// Configure the use of Kryo serialization including our Avro registrator
.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
.set("spark.kryo.registrator", "org.kitesdk.examples.spark.AvroKyroRegistrator");
JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);
JavaPairRDD<StandardEvent, Void> events = sparkContext.newAPIHadoopRDD(conf,
DatasetKeyInputFormat.class, StandardEvent.class, Void.class);
// Map each event to two correlation keys. One with the IP address and the
// nearest 5 minute interval that happened before the event and one with the
// IP address and the nearest 5 minute interval that happened after the event