Spark常见算子汇总_代码007(未授权)

调用SparkCon text.textFile()方法，从外部存储中读取数据来创建 RDD

调用SparkCon text 的 parallelize()方法，将一个存在的集合，变成一个RDD

/** Distribute a local Scala collection to form an RDD.
   *
   * This method is identical to `parallelize`.
   */
  def makeRDD[T: ClassTag](
      seq: Seq[T],
      numSlices: Int = defaultParallelism): RDD[T] = withScope {
    parallelize(seq, numSlices)
  }

方法二：分配一个本地Scala集合形成一个RDD，为每个集合对象创建一个最佳分区。

/**
   * Distribute a local Scala collection to form an RDD, with one or more
   * location preferences (hostnames of Spark nodes) for each object.
   * Create a new partition for each collection item.
   */
  def makeRDD[T: ClassTag](seq: Seq[(T, Seq[String])]): RDD[T] = withScope {
    assertNotStopped()
    val indexToPrefs = seq.zipWithIndex.map(t => (t._2, t._1._2)).toMap
    new ParallelCollectionRDD[T](this, seq.map(_._1), math.max(seq.size, 1), indexToPrefs)
  }

scala> val rdd = sc.parallelize(1 to 6, 2)
val rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[2] at parallelize at <console>:1

scala> rdd.collect()
val res4: Array[Int] = Array(1, 2, 3, 4, 5, 6)




scala> val seq = List(("American Person", List("Tom", "Jim")), ("China Person", List("LiLei", "HanMeiMei")), ("Color Type", List("Red", "Blue")))
val seq: List[(String, List[String])] = List((American Person,List(Tom, Jim)), (China Person,List(LiLei, HanMeiMei)), (Color Type,List(Red, Blue)))

scala> val rdd2 = sc.makeRDD(seq)
val rdd2: org.apache.spark.rdd.RDD[String] = ParallelCollectionRDD[0] at makeRDD at <console>:1

scala> rdd2.partitions.size
val res0: Int = 3

scala> rdd2.foreach(println)
American Person
Color Type
China Person

scala> val rdd1 = sc.parallelize(seq)
val rdd1: org.apache.spark.rdd.RDD[(String, List[String])] = ParallelCollectionRDD[1] at parallelize at <console>:1

scala> rdd1.partitions.size
val res1: Int = 2

scala> rdd2.collect()
val res2: Array[String] = Array(American Person, China Person, Color Type)

scala> rdd1.collect()
val res3: Array[(String, List[String])] = Array((American Person,List(Tom, Jim)), (China Person,List(LiLei, HanMeiMei)), (Color Type,List(Red, Blue)))




scala> var lines = sc.textFile("/root/tmp/a.txt",3)
var lines: org.apache.spark.rdd.RDD[String] = /root/tmp/a.txt MapPartitionsRDD[4] at textFile at <console>:1

scala> lines.collect()
val res6: Array[String] = Array(a,b,c)

scala> lines.partitions.size
val res7: Int = 3

flatMap

scala> var lines = sc.textFile("/root/tmp/a.txt",3)
var lines: org.apache.spark.rdd.RDD[String] = /root/tmp/a.txt MapPartitionsRDD[13] at textFile at <console>:1

scala> lines.flatMap(x=>x.split(",")).map(x=>(x,1)).reduceByKey((a,b)=>a+b).foreach(println)
(c,2)
(b,1)
(d,1)
(a,2)


scala> lines.collect()
val res27: Array[String] = Array(a,b,c, c, a,d)

scala> lines.map(_.split(",")).collect()
val res25: Array[Array[String]] = Array(Array(a, b, c), Array(c), Array(a, d))

scala> lines.flatMap(_.split(",")).collect()
val res26: Array[String] = Array(a, b, c, c, a, d)