Test generate dataset GroupByTest Spark

gistfile1.txt

import java.util.Random

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.SparkContext._

    var numMappers = 100
    var numKVPairs = 10000
    var valSize = 1000
    var numReducers = 36

    val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p =>
      val ranGen = new Random
      var arr1 = new Array[(Int, Array[Byte])](numKVPairs)
      for (i <- 0 until numKVPairs) {
        val byteArr = new Array[Byte](valSize)
        ranGen.nextBytes(byteArr)
        arr1(i) = (i, byteArr)
      }
      arr1
    }.cache
    // Enforce that everything has been calculated and in cache
  pairs1.count
  pairs1.groupByKey(numReducers).count