io.improbable.keanu.model

Class ModelScoring

java.lang.Object

io.improbable.keanu.model.ModelScoring

public class ModelScoring
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
ModelScoring()

Method Summary

Modifier and Type	Method and Description
static double	accuracy(BooleanTensor predictedOutput, BooleanTensor trueOutput) Calculates the accuracy of a predicted output, given a true output.
static double	coefficientOfDetermination(DoubleTensor predictedOutput, DoubleTensor trueOutput) Calculates the coefficient of determination - i.e.

Methods inherited from class java.lang.Object

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

Constructor Detail

ModelScoring

public ModelScoring()

Method Detail

coefficientOfDetermination

public static double coefficientOfDetermination(DoubleTensor predictedOutput,
                                                DoubleTensor trueOutput)

Calculates the coefficient of determination - i.e. the R^2 value - for the given predicted output and true values.

Parameters:

predictedOutput - predicted output

trueOutput - the true output to compare the predicted output against

Returns:

the coefficient, a value less than 1, where any value above 0 resembles correlation

accuracy

public static double accuracy(BooleanTensor predictedOutput,
                              BooleanTensor trueOutput)

Calculates the accuracy of a predicted output, given a true output. That is the ratio of correct predictions to the total number of predictions.

Parameters:

predictedOutput - predicted output

trueOutput - the true output to compare against

Returns:

the accuracy