Package smile.clustering.linkage

package smile.clustering.linkage
Cluster dissimilarity measures. An agglomerative hierarchical clustering builds the hierarchy from the individual elements by progressively merging clusters. The linkage criteria determines the distance between clusters (i.e. sets of observations) based on as a pairwise distance function between observations. Some commonly used linkage criteria are
  • Maximum or complete linkage clustering
  • Minimum or single-linkage clustering
  • Mean or average linkage clustering, or UPGMA
  • Unweighted Pair Group Method using Centroids, or UPCMA (also known as centroid linkage)
  • Weighted Pair Group Method with Arithmetic mean, or WPGMA.
  • Weighted Pair Group Method using Centroids, or WPGMC (also known as median linkage)
  • Ward's linkage
  • Classes
    Class
    Description
    CompleteLinkage
    Complete linkage.
    Linkage
    A measure of dissimilarity between clusters (i.e.
    SingleLinkage
    Single linkage.
    UPGMALinkage
    Unweighted Pair Group Method with Arithmetic mean (also known as average linkage).
    UPGMCLinkage
    Unweighted Pair Group Method using Centroids (also known as centroid linkage).
    WardLinkage
    Ward's linkage.
    WPGMALinkage
    Weighted Pair Group Method with Arithmetic mean.
    WPGMCLinkage
    Weighted Pair Group Method using Centroids (also known as median linkage).