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
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package spark.examples
import java.util.Random
import spark.util.Vector
import spark.SparkContext._
import scala.collection.mutable.HashMap
import scala.collection.mutable.HashSet
/**
* K-means clustering.
*/
object LocalKMeans {
val N = 1000
val R = 1000 // Scaling factor
val D = 10
val K = 10
val convergeDist = 0.001
val rand = new Random(42)
def generateData = {
def generatePoint(i: Int) = {
Vector(D, _ => rand.nextDouble * R)
}
Array.tabulate(N)(generatePoint)
}
def closestPoint(p: Vector, centers: HashMap[Int, Vector]): Int = {
var index = 0
var bestIndex = 0
var closest = Double.PositiveInfinity
for (i <- 1 to centers.size) {
val vCurr = centers.get(i).get
val tempDist = p.squaredDist(vCurr)
if (tempDist < closest) {
closest = tempDist
bestIndex = i
}
}
return bestIndex
}
def main(args: Array[String]) {
val data = generateData
var points = new HashSet[Vector]
var kPoints = new HashMap[Int, Vector]
var tempDist = 1.0
while (points.size < K) {
points.add(data(rand.nextInt(N)))
}
val iter = points.iterator
for (i <- 1 to points.size) {
kPoints.put(i, iter.next())
}
println("Initial centers: " + kPoints)
while(tempDist > convergeDist) {
var closest = data.map (p => (closestPoint(p, kPoints), (p, 1)))
var mappings = closest.groupBy[Int] (x => x._1)
var pointStats = mappings.map(pair => pair._2.reduceLeft [(Int, (Vector, Int))] {case ((id1, (x1, y1)), (id2, (x2, y2))) => (id1, (x1 + x2, y1+y2))})
var newPoints = pointStats.map {mapping => (mapping._1, mapping._2._1/mapping._2._2)}
tempDist = 0.0
for (mapping <- newPoints) {
tempDist += kPoints.get(mapping._1).get.squaredDist(mapping._2)
}
for (newP <- newPoints) {
kPoints.put(newP._1, newP._2)
}
}
println("Final centers: " + kPoints)
}
}
|
