mlrl.testbed_sklearn.experiments.input.dataset.splitters.splitter_cross_validation module

Author: Michael Rapp (michael.rapp.ml@gmail.com)

Provides classes for splitting datasets into multiple, equally sized, folds consisting of a training and a test dataset.

class mlrl.testbed_sklearn.experiments.input.dataset.splitters.splitter_cross_validation.CrossValidationSplitter(dataset_reader: DatasetReader | None, num_folds: int, first_fold: int, last_fold: int, random_state: int)

Bases: DatasetSplitter

Splits a tabular dataset into training and test datasets corresponding to the individual folds of a cross validation.

class DynamicSplit(splitter: CrossValidationSplitter, state: ExperimentState)

Bases: Split

A split into training and test datasets that corresponds to an individual fold of a cross validation and is created dynamically.

class Cache(training_datasets: list[TabularDataset] = <factory>, test_datasets: list[TabularDataset] = <factory>)

Bases: object

Caches training and test datasets that correspond to individual folds.

Attributes:

training_datasets: A list that stores the training datasets test_datasets: A list that stores the test datasets

test_datasets: list[TabularDataset]

training_datasets: list[TabularDataset]

get_state(dataset_type: DatasetType) → ExperimentState

See mlrl.testbed.experiments.input.dataset.splitters.splitter.DatasetSplitter.Split.get_state()

class PredefinedSplit(splitter: CrossValidationSplitter, state: ExperimentState)

Bases: Split

A predefined split into training and test datasets that corresponds to an individual fold of a cross validation.

class Cache(num_folds: int)

Bases: object

Caches the datasets that correspond to individual folds of a cross validation.

get_state(dataset_type: DatasetType) → ExperimentState

See mlrl.testbed.experiments.input.dataset.splitters.splitter.DatasetSplitter.Split.get_state()

split(state: ExperimentState) → Generator[Split, None, None]

See mlrl.testbed.experiments.input.dataset.splitters.splitter.DatasetSplitter.split()