FindSimilar.scala

def findSimilar(target: String, rdd: RDD[(String, Seq[String])]): RDD[(String, Double, Seq[String])] = {
  val mapped = rdd.map {
    case (author, commits) =>
      val words = commits.flatMap(_.split(" "))
      (author, words)
  }
  countSimilarity(target.split(" "), mapped)
}

private def findSimilar(target: Array[String], rdd: RDD[(String, Seq[String])]): RDD[(String, Double, Seq[String])] = {
  rdd.map {
    case (author, words) =>
      val matching = (for {
        w <- words
        t <- target
        score = scoreSimilarity(t, w)
      } yield (score, w))

      val score = matching.map(_._1).sum
      val wordsMatched = matching.map(_._2)

      (author, score, wordsMatched)
  }.sortBy(_._2, false)
}