void Clusters::compute_centroids()
{
time_t start_time = time(NULL);
bool verbose = true;
if(verbose) {
cout << "Computing centroids..." << endl;
cout << "Wiping old spread and centroid" << endl;
}
int i;
for(i = 0; i < centroids.size(); i++) {
spread[i] = 0;
centroids[i].clear();
}
if(verbose) cout << "Computing new centroids" << endl;
int iter_count = 0;
for(int i = 0; i < nclusters; i++) {
iter_count += recompute_centroid(i);
}
if(verbose)
cout << "Done with centroid recompute. ("
<< difftime(time(NULL), start_time)
<< " sec, " << iter_count << " iter)" << endl;
}
void oskmeans::clusterize()
{
// initialize.
initialize();
if (_snippets.empty())
return;
// clustering.
while (!stopping_criterion())
{
#ifdef DEBUG
std::cerr << "[Debug]:clusterize, iteration #" << _iterations << std::endl;
#endif
for (short c=0; c<_K; c++)
{
// clear the cluster.
_clusters[c].clear();
}
// clear the garbage cluster.
_garbage_cluster.clear();
// iterates points and associate each of them with a cluster.
hash_map<uint32_t,hash_map<uint32_t,float,id_hash_uint>*,id_hash_uint>::const_iterator hit
= _points.begin();
while (hit!=_points.end())
{
float learning_rate = oskmeans::_nu0*pow((oskmeans::_nuf/oskmeans::_nu0),_t/static_cast<float>(_points.size()*oskmeans::_niterations));
#ifdef DEBUG
std::cerr << "learning rate: " << learning_rate << std::endl;
#endif
// find closest cluster to this point.
short cl = assign_cluster((*hit).first,(*hit).second);
// recomputation of centroids/medoids.
if (cl != -1)
{
float cl_norm = 0.0;
recompute_centroid(learning_rate,&_clusters[cl]._c,(*hit).second,cl_norm);
normalize_centroid(&_clusters[cl]._c,cl_norm);
}
++hit;
_t++;
}
// count iteration.
_iterations++;
}
}
