Software Packages for Clustering and Classification

Licensing Information

  We use the GNU General Public License (GPL), version 3.

Environment

  The software packages were developed under Unix/Linux OS using C, Matlab, or R.

Suggestions/Bug Report

  Please contact Jia Li for suggestions and report of bugs (Email: jiali at psu dot edu).

Download

• C codes:
  
  1. Modal clustering and linkage clustering: HMAC ( C, Matlab, R source codes with usage document )
     Related publication:
     • J. Li, S. Ray, B. G. Lindsay, "A nonparametric statistical approach to clustering via mode identification," Journal of Machine Learning Research , 8(8):1687-1723, 2007. (download)
     
     
  2. Two-way Poisson Mixture Model for classification of count data, e.g., word count data for document classification. ( C codes with usage document )
     Related publication:
     • Jia Li, Hongyuan Zha, "Two-way Poisson mixture models for simultaneous document classification and word clustering," Computational Statistics and Data Analysis, 50(1):163-180, 2006. (download)
     
     
• Matlab codes:
  
  1. Clustering by multi-layer mixture model ( download the package ). Special thanks go to Francesca Martella from Leids University Medical Center, Netherlands, for documenting the codes and improving the organization.
     Related publication:
     • Jia Li, "Clustering based on a multi-layer mixture model," Journal of Computational and Graphical Statistics , 14(3):547-568, 2005. (download)
  2. Gaussian mixture model-based clustering, estimation by classification EM (CEM)
     
  3. Demo for clustering using the following methods, a subroutine for plotting results (needed by the demo program).
     
  4. K-means clustering
     
  5. Gaussian mixture model-based clustering, estimation by EM , EM initialization.
     
  
  
• R codes
  1. Variable selection for clustering by Ridgeline-Based Separability ( R codes with usage document )
     Related publication:
     • Hyangmin Lee, Jia Li, "Variable selection for clustering by separability based on ridgelines," Journal of Computational and Graphical Statistics, 21(2):315-337, 2012.