kjsingh

import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.generic.GenericData.Array;
import org.apache.avro.generic.GenericData.EnumSymbol;
import org.apache.avro.generic.GenericData.Fixed;
import org.apache.avro.file.DataFileWriter;
import org.apache.avro.io.DatumWriter;
import org.apache.avro.io.EncoderFactory;
import org.apache.avro.io.JsonEncoder;

kjsingh

val rdd = sc.parallelize(1 to 100)
//rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[0] at parallelize at <console>:24

var max = 3
//max: Int = 3

var multiRdds:List[org.apache.spark.rdd.RDD[Int]] = Nil
//multiRdds: List[org.apache.spark.rdd.RDD[Int]] = List()

for(i <- 0 until max) {multiRdds = rdd.zipWithIndex.filter(_._2 % max == i).map(_._1)::multiRdds}