plJointDistribution createClusteringJointDist( const Variables& variables, const Clustering& clustering) {
plComputableObjectList cndProbTabs;
for ( Clustering::const_iterator it = clustering.begin(); it != clustering.end(); ++it ) {
cndProbTabs *= createClusterJointDist( variables, *it);
}
//std::cout << cndProbTabs << std::endl;
plJointDistribution jointDist( variables, cndProbTabs );
return jointDist;
}
bool MatchingDynamicClusterer::bootstrap( Clustering &step_clustering )
{
m_dynamic.clear();
Clustering::iterator cit;
Clustering::iterator cend = step_clustering.end();
int step_cluster_index = 0;
for( cit = step_clustering.begin() ; cit != cend; cit++, step_cluster_index++ )
{
// if( (*cit).size() < MIN_CLUSTER_SIZE || (*cit).size() > MAX_CLUSTER_SIZE )
if( (*cit).size() < MIN_CLUSTER_SIZE )
{
continue;
}
DynamicCluster dc;
dc.update( m_step, step_cluster_index, *cit );
m_dynamic.push_back(dc);
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Birth: Community M" << m_dynamic.size() << endl;
#endif
}
return true;
}
bool MapMatchingDynamicClusterer::add_clustering( Clustering &step_clustering )
{
m_step += 1;
/// First?
if( m_step == 1 )
{
return bootstrap(step_clustering);
}
int step_cluster_index = 0;
/// Build a map of Nodes -> Dynamic Communities containing those nodes
map<NODE,set<int> > fastmap;
DynamicClustering::iterator dit;
DynamicClustering::iterator dend = m_dynamic.end();
int dyn_count = (int)m_dynamic.size();
int dyn_index = 0;
long* dyn_sizes = new long[dyn_count+1];
for( dit = m_dynamic.begin() ; dit != dend; dit++, dyn_index++ )
{
// Dead?
if( m_death_age > 0 && m_dynamic[dyn_index].is_dead( m_step, m_death_age ) )
{
dyn_sizes[dyn_index] = 0;
continue;
}
Cluster& front = (*dit).front();
dyn_sizes[dyn_index] = (long)front.size();
Cluster::const_iterator fit;
Cluster::const_iterator fend = front.end();
for( fit = front.begin() ; fit != fend; fit++ )
{
NODE node_index = *fit;
if( !fastmap.count( node_index ) )
{
set<int> first;
first.insert(dyn_index);
fastmap.insert( make_pair(node_index,first) );
}
else
{
fastmap[node_index].insert(dyn_index);
}
}
}
/// Now try to match all
int* all_intersection = new int[dyn_count+1];
vector<DynamicCluster> fresh;
PairVector matched_pairs;
map<NODE,set<int> >::const_iterator mend = fastmap.end();
Clustering::iterator cit;
Clustering::iterator cend = step_clustering.end();
for( cit = step_clustering.begin() ; cit != cend; cit++, step_cluster_index++ )
{
long size_step = (long)(*cit).size();
if( size_step < MIN_CLUSTER_SIZE )
{
continue;
}
// Compute all intersections
for( dyn_index = 0; dyn_index < dyn_count; dyn_index++)
{
all_intersection[dyn_index] = 0;
}
Cluster::const_iterator xit;
Cluster::const_iterator xend = (*cit).end();
for( xit = (*cit).begin() ; xit != xend; xit++ )
{
NODE node_index = *xit;
map<NODE,set<int> >::const_iterator mit = fastmap.find(node_index);
if( mit != mend )
{
set<int>::const_iterator sit;
for ( sit = fastmap[node_index].begin(); sit != fastmap[node_index].end(); sit++ )
{
all_intersection[(*sit)]++;
}
}
}
// Find matches
vector<int> matches;
for( dyn_index = 0; dyn_index < dyn_count; dyn_index++)
{
if( dyn_sizes[dyn_index] == 0 || all_intersection[dyn_index] == 0 )
{
continue;
}
#ifdef SIM_OVERLAP
double sim = ((double)(all_intersection[dyn_index]))/min(size_step,dyn_sizes[dyn_index]);
#else
double sim = ((double)(all_intersection[dyn_index]))/(size_step+dyn_sizes[dyn_index]-all_intersection[dyn_index]);
#endif
if( sim > m_threshold )
{
matches.push_back( dyn_index );
}
}
// new community?
