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

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

Provides classes for representing characteristics of an output matrix that are part of output data.

class mlrl.testbed_sklearn.experiments.output.characteristics.data.characteristics.Characteristic(option_key: str, name: str, function: Callable[[Any], Number], percentage: bool = False)

Bases: OutputValue

An individual characteristic that is part of output data.

Function

alias of Callable[[Any], Number]

class mlrl.testbed_sklearn.experiments.output.characteristics.data.characteristics.OutputCharacteristics(values: list[tuple[Characteristic, Any]], properties: Properties, context: Context = Context(include_dataset_type=True, include_prediction_scope=True, include_fold=True))

Bases: TabularOutputData

Represents characteristics of an output matrix that are part of output data.

OPTION_DISTINCT_LABEL_VECTORS = 'distinct_label_vectors'

OPTION_LABEL_CARDINALITY = 'label_cardinality'

OPTION_LABEL_IMBALANCE_RATIO = 'label_imbalance_ratio'

OPTION_OUTPUTS = 'outputs'

OPTION_OUTPUT_DENSITY = 'output_density'

OPTION_OUTPUT_SPARSITY = 'output_sparsity'

to_table(options: Options, **kwargs) → Table | None

See mlrl.testbed.experiments.output.data.TabularOutputData.to_table()

to_text(options: Options, **kwargs) → str | None

See mlrl.testbed.experiments.output.data.TextualOutputData.to_text()

mlrl.testbed_sklearn.experiments.output.characteristics.data.characteristics.get_output_characteristics(problem_domain: ProblemDomain) → list[Characteristic]

Returns the output characteristics to be used, depending on the problem domain.

Parameters:

problem_domain – The problem domain

Returns:

A list that stores the output characteristics