LearnAPI.jl

A base Julia interface for machine learning and statistics

Comprehensive documentation is here.

New contributions welcome. See the road map.

Code snippet

Configure a machine learning algorithm:

julia> ridge = Ridge(lambda=0.1)

Inspect available functionality:

julia> LearnAPI.functions(ridge)
(:(LearnAPI.fit), :(LearnAPI.learner), :(LearnAPI.strip), :(LearnAPI.obs), 
:(LearnAPI.features), :(LearnAPI.target), :(LearnAPI.predict), :(LearnAPI.coefficients))

Train:

julia> model = fit(ridge, data)

Predict:

julia> predict(model, data)[1]
"virginica"

Predict a probability distribution (proxy for the target):

julia> predict(model, Distribution(), data)[1]
UnivariateFinite{Multiclass{3}}(setosa=>0.0, versicolor=>0.25, virginica=>0.75)

Credits

Created by Anthony Blaom, in cooperation with Cameron Bieganek and other members of the Julia community.