import org.apache.spark.mllib.clustering.dbscan.DBSCAN

object DBSCANSample {

  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("DBSCAN Sample")
    val sc = new SparkContext(conf)

    val data = sc.textFile(src)

    val parsedData = data.map(s => Vectors.dense(s.split(',').map(_.toDouble))).cache()

    log.info(s"EPS: $eps minPoints: $minPoints")

    val model = DBSCAN.train(
      parsedData,
      eps = eps,
      minPoints = minPoints,
      maxPointsPerPartition = maxPointsPerPartition)

    model.labeledPoints.map(p =>  s"${p.x},${p.y},${p.cluster}").saveAsTextFile(dest)

    sc.stop()
  }
}