xaib.explainers.feature_importance¶

class xaib.explainers.feature_importance.constant_explainer.ConstantExplainer(constant: Any, *args: Any, **kwargs: Any)[source]¶

predict(x: Any, model: Model) → Any[source]¶

Method to encapsulate inference. May include preprocessing steps to make model self-sufficient.

class xaib.explainers.feature_importance.lime_explainer.LimeExplainer(train_ds, labels, *args, meta_prefix=None, **kwargs)[source]¶

predict(x, model)[source]¶

Method to encapsulate inference. May include preprocessing steps to make model self-sufficient.

class xaib.explainers.feature_importance.linear_regression_explainer.LinearRegressionExplainer(get_coef)[source]¶

predict(x, model)[source]¶

Method to encapsulate inference. May include preprocessing steps to make model self-sufficient.

class xaib.explainers.feature_importance.random_explainer.RandomExplainer(shift=0, magnitude=1, *args, **kwargs)[source]¶

predict(x: Any, model: Model) → Any[source]¶

Method to encapsulate inference. May include preprocessing steps to make model self-sufficient.

class xaib.explainers.feature_importance.shap_explainer.ShapExplainer(train_ds, *args, meta_prefix=None, **kwargs)[source]¶

predict(x, model)[source]¶

Method to encapsulate inference. May include preprocessing steps to make model self-sufficient.