Reading from S3 returns an inconsistent number of items with Spark 0.9.1

for k in part-0*
do
  echo $k
  awk -F ";" '
    NF != 10000 {
      print "Wrong number of items:",NF
    }

    END {
      if (NR != 1000) {
        print "Wrong number of rows:",NR
      }
    }' "$k"
done

package fi.helsinki.cs.nodes.matrix

import java.util.Random
import org.apache.spark._
import org.apache.spark.SparkContext._
import scala.collection.mutable.ListBuffer
import org.apache.spark.rdd.RDD
import org.apache.spark.storage.StorageLevel._

object GenerateRandomMatrix {
  def NewGeMatrix(rSeed: Int, rdd: RDD[Int], features: Int) = {
    rdd.mapPartitions(part => part.map(xarr => {
        val rdm = new Random(rSeed + xarr)
        val arr = new Array[Double](features)
        for (i <- 0 until features)
          arr(i) = rdm.nextDouble()
        new Row(xarr, arr)
      }))
  }

  case class Row(id: Int, elements: Array[Double]) {}

  def rowFromText(line: String) = {
    val idarr = line.split(" ")
    val arr = idarr(1).split(";")
    // -1 to fix saved matrix indexing error
    new Row(idarr(0).toInt-1, arr.map(_.toDouble))
  }

  def main(args: Array[String]) {
    val master = args(0)
    val tasks = args(1).toInt
    val savePath = args(2)
    val read = args.contains("read")
    
    val datapoints = 1000000
    val features = 10000

    val sc = new SparkContext(master, "RandomMatrix")
    if (read) {
      val randomMatrix: RDD[Row] = sc.textFile(savePath, tasks).map(rowFromText).persist(MEMORY_AND_DISK)
      println("Row item counts: "+ randomMatrix.count)
    } else {
      val rdd = sc.parallelize(0 until datapoints, tasks)
      val bcSeed = sc.broadcast(128)
      /* Generating a matrix of random Doubles */
      val randomMatrix = NewGeMatrix(bcSeed.value, rdd, features).persist(MEMORY_AND_DISK)
      randomMatrix.map(row => row.id + " " + row.elements.mkString(";")).saveAsTextFile(savePath)
    }
    
    sc.stop
  }
}