int randomEMinit(double **x, int n, int p, int nclass, double *pi,
double **Mu, double **LTSigma)
{
int *ordr,i,j,*clas,*nc;
/* This is a bug. Modified by Wei-Chen Chen on 2009/03/13.
MAKE_VECTOR(ordr,n);
*/
MAKE_VECTOR(ordr, nclass);
MAKE_VECTOR(clas, n);
MAKE_VECTOR(nc, nclass);
do {
/* This is a bug. Modified by Wei-Chen Chen on 2009/03/13.
i=srswor(n, n, ordr);
*/
i=srswor(n, nclass, ordr);
for(i=0;i<nclass;i++){
for(j=0;j<p;j++) Mu[i][j]=x[ordr[i]][j];
}
for(i=0;i<n;i++) clas[i]=assign_closest(x[i],p,nclass,Mu);
j=initials(x,n,p,nclass,nc,Mu,LTSigma,clas);
} while (j==0);
for(i=0;i<nclass;i++) pi[i]=1.*nc[i]/n;
FREE_VECTOR(nc);
FREE_VECTOR(clas);
FREE_VECTOR(ordr);
return 0;
}
void kmeans(std::vector<DataPoint> data_points, int k) {
std::vector<DataPoint> centroids = initial_centroids(data_points, k);
int changed = data_points.size();
double done_threshold = (k * 0.10 * data_points.size());
while (changed > done_threshold) {
changed = 0;
for (std::vector<DataPoint>::iterator it = data_points.begin();
it != data_points.end(); ++it) {
assign_closest(centroids, *it, changed);
}
// Memory leak. Delete attr of old, synthetic, centroids
centroids = recompute_centroids(data_points, centroids);
}
print_data_points(centroids);
print_data_points(data_points);
}
/* This function is called by ss_shortems().
Mu[0, ..., labK-1] should be assigned before calling this function.
*/
void ss_randomEMinit(double **x, int n, int p, int nclass, double *pi,
double **Mu, double **LTSigma,
int *lab, int labK, int nonlab_total, int *lab_index){
int *ordr, i, j, *clas, *nc;
int new_nclass = nclass - labK;
double labMu[labK][p];
for(i = 0; i < labK; i++){
for(j = 0; j < p; j++) labMu[i][j] = Mu[i][j];
}
/* Initial centers for all other unknown clusters. */
MAKE_VECTOR(ordr, new_nclass);
MAKE_VECTOR(clas, n);
MAKE_VECTOR(nc, nclass);
do{
for(i = 0; i < labK; i++){
for(j = 0; j < p; j++) Mu[i][j] = labMu[i][j];
}
i = srswor(nonlab_total, new_nclass, ordr);
for(i = labK; i < nclass; i++){
for(j = 0; j < p; j++) Mu[i][j] = x[lab_index[ordr[i - labK]]][j];
}
for(i = 0; i < n; i++){
if(lab[i] == -1){
clas[i] = assign_closest(x[i], p, nclass, Mu);
} else{
clas[i] = lab[i];
}
}
j = initials(x, n, p, nclass, nc, Mu, LTSigma, clas);
} while(j == 0);
for(i = 0; i < nclass; i++) pi[i] = 1. * nc[i] / n;
FREE_VECTOR(nc);
FREE_VECTOR(clas);
FREE_VECTOR(ordr);
} /* End of ss_randomEMinit(). */
void RunKMedoids(const leveldb::Slice& begin,
const leveldb::Slice& end,
int K, leveldb::DB* db,
leveldb::DB* work_db, int concurrency,
std::ostream& ivar_out, std::ostream& cent_out) {
auto very_start = std::chrono::system_clock::now();
auto key_centroids = uniform_init(begin, end, K);
std::vector<GDELTMini> val_centroids(K);
{
auto it = iter(db);
for (int i = 0; i < K; ++i) {
it->Seek(key_centroids[i]);
CHECK(it->Valid());
read(it->value(), val_centroids[i]);
}
}
std::cout << "Divying up range among threads... " << std::flush;
auto parvec = get_par_ranges(uniform_init(begin, end, concurrency), db, end);
std::cout << "DONE" << std::endl;
int i = 0;
bool centers_changed = true;
vuad totals(K);
vuai cluster_sizes(K);
for (int i = 0; i < K; ++i) {
cluster_sizes[i].reset(new std::atomic<int>);
totals[i].reset(new std::atomic<double>);
}
while (centers_changed) {
auto start = std::chrono::system_clock::now();
assign_closest(parvec, totals, K, work_db, val_centroids, concurrency,
cluster_sizes);
auto tot = std::accumulate(totals.begin(), totals.end(), 0.0,
[](double sum, typename vuad::value_type& d) {
return sum + d->load();
});
auto end = std::chrono::system_clock::now();
std::cout << "Iteration " << ++i << " total intravariance " << tot;
std::cout << "\n Assigning medoids took " << secs(start, end)
<< "s" << std::endl;
start = std::chrono::system_clock::now();
for (auto& d : totals) {
ivar_out << d->load() << " ";
}
ivar_out << std::endl;
cent_out << key_centroids << std::endl;
end = std::chrono::system_clock::now();
std::cout << " Saving medoids took " << secs(start, end)
<< " s" << std::endl;
start = std::chrono::system_clock::now();
centers_changed = update_medoids(concurrency, K, db, work_db,
val_centroids, key_centroids,
totals, cluster_sizes);
end = std::chrono::system_clock::now();
std::cout << " Medoid update took " << secs(start, end)
<< " s" << std::endl;
start = end;
}
auto very_end = std::chrono::system_clock::now();
std::cout << "K-medoid clustering COMPLETE in "
<< secs(very_start, very_end) << " s" << std::endl;
}