Package org.tribuo.classification.explanations.lime

Class LIMEExplanation

java.lang.Object

org.tribuo.classification.explanations.lime.LIMEExplanation

All Implemented Interfaces:

Serializable, Explanation<Regressor>

public class LIMEExplanation
extends Object
implements Explanation<Regressor>

An Explanation using LIME.

Wraps a SparseModel Regressor which is trained to predict the probabilities generated by the true Model.

See:

 Ribeiro MT, Singh S, Guestrin C.
 "Why should I trust you?: Explaining the predictions of any classifier"
 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2016.
 

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
LIMEExplanation(org.tribuo.SparseModel<Regressor> model, org.tribuo.Prediction<Label> prediction, RegressionEvaluation evaluation)	Constructs a LIME explanation.

Method Summary

Modifier and Type	Method	Description
List<String>	getActiveFeatures()	Returns the names of the active features in this explanation.
RegressionEvaluation	getEvaluation()	Gets the evaluator which scores how close the sparse model's predictions are to the complex model's predictions.
org.tribuo.SparseModel<Regressor>	getModel()	Returns the explanining model.
org.tribuo.Prediction<Label>	getPrediction()	The original model's prediction which is being explained.
double	getRMSE(String name)	Get the RMSE of a specific dimension of the explanation model.
String	toString()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Details

LIMEExplanation

public LIMEExplanation(org.tribuo.SparseModel<Regressor> model,
 org.tribuo.Prediction<Label> prediction,
 RegressionEvaluation evaluation)

Constructs a LIME explanation.

Parameters:

model - The explanation model.

prediction - The prediction being explained.

evaluation - The evaluation of the explanation model on the sampled data.

Method Details

getActiveFeatures

public List<String> getActiveFeatures()

Description copied from interface: Explanation

Returns the names of the active features in this explanation.

Specified by:

getActiveFeatures in interface Explanation<Regressor>

Returns:

The active feature names.

getModel

public org.tribuo.SparseModel<Regressor> getModel()

Description copied from interface: Explanation

Returns the explanining model.

Specified by:

getModel in interface Explanation<Regressor>

Returns:

The explanation model.

getPrediction

public org.tribuo.Prediction<Label> getPrediction()

Description copied from interface: Explanation

The original model's prediction which is being explained.

Specified by:

getPrediction in interface Explanation<Regressor>

Returns:

The original prediction.

getEvaluation

public RegressionEvaluation getEvaluation()

Gets the evaluator which scores how close the sparse model's predictions are to the complex model's predictions.

Returns:

The evaluation.

getRMSE

public double getRMSE(String name)

Get the RMSE of a specific dimension of the explanation model.

Parameters:

name - The dimension to look at.

Returns:

The RMSE of the explanation model.

toString

public String toString()

Overrides:

toString in class Object