| val rdd = sc.parallelize(List(1, 2, 3, 3))
// collect：返回RDD中的所有元素
rdd.collect()
// count：返回RDD中的元素个数
rdd.count()
// countByValue：返回个元素在RDD中出现的次数
rdd.countByValue()
// take：从RDD中返回2个元素
rdd.take(2)
// top：从RDD中返回最前面的2个元素
val x = rdd.top(2)
// takeOrdered：从RDD中按照提供的顺序返回最前面的2个元素
rdd.takeOrdered(2)
object Ord extends Ordering[Int] {
override def compare(x: Int, y: Int): Int = {
if (x < y) 1 else -1;
}
}
val pa = sc.parallelize(Array(1, 2, 3, 4, 5, 6))
pa.takeOrdered(3)(Ord)
// foreach(func)：对RDD中的每个元素使用给定的函数
rdd.foreach(println)
结果：
scala> val rdd = sc.parallelize(List(1, 2, 3, 3))
rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[37] at parallelize at <console>:24
scala> rdd.collect()
res18: Array[Int] = Array(1, 2, 3, 3)
scala> rdd.count()
res19: Long = 4
scala> rdd.countByValue()
res20: scala.collection.Map[Int,Long] = Map(1 -> 1, 2 -> 1, 3 -> 2)
scala> rdd.take(2)
res21: Array[Int] = Array(1, 2)
scala> val x = rdd.top(2)
x: Array[Int] = Array(3, 3)
scala> rdd.takeOrdered(2)
res22: Array[Int] = Array(1, 2)
scala> object Ord extends Ordering[Int] {
| override def compare(x: Int, y: Int): Int = {
| if (x < y) 1 else -1;
| }
| }
defined object Ord
scala> val pa = sc.parallelize(Array(1, 2, 3, 4, 5, 6))
pa: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[43] at parallelize at <console>:24
scala> pa.takeOrdered(3)(Ord)
res23: Array[Int] = Array(6, 5, 4)
scala> rdd.foreach(println)
2
1
3
3
| 