void kmeans_compressor::bicriteria_to_coreset(
wplist& src,
wplist& bicriteria,
csize_t dstsize,
wplist& dst) {
if (bicriteria.size() == 0) {
dst = src;
return;
}
double weight_sum = 0;
double squared_min_dist_sum = 0;
for (wplist::iterator it = src.begin(); it != src.end(); ++it) {
std::pair<int, double> m = min_dist(*it, bicriteria);
(*it).free_long = m.first;
(*it).free_double = m.second;
bicriteria.at((*it).free_long).free_double += (*it).weight;
squared_min_dist_sum += pow((*it).free_double, 2) * (*it).weight;
weight_sum += (*it).weight;
}
std::vector<double> weights;
double sumw = 0;
double prob = 0;
for (wplist::iterator it = src.begin(); it != src.end(); ++it) {
weighted_point p = *it;
weighted_point bp = bicriteria.at(p.free_long);
prob = get_probability(p, bp, weight_sum, squared_min_dist_sum);
(*it).free_double = prob;
weights.push_back(prob);
sumw += prob;
}
discrete_distribution d(weights.begin(), weights.end());
std::vector<size_t> ind(dstsize);
std::generate(ind.begin(), ind.end(), d);
for (std::vector<size_t>::iterator it = ind.begin(); it != ind.end(); ++it) {
weighted_point sample = src.at(*it);
sample.weight = 1.0 / dstsize * sumw / sample.free_double * sample.weight;
sample.free_double = 0;
sample.free_long = 0;
dst.push_back(sample);
}
}
void kmeans_compressor::get_bicriteria(
const wplist& src, csize_t bsize, csize_t dstsize, wplist& dst) {
timer_start();
dst.clear();
wplist resid = src;
vector<double> weights(src.size());
double r = (1 - exp(bsize*(log(bsize)-log(src.size()))/dstsize)) / 2;
r = max(0.1, r);
std::vector<size_t> ind(bsize);
while (resid.size() > 1 && dst.size() < dstsize) {
timer_start();
weights.resize(resid.size());
for (wplist::iterator it = resid.begin(); it != resid.end(); ++it) {
weights[it - resid.begin()] = it->weight;
}
discrete_distribution d(weights.begin(), weights.end());
std::generate(ind.begin(), ind.end(), d);
std::sort(ind.begin(), ind.end());
std::vector<size_t>::iterator it = std::unique(ind.begin(), ind.end());
ind.erase(it, ind.end());
for (it = ind.begin(); it != ind.end(); ++it) {
weighted_point p = resid[*it];
p.free_long = 0;
dst.push_back(p);
}
for (wplist::iterator itr = resid.begin(); itr != resid.end(); ++itr) {
(*itr).free_double = min_dist(*itr, dst).second;
}
std::sort(resid.begin(), resid.end(), compare_weight);
csize_t size = (csize_t)std::min(static_cast<double>(resid.size()),
static_cast<double>(resid.size()*r));
if (size == 0) {
size = 1;
}
resid.resize(size);
}
}