clustering.core.qt
Quality Threshold (QT) clustering algorithm
From: https://sites.google.com/site/dataclusteringalgorithms/quality-threshold-clustering-algorithm-1
1) Initialize the threshold distance allowed for clusters and the
minimum cluster size.
2) Build a candidate cluster for each data point by including the
closest point, the next closest, and so on, until the distance
of the cluster surpasses the threshold.
3) Save the candidate cluster with the most points as the first true
cluster, and remove all points in the cluster from further
consideration.
4) Repeat with the reduced set of points until no more cluster can
be formed having the minimum cluster size.
candidate-cluster
(candidate-cluster distance-fn point dataset threshold)
Determine which members of the dataset are closed to the candidate
point within the given threshold
cluster
(cluster distance-fn dataset threshold min-size)
Groups members of supplied dataset into specific clusters according to the
provided distance function (this should take 2 collection members and return
a scalar difference between them). Candidate clusters are assembled such
that the distance of the cluster surpasses the threshold. Further clusters
are formed from the remaining points until no more clusters can be formed
having the minimum cluster size.
most-candidates
(most-candidates distance-fn dataset threshold)