Package org.apache.spark.mllib.clustering

Class KMeansModel

Object

org.apache.spark.mllib.clustering.KMeansModel

All Implemented Interfaces:

Serializable, PMMLExportable, Saveable, scala.Serializable

Direct Known Subclasses:

StreamingKMeansModel

public class KMeansModel
extends Object
implements Saveable, scala.Serializable, PMMLExportable

A clustering model for K-means. Each point belongs to the cluster with the closest center.

See Also:

• Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	KMeansModel.Cluster$
static class	KMeansModel.SaveLoadV1_0$
static class	KMeansModel.SaveLoadV2_0$

Constructor Summary

Constructors

Constructor	Description
KMeansModel(Iterable<Vector> centers)	A Java-friendly constructor that takes an Iterable of Vectors.
KMeansModel(Vector[] clusterCenters)
KMeansModel(Vector[] clusterCenters, String distanceMeasure, double trainingCost, int numIter)

Method Summary

Modifier and Type	Method	Description
Vector[]	clusterCenters()
double	computeCost(RDD<Vector> data)	Return the K-means cost (sum of squared distances of points to their nearest center) for this model on the given data.
String	distanceMeasure()
int	k()	Total number of clusters.
static KMeansModel	load(SparkContext sc, String path)
JavaRDD<Integer>	predict(JavaRDD<Vector> points)	Maps given points to their cluster indices.
int	predict(Vector point)	Returns the cluster index that a given point belongs to.
RDD<Object>	predict(RDD<Vector> points)	Maps given points to their cluster indices.
void	save(SparkContext sc, String path)	Save this model to the given path.
double	trainingCost()

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.spark.mllib.pmml.PMMLExportable

toPMML, toPMML, toPMML, toPMML, toPMML

Constructor Details

KMeansModel

public KMeansModel(Vector[] clusterCenters,
 String distanceMeasure,
 double trainingCost,
 int numIter)

KMeansModel

public KMeansModel(Vector[] clusterCenters)

KMeansModel

public KMeansModel(Iterable<Vector> centers)

A Java-friendly constructor that takes an Iterable of Vectors.

Parameters:

centers - (undocumented)

Method Details

load

public static KMeansModel load(SparkContext sc,
 String path)

clusterCenters

public Vector[] clusterCenters()

distanceMeasure

public String distanceMeasure()

trainingCost

public double trainingCost()

k

public int k()

Total number of clusters.

Returns:

(undocumented)

predict

public int predict(Vector point)

Returns the cluster index that a given point belongs to.

Parameters:

point - (undocumented)

Returns:

(undocumented)

predict

public RDD<Object> predict(RDD<Vector> points)

Maps given points to their cluster indices.

Parameters:

points - (undocumented)

Returns:

(undocumented)

predict

public JavaRDD<Integer> predict(JavaRDD<Vector> points)

Maps given points to their cluster indices.

Parameters:

points - (undocumented)

Returns:

(undocumented)

computeCost

public double computeCost(RDD<Vector> data)

Return the K-means cost (sum of squared distances of points to their nearest center) for this model on the given data.

Parameters:

data - (undocumented)

Returns:

(undocumented)

save

public void save(SparkContext sc,
 String path)

Description copied from interface: Saveable

Save this model to the given path.

This saves: - human-readable (JSON) model metadata to path/metadata/ - Parquet formatted data to path/data/

The model may be loaded using Loader.load.

Specified by:

save in interface Saveable

Parameters:

sc - Spark context used to save model data.

path - Path specifying the directory in which to save this model. If the directory already exists, this method throws an exception.