Ich verwende spark, um den PageRank von Nutzerbewertungen zu berechnen, erhalte aber weiterhin Spark java.lang.StackOverflowError, wenn ich meinen Code auf einem großen Datensatz (40.000 Einträge) ausführe. Wenn Sie den Code für eine kleine Anzahl von Einträgen ausführen, funktioniert er jedoch einwandfrei.

Entry Beispiel,:

product/productId: B00004CK40   review/userId: A39IIHQF18YGZA   review/profileName: C. A. M. Salas  review/helpfulness: 0/0 review/score: 4.0   review/time: 1175817600 review/summary: Reliable comedy review/text: Nice script, well acted comedy, and a young Nicolette Sheridan. Cusak is in top form.

Der Code

public void calculatePageRank() {
    sc.clearCallSite();
    sc.clearJobGroup();

    JavaRDD < String > rddFileData = sc.textFile(inputFileName).cache();
    sc.setCheckpointDir("pagerankCheckpoint/");

    JavaRDD < String > rddMovieData = rddFileData.map(new Function < String, String > () {

        @Override
        public String call(String arg0) throws Exception {
            String[] data = arg0.split("\t");
            String movieId = data[0].split(":")[1].trim();
            String userId = data[1].split(":")[1].trim();
            return movieId + "\t" + userId;
        }
    });

    JavaPairRDD<String, Iterable<String>> rddPairReviewData = rddMovieData.mapToPair(new PairFunction < String, String, String > () {

        @Override
        public Tuple2 < String, String > call(String arg0) throws Exception {
            String[] data = arg0.split("\t");
            return new Tuple2 < String, String > (data[0], data[1]);
        }
    }).groupByKey().cache();


    JavaRDD<Iterable<String>> cartUsers = rddPairReviewData.map(f -> f._2());
      List<Iterable<String>> cartUsersList = cartUsers.collect();
      JavaPairRDD<String,String> finalCartesian = null;
      int iterCounter = 0;
      for(Iterable<String> out : cartUsersList){
          JavaRDD<String> currentUsersRDD = sc.parallelize(Lists.newArrayList(out));
          if(finalCartesian==null){
              finalCartesian = currentUsersRDD.cartesian(currentUsersRDD);
          }
          else{
              finalCartesian = currentUsersRDD.cartesian(currentUsersRDD).union(finalCartesian);
              if(iterCounter % 20 == 0) {
                  finalCartesian.checkpoint();
              }
          }
      }
      JavaRDD<Tuple2<String,String>> finalCartesianToTuple = finalCartesian.map(m -> new Tuple2<String,String>(m._1(),m._2()));

      finalCartesianToTuple = finalCartesianToTuple.filter(x -> x._1().compareTo(x._2())!=0);
      JavaPairRDD<String, String> userIdPairs = finalCartesianToTuple.mapToPair(m -> new Tuple2<String,String>(m._1(),m._2()));

      JavaRDD<String> userIdPairsString = userIdPairs.map(new Function < Tuple2<String, String>, String > () {

        //Tuple2<Tuple2<MovieId, userId>, Tuple2<movieId, userId>>
          @Override
          public String call (Tuple2<String, String> t) throws Exception {
            return t._1 + " " + t._2;
          }
      });

    try {

//calculate pagerank using this https://github.com/apache/spark/blob/master/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java
        JavaPageRank.calculatePageRank(userIdPairsString, 100);
    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }

    sc.close();

}