double Linear_Kernel_Kmeans::BuildFastKernel()
{ // Compute the cluster centers, which are the average of its data points
emptycenters=0;
eval.Zero();
if(useMedian==false)
{
for(int i=0;i<n;i++)
for(int j=0;j<m;j++)
eval.p[labels[i]][j] += data.p[i][j];
for(int i=0;i<k;i++)
{
if(counts[i]>0)
{
double r = 1.0/counts[i];
for(int j=0;j<m;j++) eval.p[i][j] *= r;
}
else
emptycenters++;
}
validcenters = k - emptycenters;
RemoveEmptyClusters();
}
else
{
Array2dC<double> t(k,*std::max_element(counts,counts+k));
Array2dC<int> added(1,k);
for(int i=0;i<m;i++) // each dimension
{
added.Zero();
for(int j=0;j<n;j++)
{
t.p[labels[j]][added.buf[labels[j]]] = data.p[j][i];
added.buf[labels[j]]++;
}
for(int j=0;j<k;j++)
{
assert(added.buf[j]==counts[j]);
std::sort(t.p[j],t.p[j]+added.buf[j]);
if(added.buf[j]%2==0)
eval.p[j][i] = (t.p[j][added.buf[j]/2-1]+t.p[j][added.buf[j]/2])/2.0;
else
eval.p[j][i] = t.p[j][added.buf[j]/2];
}
}
}
return ComputeConstants();
}
// Cluster_Kmeans::Cluster()
int Cluster_Kmeans::Cluster() {
// First determine which frames are being clustered.
Iarray const& FramesToCluster = FrameDistances().FramesToCluster();
// Determine seeds
FindKmeansSeeds( FramesToCluster );
if (mode_ == RANDOM)
RN_.rn_set( kseed_ );
int pointCount = (int)FramesToCluster.size();
// This array will hold the indices of the points to process each iteration.
// If sequential this is just 0 -> pointCount. If random this will be
// reassigned each iteration.
Iarray PointIndices;
PointIndices.reserve( pointCount );
for (int processIdx = 0; processIdx != pointCount; processIdx++)
PointIndices.push_back( processIdx );
// Add the seed clusters
for (Iarray::const_iterator seedIdx = SeedIndices_.begin();
seedIdx != SeedIndices_.end(); ++seedIdx)
{
int seedFrame = FramesToCluster[ *seedIdx ];
// A centroid is created for new clusters.
AddCluster( ClusterDist::Cframes(1, seedFrame) );
// NOTE: No need to calc best rep frame, only 1 frame.
if (debug_ > 0)
mprintf("Put frame %i in cluster %i (seed index=%i).\n",
seedFrame, clusters_.back().Num(), *seedIdx);
}
// Assign points in 3 passes. If a point looked like it belonged to cluster A
// at first, but then we added many other points and altered our cluster
// shapes, its possible that we will want to reassign it to cluster B.
for (int iteration = 0; iteration != maxIt_; iteration++)
{
if (mode_ == RANDOM)
ShufflePoints( PointIndices );
// Add each point to an existing cluster, and recompute centroid
mprintf("\tRound %i: ", iteration);
ProgressBar progress( PointIndices.size() );
int Nchanged = 0;
int prog = 0;
for (Iarray::const_iterator pointIdx = PointIndices.begin();
pointIdx != PointIndices.end(); ++pointIdx, ++prog)
{
if (debug_ < 1) progress.Update( prog );
int oldClusterIdx = -1;
// if ( iteration != 0 || mode_ != SEQUENTIAL) // FIXME: Should this really happen for RANDOM
// {
int pointFrame = FramesToCluster[ *pointIdx ];
if (debug_ > 0)
mprintf("DEBUG: Processing frame %i (index %i)\n", pointFrame, *pointIdx);
bool pointWasYanked = true;
if (iteration > 0) {
// Yank this point out of its cluster, recompute the centroid
for (cluster_it C1 = clusters_.begin(); C1 != clusters_.end(); ++C1)
{
if (C1->HasFrame( pointFrame ))
{
// If this point is alone in its cluster its in the right place
if (C1->Nframes() == 1) {
pointWasYanked = false;
continue; // FIXME: should this be a break?
}
//oldBestRep = C1->BestRepFrame();
oldClusterIdx = C1->Num();
C1->RemoveFrameUpdateCentroid( Cdist_, pointFrame ); // TEST
// C1->RemoveFrameFromCluster( pointFrame );
//newBestRep = C1->FindBestRepFrame();
// C1->CalculateCentroid( Cdist_ );
if (debug_ > 0)
mprintf("Remove Frame %i from cluster %i\n", pointFrame, C1->Num());
//if (clusterToClusterCentroid_) {
// if (oldBestRep != NewBestRep)
// C1->AlignToBestRep( Cdist_ ); // FIXME: Only relevant for COORDS dist?
// C1->CalculateCentroid( Cdist_ ); // FIXME: Seems unnessecary to align prior
//}
}
}
} else {
// First iteration. If this point is already in a cluster it is a seed.
for (cluster_it C1 = clusters_.begin(); C1 != clusters_.end(); ++C1)
{
if (C1->HasFrame( pointFrame )) {
pointWasYanked = false;
if (debug_ > 0)
mprintf("Frame %i was already used to seed cluster %i\n",
pointFrame, C1->Num());
continue; // FIXME break?
}
}
}
if (pointWasYanked) {
// Find out what cluster this point is now closest to.
double closestDist = -1.0;
cluster_it closestCluster = clusters_.begin();
for (cluster_it C1 = clusters_.begin(); C1 != clusters_.end(); ++C1)
{
double dist = Cdist_->FrameCentroidDist(pointFrame, C1->Cent());
if (closestDist < 0.0 || dist < closestDist)
{
closestDist = dist;
closestCluster = C1;
}
}
//oldBestRep = closestCluster->BestRepFrame();
closestCluster->AddFrameUpdateCentroid( Cdist_, pointFrame ); // TEST
// closestCluster->AddFrameToCluster( pointFrame );
//newBestRep = closestCluster->FindBestFrameFrame();
// closestCluster->CalculateCentroid( Cdist_ );
if (closestCluster->Num() != oldClusterIdx)
{
Nchanged++;
if (debug_ > 0)
mprintf("Remove Frame %i from cluster %i, but add to cluster %i (dist= %f).\n",
pointFrame, oldClusterIdx, closestCluster->Num(), closestDist);
} else {
if (debug_ > 0)
mprintf("Frame %i staying in cluster %i\n", pointFrame, closestCluster->Num());
}
if (clusterToClusterCentroid_) {
//if (oldBestRep != NewBestRep) {
// C1->AlignToBestRep( Cdist_ ); // FIXME: Only relevant for COORDS dist?
// C1->CalculateCentroid( Cdist_ ); // FIXME: Seems unnessecary to align prior
//}
}
}
// }
} // END loop over points to cluster
if (Nchanged == 0) {
mprintf("\tK-means round %i: No change. Skipping the rest of the iterations.\n", iteration);
break;
} else
mprintf("\tK-means round %i: %i points changed cluster assignment.\n", iteration, Nchanged);
} // END k-means iterations
// Remove any empty clusters
// FIXME: Will there ever be empty clusters?
RemoveEmptyClusters();
// NOTE in PTRAJ here align all frames to best rep
return 0;
}
