/*************************************************************************
This function performs clustering by k-means++ algorithm.
You may change algorithm properties by calling:
* ClusterizerSetKMeansLimits() to change number of restarts or iterations
* ClusterizerSetKMeansInit() to change initialization algorithm
By default, one restart and unlimited number of iterations are used.
Initialization algorithm is chosen automatically.
COMMERCIAL EDITION OF ALGLIB:
! Commercial version of ALGLIB includes two important improvements of
! this function:
! * multicore support (can be used from C# and C++)
! * access to high-performance C++ core (actual for C# users)
!
! K-means clustering algorithm has two phases: selection of initial
! centers and clustering itself. ALGLIB parallelizes both phases.
! Parallel version is optimized for the following scenario: medium or
! high-dimensional problem (20 or more dimensions) with large number of
! points and clusters. However, some speed-up can be obtained even when
! assumptions above are violated.
!
! As for native-vs-managed comparison, working with native core brings
! 30-40% improvement in speed over pure C# version of ALGLIB.
!
! We recommend you to read 'Working with commercial version' section of
! ALGLIB Reference Manual in order to find out how to use performance-
! related features provided by commercial edition of ALGLIB.
INPUT PARAMETERS:
S - clusterizer state, initialized by ClusterizerCreate()
K - number of clusters, K>=0.
K can be zero only when algorithm is called for empty
dataset, in this case completion code is set to
success (+1).
If K=0 and dataset size is non-zero, we can not
meaningfully assign points to some center (there are no
centers because K=0) and return -3 as completion code
(failure).
OUTPUT PARAMETERS:
Rep - clustering results; see description of KMeansReport
structure for more information.
NOTE 1: k-means clustering can be performed only for datasets with
Euclidean distance function. Algorithm will return negative
completion code in Rep.TerminationType in case dataset was added
to clusterizer with DistType other than Euclidean (or dataset was
specified by distance matrix instead of explicitly given points).
-- ALGLIB --
Copyright 10.07.2012 by Bochkanov Sergey
*************************************************************************/
public static void clusterizerrunkmeans(clusterizerstate s,
int k,
kmeansreport rep)
{
double[,] dummy = new double[0,0];
alglib.ap.assert(k>=0, "ClusterizerRunKMeans: K<0");
//
// Incorrect distance type
//
if( s.disttype!=2 )
{
rep.npoints = s.npoints;
rep.terminationtype = -5;
rep.k = k;
rep.iterationscount = 0;
rep.energy = 0.0;
return;
}
//
// K>NPoints or (K=0 and NPoints>0)
//
if( k>s.npoints || (k==0 && s.npoints>0) )
{
rep.npoints = s.npoints;
rep.terminationtype = -3;
rep.k = k;
rep.iterationscount = 0;
rep.energy = 0.0;
return;
}
//
// No points
//
if( s.npoints==0 )
{
rep.npoints = 0;
rep.terminationtype = 1;
rep.k = k;
rep.iterationscount = 0;
rep.energy = 0.0;
return;
}
//
// Normal case:
// 1<=K<=NPoints, Euclidean distance
//
rep.npoints = s.npoints;
rep.nfeatures = s.nfeatures;
rep.k = k;
rep.npoints = s.npoints;
rep.nfeatures = s.nfeatures;
kmeansgenerateinternal(s.xy, s.npoints, s.nfeatures, k, s.kmeansinitalgo, s.kmeansmaxits, s.kmeansrestarts, s.kmeansdbgnoits, ref rep.terminationtype, ref rep.iterationscount, ref dummy, false, ref rep.c, true, ref rep.cidx, ref rep.energy, s.kmeanstmp);
}
/*************************************************************************
Single-threaded stub. HPC ALGLIB replaces it by multithreaded code.
*************************************************************************/
public static void _pexec_clusterizerrunkmeans(clusterizerstate s,
int k,
kmeansreport rep)
{
clusterizerrunkmeans(s,k,rep);
}
public override alglib.apobject make_copy()
{
kmeansreport _result = new kmeansreport();
_result.npoints = npoints;
_result.nfeatures = nfeatures;
_result.terminationtype = terminationtype;
_result.iterationscount = iterationscount;
_result.energy = energy;
_result.k = k;
_result.c = (double[,])c.Clone();
_result.cidx = (int[])cidx.Clone();
return _result;
}
