问Apache火花中所有对点之间的距离

EN

JavaRDD<String> input = sc.textFile("/path/to/your/file");

// map each line to pairs of Double, representing the points
JavaPairRDD<Double, Double> points = input.mapToPair(
      new PairFunction<String, Double, Double>() {
          public Tuple2<Double, Double> call(String s) throws Exception {
              String[] parts = s.split(" +");
              return new Tuple2<>(
                      Double.parseDouble(parts[0]),
                      Double.parseDouble(parts[1]));
          }
      }
);

// then, get the cartesian product of the point set, and map
// each resulting pair of points to the distance between them
JavaDoubleRDD distances = points.cartesian(points).mapToDouble(new DoubleFunction<Tuple2<Tuple2<Double, Double>, Tuple2<Double, Double>>>() {
  public double call(Tuple2<Tuple2<Double, Double>, Tuple2<Double, Double>> pointPair) throws Exception {
      Double lat1 = pointPair._1()._1();
      Double lon1 = pointPair._1()._2();
      Double lat2 = pointPair._2()._1();
      Double lon2 = pointPair._2()._2();
      return dist(lat1, lon1, lat2, lon2); // omitted for clarity
  }
});

// then, do something with your distances
distances.foreach(new VoidFunction<Double>() {
  public void call(Double aDouble) throws Exception {
      System.out.println("D: " + aDouble);
  }
});