ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Uniform whitespace across scala examples

Browse source
This commit is contained in:
Andrew Ash 2013-04-09 23:35:13 -04:00
parent adba773fab
commit f1d8871ca1
4 changed files with 72 additions and 72 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

130
examples/src/main/scala/spark/examples/LocalKMeans.scala
View file

@ -10,73 +10,73 @@ 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
}
val N = 1000
val R = 1000 // Scaling factor
val D = 10
val K = 10
val convergeDist = 0.001
val rand = new Random(42)
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())
}
def generateData = {
def generatePoint(i: Int) = {
Vector(D, _ => rand.nextDouble * R)
}
Array.tabulate(N)(generatePoint)
}
println("Initial centers: " + kPoints)
def closestPoint(p: Vector, centers: HashMap[Int, Vector]): Int = {
var index = 0
var bestIndex = 0
var closest = Double.PositiveInfinity
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)
}
}
for (i <- 1 to centers.size) {
val vCurr = centers.get(i).get
val tempDist = p.squaredDist(vCurr)
if (tempDist < closest) {
closest = tempDist
bestIndex = i
}
}
println("Final centers: " + kPoints)
}
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)
}
}

6
examples/src/main/scala/spark/examples/MultiBroadcastTest.scala
View file

@ -8,7 +8,7 @@ object MultiBroadcastTest {
System.err.println("Usage: BroadcastTest <master> [<slices>] [numElem]")
System.exit(1)
}
val sc = new SparkContext(args(0), "Broadcast Test",
System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))
@ -19,7 +19,7 @@ object MultiBroadcastTest {
for (i <- 0 until arr1.length) {
arr1(i) = i
}
var arr2 = new Array[Int](num)
for (i <- 0 until arr2.length) {
arr2(i) = i
@ -30,7 +30,7 @@ object MultiBroadcastTest {
sc.parallelize(1 to 10, slices).foreach {
i => println(barr1.value.size + barr2.value.size)
}
System.exit(0)
}
}

4
examples/src/main/scala/spark/examples/SimpleSkewedGroupByTest.scala
View file

@ -11,7 +11,7 @@ object SimpleSkewedGroupByTest {
"[numMappers] [numKVPairs] [valSize] [numReducers] [ratio]")
System.exit(1)
}
var numMappers = if (args.length > 1) args(1).toInt else 2
var numKVPairs = if (args.length > 2) args(2).toInt else 1000
var valSize = if (args.length > 3) args(3).toInt else 1000
@ -20,7 +20,7 @@ object SimpleSkewedGroupByTest {
val sc = new SparkContext(args(0), "GroupBy Test",
System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))
val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p =>
val ranGen = new Random
var result = new Array[(Int, Array[Byte])](numKVPairs)

4
examples/src/main/scala/spark/examples/SkewedGroupByTest.scala
View file

@ -10,7 +10,7 @@ object SkewedGroupByTest {
System.err.println("Usage: GroupByTest <master> [numMappers] [numKVPairs] [KeySize] [numReducers]")
System.exit(1)
}
var numMappers = if (args.length > 1) args(1).toInt else 2
var numKVPairs = if (args.length > 2) args(2).toInt else 1000
var valSize = if (args.length > 3) args(3).toInt else 1000
@ -18,7 +18,7 @@ object SkewedGroupByTest {
val sc = new SparkContext(args(0), "GroupBy Test",
System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")))
val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p =>
val ranGen = new Random