if( matches.empty() )
{
DynamicCluster dc;
dc.update( m_step, step_cluster_index, *cit );
fresh.push_back(dc);
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Birth: Community M" << (m_dynamic.size()+fresh.size()) << " from C" << step_cluster_index+1 << endl;
#endif
}
else
{
vector<int>::const_iterator iit;
for( iit = matches.begin() ; iit != matches.end(); iit++ )
{
pair<int,int> p(step_cluster_index,(*iit));
matched_pairs.push_back(p);
}
}
}
// Actually update existing dynamic communities now
set<int> matched_dynamic;
PairVector::const_iterator pit;
for( pit = matched_pairs.begin(); pit != matched_pairs.end(); pit++ )
{
int step_cluster_index = (*pit).first;
int dyn_cluster_index = (*pit).second;
// already processed this dynamic cluster?
if( matched_dynamic.count( dyn_cluster_index ) )
{
DynamicCluster dc( m_dynamic[dyn_cluster_index], m_step, step_cluster_index, step_clustering[step_cluster_index] );
fresh.push_back(dc);
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Split: Matched C" << (step_cluster_index+1) << " to M" << (dyn_cluster_index+1) << ". Splitting to M" << (m_dynamic.size()+fresh.size()) << endl;
#endif
}
else
{
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Continuation: Matched C" << (step_cluster_index+1) << " to M" << (dyn_cluster_index+1) << endl;
#endif
m_dynamic[dyn_cluster_index].update( m_step, step_cluster_index, step_clustering[step_cluster_index] );
matched_dynamic.insert(dyn_cluster_index);
}
}
// And finally add any new dynamic communities
for( dit = fresh.begin() ; dit != fresh.end(); dit++ )
{
m_dynamic.push_back(*dit);
}
delete[] dyn_sizes;
delete[] all_intersection;
return true;
}
bool MatchingDynamicClusterer::add_clustering( Clustering &step_clustering )
{
m_step += 1;
/// First?
if( m_step == 1 )
{
return bootstrap(step_clustering);
}
/// Otherwise, try to match all
Clustering::iterator cit;
Clustering::iterator cend = step_clustering.end();
int step_cluster_index = 0;
vector<DynamicCluster> fresh;
PairVector matched_pairs;
for( cit = step_clustering.begin() ; cit != cend; cit++, step_cluster_index++ )
{
vector<int> matches;
find_matches( *cit, matches );
// new community?
if( matches.empty() )
{
DynamicCluster dc;
dc.update( m_step, step_cluster_index, *cit );
fresh.push_back(dc);
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Birth: Community M" << (m_dynamic.size()+fresh.size()) << " from C" << step_cluster_index+1 << endl;
#endif
}
else
{
vector<int>::const_iterator iit;
for( iit = matches.begin() ; iit != matches.end(); iit++ )
{
pair<int,int> p(step_cluster_index,(*iit));
matched_pairs.push_back(p);
}
}
}
// Actually update existing dynamic communities now
set<int> matched_dynamic;
PairVector::const_iterator pit;
for( pit = matched_pairs.begin(); pit != matched_pairs.end(); pit++ )
{
int step_cluster_index = (*pit).first;
int dyn_cluster_index = (*pit).second;
// already processed this dynamic cluster?
if( matched_dynamic.count( dyn_cluster_index ) )
{
DynamicCluster dc( m_dynamic[dyn_cluster_index], m_step, step_cluster_index, step_clustering[step_cluster_index] );
fresh.push_back(dc);
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Split: Matched C" << (step_cluster_index+1) << " to M" << (dyn_cluster_index+1) << ". Splitting to M" << (m_dynamic.size()+fresh.size()) << endl;
#endif
}
else
{
#ifdef DEBUG_MATCHING
cout << "T" << m_step << ": Continuation: Matched C" << (step_cluster_index+1) << " to M" << (dyn_cluster_index+1) << endl;
#endif
m_dynamic[dyn_cluster_index].update( m_step, step_cluster_index, step_clustering[step_cluster_index] );
matched_dynamic.insert(dyn_cluster_index);
}
}
// And finally add any new dynamic communities
DynamicClustering::const_iterator dit;
for( dit = fresh.begin() ; dit != fresh.end(); dit++ )
{
m_dynamic.push_back(*dit);
}
return true;
}