Skip to content

Pzheng/gaussian euclidean #448

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Jun 9, 2015
Merged

Pzheng/gaussian euclidean #448

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8983c1a
add distribution folder
Jun 2, 2015
5338799
add implementation and tests
Jun 2, 2015
640f0bc
move those to stats package
Jun 2, 2015
e02d29b
get ./sbt test working
Jun 2, 2015
0466c53
respond to comments
Jun 3, 2015
ec9a55b
add sample and stddev
Jun 4, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 48 additions & 0 deletions ...bird-core/src/main/scala/com/twitter/algebird/statistics/GaussianDistributionMonoid.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
package com.twitter.algebird.statistics

import com.twitter.algebird.Monoid

/**
* @mean - Mean
* @sigma2 - Variance, where sqrt(sigma2) is the standard deviation
* aka Normal distribution
*/
case class GaussianDistribution(mean: Double, sigma2: Double) {
def stddev: Double = math.sqrt(sigma2)

def sample(r: java.util.Random): Double =
mean + r.nextGaussian() * stddev
}

object GaussianDistribution {
implicit val monoid: Monoid[GaussianDistribution] = GaussianDistributionMonoid
}

/**
* This monoid stems from the fact that if X and Y are independent random variables
* that are normally distributed, then their sum is also
* normally distributed, with its new mean equal to the sum of two means
* and variance equal to the sum of two variances.
* http://en.wikipedia.org/wiki/Sum_of_normally_distributed_random_variables
*/
object GaussianDistributionMonoid extends Monoid[GaussianDistribution] {
override def zero = new GaussianDistribution(0, 0)

override def plus(left: GaussianDistribution, right: GaussianDistribution): GaussianDistribution =
new GaussianDistribution(left.mean + right.mean, left.sigma2 + right.sigma2)

override def sumOption(its: TraversableOnce[GaussianDistribution]): Option[GaussianDistribution] =
if (its.isEmpty)
None
else {
var mean = 0.0
var sigma2 = 0.0
val it = its.toIterator
while (it.hasNext) {
val g = it.next
mean += g.mean
sigma2 += g.sigma2
}
Some(GaussianDistribution(mean, sigma2))
}
}
20 changes: 20 additions & 0 deletions ...test/src/test/scala/com/twitter/algebird/statistics/GaussianDistributionMonoidTests.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
package com.twitter.algebird.statistics

import com.twitter.algebird.CheckProperties
import org.scalacheck.{ Arbitrary, Gen }
import org.scalatest._

class GaussianDistributionMonoidTests extends CheckProperties {
import com.twitter.algebird.BaseProperties._

implicit val gaussianGenerators = Arbitrary {
for (
mean <- Gen.choose(0, 10000);
sigma <- Gen.choose(0, 10000)
) yield (GaussianDistribution(mean, sigma))
}

property("GaussianDistributionMonoid is a Monoid") {
monoidLaws[GaussianDistribution]
}
}