ParityOutput#

class dataeval.metrics.bias.ParityOutput(score: TData, p_value: TData, metadata_names: list[str] | None)#

Output class for parity() and label_parity() bias metrics

score#

chi-squared score(s) of the test

Type:

np.float64 | NDArray[np.float64]

p_value#

p-value(s) of the test

Type:

np.float64 | NDArray[np.float64]

metadata_names#

Names of each metadata factor

Type:

list[str] | None