val name = sc.textFile("spark5/EmployeeName.csv")
val namePairRDD = name.map(x => (x.split(",")(0), x.split(",")(1)))

val salary = sc.textFile("spark5/EmployeeSalary.csv")
val salaryPairRDD = salary.map(x => (x.split(",")(0), x.split(",")(1)))

val joined = namePairRDD.join(salaryPairRDD)
val keyRemoved = joined.values
val swapped = keyRemoved.map(_.swap)

val groupByKey = swapped.groupByKey().collect()

val rddByKey = groupByKey.map {
	case (k, v) => k -> sc.makeRDD(v.toSeq)
}

rddByKey.foreach { case (k, rdd) => rdd.saveAsTextFile("spark5/Employee" + k) }