@SuppressWarnings("serial")
public static void main(String[] args) throws Exception {
if (!parseParameters(args)) {
return;
}
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Edge<Long, NullValue>> edges = getEdgesDataSet(env);
Graph<Long, Long, NullValue> graph =
Graph.fromDataSet(
edges,
new MapFunction<Long, Long>() {
@Override
public Long map(Long value) throws Exception {
return value;
}
},
env);
DataSet<Vertex<Long, Long>> verticesWithMinIds =
graph.run(new GSAConnectedComponents<Long, Long, NullValue>(maxIterations));
// emit result
if (fileOutput) {
verticesWithMinIds.writeAsCsv(outputPath, "\n", ",");
// since file sinks are lazy, we trigger the execution explicitly
env.execute("Connected Components Example");
} else {
verticesWithMinIds.print();
}
}
@Override
public VertexMetrics<K, VV, EV> run(Graph<K, VV, EV> input) throws Exception {
super.run(input);
DataSet<Vertex<K, Degrees>> vertexDegree =
input.run(
new VertexDegrees<K, VV, EV>()
.setIncludeZeroDegreeVertices(includeZeroDegreeVertices)
.setParallelism(parallelism));
vertexDegree.output(new VertexMetricsHelper<K>(id)).name("Vertex metrics");
return this;
}
@Override
public DataSet<Edge<K, Tuple2<EV, LongValue>>> run(Graph<K, VV, EV> input) throws Exception {
// t, d(t)
DataSet<Vertex<K, LongValue>> vertexDegrees =
input.run(
new VertexDegree<K, VV, EV>()
.setReduceOnTargetId(!reduceOnSourceId)
.setParallelism(parallelism));
// s, t, d(t)
return input
.getEdges()
.join(vertexDegrees, JoinHint.REPARTITION_HASH_SECOND)
.where(1)
.equalTo(0)
.with(new JoinEdgeWithVertexDegree<K, EV>())
.setParallelism(parallelism)
.name("Edge target degree");
}