val file = sc.textFile("/tmp/zk_test/algoAcceleration/DBSCAN/farm.ds") file.take(10).foreach(println(_)) file.count val data = file.map(x => x.split(" ")).filter(_.length == 6).map(x => x.slice(1, 6).mkString(" ")) data.take(10).foreach(println(_)) data.count data.repartition(1).saveAsTextFile("/tmp/zk_test/algoAcceleration/DBSCAN/farm") val file = sc.textFile("/tmp/zk_test/algoAcceleration/DBSCAN/house.ds") file.take(10).foreach(println(_)) file.count val data = file.map(x => x.split(" ")).filter(_.length == 8).map(x => x.slice(1, 8).mkString(" ")) data.count data.take(10).foreach(println(_)) data.repartition(1).saveAsTextFile("/tmp/zk_test/algoAcceleration/DBSCAN/house")