YinYangKMeans.Par (ELKI: Environment for DeveLoping KDD-Applications Supported by Index-Structures)

java.lang.Object
- elki.clustering.kmeans.AbstractKMeans.Par<V>
- - elki.clustering.kmeans.YinYangKMeans.Par<V>

All Implemented Interfaces:

elki.utilities.optionhandling.Parameterizer

Enclosing class:

YinYangKMeans<V extends elki.data.NumberVector>
```
public static class YinYangKMeans.Par<V extends elki.data.NumberVector>
extends AbstractKMeans.Par<V>
```
Parameterization class.

Author:

Minh Nhat Nguyen

Field Summary

Fields
Modifier and Type	Field	Description
`protected int`	`t`	Number of groups in the initial clustering of the centroids.
`static elki.utilities.optionhandling.OptionID`	`T_ID`	Parameter to specify t the number of centroid groups.

Fields inherited from class elki.clustering.kmeans.AbstractKMeans.Par
distance, initializer, k, maxiter, varstat

Constructor Summary

Constructors
Constructor Description

Par()

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method	Description
`void`	`configure(elki.utilities.optionhandling.parameterization.Parameterization config)`
`YinYangKMeans<V>`	`make()`
`protected boolean`	`needsMetric()`	Users could use other non-metric distances at their own risk; but some k-means variants make explicit use of the triangle inequality, we emit extra warnings then.

Methods inherited from class elki.clustering.kmeans.AbstractKMeans.Par
getParameterDistance, getParameterInitialization, getParameterK, getParameterMaxIter, getParameterVarstat

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

- Field Detail
  - T_ID
```
public static final elki.utilities.optionhandling.OptionID T_ID
```
    Parameter to specify t the number of centroid groups.
  - t
```
protected int t
```
    Number of groups in the initial clustering of the centroids.
- Constructor Detail
  - Par
```
public Par()
```
- Method Detail
  - needsMetric
```
protected boolean needsMetric()
```
    Description copied from class: AbstractKMeans.Par
    
    Users could use other non-metric distances at their own risk; but some k-means variants make explicit use of the triangle inequality, we emit extra warnings then.
    
    Overrides:
    
    needsMetric in class AbstractKMeans.Par<V extends elki.data.NumberVector>
    
    Returns:
    
    true if the algorithm uses triangle inequality
  - configure
```
public void configure(elki.utilities.optionhandling.parameterization.Parameterization config)
```
    Specified by:
    
    configure in interface elki.utilities.optionhandling.Parameterizer
    
    Overrides:
    
    configure in class AbstractKMeans.Par<V extends elki.data.NumberVector>
  - make
```
public YinYangKMeans<V> make()
```
    Specified by:
    
    make in interface elki.utilities.optionhandling.Parameterizer
    
    Specified by:
    
    make in class AbstractKMeans.Par<V extends elki.data.NumberVector>