statsmodels.jl and MLJ interfaces

cscherrer / BayesianLinearRegression.jl

A Julia implementation of Bayesian linear regression using marginal likelihood for hyperparameter optimization, as presented in Chris Bishop's book.

Other

27 stars 0 forks source link

Open AriMKatz opened 4 years ago

AriMKatz commented 4 years ago

Really cool package, looking forward to taking it for a spin.

Would be great to interface with statsmodels.jl for an additional R style model fitting API.

Also a connection to MLJ would be useful as well.

cscherrer commented 4 years ago

Oh great idea! I hadn't thought of StatsModels. I've played with connecting MLJ, but to really do it the right way it needs support for correlated weights: https://github.com/alan-turing-institute/MLJ.jl/issues/552