K-fold cross validation iterator.

Returns indices for training and test sets.

Parameters
----------
n : Positive integer greater than one. The number of samples.

K : Positive integer greater than or equal to two. The number of folds.

stratified_k_fold(y, K=7)

source code

Stratified k-fold cross validation iterator.

Returns indices for training and test sets.

Parameters
----------
y : Numpy array with n > 1 elements. The class labels. These labels are
        used to stratify the folds.

K : Positive integer greater than or equal to two. The number of folds.

bootstrap(n, B=100, seed=None)

source code

Bootstrap sample iterator.

Returns indices for a bootstrap training set.

Parameters
----------
n : Positive integer greater than one. The number of samples.

B : Positive integer greater than or equal to two. The number of bootstrap
        samples to draw.

seed : Integer. A random seed to initialise the random number generator
        with. Use in order to obtain deterministic results. The seed is not
        used if the seed is None.

stratified_bootstrap(y, B=100, seed=None)

source code

Stratified bootstrap sample iterator.

Returns indices for a bootstrap training set.

Parameters
----------
y : Numpy array with n > 1 elements. The class labels. These labels are
        used to stratify the samples.

B : Positive integer greater than or equal to two. The number of bootstrap
        samples to draw.

seed : Integer. A random seed to initialise the random number generator
        with. Use in order to obtain deterministic results. The seed is not
        used if the seed is None.