今天，这个是spark的高级算子的讲解的最后一个章节，今天我们来介绍几个简单的算子，
countByKey
val rdd1 = sc.parallelize(List(("a", 1), ("b", 2), ("b", 2), ("c", 2), ("c", 1)))
rdd1.countByKey
rdd1.countByValue
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
filterByRange
val rdd1 = sc.parallelize(List(("e", 5), ("c", 3), ("d", 4), ("c", 2), ("a", 1)))
val rdd2 = rdd1.filterByRange("b", "d")
rdd2.collect
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
flatMapValues : Array((a,1), (a,2), (b,3), (b,4))
val rdd3 = sc.parallelize(List(("a", "1 2"), ("b", "3 4")))
val rdd4 = rdd3.flatMapValues(_.split(" "))
rdd4.collect
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
foldByKey
val rdd1 = sc.parallelize(List("dog", "wolf", "cat", "bear"), 2)
val rdd2 = rdd1.map(x => (x.length, x))
val rdd3 = rdd2.foldByKey("")(_+_)
val rdd = sc.textFile("hdfs://node-1.itcast.cn:9000/wc").flatMap(_.split(" ")).map((_, 1))
rdd.foldByKey(0)(_+_)
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
foreachPartition
val rdd1 = sc.parallelize(List(1, 2, 3, 4, 5, 6, 7, 8, 9), 3)
rdd1.foreachPartition(x => println(x.reduce(_ + _)))
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
keyBy : 以传入的参数做key
val rdd1 = sc.parallelize(List("dog", "salmon", "salmon", "rat", "elephant"), 3)
val rdd2 = rdd1.keyBy(_.length)
rdd2.collect
-------------------------------------------------------------------------------------------
-------------------------------------------------------------------------------------------
keys values
val rdd1 = sc.parallelize(List("dog", "tiger", "lion", "cat", "panther", "eagle"), 2)
val rdd2 = rdd1.map(x => (x.length, x))
rdd2.keys.collect
rdd2.values.collect