Cross-validation in ScikitLearn.jl is the same as in scikit-learn:

using ScikitLearn.CrossValidation: cross_val_score

cross_val_score(LogisticRegression(), X, y; cv=5)  # 5-fold

See ?cross_val_score and the user guide for details.

We support all the scikit-learn cross-validation iterators (KFold, StratifiedKFold, etc.) For example:

> ScikitLearn.CrossValidation.KFold(10, n_folds=3)

3-element Array{Tuple{Array{Int64,1},Array{Int64,1}},1}:

These iterators can be passed to cross_val_score's cv argument.

Note: the most common iterators have been translated to Julia. The others still require scikit-learn (python) to be installed.


Cross-validated predictions

cross_val_predict performs cross-validation and returns the test-set predicted values. Documentation here