Contents
Main
Site map
Links
Site and author
News
Contact

k-means++ clustering

The k-means algorithm is one of the most commonly used clustering methods. The algorithm strives for partitioning into clusters minimizing the sum of intracluster distances squared. The base method is fully detailed in Wikipedia. The ALGLIB package implements an algorithm version that is called "k-means++".

Assumptions

  • The number of clusters is predetermined
  • The Euclidean distance is an adequate measure of similarity of the set elements

Manual entries

C++ kmeans.h   
C# kmeans.cs   
Delphi kmeans.pas   
FreePascal kmeans.pas   
VBA kmeans.bas   

This article is intended for personal use only.

Download ALGLIB

C#

C# source.

alglib-2.4.0.csharp.zip

 

C++

C++ source.

alglib-2.4.0.cpp.zip

 

C++, multiple precision arithmetic

C++ source. MPFR/GMP is used.

GMP source is available from gmplib.org. MPFR source is available from www.mpfr.org.

alglib-2.4.0.mpfr.zip

 

FreePascal

FreePascal source.

alglib-2.4.0.freepascal.zip

 

Delphi

Delphi source.

alglib-2.4.0.delphi.zip

 

Visual Basic

VBA source.

alglib-2.4.0.vb6.zip

 


 
 
Sergey Bochkanov, Vladimir Bystritsky
Copyright © 1999-2010