Alternative explanations and ensured filters¶
Alternative explanations show how feature changes may change predictions.
Semantics and non-guarantees are defined in Calibrated interval semantics.
Generate alternatives¶
alternatives = explainer.explore_alternatives(X_query)
alt0 = alternatives[0]
For probabilistic regression:
alternatives = explainer.explore_alternatives(X_query, threshold=150.0)
Ensured filters¶
The alternative object supports these filters:
super_explanations()semi_explanations()counter_explanations()ensured_explanations()pareto_explanations()
Plotting and conjunctions¶
alt0.add_conjunctions(n_top_features=5, max_rule_size=2)
alt0.plot(style="triangular", show=False)