def scioWithAlgebird()

in src/main/scala/com/spotify/bdrc/pipeline/TopItems.scala [77:88]


  def scioWithAlgebird(input: SCollection[Rating]): SCollection[(String, Double)] = {
    import com.twitter.algebird.Aggregator.sortedReverseTake
    val aggregator = sortedReverseTake[(String, Double)](topK)(Ordering.by(_._2))
    input
      .map(x => (x.item, x.score))
      // Sum values with an implicit `Semigroup[Double]`
      .sumByKey
      // Aggregate globally into a single `Seq[(String, Double)]`
      .aggregate(aggregator)
      // Flatten result `Seq[(String, Double)]`
      .flatten
  }