All Classes and Interfaces
Class
Description
An AgglomerationMethod represents the Lance-Williams dissimilarity update formula
used for hierarchical agglomerative clustering.
The "average", "group average", "unweighted average", or
"Unweighted Pair Group Method using Arithmetic averages (UPGMA)",
is a graph-based approach.
The "centroid" or "Unweighted Pair-Group Method using Centroids (UPGMC)"
method is a geometric approach that links the centroids of clusters.
HierarchicalAgglomerativeClusterer.cluster() takes a ClusteringBuilder as its argument,
calling its merge() method whenever it merges two clusters.
A ClusteringBuilderMultiplexer is a ClusteringBuilder that forwards calls to two other ClusteringBuilders.
A ClusteringMatrixBuilder builds a matrix in which
each row represents a step in the clustering
and each column represents an observation or cluster.
The "complete", "maximum", "clique",
"furthest neighbor", or "furthest distance" method is a graph-based approach.
A Dendrogram represents the results of hierachical agglomerative clustering.
A DendrogramBuilder creates a Dendrogram consisting of ObservationNodes and
MergeNodes.
A DendrogramNode is a node in a Dendrogram.
Computes the dissimilarity between two observations in an experiment.
An experiment consists of a number of observations.
The HierarchicalAgglomerativeClusterer creates a hierarchical agglomerative clustering.
The "median", "weighted centroid", "weighted center of mass distance", "Gower",
or "Weighted Pair-Group Method using Centroids (WPGMC)" method is a geometric approach.
A MergeNode represents an interior node in a Dendrogram.
An ObservationNode represents a leaf node in a Dendrogram.
The "single linkage", "minimum", "shortest distance", or "nearest neighbor" method is a graph-based approach.
The "Ward", "inner squared distance", "sum of squares", "error sum of squares",
or "minimum variance" method.
The "weighted average", "McQuitty", or
"Weighted Pair-Group Method using Arithmetic averages, or WPGMA)" method.