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_r386452407
##########
File path:
mllib/src/main/scala/org/apache/spark/mllib/clustering/DistanceMeasure.scala
##########
@@ -24,16 +24,60 @@ import org.apache.spark.mllib.util.MLUtils
private[spark] abstract class DistanceMeasure extends Serializable {
+ /**
+ * Radii of centers used in triangle inequality to obtain useful bounds to
find
+ * closest centers.
+ *
+ * @see <a
href="https://www.aaai.org/Papers/ICML/2003/ICML03-022.pdf";>Charles Elkan,
+ * Using the Triangle Inequality to Accelerate k-Means</a>
+ *
+ * @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.
+ */
+ def computeRadii(centers: Array[VectorWithNorm]): Array[Double] = {
+ val k = centers.length
+ Array.fill(k)(Double.NaN)
+ }
+
/**
* @return the index of the closest center to the given point, as well as
the cost.
*/
def findClosest(
- centers: TraversableOnce[VectorWithNorm],
+ centers: Array[VectorWithNorm],
+ radii: Array[Double],
point: VectorWithNorm): (Int, Double) = {
var bestDistance = Double.PositiveInfinity
var bestIndex = 0
var i = 0
- centers.foreach { center =>
+ var found = false
+ while (i < centers.length && !found) {
+ val center = centers(i)
+ val d = distance(center, point)
+ val r = radii(i)
+ if (d < r) {
+ bestDistance = d
+ bestIndex = i
+ found = true
Review comment:
Just return here rather than carry a flag around?
----------------------------------------------------------------
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]
