Examples with VertexDegrees org.apache.flink.graph.asm.degree.annotate.directed.VertexDegrees used on opensource projects

Example 1 with VertexDegrees

use of org.apache.flink.graph.asm.degree.annotate.directed.VertexDegrees in project flink by apache.

the class PageRank method runInternal.

@Override
public DataSet<Result<K>> runInternal(Graph<K, VV, EV> input) throws Exception {
    // vertex degree
    DataSet<Vertex<K, Degrees>> vertexDegree = input.run(new VertexDegrees<K, VV, EV>().setParallelism(parallelism));
    // vertex count
    DataSet<LongValue> vertexCount = GraphUtils.count(vertexDegree);
    // s, t, d(s)
    DataSet<Edge<K, LongValue>> edgeSourceDegree = input.run(new EdgeSourceDegrees<K, VV, EV>().setParallelism(parallelism)).map(new ExtractSourceDegree<K, EV>()).setParallelism(parallelism).name("Extract source degree");
    // vertices with zero in-edges
    DataSet<Tuple2<K, DoubleValue>> sourceVertices = vertexDegree.flatMap(new InitializeSourceVertices<K>()).withBroadcastSet(vertexCount, VERTEX_COUNT).setParallelism(parallelism).name("Initialize source vertex scores");
    // s, initial pagerank(s)
    DataSet<Tuple2<K, DoubleValue>> initialScores = vertexDegree.map(new InitializeVertexScores<K>()).withBroadcastSet(vertexCount, VERTEX_COUNT).setParallelism(parallelism).name("Initialize scores");
    IterativeDataSet<Tuple2<K, DoubleValue>> iterative = initialScores.iterate(maxIterations);
    // s, projected pagerank(s)
    DataSet<Tuple2<K, DoubleValue>> vertexScores = iterative.coGroup(edgeSourceDegree).where(0).equalTo(0).with(new SendScore<K>()).setParallelism(parallelism).name("Send score").groupBy(0).reduce(new SumScore<K>()).setCombineHint(CombineHint.HASH).setParallelism(parallelism).name("Sum");
    // ignored ID, total pagerank
    DataSet<Tuple2<K, DoubleValue>> sumOfScores = vertexScores.reduce(new SumVertexScores<K>()).setParallelism(parallelism).name("Sum");
    // s, adjusted pagerank(s)
    DataSet<Tuple2<K, DoubleValue>> adjustedScores = vertexScores.union(sourceVertices).setParallelism(parallelism).name("Union with source vertices").map(new AdjustScores<K>(dampingFactor)).withBroadcastSet(sumOfScores, SUM_OF_SCORES).withBroadcastSet(vertexCount, VERTEX_COUNT).setParallelism(parallelism).name("Adjust scores");
    DataSet<Tuple2<K, DoubleValue>> passThrough;
    if (convergenceThreshold < Double.MAX_VALUE) {
        passThrough = iterative.join(adjustedScores).where(0).equalTo(0).with(new ChangeInScores<K>()).setParallelism(parallelism).name("Change in scores");
        iterative.registerAggregationConvergenceCriterion(CHANGE_IN_SCORES, new DoubleSumAggregator(), new ScoreConvergence(convergenceThreshold));
    } else {
        passThrough = adjustedScores;
    }
    return iterative.closeWith(passThrough).map(new TranslateResult<K>()).setParallelism(parallelism).name("Map result");
}