mlrl.testbed_sklearn.experiments.output.characteristics.data.characteristics_prediction module

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

Provides classes for representing characteristics of binary predictions that are part of output data.

class mlrl.testbed_sklearn.experiments.output.characteristics.data.characteristics_prediction.PredictionCharacteristics(values: list[tuple[Characteristic, Any]])

Bases: OutputCharacteristics

Represents characteristics of binary predictions that are part of output data.

CONTEXT = Context(include_dataset_type=True, include_prediction_scope=True, include_fold=True)

PROPERTIES = TabularProperties(name='Prediction characteristics', file_name='prediction_characteristics', has_header=True)

static from_prediction_matrix(problem_domain: ProblemDomain, prediction_matrix: OutputMatrix) → PredictionCharacteristics

Creates and returns OutputCharacteristics from a given output matrix.

Parameters:

• problem_domain – The problem domain, the output matrix corresponds to

• prediction_matrix – An prediction matrix

Returns:

The OutputCharacteristics that have been created