Java Code Examples for org.apache.spark.streaming.api.java.JavaReceiverInputDStream#map()
The following examples show how to use
org.apache.spark.streaming.api.java.JavaReceiverInputDStream#map() .
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: StateFulProcessingExample.java From Apache-Spark-2x-for-Java-Developers with MIT License | 4 votes |
public static void main(String[] args) throws InterruptedException { System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils"); SparkSession sparkSession = SparkSession.builder().master("local[*]").appName("Stateful Streaming Example") .config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate(); JavaStreamingContext jssc= new JavaStreamingContext(new JavaSparkContext(sparkSession.sparkContext()), Durations.milliseconds(1000)); JavaReceiverInputDStream<String> inStream = jssc.socketTextStream("10.204.136.223", 9999); jssc.checkpoint("C:\\Users\\sgulati\\spark-checkpoint"); JavaDStream<FlightDetails> flightDetailsStream = inStream.map(x -> { ObjectMapper mapper = new ObjectMapper(); return mapper.readValue(x, FlightDetails.class); }); JavaPairDStream<String, FlightDetails> flightDetailsPairStream = flightDetailsStream .mapToPair(f -> new Tuple2<String, FlightDetails>(f.getFlightId(), f)); Function3<String, Optional<FlightDetails>, State<List<FlightDetails>>, Tuple2<String, Double>> mappingFunc = ( flightId, curFlightDetail, state) -> { List<FlightDetails> details = state.exists() ? state.get() : new ArrayList<>(); boolean isLanded = false; if (curFlightDetail.isPresent()) { details.add(curFlightDetail.get()); if (curFlightDetail.get().isLanded()) { isLanded = true; } } Double avgSpeed = details.stream().mapToDouble(f -> f.getTemperature()).average().orElse(0.0); if (isLanded) { state.remove(); } else { state.update(details); } return new Tuple2<String, Double>(flightId, avgSpeed); }; JavaMapWithStateDStream<String, FlightDetails, List<FlightDetails>, Tuple2<String, Double>> streamWithState = flightDetailsPairStream .mapWithState(StateSpec.function(mappingFunc).timeout(Durations.minutes(5))); streamWithState.print(); jssc.start(); jssc.awaitTermination(); }
Example 2
Source File: StateLessProcessingExample.java From Apache-Spark-2x-for-Java-Developers with MIT License | 3 votes |
public static void main(String[] args) throws InterruptedException { System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils"); SparkSession sparkSession = SparkSession.builder().master("local[*]").appName("stateless Streaming Example") .config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate(); JavaStreamingContext jssc = new JavaStreamingContext(new JavaSparkContext(sparkSession.sparkContext()), Durations.milliseconds(1000)); JavaReceiverInputDStream<String> inStream = jssc.socketTextStream("10.204.136.223", 9999); JavaDStream<FlightDetails> flightDetailsStream = inStream.map(x -> { ObjectMapper mapper = new ObjectMapper(); return mapper.readValue(x, FlightDetails.class); }); //flightDetailsStream.print(); //flightDetailsStream.foreachRDD((VoidFunction<JavaRDD<FlightDetails>>) rdd -> rdd.saveAsTextFile("hdfs://namenode:port/path")); JavaDStream<FlightDetails> window = flightDetailsStream.window(Durations.minutes(5),Durations.minutes(1)); JavaPairDStream<String, Double> transfomedWindow = window.mapToPair(f->new Tuple2<String,Double>(f.getFlightId(),f.getTemperature())). mapValues(t->new Tuple2<Double,Integer>(t,1)) .reduceByKey((t1, t2) -> new Tuple2<Double, Integer>(t1._1()+t2._1(), t1._2()+t2._2())).mapValues(t -> t._1()/t._2()); transfomedWindow.cache(); transfomedWindow.print(); jssc.start(); jssc.awaitTermination(); }