// assessClusters assigns the results to the CentPointDist matrix.
func assessClusters(CentPointDist *matrix.DenseMatrix, results <-chan PairPointCentroidResult) bool {
change := false
for result := range results {
if CentPointDist.Get(result.rowNum, 0) != result.centroidRowNum {
change = true
}
CentPointDist.Set(result.rowNum, 0, result.centroidRowNum)
CentPointDist.Set(result.rowNum, 1, result.distSquared)
}
return change
}
// Kmeansbi bisects a given cluster and determines which centroids give the lowest error.
// Take the points in a cluster
// While the number of cluster < k
// for every cluster
// measure total error
// cacl kmeansp with k=2 on a given cluster
// measure total error after kmeansp split
// choose the cluster split with the lowest SSE
// commit the chosen split
//
// N.B. We are using SSE until the BIC is completed.
func Kmeansbi(datapoints *matrix.DenseMatrix, k int, cc CentroidChooser, measurer matutil.VectorMeasurer) (matCentroidlist, clusterAssignment *matrix.DenseMatrix, err error) {
numRows, numCols := datapoints.GetSize()
clusterAssignment = matrix.Zeros(numRows, numCols)
matCentroidlist = matrix.Zeros(k, numCols)
centroid0 := datapoints.MeanCols()
centroidlist := []*matrix.DenseMatrix{centroid0}
// Initially create one cluster.
for j := 0; j < numRows; j++ {
point := datapoints.GetRowVector(j)
distJ, err := measurer.CalcDist(centroid0, point)
if err != nil {
return matCentroidlist, clusterAssignment, errors.New(fmt.Sprintf("Kmeansbi: CalcDist returned err=%v", err))
}
clusterAssignment.Set(j, 1, math.Pow(distJ, 2))
}
var bestClusterAssignment, bestNewCentroids *matrix.DenseMatrix
var bestCentroidToSplit int
// Find the best centroid configuration.
for len(centroidlist) < k {
lowestSSE := math.Inf(1)
// Split cluster
for i, _ := range centroidlist {
// Get the points in this cluster
pointsCurCluster, err := clusterAssignment.FiltCol(float64(i), float64(i), 0)
if err != nil {
return matCentroidlist, clusterAssignment, err
}
centroids, splitClusterAssignment, err := Kmeansp(pointsCurCluster, 2, cc, measurer)
if err != nil {
return matCentroidlist, clusterAssignment, err
}
/* centroids is a 2X2 matrix of the best centroids found by kmeans
splitClustAssignment is a mX2 matrix where col0 is either 0 or 1 and refers to the rows in centroids
where col1 cotains the squared error between a centroid and a point. The rows here correspond to
the rows in ptsInCurrCluster. For example, if row 2 contains [1, 7.999] this means that centroid 1
has been paired with the point in row 2 of splitClustAssignment and that the squared error (distance
between centroid and point) is 7.999.
*/
// Calculate the sum of squared errors for each centroid.
// This give a statistcal measurement of how good
// the clustering is for this cluster.
sseSplit := splitClusterAssignment.SumCol(1)
// Calculate the SSE for the original cluster
sqerr, err := clusterAssignment.FiltCol(float64(0), math.Inf(1), 0)
if err != nil {
return matCentroidlist, clusterAssignment, err
}
sseNotSplit := sqerr.SumCol(1)
// TODO: Pre-BCI is this the best way to evaluate?
if sseSplit+sseNotSplit < lowestSSE {
bestCentroidToSplit = 1
bestNewCentroids = matrix.MakeDenseCopy(centroids)
bestClusterAssignment = matrix.MakeDenseCopy(splitClusterAssignment)
}
}
// Applying the split overwrites the existing cluster assginments for the
// cluster you have decided to split. Kmeansp() returned two clusters
// labeled 0 and 1. Change these cluster numbers to the cluster number
// you are splitting and the next cluster to be added.
m, err := bestClusterAssignment.FiltColMap(1, 1, 0)
if err != nil {
return matCentroidlist, clusterAssignment, err
}
for i, _ := range m {
bestClusterAssignment.Set(i, 0, float64(len(centroidlist)))
}
n, err := bestClusterAssignment.FiltColMap(0, 0, 0)
if err != nil {
return matCentroidlist, clusterAssignment, err
}
for i, _ := range n {
bestClusterAssignment.Set(i, 1, float64(bestCentroidToSplit))
}
fmt.Printf("Best centroid to split %f\n", bestCentroidToSplit)
r, _ := bestClusterAssignment.GetSize()
fmt.Printf("The length of best cluster assesment is %f\n", r)
// Replace a centroid with the two best centroids from the split.
centroidlist[bestCentroidToSplit] = bestNewCentroids.GetRowVector(0)
centroidlist = append(centroidlist, bestNewCentroids.GetRowVector(1))
// Reassign new clusters and SSE
rows, _ := clusterAssignment.GetSize()
for i, j := 0, 0; i < rows; i++ {
if clusterAssignment.Get(i, 0) == float64(bestCentroidToSplit) {
clusterAssignment.Set(i, 0, bestClusterAssignment.Get(j, 0))
clusterAssignment.Set(i, 1, bestClusterAssignment.Get(j, 1))
j++
}
}
// make centroidlist into a matrix
s := make([][]float64, len(centroidlist))
for i, mat := range centroidlist {
s[i][0] = mat.Get(0, 0)
s[i][1] = mat.Get(0, 1)
}
matCentroidlist = matrix.MakeDenseMatrixStacked(s)
}
return matCentroidlist, clusterAssignment, nil
}
// processPairPointToCentroidResults assigns the results to the centroidSqErr matrix.
func processPairPointToCentroidResults(centroidSqErr *matrix.DenseMatrix, results <-chan PairPointCentroidResult) {
for result := range results {
centroidSqErr.Set(result.rowNum, 0, result.centroidRowNum)
centroidSqErr.Set(result.rowNum, 1, result.distSquared)
}
}
