def sparkWithAlgebird()

in src/main/scala/com/spotify/bdrc/pipeline/TopItems.scala [101:112]

• 10 lines of code
• 1 McCabe index (conditional complexity)

  def sparkWithAlgebird(input: RDD[Rating]): Seq[(String, Double)] = {
    import com.twitter.algebird.Aggregator.sortedReverseTake
    import com.twitter.algebird.spark._
    val aggregator = sortedReverseTake[(String, Double)](topK)(Ordering.by(_._2))
    input
      .map(x => (x.item, x.score))
      // Sum values with addition
      .reduceByKey(_ + _)
      .algebird
      // `aggregate` is an action and collects data back to the driver node
      .aggregate(aggregator)
  }