public abstract class ClassificationProblemEvaluator extends ProblemEvaluator<<any>>
Classification problem evaluator
Modifier and Type | Field and Description |
---|---|
protected java.util.Comparator<IFitness> |
comparator
Fitnesses comparator
|
dataNormalized, inputInterval, logTransformation, normalizer, outputInterval, scaledTestData, scaledTrainData, unscaledMax, unscaledMin, unscaledTestData, unscaledTrainData
Constructor and Description |
---|
ClassificationProblemEvaluator()
Empty constructor
|
Modifier and Type | Method and Description |
---|---|
double[] |
getTestClassificationBehaviorArray(IClassifier classifier)
Returns an array with the bevavior of the classifier with
test dataset
|
double[][] |
getTestClassificationBehaviorMatrix(IClassifier classifier1,
IClassifier classifier2)
Returns a matrix with the comparative bevavior of two
classifiers in the test dataset
|
double |
getTestClassificationError(IClassifier classifier,
IErrorFunction<byte[][]> errorFunction)
Returns the test error value of a neural net with an specified
error function
|
double |
getTestQStatistic(IClassifier classifier1,
IClassifier classifier2)
Returns the diversity measure Q statistic of two classifiers
in test data set
|
double |
getTestQStatistic(java.util.List<IClassifier> classifiers)
Returns the diversity measure Q statistic of two classifiers
in test data set
|
double[] |
getTrainClassificationBehaviorArray(IClassifier classifier)
Returns an array with the bevavior of the classifier with
train dataset
|
double[][] |
getTrainClassificationBehaviorMatrix(IClassifier classifier1,
IClassifier classifier2)
Returns a matrix with the comparative bevavior of two
classifiers in the train dataset
|
double |
getTrainClassificationError(IClassifier classifier,
IErrorFunction<byte[][]> errorFunction)
Returns the train error value of a neural net with an specified
error function
|
double |
getTrainQStatistic(IClassifier classifier1,
IClassifier classifier2)
Returns the diversity measure Q statistic of two classifiers
in train dataset
|
double |
getTrainQStatistic(java.util.List<IClassifier> classifiers)
Returns the diversity measure Q statistic of a list of classifiers
in train dataset
|
configure, evaluate, getInputInterval, getNormalizer, getOutputInterval, getTestData, getTrainData, getUnscaledMax, getUnscaledMin, getUnscaledTestData, getUnscaledTrainData, isDataNormalized, isLogTransformation, readData, readData, setDataNormalized, setInputInterval, setLogTransformation, setNormalizer, setOutputInterval, setUnscaledTestData, setUnscaledTrainData
public ClassificationProblemEvaluator()
Empty constructor
public double getTrainClassificationError(IClassifier classifier, IErrorFunction<byte[][]> errorFunction)
Returns the train error value of a neural net with an specified error function
classifier
- Neural net to obtain the errorerrorFunction
- Error function to obtain the errorpublic double getTestClassificationError(IClassifier classifier, IErrorFunction<byte[][]> errorFunction)
Returns the test error value of a neural net with an specified error function
classifier
- Neural net to obtain the errorerrorFunction
- Error function to obtain the errorpublic double[] getTrainClassificationBehaviorArray(IClassifier classifier)
Returns an array with the bevavior of the classifier with train dataset
classifier
- Classifier to obtain the errorpublic double[] getTestClassificationBehaviorArray(IClassifier classifier)
Returns an array with the bevavior of the classifier with test dataset
classifier
- Classifier to obtain the errorpublic double[][] getTrainClassificationBehaviorMatrix(IClassifier classifier1, IClassifier classifier2)
Returns a matrix with the comparative bevavior of two classifiers in the train dataset
classifier1
- First classifierclassifier2
- Second classifierpublic double[][] getTestClassificationBehaviorMatrix(IClassifier classifier1, IClassifier classifier2)
Returns a matrix with the comparative bevavior of two classifiers in the test dataset
classifier1
- First classifierclassifier2
- Second classifierpublic double getTrainQStatistic(IClassifier classifier1, IClassifier classifier2)
Returns the diversity measure Q statistic of two classifiers in train dataset
classifier1
- First classifierclassifier2
- Second classifierpublic double getTestQStatistic(IClassifier classifier1, IClassifier classifier2)
Returns the diversity measure Q statistic of two classifiers in test data set
classifier1
- First classifierclassifier2
- Second classifierpublic double getTrainQStatistic(java.util.List<IClassifier> classifiers)
Returns the diversity measure Q statistic of a list of classifiers in train dataset
classifiers
- List of classifierspublic double getTestQStatistic(java.util.List<IClassifier> classifiers)
Returns the diversity measure Q statistic of two classifiers in test data set
classifiers
- First classifier