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();
}
}
private static DataSet<Tuple3<Integer, String, Integer>> getRanksDataSet(
ExecutionEnvironment env, ParameterTool params) {
// Create DataSet for ranks relation (Rank, URL, Avg-Visit-Duration)
if (params.has("ranks")) {
return env.readCsvFile(params.get("ranks"))
.fieldDelimiter("|")
.types(Integer.class, String.class, Integer.class);
} else {
System.out.println("Executing WebLogAnalysis example with default ranks data set.");
System.out.println("Use --ranks to specify file input.");
return WebLogData.getRankDataSet(env);
}
}
private static DataSet<Tuple2<String, String>> getDocumentsDataSet(
ExecutionEnvironment env, ParameterTool params) {
// Create DataSet for documents relation (URL, Doc-Text)
if (params.has("documents")) {
return env.readCsvFile(params.get("documents"))
.fieldDelimiter("|")
.types(String.class, String.class);
} else {
System.out.println("Executing WebLogAnalysis example with default documents data set.");
System.out.println("Use --documents to specify file input.");
return WebLogData.getDocumentDataSet(env);
}
}
private static DataSet<Point> getPointDataSet(ParameterTool params, ExecutionEnvironment env) {
DataSet<Point> points;
if (params.has("points")) {
// read points from CSV file
points =
env.readCsvFile(params.get("points")).fieldDelimiter(" ").pojoType(Point.class, "x", "y");
} else {
System.out.println("Executing K-Means example with default point data set.");
System.out.println("Use --points to specify file input.");
points = KMeansData.getDefaultPointDataSet(env);
}
return points;
}
private static DataSet<Centroid> getCentroidDataSet(
ParameterTool params, ExecutionEnvironment env) {
DataSet<Centroid> centroids;
if (params.has("centroids")) {
centroids =
env.readCsvFile(params.get("centroids"))
.fieldDelimiter(" ")
.pojoType(Centroid.class, "id", "x", "y");
} else {
System.out.println("Executing K-Means example with default centroid data set.");
System.out.println("Use --centroids to specify file input.");
centroids = KMeansData.getDefaultCentroidDataSet(env);
}
return centroids;
}
public static void main(String[] args) throws Exception {
final ParameterTool params = ParameterTool.fromArgs(args);
final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
System.out.println(
"Usage: WebLogAnalysis --documents <path> --ranks <path> --visits <path> --output <path>");
env.getConfig().setGlobalJobParameters(params);
// get input data
DataSet<Tuple2<String, String>> documents = getDocumentsDataSet(env, params);
DataSet<Tuple3<Integer, String, Integer>> ranks = getRanksDataSet(env, params);
DataSet<Tuple2<String, String>> visits = getVisitsDataSet(env, params);
// Retain documents with keywords
DataSet<Tuple1<String>> filterDocs = documents.filter(new FilterDocByKeyWords()).project(0);
// Filter ranks by minimum rank
DataSet<Tuple3<Integer, String, Integer>> filterRanks = ranks.filter(new FilterByRank());
// Filter visits by visit date
DataSet<Tuple1<String>> filterVisits = visits.filter(new FilterVisitsByDate()).project(0);
// Join the filtered documents and ranks, i.e., get all URLs with min rank and keywords
DataSet<Tuple3<Integer, String, Integer>> joinDocsRanks =
filterDocs.join(filterRanks).where(0).equalTo(1).projectSecond(0, 1, 2);
// Anti-join urls with visits, i.e., retain all URLs which have NOT been visited in a certain
// time
DataSet<Tuple3<Integer, String, Integer>> result =
joinDocsRanks.coGroup(filterVisits).where(1).equalTo(0).with(new AntiJoinVisits());
// emit result
if (params.has("output")) {
result.writeAsCsv(params.get("output"), "\n", "|");
// execute program
env.execute("WebLogAnalysis Example");
} else {
System.out.println("Printing result to stdout. Use --output to specify output path.");
result.print();
}
}
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();
}
}