de.jungblut.classification

Class UntrainableClassifier

java.lang.Object

de.jungblut.classification.UntrainableClassifier

All Implemented Interfaces:

Classifier, Predictor

public class UntrainableClassifier
extends Object
implements Classifier

Constructor Summary

Constructors

Constructor and Description
UntrainableClassifier(Predictor predictor)

Method Summary

Modifier and Type	Method and Description
int	extractPredictedClass(de.jungblut.math.DoubleVector predict) Given an already done prediction, choose the class.
int	extractPredictedClass(de.jungblut.math.DoubleVector predict, double threshold) Given an already done prediction, choose the class with a threshold.
de.jungblut.math.DoubleVector	predict(de.jungblut.math.DoubleVector features) Classifies the given features.
int	predictedClass(de.jungblut.math.DoubleVector features) Classifies the given features.
int	predictedClass(de.jungblut.math.DoubleVector features, double threshold) Classifies the given features.
de.jungblut.math.DoubleVector	predictProbability(de.jungblut.math.DoubleVector features) Classifies the given features.
void	train(de.jungblut.math.DoubleVector[] features, de.jungblut.math.DoubleVector[] outcome) Trains this classifier with the given features and the outcome.
void	train(Iterable<de.jungblut.math.DoubleVector> features, Iterable<de.jungblut.math.DoubleVector> outcome) Trains this classifier with the given features and the outcome.

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.jungblut.classification.Predictor

asClassifier

Constructor Detail

UntrainableClassifier

public UntrainableClassifier(Predictor predictor)

Method Detail

predict

public de.jungblut.math.DoubleVector predict(de.jungblut.math.DoubleVector features)

Description copied from interface: Predictor

Classifies the given features.

Specified by:

predict in interface Predictor

Returns:

the vector that contains an indicator at the index of the class. Usually zero or 1, in some cases it is a probability or activation value.

predictProbability

public de.jungblut.math.DoubleVector predictProbability(de.jungblut.math.DoubleVector features)

Description copied from interface: Predictor

Classifies the given features.

Specified by:

predictProbability in interface Predictor

Returns:

a vector that returns the probability of all outcomes. The output vector should sum to one.

predictedClass

public int predictedClass(de.jungblut.math.DoubleVector features,
                          double threshold)

Description copied from interface: Predictor

Classifies the given features.

Specified by:

predictedClass in interface Predictor

threshold - the threshold for the prediction "probability". In the sigmoid and binary case, you want to set everything greater (>) 0.5 to 1d and everything below (<=) to 0d.

Returns:

the predicted class as an integer for the output of a classifier.

predictedClass

public int predictedClass(de.jungblut.math.DoubleVector features)

Description copied from interface: Predictor

Classifies the given features.

Specified by:

predictedClass in interface Predictor

Returns:

the predicted class as an integer for the output of a classifier.

extractPredictedClass

public int extractPredictedClass(de.jungblut.math.DoubleVector predict)

Description copied from interface: Predictor

Given an already done prediction, choose the class.

Specified by:

extractPredictedClass in interface Predictor

Returns:

the class index as integer.

extractPredictedClass

public int extractPredictedClass(de.jungblut.math.DoubleVector predict,
                                 double threshold)

Description copied from interface: Predictor

Given an already done prediction, choose the class with a threshold.

Specified by:

extractPredictedClass in interface Predictor

Returns:

the class index as integer.

train

public void train(Iterable<de.jungblut.math.DoubleVector> features,
                  Iterable<de.jungblut.math.DoubleVector> outcome)

Description copied from interface: Classifier

Trains this classifier with the given features and the outcome. This is the streaming method for training, it takes parallel iterables.

Specified by:

train in interface Classifier

outcome - the outcome must have classes labeled as doubles. E.G. in the binary case you have a single element and decide between 0d and 1d. In higher dimensional cases you have each of these single elements mapped to a dimension.

train

public void train(de.jungblut.math.DoubleVector[] features,
                  de.jungblut.math.DoubleVector[] outcome)

Description copied from interface: Classifier

Trains this classifier with the given features and the outcome.

Specified by:

train in interface Classifier

outcome - the outcome must have classes labeled as doubles. E.G. in the binary case you have a single element and decide between 0d and 1d. In higher dimensional cases you have each of these single elements mapped to a dimension.