smile.clustering.linkage

Class UPGMALinkage

java.lang.Object

smile.clustering.linkage.Linkage

smile.clustering.linkage.UPGMALinkage

public class UPGMALinkage
extends Linkage

Unweighted Pair Group Method with Arithmetic mean (also known as average linkage). The distance between two clusters is the mean distance between all possible pairs of nodes in the two clusters.

In bioinformatics, UPGMA is used for the creation of phenetic trees (phenograms). UPGMA assumes a constant rate of evolution (molecular clock hypothesis), and is not a well-regarded method for inferring relationships unless this assumption has been tested and justified for the data set being used.

Constructor Summary

Constructors

Constructor and Description
UPGMALinkage(double[][] proximity) Constructor.
UPGMALinkage(int size, float[] proximity) Constructor.

Method Summary

Modifier and Type	Method and Description
void	merge(int i, int j) Merge two clusters into one and update the proximity matrix.
static UPGMALinkage	of(double[][] data) Given a set of data, computes the proximity and then the linkage.
static <T> UPGMALinkage	of(T[] data, smile.math.distance.Distance<T> distance) Given a set of data, computes the proximity and then the linkage.
java.lang.String	toString()

Methods inherited from class smile.clustering.linkage.Linkage

d, proximity, proximity, size

Methods inherited from class java.lang.Object

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

Constructor Detail

UPGMALinkage

public UPGMALinkage(double[][] proximity)

Constructor.

Parameters:

proximity - the proximity matrix to store the distance measure of dissimilarity. To save space, we only need the lower half of matrix.

UPGMALinkage

public UPGMALinkage(int size,
                    float[] proximity)

Constructor. Initialize the linkage with the lower triangular proximity matrix.

Parameters:

size - the data size.

proximity - column-wise linearized proximity matrix that stores only the lower half. The length of proximity should be size * (size+1) / 2. To save space, Linkage will use this argument directly without copy. The elements may be modified.

Method Detail

of

public static UPGMALinkage of(double[][] data)

Given a set of data, computes the proximity and then the linkage.

of

public static <T> UPGMALinkage of(T[] data,
                                  smile.math.distance.Distance<T> distance)

Given a set of data, computes the proximity and then the linkage.

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

merge

public void merge(int i,
                  int j)

Description copied from class: Linkage

Merge two clusters into one and update the proximity matrix.

Specified by:

merge in class Linkage

Parameters:

i - cluster id.

j - cluster id.