double kmedians::update_medians() {
const std::vector<point> & data = *m_ptr_data;
const size_t dimension = data[0].size();
std::vector<point> prev_medians(m_medians);
m_medians.clear();
m_medians.resize(m_clusters.size(), point(dimension, 0.0));
double maximum_change = 0.0;
for (size_t index_cluster = 0; index_cluster < m_clusters.size(); index_cluster++) {
for (size_t index_dimension = 0; index_dimension < dimension; index_dimension++) {
cluster & current_cluster = m_clusters[index_cluster];
std::sort(current_cluster.begin(), current_cluster.end(),
[this](unsigned int index_object1, unsigned int index_object2)
{
return (*m_ptr_data)[index_object1] > (*m_ptr_data)[index_object2];
});
size_t relative_index_median = (size_t) floor(current_cluster.size() / 2.0);
size_t index_median = current_cluster[relative_index_median];
if (current_cluster.size() % 2) {
size_t index_median_second = current_cluster[relative_index_median + 1];
m_medians[index_cluster][index_dimension] = (data[index_median][index_dimension] + data[index_median_second][index_dimension]) / 2.0;
}
else {
m_medians[index_cluster][index_dimension] = data[index_median][index_dimension];
}
}
double change = euclidean_distance_sqrt(&prev_medians[index_cluster], &m_medians[index_cluster]);
if (change > maximum_change) {
maximum_change = change;
}
}
return maximum_change;
}
double kmedians::update_medians(cluster_sequence & clusters, dataset & medians) {
const dataset & data = *m_ptr_data;
const std::size_t dimension = data[0].size();
std::vector<point> prev_medians(medians);
medians.clear();
medians.resize(clusters.size(), point(dimension, 0.0));
double maximum_change = 0.0;
for (std::size_t index_cluster = 0; index_cluster < clusters.size(); index_cluster++) {
calculate_median(clusters[index_cluster], medians[index_cluster]);
double change = m_metric(prev_medians[index_cluster], medians[index_cluster]);
if (change > maximum_change) {
maximum_change = change;
}
}
return maximum_change;
}
