VPTree

java.lang.Object
- org.deeplearning4j.clustering.vptree.VPTree

All Implemented Interfaces:

java.io.Serializable
```
public class VPTree
extends java.lang.Object
implements java.io.Serializable
```
Vantage point tree implementation

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

protected class VPTree.HeapObjectComparator

static class VPTree.Node

protected class VPTree.NodeBuilder

Nested Classes
Modifier and Type	Class and Description
`protected class`	`VPTree.HeapObjectComparator`
`static class`	`VPTree.Node`
`protected class`	`VPTree.NodeBuilder`

Field Summary

Fields
Modifier and Type Field and Description

static java.lang.String EUCLIDEAN

Fields
Modifier and Type	Field and Description
`static java.lang.String`	`EUCLIDEAN`

Constructor Summary

Constructors
Modifier	Constructor and Description
`protected`	`VPTree()`
	`VPTree(INDArray items)`
	`VPTree(INDArray points, boolean invert)`
	`VPTree(INDArray points, boolean invert, int workers)`
	`VPTree(INDArray items, java.lang.String similarityFunction)`
	`VPTree(INDArray items, java.lang.String similarityFunction, boolean invert)`
	`VPTree(INDArray items, java.lang.String similarityFunction, int workers, boolean invert)`
	`VPTree(java.util.List<DataPoint> items)`
	`VPTree(java.util.List<DataPoint> items, java.lang.String similarityFunction)`
	`VPTree(java.util.List<DataPoint> items, java.lang.String similarityFunction, int workers, boolean invert)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`static INDArray`	`buildFromData(java.util.List<DataPoint> data)` Create an ndarray from the datapoints
`void`	`calcDistancesRelativeTo(INDArray basePoint, INDArray distancesArr)`
`void`	`calcDistancesRelativeTo(INDArray items, INDArray basePoint, INDArray distancesArr)`
`float`	`distance(INDArray arr1, INDArray arr2)` Euclidean distance
`void`	`search(INDArray target, int k, java.util.List<DataPoint> results, java.util.List<java.lang.Double> distances)`
`void`	`search(VPTree.Node node, INDArray target, int k, java.util.PriorityQueue<HeapObject> pq, double cTau)`

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail
- EUCLIDEAN
```
public static final java.lang.String EUCLIDEAN
```
  See Also:
  
  Constant Field Values

Constructor Detail
- VPTree
```
protected VPTree()
```
- VPTree
```
public VPTree(INDArray points,
              boolean invert)
```
  Parameters:
  
  points -
  
  invert -
- VPTree
```
public VPTree(INDArray points,
              boolean invert,
              int workers)
```
  Parameters:
  
  points -
  
  invert -
  
  workers - number of parallel workers for tree building (increases memory requirements!)
- VPTree
```
public VPTree(INDArray items,
              java.lang.String similarityFunction,
              boolean invert)
```
  Parameters:
  
  items - the items to use
  
  similarityFunction - the similarity function to use
  
  invert - whether to invert the distance (similarity functions have different min/max objectives)
- VPTree
```
public VPTree(java.util.List<DataPoint> items,
              java.lang.String similarityFunction,
              int workers,
              boolean invert)
```
  Parameters:
  
  items - the items to use
  
  similarityFunction - the similarity function to use
  
  workers - number of parallel workers for tree building (increases memory requirements!)
  
  invert - whether to invert the metric (different optimization objective)
- VPTree
```
public VPTree(INDArray items,
              java.lang.String similarityFunction)
```
  Parameters:
  
  items -
  
  similarityFunction -
- VPTree
```
public VPTree(INDArray items,
              java.lang.String similarityFunction,
              int workers,
              boolean invert)
```
  Parameters:
  
  items -
  
  similarityFunction -
  
  workers - number of parallel workers for tree building (increases memory requirements!)
  
  invert -
- VPTree
```
public VPTree(java.util.List<DataPoint> items,
              java.lang.String similarityFunction)
```
  Parameters:
  
  items -
  
  similarityFunction -
- VPTree
```
public VPTree(INDArray items)
```
  Parameters:
  
  items -
- VPTree
```
public VPTree(java.util.List<DataPoint> items)
```
  Parameters:
  
  items -

Method Detail

buildFromData

public static INDArray buildFromData(java.util.List<DataPoint> data)

Create an ndarray from the datapoints

Parameters:: data -
Returns:

calcDistancesRelativeTo

public void calcDistancesRelativeTo(INDArray items,
                                    INDArray basePoint,
                                    INDArray distancesArr)

Parameters:: basePoint -; distancesArr -

calcDistancesRelativeTo

public void calcDistancesRelativeTo(INDArray basePoint,
                                    INDArray distancesArr)

distance

public float distance(INDArray arr1,
                      INDArray arr2)

Euclidean distance

Returns:: the distance between the two points

search

public void search(@NonNull
                   INDArray target,
                   int k,
                   java.util.List<DataPoint> results,
                   java.util.List<java.lang.Double> distances)

Parameters:: target -; k -; results -; distances -

search

public void search(VPTree.Node node,
                   INDArray target,
                   int k,
                   java.util.PriorityQueue<HeapObject> pq,
                   double cTau)

Parameters:: node -; target -; k -; pq -

Class VPTree

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

EUCLIDEAN

Constructor Detail

VPTree

VPTree

VPTree

VPTree

VPTree

VPTree

VPTree

VPTree

VPTree

VPTree

Method Detail

buildFromData

calcDistancesRelativeTo

calcDistancesRelativeTo

distance

search

search