srowen commented on a change in pull request #27758: [SPARK-31007][ML] KMeans
optimization based on triangle-inequality
URL: https://github.com/apache/spark/pull/27758#discussion_r386456920
##########
File path:
mllib/src/main/scala/org/apache/spark/mllib/clustering/DistanceMeasure.scala
##########
@@ -154,22 +198,86 @@ object DistanceMeasure {
}
private[spark] class EuclideanDistanceMeasure extends DistanceMeasure {
+
+ /**
+ * @return Radii of centers. If distance between point x and center c is
less than
+ * the radius of center c, then center c is the closest center to
point x.
+ * For Euclidean distance, radius of center c is half of the
distance between
+ * center c and its closest center.
+ */
+ override def computeRadii(centers: Array[VectorWithNorm]): Array[Double] = {
+ val k = centers.length
+ if (k == 1) {
+ Array(Double.NaN)
+ } else {
+ val distances = Array.fill(k)(Double.PositiveInfinity)
+ var i = 0
+ while (i < k) {
+ var j = i + 1
+ while (j < k) {
+ val d = distance(centers(i), centers(j))
+ if (d < distances(i)) distances(i) = d
+ if (d < distances(j)) distances(j) = d
+ j += 1
+ }
+ i += 1
+ }
+
+ distances.map(_ / 2)
+ }
+ }
+
+ /**
+ * @return the index of the closest center to the given point, as well as
the cost.
+ */
+ override def findClosest(
+ centers: Array[VectorWithNorm],
+ radii: Array[Double],
+ point: VectorWithNorm): (Int, Double) = {
+ var bestDistance = Double.PositiveInfinity
+ var bestIndex = 0
+ var i = 0
+ var found = false
+ while (i < centers.length && !found) {
+ val center = centers(i)
+ // Since `\|a - b\| \geq |\|a\| - \|b\||`, we can use this lower bound
to avoid unnecessary
+ // distance computation.
+ var lowerBoundOfSqDist = center.norm - point.norm
+ lowerBoundOfSqDist = lowerBoundOfSqDist * lowerBoundOfSqDist
+ if (lowerBoundOfSqDist < bestDistance) {
+ val d = EuclideanDistanceMeasure.fastSquaredDistance(center, point)
+ val r = radii(i)
+ if (d < r * r) {
+ bestDistance = d
+ bestIndex = i
+ found = true
Review comment:
Same, just return?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
