minimize(model) -> <smaller version of model suitable for serialization>

Typical workflow

model = fit(algorithm, X, y)
ŷ = predict(model, LiteralTarget(), Xnew)

small_model = minimize(model)
serialize("my_model.jls", small_model)

recovered_model = deserialize("my_random_forest.jls")
@assert predict(recovered_model, LiteralTarget(), Xnew) == ŷ

# throws MethodError:

Implementation guide



minimize(model; options...)

Return a version of model that will generally have a smaller memory allocation than model, suitable for serialization. Here model is any object returned by fit. Accessor functions that can be called on model may not work on minimize(model), but predict, transform and inverse_transform will work, if implemented for model. Check LearnAPI.functions(LearnAPI.algorithm(model)) to view see what the original model implements.

Specific algorithms may provide keyword options to control how much of the original functionality is preserved by minimize.

Extended help

New implementations

Overloading minimize for new algorithms is optional. The fallback is the identity. If overloaded, you must include minimize in the tuple returned by the LearnAPI.functions trait.

New implementations must enforce the following identities, whenever the right-hand side is defined:

predict(minimize(model; options...), args...; kwargs...) ==
    predict(model, args...; kwargs...)
transform(minimize(model; options...), args...; kwargs...) ==
    transform(model, args...; kwargs...)
inverse_transform(minimize(model; options), args...; kwargs...) ==
    inverse_transform(model, args...; kwargs...)


minimize(minimize(model)) == minimize(model)