Class Evaluators

java.lang.Object

deepnetts.eval.Evaluators

public class Evaluators
extends Object

Utility methods for evaluating machine learning models.

Method Summary

Modifier and Type	Method	Description
static ClassificationMetrics	evaluateClassifier(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)
static RegressionMetrics	evaluateRegressor(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)	Evaluates specified neural network with test set, as a regression model and returns basic regression evauation metrics.

Methods inherited from class Object

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

Method Details

evaluateRegressor

public static RegressionMetrics evaluateRegressor(NeuralNetwork<?> neuralNet,
 javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)

Evaluates specified neural network with test set, as a regression model and returns basic regression evauation metrics. Tells you how good the network approximates function described with test set.

Parameters:

neuralNet -

testSet -

Returns:

regression performance measures

See Also:

• EvaluationMetrics

evaluateClassifier

public static ClassificationMetrics evaluateClassifier(NeuralNetwork<?> neuralNet,
 javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)

Parameters:

neuralNet -

testSet -

Returns:

classification performance measure