org.tribuo

Class Excuse<T extends Output<T>>

java.lang.Object

org.tribuo.Excuse<T>

Direct Known Subclasses:

EnsembleExcuse

public class Excuse<T extends Output<T>>
extends Object

Holds an Example, a Prediction and a Map from String to List of Pairs that contains the per output explanation.

Constructor Summary

Constructors

Constructor and Description
Excuse(Example<T> example, Prediction<T> prediction, Map<String,List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>>> weights) Constructs an excuse for the prediction of the supplied example, using the feature weights.

Method Summary

Modifier and Type	Method and Description
List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>>	excuse(String label) Returns the features involved in this excuse.
Example<T>	getExample() The example being excused.
Prediction<T>	getPrediction() Returns the prediction being excused.
Map<String,List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>>>	getScores() Returns the scores for all outputs and the relevant feature values.

Methods inherited from class java.lang.Object

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

Constructor Detail

Excuse

public Excuse(Example<T> example,
              Prediction<T> prediction,
              Map<String,List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>>> weights)

Constructs an excuse for the prediction of the supplied example, using the feature weights.

Parameters:

example - The example to excuse.

prediction - The prediction to excuse.

weights - The feature weights involved.

Method Detail

excuse

public List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>> excuse(String label)

Returns the features involved in this excuse.

Parameters:

label - The features for the requested output.

Returns:

The features invovled.

getPrediction

public Prediction<T> getPrediction()

Returns the prediction being excused.

Returns:

The prediction.

getScores

public Map<String,List<com.oracle.labs.mlrg.olcut.util.Pair<String,Double>>> getScores()

Returns the scores for all outputs and the relevant feature values.

Returns:

The output scores and feature values.

getExample

public Example<T> getExample()

The example being excused.

Returns:

The example.