edu.cornell.med.icb.stat
Class AreaUnderTheRocCurveCalculator

java.lang.Object
  edu.cornell.med.icb.stat.PredictionStatisticCalculator
      edu.cornell.med.icb.stat.AreaUnderTheRocCurveCalculator

public class AreaUnderTheRocCurveCalculator
extends PredictionStatisticCalculator

Author:

Fabien Campagne Date: Oct 8, 2009 Time: 5:42:26 PM

Field Summary

Fields inherited from class edu.cornell.med.icb.stat.PredictionStatisticCalculator

highestStatisticIsBest, optimalThreshold, statistic, zero

Constructor Summary

AreaUnderTheRocCurveCalculator()

Method Summary

double	evaluateStatistic(double[] decisionValues, double[] labels)
double	evaluateStatisticAtThreshold(double threshold, double[] decisionValues, double[] labels) Evaluate the statistic for a given decision function threshold.
String	getMeasureName()
double	thresholdIndependentStatistic(double[] decisionValues, double[] labels) Calculates the Matthews Correlation coefficient.
double	thresholdIndependentStatistic(ObjectList<double[]> decisionValueList, ObjectList<double[]> labelList) Calculates the optimal statistic at any decision threshold.
double	thresholdIndependentStatisticStd(ObjectList<double[]> decisionValueList, ObjectList<double[]> trueLabelList)

Methods inherited from class edu.cornell.med.icb.stat.PredictionStatisticCalculator

evaluateContingencyTable, evaluateStatisticAtThreshold, predictivePotential, thresholdIndependentStatisticSte

Methods inherited from class java.lang.Object

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

Constructor Detail

AreaUnderTheRocCurveCalculator

public AreaUnderTheRocCurveCalculator()

Method Detail

getMeasureName

public String getMeasureName()

Specified by:

getMeasureName in class PredictionStatisticCalculator

evaluateStatisticAtThreshold

public double evaluateStatisticAtThreshold(double threshold,
                                           double[] decisionValues,
                                           double[] labels)

Description copied from class: PredictionStatisticCalculator

Evaluate the statistic for a given decision function threshold.

Specified by:

evaluateStatisticAtThreshold in class PredictionStatisticCalculator

thresholdIndependentStatistic

public double thresholdIndependentStatistic(double[] decisionValues,
                                            double[] labels)

Description copied from class: PredictionStatisticCalculator

Calculates the Matthews Correlation coefficient. Find the maximal MCC value irrespective of the threshold on the decision value. All the possible thresholds on the decision value are scanned and the maximum MCC values found is returned.

Overrides:

thresholdIndependentStatistic in class PredictionStatisticCalculator

Returns:

evaluateStatistic

public double evaluateStatistic(double[] decisionValues,
                                double[] labels)

thresholdIndependentStatistic

public double thresholdIndependentStatistic(ObjectList<double[]> decisionValueList,
                                            ObjectList<double[]> labelList)

Calculates the optimal statistic at any decision threshold. All the possible thresholds on the decision value are scanned and the optimal statistic found is returned. When highestStatisticIsBest is true, the largest statistic found at any threshold is returned. Otherwise, the lowest statistic is returned.

Overrides:

thresholdIndependentStatistic in class PredictionStatisticCalculator

Parameters:

decisionValueList - Each element of this list should corresponds to a split of evaluation (decision values).

labelList - Each element of this list should corresponds to a split of evaluation (true labels).

Returns:

thresholdIndependentStatisticStd

public double thresholdIndependentStatisticStd(ObjectList<double[]> decisionValueList,
                                               ObjectList<double[]> trueLabelList)

Overrides:

thresholdIndependentStatisticStd in class PredictionStatisticCalculator