Created
March 4, 2014 17:43
-
-
Save MishaelRosenthal/9351719 to your computer and use it in GitHub Desktop.
A Scala implementation and testing of incremental mean and variance calculation. Also includes a pimp my library implementation for general Iterable collection.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.liveperson.predictivedialer.common.utils | |
/** | |
* Created with IntelliJ IDEA. | |
* User: mishaelr | |
* Date: 3/4/14 | |
* Time: 7:18 PM | |
* | |
* This object contains static methods that can be used for calculating mean in variance incrementally. | |
* Based on the following: | |
* http://nfs-uxsup.csx.cam.ac.uk/~fanf2/hermes/doc/antiforgery/stats.pdf | |
*/ | |
object IncrementalStatistics { | |
/** | |
* @param index Note: index starts from one, not from zero! | |
* Namely, the index for the first element should be 1. | |
*/ | |
case class MeanTuple(mean: Double, index: Int) | |
case class VarianceTuple(meanTuple: MeanTuple, sum: Double) | |
/** | |
* Initial meanTuple value should be: | |
* MeanTuple(0.0, 0) | |
*/ | |
def updateMean(meanTuple: MeanTuple, newValue: Double) = { | |
import meanTuple._ | |
MeanTuple(mean + (1.0/(index+1)) * (newValue - mean), index+1) | |
} | |
/** | |
* Initial varianceTuple should be: | |
* VarianceTuple(MeanTuple(0.0, 0), 0.0) | |
*/ | |
def updateVarianceTuple(varianceTuple: VarianceTuple, newValue: Double) = { | |
import varianceTuple._ | |
val newMean = updateMean(meanTuple, newValue) | |
val newS = sum + (newValue - meanTuple.mean) * (newValue - newMean.mean) | |
VarianceTuple(newMean, newS) | |
} | |
/** | |
* Calculates the variance from the tuple. | |
*/ | |
def getVarianceFromTuple(varianceTuple: VarianceTuple) = { | |
varianceTuple.sum / varianceTuple.meanTuple.index | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.liveperson.predictivedialer.common.utils | |
/** | |
* Created with IntelliJ IDEA. | |
* User: mishaelr | |
* Date: 1/16/14 | |
* Time: 3:12 PM | |
*/ | |
object IterableWithStatistics { | |
import IncrementalStatistics._ | |
implicit class RichIterable[+A](collection: Iterable[A]){ | |
def mean[B >: A](implicit num: Numeric[B]) = { | |
if(collection.isEmpty) { | |
0.0 | |
} else { | |
val meanTuple = collection.foldLeft(MeanTuple(0.0, 0)){case (mean, x) => updateMean(mean, num.toDouble(x))} | |
meanTuple.mean | |
} | |
} | |
def variance[B >: A](implicit num: Numeric[B]) = { | |
if(collection.isEmpty) { | |
0.0 | |
} else { | |
getVarianceFromTuple { | |
collection.foldLeft(VarianceTuple(MeanTuple(0.0, 0), 0.0)){ case (tuple, x) => updateVarianceTuple(tuple, num.toDouble(x))} | |
} | |
} | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.liveperson.predictivedialer.common.utils | |
import org.scalatest.junit.JUnitRunner | |
import org.scalatest.prop.Checkers | |
import org.scalacheck.Prop._ | |
import org.scalacheck.{Prop, Gen} | |
import org.junit.runner.RunWith | |
import org.scalatest.{Matchers, FunSuite} | |
import com.liveperson.predictivedialer.common.utils.IterableWithStatistics._ | |
/** | |
* Created with IntelliJ IDEA. | |
* User: mishaelr | |
* Date: 2/2/14 | |
* Time: 11:07 AM | |
* | |
* Error tolerance of 0.001%. | |
*/ | |
@RunWith(classOf[JUnitRunner]) | |
class IterableWithStatisticsTest extends FunSuite with Checkers with Matchers{ | |
val smallDouble = Gen.chooseNum(-1000.0, 1000.0) | |
test("mean") { | |
check { | |
Prop.forAll(Gen.containerOf[List,Double](smallDouble)){ | |
(list: List[Double]) => | |
if(list.isEmpty || list.sum / list.size == 0) { | |
0.0 === list.mean | |
} else { | |
val expected = list.sum / list.size | |
val actual = list.mean | |
expected === actual +- (0.00001 * math.abs(expected)) | |
} | |
} | |
} | |
} | |
test("variance") { | |
check { | |
Prop.forAll(Gen.containerOf[List,Double](smallDouble)){ | |
(list: List[Double]) => | |
if(list.isEmpty || list.map{x => math.pow(x-list.mean, 2)}.mean == 0) { | |
0.0 === list.variance | |
} else { | |
val expected = list.map{x => math.pow(x-list.mean, 2)}.mean | |
val actual = list.variance | |
actual === (expected +- 0.00001 * expected) | |
} | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment