gov.sandia.cognition.learning.performance

Class MeanAbsoluteErrorEvaluator<InputType>

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.learning.performance.AbstractSupervisedPerformanceEvaluator<InputType,java.lang.Double,java.lang.Double,java.lang.Double>

gov.sandia.cognition.learning.performance.MeanAbsoluteErrorEvaluator<InputType>

Type Parameters:

InputType - The type of the input to the evaluator to compute the performance of.

All Implemented Interfaces:

PerformanceEvaluator<Evaluator<? super InputType,? extends java.lang.Double>,java.util.Collection<? extends InputOutputPair<? extends InputType,java.lang.Double>>,java.lang.Double>, SupervisedPerformanceEvaluator<InputType,java.lang.Double,java.lang.Double,java.lang.Double>, CloneableSerializable, Summarizer<TargetEstimatePair<? extends java.lang.Double,? extends java.lang.Double>,java.lang.Double>, java.io.Serializable, java.lang.Cloneable

public class MeanAbsoluteErrorEvaluator<InputType>
extends AbstractSupervisedPerformanceEvaluator<InputType,java.lang.Double,java.lang.Double,java.lang.Double>

The MeanAbsoluteError class implements a method for computing the performance of a supervised learner for a scalar function by the mean absolute value between the target and estimated outputs. This can also be referred to as the mean L1 error.

Since:

2.0

Author:

Justin Basilico

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MeanAbsoluteErrorEvaluator() Creates a new instance of MeanAbsoluteError

Method Summary

Modifier and Type	Method and Description
static double	compute(java.util.Collection<? extends TargetEstimatePair<? extends java.lang.Double,? extends java.lang.Double>> data) Computes the mean absolute error for the given pairs of values.
java.lang.Double	evaluatePerformance(java.util.Collection<? extends TargetEstimatePair<? extends java.lang.Double,? extends java.lang.Double>> data) Evaluates the performance accuracy of the given estimates against the given targets.

Methods inherited from class gov.sandia.cognition.learning.performance.AbstractSupervisedPerformanceEvaluator

evaluatePerformance, summarize

Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable

clone

Methods inherited from class java.lang.Object

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

Constructor Detail

MeanAbsoluteErrorEvaluator

public MeanAbsoluteErrorEvaluator()

Creates a new instance of MeanAbsoluteError

Method Detail

evaluatePerformance

public java.lang.Double evaluatePerformance(java.util.Collection<? extends TargetEstimatePair<? extends java.lang.Double,? extends java.lang.Double>> data)

Evaluates the performance accuracy of the given estimates against the given targets.

Specified by:

evaluatePerformance in interface SupervisedPerformanceEvaluator<InputType,java.lang.Double,java.lang.Double,java.lang.Double>

Specified by:

evaluatePerformance in class AbstractSupervisedPerformanceEvaluator<InputType,java.lang.Double,java.lang.Double,java.lang.Double>

Parameters:

data - The target-estimate pairs to use to evaluate performance.

Returns:

The performance evaluation result.

compute

public static double compute(java.util.Collection<? extends TargetEstimatePair<? extends java.lang.Double,? extends java.lang.Double>> data)

Computes the mean absolute error for the given pairs of values. The absolute value of the difference between the two values in each pair is computed and then the mean over all the values is returned.

Parameters:

data - The data to compute the mean absolute error over.

Returns:

The mean absolute error.