KFoldSplitter

class KFoldSplitter(*args)

K-fold splitter.

Generates train/test indices to split samples in train/test sets. The sample is split into k folds. Each fold is then used once as test while the k - 1 other folds form the training set.

Parameters:

Nint

Size of the set of indices in which the indices are chosen

kint

Number of folds

Methods

getClassName()	Accessor to the object's name.
getN()	Set size accessor.
getName()	Accessor to the object's name.
getSize()	Number of sets generated.
hasName()	Test if the object is named.
setName(name)	Accessor to the object's name.
setRandomize(randomize)	Set the value of the randomize flag.

Examples

>>> import openturns as ot
>>> sample = ot.Normal().getSample(10)
>>> k = 5
>>> splitter = ot.KFoldSplitter(sample.getSize(), k)
>>> for indicesTrain, indicesTest in splitter:
...     sampleTrain, sampleTest = sample[indicesTrain], sample[indicesTest]

__init__(*args)

getClassName()

Accessor to the object’s name.

Returns:

class_namestr

The object class name (object.__class__.__name__).

getN()

Set size accessor.

Returns:

Nint

Size of the set of indices in which the indices are chosen

getName()

Accessor to the object’s name.

Returns:

namestr

The name of the object.

getSize()

Number of sets generated.

Returns:

lengthint

Number of sets of indices generated.

hasName()

Test if the object is named.

Returns:

hasNamebool

True if the name is not empty.

setName(name)

Accessor to the object’s name.

Parameters:

namestr

The name of the object.

setRandomize(randomize)

Set the value of the randomize flag.

Note that the default value is set via the ResourceMap entry KFoldSplitter-Randomize.

Parameters:

randomizebool

Scramble the folds.

Examples using the class

Polynomial chaos expansion cross-validation

Polynomial chaos expansion cross-validation

Compute leave-one-out error of a polynomial chaos expansion

Compute leave-one-out error of a polynomial chaos expansion