Package org.tribuo.common.nearest

Class KNNClassifierOptions

java.lang.Object

org.tribuo.common.nearest.KNNClassifierOptions

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Options, ClassificationOptions<KNNTrainer<Label>>

public class KNNClassifierOptions
extends Object
implements ClassificationOptions<KNNTrainer<Label>>

CLI Options for training a k-nearest neighbour predictor.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	KNNClassifierOptions.EnsembleCombinerType	The type of combination function.

Field Summary

Fields

Modifier and Type	Field	Description
DistanceType	distType	Distance metric to use.
KNNModel.Backend	knnBackend	Parallel backend to use.
KNNClassifierOptions.EnsembleCombinerType	knnEnsembleCombiner	Parallel backend to use.
int	knnK	K nearest neighbours to use.
int	knnNumThreads	Number of threads to use.
NeighboursQueryFactoryType	nqFactoryType	The nearest neighbour implementation factory to use.

Fields inherited from interface com.oracle.labs.mlrg.olcut.config.Options

header

Constructor Summary

Constructors

Constructor	Description
KNNClassifierOptions()

Method Summary

Modifier and Type	Method	Description
String	getOptionsDescription()
KNNTrainer<Label>	getTrainer()	Constructs the trainer based on the provided arguments.

Methods inherited from class java.lang.Object

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

Field Details

knnK

@Option(longName="knn-k",
        usage="K nearest neighbours to use.")
public int knnK

K nearest neighbours to use. Defaults to 1.

knnNumThreads

@Option(longName="knn-num-threads",
        usage="Number of threads to use.")
public int knnNumThreads

Number of threads to use. Defaults to 1.

distType

@Option(longName="knn-distance-type",
        usage="Distance metric to use.")
public DistanceType distType

Distance metric to use. Defaults to L2 (EUCLIDEAN).

knnBackend

@Option(longName="knn-backend",
        usage="Parallel backend to use.")
public KNNModel.Backend knnBackend

Parallel backend to use.

knnEnsembleCombiner

@Option(longName="knn-voting",
        usage="Parallel backend to use.")
public KNNClassifierOptions.EnsembleCombinerType knnEnsembleCombiner

Parallel backend to use.

nqFactoryType

@Option(longName="knn-neighbour-query-factory-type",
        usage="The nearest neighbour implementation factory to use.")
public NeighboursQueryFactoryType nqFactoryType

The nearest neighbour implementation factory to use. Defaults to NeighboursQueryFactoryType.BRUTE_FORCE.

Constructor Details

KNNClassifierOptions

public KNNClassifierOptions()

Method Details

getOptionsDescription

public String getOptionsDescription()

Specified by:

getOptionsDescription in interface com.oracle.labs.mlrg.olcut.config.Options

getTrainer

public KNNTrainer<Label> getTrainer()

Description copied from interface: ClassificationOptions

Constructs the trainer based on the provided arguments.

Specified by:

getTrainer in interface ClassificationOptions<KNNTrainer<Label>>

Returns:

The trainer.