jsat.datatransform.visualization

Class MDS

java.lang.Object

jsat.datatransform.visualization.MDS

All Implemented Interfaces:

Serializable, Cloneable, VisualizationTransform

public class MDS
extends Object
implements VisualizationTransform

Multidimensional scaling is an algorithm for finding low dimensional embeddings of arbitrary distance matrices. MDS will attempt to find an embedding that maintains the same pair-wise distances between all items in the distance matrix. MDS is a non-convex problem, so different runs can produce different results.

MDS can be used on arbitrary dissimilarity matrices by calling transform(jsat.linear.Matrix, java.util.concurrent.ExecutorService).

Author:

Edward Raff

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MDS()

Method Summary

Modifier and Type	Method and Description
DistanceMetric	getEmbeddingMetric()
int	getTargetDimension()
double	getTolerance()
void	setEmbeddingMetric(DistanceMetric embedMetric) Sets the distance metric to use when creating the initial dissimilarity matrix of a new dataset.
boolean	setTargetDimension(int target) Sets the target dimension to embed new dataset to.
void	setTolerance(double tolerance) Sets the tolerance parameter for determining convergence.
<Type extends DataSet> Type	transform(DataSet<Type> d) Transforms the given data set, returning a dataset of the same type.
<Type extends DataSet> Type	transform(DataSet<Type> d, ExecutorService ex) Transforms the given data set, returning a dataset of the same type.
SimpleDataSet	transform(Matrix delta)
SimpleDataSet	transform(Matrix delta, ExecutorService ex)

Methods inherited from class java.lang.Object

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

Constructor Detail

MDS

public MDS()

Method Detail

setTolerance

public void setTolerance(double tolerance)

Sets the tolerance parameter for determining convergence.

Parameters:

tolerance - the tolerance for declaring convergence

getTolerance

public double getTolerance()

Returns:

the tolerance parameter

setEmbeddingMetric

public void setEmbeddingMetric(DistanceMetric embedMetric)

Sets the distance metric to use when creating the initial dissimilarity matrix of a new dataset. By default the Euclidean distance is used, but any distance may be substituted.The chosen distance need not be a valid metric, its only requirement is symmetry.

Parameters:

embedMetric - the distance metric to use when creating the dissimilarity matrix.

getEmbeddingMetric

public DistanceMetric getEmbeddingMetric()

Returns:

the distance metric used when creating a dissimilarity matrix

transform

public <Type extends DataSet> Type transform(DataSet<Type> d)

Description copied from interface: VisualizationTransform

Transforms the given data set, returning a dataset of the same type.

Specified by:

transform in interface VisualizationTransform

Type Parameters:

Type - the dataset type

Parameters:

d - the data set to transform

Returns:

the lower dimension dataset for visualization.

transform

public <Type extends DataSet> Type transform(DataSet<Type> d,
                                             ExecutorService ex)

Description copied from interface: VisualizationTransform

Transforms the given data set, returning a dataset of the same type.

Specified by:

transform in interface VisualizationTransform

Type Parameters:

Type - the dataset type

Parameters:

d - the data set to transform

ex - the source of threads for parallel computation

Returns:

the lower dimension dataset for visualization.

transform

public SimpleDataSet transform(Matrix delta)

transform

public SimpleDataSet transform(Matrix delta,
                               ExecutorService ex)

getTargetDimension

public int getTargetDimension()

Specified by:

getTargetDimension in interface VisualizationTransform

Returns:

the number of dimensions that a dataset will be embedded down to

setTargetDimension

public boolean setTargetDimension(int target)

Description copied from interface: VisualizationTransform

Sets the target dimension to embed new dataset to. Many visualization methods may only support a target of 2 or 3 dimensions, or only one of those options. For that reason a boolean value will be returned indicating if the target size was acceptable. If not, no change to the object will occur.

Specified by:

setTargetDimension in interface VisualizationTransform

Parameters:

target - the new target dimension size when VisualizationTransform.transform(jsat.DataSet) is called.

Returns:

true if this transform supports that dimension and it was set, false if the target dimension is unsupported and the previous value will be used instead.