facet.explanation.parallel.ExplainerJob

class facet.explanation.parallel.ExplainerJob(explainer, X, y=None, *, interactions, **kwargs)

A call to an explanation function with given X and y values.

Bases

Job [Union [ndarray [Any, dtype [Any]], List [ndarray [Any, dtype [Any]]]]]

Metaclasses

ABCMeta

Parameters

• explainer (BaseExplainer) – the SHAP explainer to use

• X (Union[ndarray[Any, dtype[Any]], DataFrame, Pool]) – the feature values of the observations to be explained

• y (Union[ndarray[Any, dtype[Any]], Series, None]) – the target values of the observations to be explained

• interactions (bool) – if False, calculate SHAP values; if True, calculate SHAP interaction values

• kwargs (Any) – additional arguments specific to the explanation method

Method summary

delayed	See pytools.parallelization.Job.delayed()
run	Run this job.

Attribute summary

explainer	the SHAP explainer to use
interactions	if False, calculate SHAp values; otherwise, calculate SHAP interaction values
X	the feature values of the observations to be explained
y	the target values of the observations to be explained
kwargs	additional arguments specific to the explanation method

Definitions

classmethod delayed(function)

See pytools.parallelization.Job.delayed()

run()

Run this job.

Return type

Union[ndarray[Any, dtype[Any]], List[ndarray[Any, dtype[Any]]]]

Returns

the result produced by the job

X: Union[numpy.ndarray[Any, numpy.dtype[Any]], pandas.DataFrame, facet.explanation.Pool]

the feature values of the observations to be explained

explainer: facet.explanation.base.BaseExplainer

the SHAP explainer to use

interactions: bool

if False, calculate SHAp values; otherwise, calculate SHAP interaction values

kwargs: Dict[str, Any]

additional arguments specific to the explanation method

y: Optional[Union[numpy.ndarray[Any, numpy.dtype[Any]], pandas.Series]]

the target values of the observations to be explained

previous

facet.explanation.parallel

next

facet.explanation.parallel.ExplainerQueue