val a = sc.parallelize(List("dog", "salmon", "salmon", "rat", "elephant"), 3)
val b = a.map(_.length)
val c = a.zip(b)
c.collect
res0: Array[(String, Int)] = Array((dog,3), (salmon,6), (salmon,6), (rat,3), (elephant,8))
val a = sc.parallelize(List("dog", "tiger", "lion", "cat", "panther", "eagle"), 2)
val b = a.map(x => (x.length, x))
b.mapValues("x" + _ + "x").collect
res5: Array[(Int, String)] = Array((3,xdogx), (5,xtigerx), (4,xlionx), (3,xcatx), (7,xpantherx), (5,xeaglex))
2)combineByKey
val a = sc.parallelize(List("dog","cat","gnu","salmon","rabbit","turkey","wolf","bear","bee"), 3)
val b = sc.parallelize(List(1,1,2,2,2,1,2,2,2), 3)
val c = b.zip(a)
val d = c.combineByKey(List(_), (x:List[String], y:String) => y :: x, (x:List[String], y:List[String]) => x ::: y)
d.collect
res16: Array[(Int, List[String])] = Array((1,List(cat, dog, turkey)), (2,List(gnu, rabbit, salmon, bee, bear, wolf)))
3)reduceByKey
val a = sc.parallelize(List("dog", "cat", "owl", "gnu", "ant"), 2)
val b = a.map(x => (x.length, x))
b.reduceByKey(_ + _).collect
res86: Array[(Int, String)] = Array((3,dogcatowlgnuant))
val a = sc.parallelize(List(“dog”, “tiger”, “lion”, “cat”, “panther”, “eagle”), 2) val b = a.map(x => (x.length, x)) b.reduceByKey(_ + _).collect res87: Array[(Int, String)] = Array((4,lion), (3,dogcat), (7,panther), (5,tigereagle))
4)partitionBy
(对RDD进行分区操作)
5)cogroup
val a = sc.parallelize(List(1, 2, 1, 3), 1)
val b = a.map((_, "b"))
val c = a.map((_, "c"))
b.cogroup(c).collect
res7: Array[(Int, (Iterable[String], Iterable[String]))] = Array(
(2,(ArrayBuffer(b),ArrayBuffer(c))),
(3,(ArrayBuffer(b),ArrayBuffer(c))),
(1,(ArrayBuffer(b, b),ArrayBuffer(c, c)))
)
6)join
val a = sc.parallelize(List("dog", "salmon", "salmon", "rat", "elephant"), 3)
val b = a.keyBy(_.length)
val c = sc.parallelize(List("dog","cat","gnu","salmon","rabbit","turkey","wolf","bear","bee"), 3)
val d = c.keyBy(_.length)
b.join(d).collect
val a = sc.parallelize(List("dog", "salmon", "salmon", "rat", "elephant"), 3)
val b = a.keyBy(_.length)
val c = sc.parallelize(List("dog","cat","gnu","salmon","rabbit","turkey","wolf","bear","bee"), 3)
val d = c.keyBy(_.length)
b.leftOuterJoin(d).collect
val a = sc.parallelize(List("dog", "salmon", "salmon", "rat", "elephant"), 3)
val b = a.keyBy(_.length)
val c = sc.parallelize(List("dog","cat","gnu","salmon","rabbit","turkey","wolf","bear","bee"), 3)
val d = c.keyBy(_.length)
b.rightOuterJoin(d).collect
val c = sc.parallelize(List("cat", "dog", "tiger", "lion", "gnu", "crocodile", "ant", "whale", "dolphin", "spider"), 3)
c.foreach(x => println(x + "s are yummy"))
lions are yummy
gnus are yummy
crocodiles are yummy
ants are yummy
whales are yummy
dolphins are yummy
spiders are yummy
2)saveAsTextFile
val a = sc.parallelize(1 to 10000, 3)
a.saveAsTextFile("mydata_a")
14/04/0321:11:36 INFO FileOutputCommitter: Saved output of task 'attempt_201404032111_0000_m_000002_71' to file:/home/cloudera/Documents/spark-0.9.0-incubating-bin-cdh4/bin/mydata_a
val c = sc.parallelize(List("Gnu", "Cat", "Rat", "Dog", "Gnu", "Rat"), 2)
c.collect
res29: Array[String] = Array(Gnu, Cat, Rat, Dog, Gnu, Rat)
5)collectAsMap
val a = sc.parallelize(List(1, 2, 1, 3), 1)
val b = a.zip(a)
b.collectAsMap
res1: scala.collection.Map[Int,Int] = Map(2 -> 2, 1 -> 1, 3 -> 3)
6)reduceByKeyLocally
val a = sc.parallelize(List("dog", "cat", "owl", "gnu", "ant"), 2)
val b = a.map(x => (x.length, x))
b.reduceByKey(_ + _).collect
res86: Array[(Int, String)] = Array((3,dogcatowlgnuant))
7)lookup
val a = sc.parallelize(List("dog", "tiger", "lion", "cat", "panther", "eagle"), 2)
val b = a.map(x => (x.length, x))
b.lookup(5)
res0: Seq[String] = WrappedArray(tiger, eagle)
8)count
val c = sc.parallelize(List("Gnu", "Cat", "Rat", "Dog"), 2)
c.count
res2: Long = 4
9)top
val c = sc.parallelize(Array(6, 9, 4, 7, 5, 8), 2)
c.top(2)
res28: Array[Int] = Array(9, 8)
10)reduce
val a = sc.parallelize(1 to 100, 3)
a.reduce(_ + _)
res41: Int = 5050
11)fold
val a = sc.parallelize(List(1,2,3), 3)
a.fold(0)(_ + _)
res59: Int = 6
12)aggregate
val z = sc.parallelize(List(1,2,3,4,5,6), 2)
// lets first print out the contents of the RDD with partition labels def myfunc(index: Int, iter: Iterator[(Int)]) : Iterator[String] = { iter.toList.map(x => “[partID:” + index + ", val: " + x + “]”).iterator }