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

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

Provides classes for representing characteristics of a datasets that are part of output data.

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

Bases: TabularOutputData

Represents characteristics of a tabular dataset that are part of output data.

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

OPTION_EXAMPLES = 'examples'

OPTION_FEATURES = 'features'

OPTION_FEATURE_DENSITY = 'feature_density'

OPTION_FEATURE_SPARSITY = 'feature_sparsity'

OPTION_NOMINAL_FEATURES = 'nominal_features'

OPTION_NUMERICAL_FEATURES = 'numerical_features'

OPTION_ORDINAL_FEATURES = 'ordinal_features'

PROPERTIES = TabularProperties(name='Data characteristics', file_name='data_characteristics', has_header=True)

static from_dataset(problem_domain: ProblemDomain, dataset: TabularDataset) → DataCharacteristics

Creates and returns DataCharacteristics from a given dataset.

Parameters:

• problem_domain – The problem domain, the dataset is concerned with

• dataset – The dataset

Returns:

The DataCharacteristics that have been created

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()