javax.datamining.supervised.regression
Interface RegressionTestMetrics

All Superinterfaces:

MiningObject, TestMetrics

public interface RegressionTestMetrics

extends TestMetrics

A RegressionTestResult provides an interface to access the metadata resulting from executing a RegressionTestTask.

Author:

JSR-73 Java Data Mining Expert Group

See Also:

MiningObject, TestMetrics

Method Summary

java.lang.Double	getMeanAbsoluteError() Returns the mean absolute error of predictions.
java.lang.Double	getMeanActualValue() Returns the mean (i.e., the average of) actual target value.
java.lang.Double	getMeanPredictedValue() Returns the mean (i.e., the average of ) predicted target value.
java.lang.Double	getRMSError() Returns the root mean sum of squared errors of predictions.
java.lang.Double	getRSquared() Returns proportional reduction in the variability of the target associated with the predicted target values.

Methods inherited from interface javax.datamining.supervised.TestMetrics

getModelName, getTaskIdentifier, getTestDataName

Methods inherited from interface javax.datamining.MiningObject

getCreationDate, getCreatorInfo, getDescription, getName, getObjectIdentifier, getObjectType, setDescription

Method Detail

getMeanAbsoluteError

public java.lang.Double getMeanAbsoluteError()

Returns the mean absolute error of predictions. If not computed, it returns null.

Returns:

Double

getMeanActualValue

public java.lang.Double getMeanActualValue()

Returns the mean (i.e., the average of) actual target value. If not computed, it returns null.

Returns:

Double

getMeanPredictedValue

public java.lang.Double getMeanPredictedValue()

Returns the mean (i.e., the average of ) predicted target value. If not computed, it returns null.

Returns:

Double

getRMSError

public java.lang.Double getRMSError()

Returns the root mean sum of squared errors of predictions. If not computed, it returns null.

Returns:

Double

getRSquared

public java.lang.Double getRSquared()

Returns proportional reduction in the variability of the target associated with the predicted target values.

If not computed, it returns null.

Returns:

Double