Code from Part 1 of Spark Transformations in Scala

Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /___/ .__/\_,_/_/ /_/\_\   version 1.1.0
      /_/

Using Scala version 2.10.4 (Java HotSpot(TM) 64-Bit Server VM, Java 1.6.0_65)
Type in expressions to have them evaluated.
Type :help for more information.
2015-12-10 11:06:08.048 java[89392:1203] Unable to load realm info from SCDynamicStore
15/12/10 11:06:08 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Spark context available as sc.

scala> val babyNames = sc.textFile("baby_names.csv")
babyNames: org.apache.spark.rdd.RDD[String] = baby_names.csv MappedRDD[1] at textFile at <console>:12

scala> val rows = babyNames.map(line => line.split(","))
rows: org.apache.spark.rdd.RDD[Array[String]] = MappedRDD[2] at map at <console>:14

scala> sc.parallelize(List(1,2,3)).flatMap(x=>List(x,x,x)).collect 
res0: Array[Int] = Array(1, 1, 1, 2, 2, 2, 3, 3, 3)

scala> sc.parallelize(List(1,2,3)).map(x=>List(x,x,x)).collect
res1: Array[List[Int]] = Array(List(1, 1, 1), List(2, 2, 2), List(3, 3, 3))

scala> 

scala> sc.parallelize(List(1,2,3)).flatMap(x=>List(x,x,x))
res2: org.apache.spark.rdd.RDD[Int] = FlatMappedRDD[8] at flatMap at <console>:13

scala> sc.parallelize(List(1,2,3)).map(x=>List(x,x,x))
res3: org.apache.spark.rdd.RDD[List[Int]] = MappedRDD[10] at map at <console>:13

scala> val davidRows = rows.filter(row => row(1).contains("DAVID"))
davidRows: org.apache.spark.rdd.RDD[Array[String]] = FilteredRDD[11] at filter at <console>:16

scala> val parallel = sc.parallelize(1 to 9, 3)
parallel: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[12] at parallelize at <console>:12

scala> parallel.mapPartitions( x => List(x.next).iterator).collect
res4: Array[Int] = Array(1, 4, 7)

scala> val parallel = sc.parallelize(1 to 9)
parallel: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[14] at parallelize at <console>:12

scala> parallel.mapPartitions( x => List(x.next).iterator).collect
res5: Array[Int] = Array(1, 2, 3, 4, 5, 6, 7, 8)

scala> parallel.mapPartitionsWithIndex( (index: Int, it: Iterator[Int]) => it.toList.map(x => index + ", "+x).iterator).collect
res6: Array[String] = Array(0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 7, 9)

scala> val parallel = sc.parallelize(1 to 9, 3)
parallel: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[17] at parallelize at <console>:12

scala> parallel.mapPartitionsWithIndex( (index: Int, it: Iterator[Int]) => it.toList.map(x => index + ", "+x).iterator).collect
res7: Array[String] = Array(0, 1, 0, 2, 0, 3, 1, 4, 1, 5, 1, 6, 2, 7, 2, 8, 2, 9)

scala> val parallel = sc.parallelize(1 to 9)
parallel: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[19] at parallelize at <console>:12

scala> parallel.sample(true,.2).count 
res8: Long = 2

scala> parallel.sample(true,.2).count 
res9: Long = 2

scala> parallel.sample(true,.2).count 
res10: Long = 2

scala> parallel.sample(true,.2).count 
res11: Long = 3

scala> parallel.sample(true,.2).count 
res12: Long = 2

scala> parallel.sample(true,.2).count 
res13: Long = 0

scala> parallel.sample(true,.1) 
res14: org.apache.spark.rdd.RDD[Int] = PartitionwiseSampledRDD[26] at sample at <console>:15