org.tribuo.classification.explanations

Interface Explanation<T extends Output<T>>

All Superinterfaces:

Serializable

All Known Implementing Classes:

LIMEExplanation

public interface Explanation<T extends Output<T>>
extends Serializable

An explanation knows what features are used, what the explaining Model is and what the original Model's prediction is.

Method Summary

Modifier and Type	Method and Description
List<String>	getActiveFeatures() Returns the names of the active features in this explanation.
Model<T>	getModel() Returns the explanining model.
Prediction<Label>	getPrediction() The original model's prediction which is being explained.

Method Detail

getActiveFeatures

List<String> getActiveFeatures()

Returns the names of the active features in this explanation.

Returns:

The active feature names.

getModel

Model<T> getModel()

Returns the explanining model.

Returns:

The explanation model.

getPrediction

Prediction<Label> getPrediction()

The original model's prediction which is being explained.

Returns:

The original prediction.