org.apache.spark.mllib.linalg
Class SparseVector

Object
  org.apache.spark.mllib.linalg.SparseVector

All Implemented Interfaces:

java.io.Serializable, Vector

public class SparseVector
extends Object
implements Vector

A sparse vector represented by an index array and an value array.

param: size size of the vector. param: indices index array, assume to be strictly increasing. param: values value array, must have the same length as the index array.

See Also:

Serialized Form

Constructor Summary

SparseVector(int size, int[] indices, double[] values)

Method Summary

SparseVector	copy() Makes a deep copy of this vector.
int	hashCode() Returns a hash code value for the vector.
int[]	indices()
int	numActives() Number of active entries.
int	numNonzeros() Number of nonzero elements.
int	size() Size of the vector.
double[]	toArray() Converts the instance to a double array.
SparseVector	toSparse() Converts this vector to a sparse vector with all explicit zeros removed.
String	toString()
static scala.Option<scala.Tuple3<Object,int[],double[]>>	unapply(SparseVector sv)
double[]	values()

Methods inherited from class Object

equals, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.spark.mllib.linalg.Vector

apply, compressed, equals, toDense

Constructor Detail

SparseVector

public SparseVector(int size,
                    int[] indices,
                    double[] values)

Method Detail

unapply

public static scala.Option<scala.Tuple3<Object,int[],double[]>> unapply(SparseVector sv)

size

public int size()

Description copied from interface: Vector

Size of the vector.

Specified by:

size in interface Vector

Returns:

(undocumented)

indices

public int[] indices()

values

public double[] values()

toString

public String toString()

Overrides:

toString in class Object

toArray

public double[] toArray()

Description copied from interface: Vector

Converts the instance to a double array.

Specified by:

toArray in interface Vector

Returns:

(undocumented)

copy

public SparseVector copy()

Description copied from interface: Vector

Makes a deep copy of this vector.

Specified by:

copy in interface Vector

Returns:

(undocumented)

hashCode

public int hashCode()

Description copied from interface: Vector

Returns a hash code value for the vector. The hash code is based on its size and its nonzeros in the first 16 entries, using a hash algorithm similar to java.util.Arrays.hashCode.

Specified by:

hashCode in interface Vector

Overrides:

hashCode in class Object

Returns:

(undocumented)

numActives

public int numActives()

Description copied from interface: Vector

Number of active entries. An "active entry" is an element which is explicitly stored, regardless of its value. Note that inactive entries have value 0.

Specified by:

numActives in interface Vector

Returns:

(undocumented)

numNonzeros

public int numNonzeros()

Description copied from interface: Vector

Number of nonzero elements. This scans all active values and count nonzeros.

Specified by:

numNonzeros in interface Vector

Returns:

(undocumented)

toSparse

public SparseVector toSparse()

Description copied from interface: Vector

Converts this vector to a sparse vector with all explicit zeros removed.

Specified by:

toSparse in interface Vector

Returns:

(undocumented)