可以调用RDD上的各种方法：

// set up an example -- an RDD of arrays
val sparkConf = new SparkConf().setMaster("local").setAppName("Example")
val sc = new SparkContext(sparkConf)
val testData = Array(Array(1,2,3), Array(4,5,6,7,8))
val testRDD = sc.parallelize(testData, 2)

// Print the RDD of arrays.
testRDD.collect().foreach(a => println(a.size))

// Use map() to create an RDD with the array sizes.
val countRDD = testRDD.map(a => a.size)

// Print the elements of this new RDD.
countRDD.collect().foreach(a => println(a))

// Use filter() to create an RDD with just the longer arrays.
val bigRDD = testRDD.filter(a => a.size > 3)

// Print each remaining array.
bigRDD.collect().foreach(a => {
    a.foreach(e => print(e + " "))
    println()
  })
}