853, the preferred way of exporting the learning network is to replace `MLJ.fit` definition above with the simpler ```julia function MLJ.prefit(thresholder::Thresholder, verbosity, X, y) Xs = source(X) ys =...
Yes, it is trained, but the *public* API doesn't give you a way to produce *probabilistic* predictions. It *is* possible to get them without retraining, but it's a hack (non-public...
Closing as question resolved.
FYI: I generally point to https://alan-turing-institute.github.io/MLJ.jl/dev/ (rather than the MLJ repo). I suppose you're suggesting a replacement for that?
This is now work in progress. Standby for a new landing page soon.