1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
package spark.examples
import java.util.Random
import spark.SparkContext
import spark.util.Vector
import spark.SparkContext._
import scala.collection.mutable.HashMap
import scala.collection.mutable.HashSet
/**
* K-means clustering.
*/
object SparkKMeans {
val R = 1000 // Scaling factor
val rand = new Random(42)
def parseVector(line: String): Vector = {
return new Vector(line.split(' ').map(_.toDouble))
}
def closestPoint(p: Vector, centers: Array[Vector]): Int = {
var index = 0
var bestIndex = 0
var closest = Double.PositiveInfinity
for (i <- 0 until centers.length) {
val tempDist = p.squaredDist(centers(i))
if (tempDist < closest) {
closest = tempDist
bestIndex = i
}
}
return bestIndex
}
def main(args: Array[String]) {
if (args.length < 4) {
System.err.println("Usage: SparkLocalKMeans <master> <file> <k> <convergeDist>")
System.exit(1)
}
val sc = new SparkContext(args(0), "SparkLocalKMeans",
System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))
val lines = sc.textFile(args(1))
val data = lines.map(parseVector _).cache()
val K = args(2).toInt
val convergeDist = args(3).toDouble
var kPoints = data.takeSample(false, K, 42).toArray
var tempDist = 1.0
while(tempDist > convergeDist) {
var closest = data.map (p => (closestPoint(p, kPoints), (p, 1)))
var pointStats = closest.reduceByKey{case ((x1, y1), (x2, y2)) => (x1 + x2, y1 + y2)}
var newPoints = pointStats.map {pair => (pair._1, pair._2._1 / pair._2._2)}.collectAsMap()
tempDist = 0.0
for (i <- 0 until K) {
tempDist += kPoints(i).squaredDist(newPoints(i))
}
for (newP <- newPoints) {
kPoints(newP._1) = newP._2
}
println("Finished iteration (delta = " + tempDist + ")")
}
println("Final centers:")
kPoints.foreach(println)
System.exit(0)
}
}
|
