static void kmeans_center_multiple_restarts(
unsigned nb_restarts, cluster_t nb_center,
void (*center_init_f)(cluster_t, histogram_c &, dataset_t &, nbgen &),
histogram_c ¢er, dataset_t &dataset, nbgen &rng) {
std::vector<histogram_c> center_c(nb_restarts);
for (unsigned i = 0; i < nb_restarts; ++i)
center_init_f(nb_center, center_c[i], dataset, rng);
unsigned nb_features = dataset[0].histogram.size();
std::vector<double> cluster_dists(nb_restarts);
for (unsigned r = 0; r < nb_restarts; ++r) {
double sum = 0;
unsigned count = 0;
std::vector<double> distances(nb_center, 0);
for (unsigned i = 0; i < nb_center; ++i) {
for (unsigned j = 0; j < nb_center; ++j) {
if (j == i)
continue;
double dist = l2_distance(center_c[r][i], center_c[r][j], nb_features);
distances[i] += dist;
++count;
}
sum += distances[i];
}
cluster_dists[r] = sum / count;
// printf("restart:%u -> %f\n", r, cluster_dists[r]);
}
size_t max_cluster = std::distance(
cluster_dists.begin(),
std::max_element(cluster_dists.begin(), cluster_dists.end()));
// printf("min center index: %zu\n", max_cluster);
center = center_c[max_cluster];
}
void find_optimal_clustering(Mat &dists, std::vector<idx_cluster_t> &idxClusters, const cluster_vars &vars) {
int optimalClusters = floor(sqrt(dists.rows));
Mat initial;
double r = vars.mcl_inflation_power;
double r_dec = r - 1;
double multStep = 0.6;
cluster_dists(dists, initial, r, vars);
interpret_clusters(initial, idxClusters);
double clusterRatio = (int)idxClusters.size() / (double)optimalClusters;
int iterations = vars.cluster_max_iterations;
double r_used = r;
if(clusterRatio < 1) {
// want more clusters - larger r
Mat prevmat;
for(int i = 0; i < iterations; i++) {
r_dec *= (1 - multStep) + 1;
r_used = 1 + r_dec;
Mat mclmat;
cluster_dists(dists, mclmat, r_used, vars);
idxClusters.clear();
interpret_clusters(mclmat, idxClusters);
clusterRatio = (int)idxClusters.size() / (double)optimalClusters;
//printf(" - %3d: Testing r of %6.3f and got clusterRatio of %6.3f\n", i, r_used, clusterRatio);
if(clusterRatio > 1) {
interpret_clusters(prevmat, idxClusters);
break;
}
else if(clusterRatio == 1.0) {
break;
}
else {
mclmat.copyTo(prevmat);
}
}
//printf(" - Finally using r of %6.3f to get %3d clusters from %3d hists for a clusterRatio of %6.3f\n", r_used, (int)idxClusters.size(), dists.rows, clusterRatio);
}
else if(clusterRatio > 1) {
// want fewer clusters - smaller r
for(int i = 0; i < iterations; i++) {
r_dec *= multStep;
r_used = 1 + r_dec;
Mat mclmat;
cluster_dists(dists, mclmat, r_used, vars);
idxClusters.clear();
interpret_clusters(mclmat, idxClusters);
clusterRatio = (int)idxClusters.size() / (double)optimalClusters;
//printf(" - %3d: Testing r of %6.3f and got clusterRatio of %6.3f\n", i, r_used, clusterRatio);
if(clusterRatio <= 1.0) {
break;
}
}
//printf(" - Using r of %6.3f to get %3d clusters from %3d hists for a clusterRatio of %6.3f\n", r_used, (int)idxClusters.size(), dists.rows, clusterRatio);
}
/*
int optimalClustersMax = ceil(sqrt(dists.rows));
int optimalClustersMin = floor(sqrt(dists.rows));
int optimalCase = (int)ceil(sqrt((int)dists.rows)*2);
double optimalRatio = optimalCase / (double)dists.rows;
*/
/*
printf("Optimal Case Checks: %d\n", optimalCase);
printf("Optimal Check Ratio: %.3f\n", optimalRatio);
printf("Optimal Clusters: %d - %d\n\n", optimalClustersMin, optimalClustersMax);
*/
/*
Mat initial;
double r = vars.mcl_inflation_power;
cluster_dists(dists, initial, r, vars);
interpret_clusters(initial, idxClusters);
int checkClusters = (int)idxClusters.size();
int iterations = vars.cluster_max_iterations;
int base = 7;
bool makeLarger = (checkClusters < optimalClustersMin);
for(int i = 0; i < iterations; i++) {
if(checkClusters < optimalClustersMin && makeLarger)
r *= (base + 1.0 + i) / base; // need more clusters - larger r
else if(checkClusters > optimalClustersMax && !makeLarger)
r *= (base - 1.0 - i) / base; // need fewer clusters - smaller r
else
break;
if(r <= 1)
break;
Mat mclmat;
cluster_dists(dists, mclmat, r, vars);
idxClusters.clear();
interpret_clusters(mclmat, idxClusters);
checkClusters = (int)idxClusters.size();
}
*/
}
