💎 API Reference

This is the class and function reference of XAIoGraphs.

For more information, please refer to the whole User Guide because the class and function raw specifications might not be sufficient to provide comprehensive instructions on how to utilize them.

xaiographs.Explainer

xaiographs.Explainer

The Explainer class provides an abstract layer which encapsulates everything related to the explanation process from statistics calculation, importance calculation (using the engine chosen by the user) and information export for visualization tasks.

xaiographs.Why

xaiographs.Why

This class is intended to provide an explanation on why a given case has been assigned a certain label (target value), combining case-specific reason (feature-value), model-specific reason (feature-value per target) and the target itself.

xaiographs.Fairness

xaiographs.Fairness

The Fairness class offers functionalities to explain how fair or unfair are the classifications made by a (Deep) Machine Learning model on a set of features that we consider sensitive (gender, ethnic group, religion, age, etc.).

xaiographs.datasets

xaiographs.datasets.load_titanic	Returns Titanic dataset with the following Features:
xaiographs.datasets.load_titanic_discretized	Returns titanic dataset (and other metadata) to be tested in xaiographs.
xaiographs.datasets.load_titanic_why	Returns the necessary DataFrames to test the WHY module of XAIoGraphs with the explainability calculated with the Titanic dataset.
xaiographs.datasets.load_compas	Returns COMPAS dataset with the following Features:
xaiographs.datasets.load_compas_discretized	Returns COMPAS dataset (and other metadata) to be tested in xaiographs.
xaiographs.datasets.load_compas_why	Returns the necessary DataFrames to test the WHY module of XAIoGraphs with the explainability calculated with the COMPAS dataset.
xaiographs.datasets.load_compas_reality_discretized	Returns COMPAS dataset (and other metadata) to be tested in xaiographs.
xaiographs.datasets.load_compas_reality_why	Returns the necessary DataFrames to test the WHY module of XAIoGraphs with the explainability calculated with the COMPAS dataset.
xaiographs.datasets.load_body_performance	Returns body performance dataset with the following Features:
xaiographs.datasets.load_body_performance_discretized	Returns body performance dataset (and other metadata) to be tested in xaiographs.
xaiographs.datasets.load_body_performance_why	Returns the necessary DataFrames to test the WHY module of XAIoGraphs with the explainability calculated with the Body Performance dataset.
xaiographs.datasets.load_education_performance	Returns body performance dataset with the following Features:
xaiographs.datasets.load_education_performance_discretized	Returns education performance dataset (and other metadata) to be tested in xaiographs.
xaiographs.datasets.load_education_performance_why	Returns the necessary DataFrames to test the WHY module of XAIoGraphs with the explainability calculated with the Body Performance dataset.