clustDDist: Clustering Discrete Distributions

Share:

Clustering of units described with distributions is considered. Frequent approach for clustering such data combines non-hierarchical method (to allow clustering of large amount of units) with hierarchical clustering method (to build dendrogram from the obtained nonhierarchical clusters and determine the most 'natural' final clustering(s) from it). The use of the squared Euclidean distance as an error function favors patterns of distributions that have one steep high peak. Here several alternative error functions are implemented. They characterize errors between clustered units and a cluster representative - leader (which needs not be defined in the same space). For these error functions the adapted leaders methods and compatible agglomerative hierarchical clustering methods are implemented.

Author
Natasa Kejzar, Vladimir Batagelj, Simona Korenjak-Cerne
Date of publication
None
Maintainer
Natasa Kejzar <natasa.kejzar@fdv.uni-lj.si>
License
GPL-2
Version
1.3

View on R-Forge

Man pages

clustDDist-internal
Internal Functions in the clustDDist package
clustDDist-package
Clustering (Discrete) Distributions
compute.plot.order
Compute Order for Units where Hierarchical Clustering was...
from.Leaders
Returns List to Help Chaining Leaders and Hierarchical...
hierarch
Clustering of Units with Adapted Hierarchical Clustering...
leaders
Clustering of Units with Adapted Leaders Method for Different...
patents
Dataset of US patents from 1980 to 1999, citations...

Files in this package

clustDDist
clustDDist/data
clustDDist/data/patents.rda
clustDDist/R
clustDDist/R/fromLeaders.R
clustDDist/R/leaders.R
clustDDist/R/centers.R
clustDDist/R/hierarch.R
clustDDist/NAMESPACE
clustDDist/inst
clustDDist/inst/CITATION
clustDDist/DESCRIPTION
clustDDist/man
clustDDist/man/patents.Rd
clustDDist/man/leaders.Rd
clustDDist/man/clustDDist-internal.Rd
clustDDist/man/from.Leaders.Rd
clustDDist/man/clustDDist-package.Rd
clustDDist/man/hierarch.Rd
clustDDist/man/compute.plot.order.Rd