summary statistics

scala.scala

case class MeasureUnit(name: String, value: Double)

val measureSeq = Seq(MeasureUnit("metric1", 0.04), MeasureUnit("metric1", 0.09),
  MeasureUnit("metric2", 0.64), MeasureUnit("metric2", 0.34), MeasureUnit("metric2", 0.84))

type Name = String

// "metric1" -> Seq(0.04, 0.09), "metric2" -> Seq(0.64, 0.34, 0.84)
val groupedMeasures: Map[Name, Seq[Double]] =
  measureSeq
    .groupBy(_.name)
    .mapValues(_ map (_.value))


type Mean = Double

def mean[T](item: Traversable[T])(implicit n: Numeric[T]) = {
  n.toDouble(item.sum) / item.size.toDouble
}

def variance[T](items: Traversable[T])(implicit n: Numeric[T]): Double = {
  val itemMean = mean(items)
  val count = items.size
  val sumOfSquares = items.foldLeft(0.0d)((total, item) => {
    val itemDbl = n.toDouble(item)
    val square = math.pow(itemDbl - itemMean, 2)
    total + square
  })
  sumOfSquares / count.toDouble
}

val meanMapping: Map[Name, Mean] = groupedMeasures mapValues mean

type Variance = Double

val varianceMapping: Map[Name, Variance] = groupedMeasures mapValues variance

type Summary = Tuple2[Mean, Variance]

val summaryMapping: Map[Name, Summary] =
  groupedMeasures mapValues { s => (mean(s), variance(s)) }