public Generator(ParameterTool pt) {
this.payload = new byte[pt.getInt("payload")];
this.delay = pt.getInt("delay");
this.withFt = pt.has("ft");
this.latFreq = pt.getInt("latencyFreq");
this.sleepFreq = pt.getInt("sleepFreq");
}
public static void main(String[] args) throws Exception {
ParameterTool pt = ParameterTool.fromArgs(args);
int par = pt.getInt("para");
TopologyBuilder builder = new TopologyBuilder();
builder.setSpout("source0", new Generator(pt), pt.getInt("sourceParallelism"));
int i = 0;
for (; i < pt.getInt("repartitions", 1) - 1; i++) {
System.out.println("adding source" + i + " --> source" + (i + 1));
builder
.setBolt("source" + (i + 1), new RepartPassThroughBolt(pt), pt.getInt("sinkParallelism"))
.fieldsGrouping("source" + i, new Fields("id"));
}
System.out.println("adding final source" + i + " --> sink");
builder
.setBolt("sink", new Sink(pt), pt.getInt("sinkParallelism"))
.fieldsGrouping("source" + i, new Fields("id"));
Config conf = new Config();
conf.setDebug(false);
// System.exit(1);
if (!pt.has("local")) {
conf.setNumWorkers(par);
StormSubmitter.submitTopologyWithProgressBar(
"throughput-" + pt.get("name", "no_name"), conf, builder.createTopology());
} else {
conf.setMaxTaskParallelism(par);
LocalCluster cluster = new LocalCluster();
cluster.submitTopology("throughput", conf, builder.createTopology());
Thread.sleep(300000);
cluster.shutdown();
}
}
public static void main(String[] args) throws Exception {
// Checking input parameters
final ParameterTool params = ParameterTool.fromArgs(args);
System.out.println(
"Usage: KMeans --points <path> --centroids <path> --output <path> --iterations <n>");
// set up execution environment
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
env.getConfig()
.setGlobalJobParameters(params); // make parameters available in the web interface
// get input data:
// read the points and centroids from the provided paths or fall back to default data
DataSet<Point> points = getPointDataSet(params, env);
DataSet<Centroid> centroids = getCentroidDataSet(params, env);
// set number of bulk iterations for KMeans algorithm
IterativeDataSet<Centroid> loop = centroids.iterate(params.getInt("iterations", 10));
DataSet<Centroid> newCentroids =
points
// compute closest centroid for each point
.map(new SelectNearestCenter())
.withBroadcastSet(loop, "centroids")
// count and sum point coordinates for each centroid
.map(new CountAppender())
.groupBy(0)
.reduce(new CentroidAccumulator())
// compute new centroids from point counts and coordinate sums
.map(new CentroidAverager());
// feed new centroids back into next iteration
DataSet<Centroid> finalCentroids = loop.closeWith(newCentroids);
DataSet<Tuple2<Integer, Point>> clusteredPoints =
points
// assign points to final clusters
.map(new SelectNearestCenter())
.withBroadcastSet(finalCentroids, "centroids");
// emit result
if (params.has("output")) {
clusteredPoints.writeAsCsv(params.get("output"), "\n", " ");
// since file sinks are lazy, we trigger the execution explicitly
env.execute("KMeans Example");
} else {
System.out.println("Printing result to stdout. Use --output to specify output path.");
clusteredPoints.print();
}
}
public Sink(ParameterTool pt) throws UnknownHostException {
this.pt = pt;
this.withFT = pt.has("ft");
this.logfreq = pt.getInt("logfreq");
this.host = InetAddress.getLocalHost().getHostName();
}
