inline double KDERules<MetricType, KernelType, TreeType>::
Score(const size_t queryIndex, TreeType& referenceNode)
{
double score, maxKernel, minKernel, bound;
const arma::vec& queryPoint = querySet.unsafe_col(queryIndex);
const double minDistance = referenceNode.MinDistance(queryPoint);
bool newCalculations = true;
if (tree::TreeTraits<TreeType>::FirstPointIsCentroid &&
lastQueryIndex == queryIndex &&
traversalInfo.LastReferenceNode() != NULL &&
traversalInfo.LastReferenceNode()->Point(0) == referenceNode.Point(0))
{
// Don't duplicate calculations.
newCalculations = false;
lastQueryIndex = queryIndex;
lastReferenceIndex = referenceNode.Point(0);
}
else
{
// Calculations are new.
maxKernel = kernel.Evaluate(minDistance);
minKernel = kernel.Evaluate(referenceNode.MaxDistance(queryPoint));
bound = maxKernel - minKernel;
}
if (newCalculations &&
bound <= (absError + relError * minKernel) / referenceSet.n_cols)
{
// Estimate values.
double kernelValue;
// Calculate kernel value based on reference node centroid.
if (tree::TreeTraits<TreeType>::FirstPointIsCentroid)
{
kernelValue = EvaluateKernel(queryIndex, referenceNode.Point(0));
}
else
{
kde::KDEStat& referenceStat = referenceNode.Stat();
kernelValue = EvaluateKernel(queryPoint, referenceStat.Centroid());
}
densities(queryIndex) += referenceNode.NumDescendants() * kernelValue;
// Don't explore this tree branch.
score = DBL_MAX;
}
else
{
score = minDistance;
}
++scores;
traversalInfo.LastReferenceNode() = &referenceNode;
traversalInfo.LastScore() = score;
return score;
}
double DTBRules<MetricType, TreeType>::Score(TreeType& queryNode,
TreeType& referenceNode)
{
// If all the queries belong to the same component as all the references
// then we prune.
if ((queryNode.Stat().ComponentMembership() >= 0) &&
(queryNode.Stat().ComponentMembership() ==
referenceNode.Stat().ComponentMembership()))
return DBL_MAX;
++scores;
const double distance = queryNode.MinDistance(&referenceNode);
const double bound = CalculateBound(queryNode);
// If all the points in the reference node are farther than the candidate
// nearest neighbor for all queries in the node, we prune.
return (bound < distance) ? DBL_MAX : distance;
}
double DTBRules<MetricType, TreeType>::Score(const size_t queryIndex,
TreeType& referenceNode)
{
size_t queryComponentIndex = connections.Find(queryIndex);
// If the query belongs to the same component as all of the references,
// then prune. The cast is to stop a warning about comparing unsigned to
// signed values.
if (queryComponentIndex ==
(size_t) referenceNode.Stat().ComponentMembership())
return DBL_MAX;
const arma::vec queryPoint = dataSet.unsafe_col(queryIndex);
const double distance = referenceNode.MinDistance(queryPoint);
// If all the points in the reference node are farther than the candidate
// nearest neighbor for the query's component, we prune.
return neighborsDistances[queryComponentIndex] < distance
? DBL_MAX : distance;
}
double DTBRules<MetricType, TreeType>::Score(const size_t queryIndex,
TreeType& referenceNode,
const double baseCaseResult)
{
// I don't really understand the last argument here
// It just gets passed in the distance call, otherwise this function
// is the same as the one above.
size_t queryComponentIndex = connections.Find(queryIndex);
// If the query belongs to the same component as all of the references,
// then prune.
if (queryComponentIndex == referenceNode.Stat().ComponentMembership())
return DBL_MAX;
const arma::vec queryPoint = dataSet.unsafe_col(queryIndex);
const double distance = referenceNode.MinDistance(queryPoint,
baseCaseResult);
// If all the points in the reference node are farther than the candidate
// nearest neighbor for the query's component, we prune.
return (neighborsDistances[queryComponentIndex] < distance) ? DBL_MAX :
distance;
}
double PellegMooreKMeansRules<MetricType, TreeType>::Score(
const size_t /* queryIndex */,
TreeType& referenceNode)
{
// Obtain the parent's blacklist. If this is the root node, we'll start with
// an empty blacklist. This means that after each iteration, we don't need to
// reset any statistics.
if (referenceNode.Parent() == NULL ||
referenceNode.Parent()->Stat().Blacklist().n_elem == 0)
referenceNode.Stat().Blacklist().zeros(centroids.n_cols);
else
referenceNode.Stat().Blacklist() =
referenceNode.Parent()->Stat().Blacklist();
// The query index is a fake index that we won't use, and the reference node
// holds all of the points in the dataset. Our goal is to determine whether
// or not this node is dominated by a single cluster.
const size_t whitelisted = centroids.n_cols -
arma::accu(referenceNode.Stat().Blacklist());
distanceCalculations += whitelisted;
// Which cluster has minimum distance to the node?
