smile.validation.metric

Class AUC

java.lang.Object

smile.validation.metric.AUC

All Implemented Interfaces:

java.io.Serializable, ProbabilisticClassificationMetric

public class AUC
extends java.lang.Object
implements ProbabilisticClassificationMetric

The area under the curve (AUC). When using normalized units, the area under the curve is equal to the probability that a classifier will rank a randomly chosen positive instance higher than a randomly chosen negative one (assuming 'positive' ranks higher than 'negative').

In statistics, a receiver operating characteristic (ROC), or ROC curve, is a graphical plot that illustrates the performance of a binary classifier system as its discrimination threshold is varied. The curve is created by plotting the true positive rate (TPR) against the false positive rate (FPR) at various threshold settings.

AUC is quite noisy as a classification measure and has some other significant problems in model comparison.

We calculate AUC based on Mann-Whitney U test (https://en.wikipedia.org/wiki/Mann-Whitney_U_test).

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static AUC	instance Default instance.

Constructor Summary

Constructors

Constructor and Description
AUC()

Method Summary

Modifier and Type	Method and Description
static double	of(int[] truth, double[] probability) Calculates AUC for binary classifier.
double	score(int[] truth, double[] probability) Returns a score to measure the quality of classification.
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Field Detail

instance

public static final AUC instance

Default instance.

Constructor Detail

AUC

public AUC()

Method Detail

score

public double score(int[] truth,
                    double[] probability)

Description copied from interface: ProbabilisticClassificationMetric

Returns a score to measure the quality of classification.

Specified by:

score in interface ProbabilisticClassificationMetric

Parameters:

truth - the true class labels.

probability - The posterior probability of positive class.

of

public static double of(int[] truth,
                        double[] probability)

Calculates AUC for binary classifier.

Parameters:

truth - The sample labels

probability - The posterior probability of positive class.

Returns:

AUC

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object