RDD Sample

gistfile1.scala

val num = 1 to 100
//num: scala.collection.immutable.Range.Inclusive = Range(1,2,3,...,100)

val numRDD = sc.parallelize(num)
//numRDD: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[11] at parallelize at <console>:14

val numFileter = numRDD.filter(_ < 10)
//numFileter: org.apache.spark.rdd.RDD[Int] = FilteredRDD[12] at filter at <console>:16

val numMap = numFileter.map(_ + 10)
//numMap: org.apache.spark.rdd.RDD[Int] = MappedRDD[13] at map at <console>:18

val numSum = numMap.reduce(_ + _)
//numSum: Int = 135