kmeans.h

Scalable k-means software and test datasets This package (a Unix tar file, gzipped) contains the sou

/* Scalable K-means clustering software
Copyright (C) 2000  Fredrik Farnstrom and James Lewis

This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; either version 2
of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.


See the file README.TXT for more information.

*/

/* kmeans.h */

class SyntheticData;
class Subcluster;
class Database;
class RAMBuffer;

class KMeans
{
protected:
	Database *database;
	int numClusters;
	int dimensions;

	Subcluster *clusters;

	float convergenceThreshold;

	static const float defaultConvergenceThreshold = 0.00001;

	void setup(void);
	void initModel(void);

	int numIterations;

	Subcluster *closestCluster(Singleton *p);

	double permutationDistance(int *permut, SyntheticData *db);
public:
	KMeans(Database *db, int k, int dim);
	virtual ~KMeans();

	void cluster(long numpoints = 0);
	double distanceToTrueClusters(SyntheticData *db);
	double logLikelihood(void);

	int getNumIterations(void)
	{	return numIterations;	}

	virtual void reset(void);
	virtual float *getPoint(void);
};

class BufferedKMeans : public KMeans
{
	RAMBuffer *buffer;
	Singleton *currentPoint;
public:
	BufferedKMeans(Database *db, int k, int dim, int buffersize);
	~BufferedKMeans();

	void fillBuffer(void);
	void reset(void);
	float *getPoint(void);
};

/* End of file kmeans.h */