size_t closestCluster = centroids.n_cols;
double minMinDistance = DBL_MAX;
for (size_t i = 0; i < centroids.n_cols; ++i)
{
if (referenceNode.Stat().Blacklist()[i] == 0)
{
const double minDistance = referenceNode.MinDistance(centroids.col(i));
if (minDistance < minMinDistance)
{
minMinDistance = minDistance;
closestCluster = i;
}
}
}
// Now, for every other whitelisted cluster, determine if the closest cluster
// owns the point. This calculation is specific to hyperrectangle trees (but,
// this implementation is specific to kd-trees, so that's okay). For
// circular-bound trees, the condition should be simpler and can probably be
// expressed as a comparison between minimum and maximum distances.
size_t newBlacklisted = 0;
for (size_t c = 0; c < centroids.n_cols; ++c)
{
if (referenceNode.Stat().Blacklist()[c] == 1 || c == closestCluster)
continue;
// This algorithm comes from the proof of Lemma 4 in the extended version
// of the Pelleg-Moore paper (the CMU tech report, that is). It has been
// adapted for speed.
arma::vec cornerPoint(centroids.n_rows);
for (size_t d = 0; d < referenceNode.Bound().Dim(); ++d)
{
if (centroids(d, c) > centroids(d, closestCluster))
cornerPoint(d) = referenceNode.Bound()[d].Hi();
else
cornerPoint(d) = referenceNode.Bound()[d].Lo();
}
const double closestDist = metric.Evaluate(cornerPoint,
centroids.col(closestCluster));
const double otherDist = metric.Evaluate(cornerPoint, centroids.col(c));
distanceCalculations += 3; // One for cornerPoint, then two distances.
if (closestDist < otherDist)
{
// The closest cluster dominates the node with respect to the cluster c.
// So we can blacklist c.
referenceNode.Stat().Blacklist()[c] = 1;
++newBlacklisted;
}
}
if (whitelisted - newBlacklisted == 1)
{
// This node is dominated by the closest cluster.
counts[closestCluster] += referenceNode.NumDescendants();
newCentroids.col(closestCluster) += referenceNode.NumDescendants() *
referenceNode.Stat().Centroid();
return DBL_MAX;
}
// Perform the base case here.
for (size_t i = 0; i < referenceNode.NumPoints(); ++i)
{
size_t bestCluster = centroids.n_cols;
double bestDistance = DBL_MAX;
for (size_t c = 0; c < centroids.n_cols; ++c)
{
if (referenceNode.Stat().Blacklist()[c] == 1)
continue;
++distanceCalculations;
// The reference index is the index of the data point.
const double distance = metric.Evaluate(centroids.col(c),
dataset.col(referenceNode.Point(i)));
if (distance < bestDistance)
{
bestDistance = distance;
bestCluster = c;
}
}
// Add to resulting centroid.
newCentroids.col(bestCluster) += dataset.col(referenceNode.Point(i));
++counts(bestCluster);
}
// Otherwise, we're not sure, so we can't prune. Recursion order doesn't make
// a difference, so we'll just return a score of 0.
return 0.0;
}
inline double KDERules<MetricType, KernelType, TreeType>::
Score(TreeType& queryNode, TreeType& referenceNode)
{
double score, maxKernel, minKernel, bound;
const double minDistance = queryNode.MinDistance(referenceNode);
// Calculations are not duplicated.
bool newCalculations = true;
if (tree::TreeTraits<TreeType>::FirstPointIsCentroid &&
(traversalInfo.LastQueryNode() != NULL) &&
(traversalInfo.LastReferenceNode() != NULL) &&
(traversalInfo.LastQueryNode()->Point(0) == queryNode.Point(0)) &&
(traversalInfo.LastReferenceNode()->Point(0) == referenceNode.Point(0)))
{
// Don't duplicate calculations.
newCalculations = false;
lastQueryIndex = queryNode.Point(0);
lastReferenceIndex = referenceNode.Point(0);
}
else
{
// Calculations are new.
maxKernel = kernel.Evaluate(minDistance);
minKernel = kernel.Evaluate(queryNode.MaxDistance(referenceNode));
bound = maxKernel - minKernel;
}
// If possible, avoid some calculations because of the error tolerance.
if (newCalculations &&
bound <= (absError + relError * minKernel) / referenceSet.n_cols)
{
// Auxiliary variables.
double kernelValue;
kde::KDEStat& referenceStat = referenceNode.Stat();
kde::KDEStat& queryStat = queryNode.Stat();
// If calculating a center is not required.
if (tree::TreeTraits<TreeType>::FirstPointIsCentroid)
{
kernelValue = EvaluateKernel(queryNode.Point(0), referenceNode.Point(0));
}
// Sadly, we have no choice but to calculate the center.
else
{
kernelValue = EvaluateKernel(queryStat.Centroid(),
referenceStat.Centroid());
}
// Sum up estimations.
for (size_t i = 0; i < queryNode.NumDescendants(); ++i)
{
densities(queryNode.Descendant(i)) +=
referenceNode.NumDescendants() * kernelValue;
}
score = DBL_MAX;
}
else
{
score = minDistance;
}
++scores;
traversalInfo.LastQueryNode() = &queryNode;
traversalInfo.LastReferenceNode() = &referenceNode;
traversalInfo.LastScore() = score;
return score;
}