cross_val_score(datasets, model_factory, ...) Evaluate model performance via cross validation for a given set of parameters.

Shuffling and splitting

KFold(data, num_folds) Create a K-Fold split of a data set as an iteratable/indexable object of K pairs, where each pair is a partition of the data set.
shuffle(sf[, random_seed]) Create a copy of the SFrame where the rows have been shuffled randomly.