change Mahout to breeze in doc

use a simple lower bound to avoid unnecessary distance computation
apache · Mar 18, 2014 · 07c3cf2 · 07c3cf2
1 parent 6f5cdde
commit 07c3cf2
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 5 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -427,10 +427,16 @@ object KMeans {
     var bestIndex = 0
     var i = 0
     centers.foreach { center =>
-      val distance: Double = fastSquaredDistance(center, point)
-      if (distance < bestDistance) {
-        bestDistance = distance
-        bestIndex = i
+      // Since `\|a - b\| \geq |\|a\| - \|b\||`, we can use this lower bound to avoid unnecessary
+      // distance computation.
+      var lowerBoundOfSqDist = math.sqrt(center.squaredNorm) - math.sqrt(point.squaredNorm)
+      lowerBoundOfSqDist = lowerBoundOfSqDist * lowerBoundOfSqDist
+      if (lowerBoundOfSqDist < bestDistance) {
+        val distance: Double = fastSquaredDistance(center, point)
+        if (distance < bestDistance) {
+          bestDistance = distance
+          bestIndex = i
+        }
       }
       i += 1
     }

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
@@ -31,7 +31,7 @@ trait Vector extends Serializable {
   def size: Int
 
   /**
-   * Converts the instance to a Mahout vector wrapper.
+   * Converts the instance to a breeze vector.
    */
   private[mllib] def toBreeze: BreezeVector[Double]
 }