org.apache.flink.graph.library.linkanalysis.PageRank.Result Java Examples

The following examples show how to use org.apache.flink.graph.library.linkanalysis.PageRank.Result. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: PageRankTest.java    From Flink-CEPplus with Apache License 2.0 6 votes vote down vote up 
@Test
public void testWithSimpleGraph() throws Exception {
	DataSet<Result<IntValue>> pr = new PageRank<IntValue, NullValue, NullValue>(DAMPING_FACTOR, 20)
		.run(directedSimpleGraph);

	List<Double> expectedResults = new ArrayList<>();
	expectedResults.add(0.0909212166211);
	expectedResults.add(0.279516064311);
	expectedResults.add(0.129562719068);
	expectedResults.add(0.223268406353);
	expectedResults.add(0.185810377026);
	expectedResults.add(0.0909212166211);

	for (Result<IntValue> result : pr.collect()) {
		int id = result.getVertexId0().getValue();
		assertEquals(expectedResults.get(id), result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #2
Source File: PageRankTest.java    From flink with Apache License 2.0 6 votes vote down vote up 
@Test
public void testWithSimpleGraph() throws Exception {
	DataSet<Result<IntValue>> pr = new PageRank<IntValue, NullValue, NullValue>(DAMPING_FACTOR, 20)
		.run(directedSimpleGraph);

	List<Double> expectedResults = new ArrayList<>();
	expectedResults.add(0.0909212166211);
	expectedResults.add(0.279516064311);
	expectedResults.add(0.129562719068);
	expectedResults.add(0.223268406353);
	expectedResults.add(0.185810377026);
	expectedResults.add(0.0909212166211);

	for (Result<IntValue> result : pr.collect()) {
		int id = result.getVertexId0().getValue();
		assertEquals(expectedResults.get(id), result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #3
Source File: PageRankTest.java    From flink with Apache License 2.0 6 votes vote down vote up 
@Test
public void testWithSimpleGraph() throws Exception {
	DataSet<Result<IntValue>> pr = new PageRank<IntValue, NullValue, NullValue>(DAMPING_FACTOR, 20)
		.run(directedSimpleGraph);

	List<Double> expectedResults = new ArrayList<>();
	expectedResults.add(0.0909212166211);
	expectedResults.add(0.279516064311);
	expectedResults.add(0.129562719068);
	expectedResults.add(0.223268406353);
	expectedResults.add(0.185810377026);
	expectedResults.add(0.0909212166211);

	for (Result<IntValue> result : pr.collect()) {
		int id = result.getVertexId0().getValue();
		assertEquals(expectedResults.get(id), result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #4
Source File: PageRankTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
/**
 * Validate a test where each result has the same values.
 *
 * @param graph input graph
 * @param count number of results
 * @param score result PageRank score
 * @param <T> graph ID type
 * @throws Exception on error
 */
private static <T> void validate(Graph<T, NullValue, NullValue> graph, long count, double score) throws Exception {
	DataSet<Result<T>> pr = new PageRank<T, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.setIncludeZeroDegreeVertices(true)
		.run(graph);

	List<Result<T>> results = pr.collect();

	assertEquals(count, results.size());

	for (Result<T> result : results) {
		assertEquals(score, result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #5
Source File: PageRankTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void testWithRMatGraph() throws Exception {
	DataSet<Result<LongValue>> pr = new PageRank<LongValue, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.run(directedRMatGraph(10, 16));

	Map<Long, Result<LongValue>> results = new HashMap<>();
	for (Result<LongValue> result :  new Collect<Result<LongValue>>().run(pr).execute()) {
		results.put(result.getVertexId0().getValue(), result);
	}

	assertEquals(902, results.size());

	Map<Long, Double> expectedResults = new HashMap<>();
	// a pseudo-random selection of results, both high and low
	expectedResults.put(0L, 0.0271152394743);
	expectedResults.put(1L, 0.0132848430616);
	expectedResults.put(2L, 0.0121819700294);
	expectedResults.put(8L, 0.0115923214664);
	expectedResults.put(13L, 0.00183241122822);
	expectedResults.put(29L, 0.000848190646547);
	expectedResults.put(109L, 0.00030846825644);
	expectedResults.put(394L, 0.000828826945546);
	expectedResults.put(652L, 0.000683948671035);
	expectedResults.put(1020L, 0.000250442325034);

	for (Map.Entry<Long, Double> expected : expectedResults.entrySet()) {
		double value = results.get(expected.getKey()).getPageRankScore().getValue();

		assertEquals(expected.getValue(), value, ACCURACY);
	}
}
Example #6
Source File: PageRankTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
/**
 * Validate a test where each result has the same values.
 *
 * @param graph input graph
 * @param count number of results
 * @param score result PageRank score
 * @param <T> graph ID type
 * @throws Exception on error
 */
private static <T> void validate(Graph<T, NullValue, NullValue> graph, long count, double score) throws Exception {
	DataSet<Result<T>> pr = new PageRank<T, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.setIncludeZeroDegreeVertices(true)
		.run(graph);

	List<Result<T>> results = pr.collect();

	assertEquals(count, results.size());

	for (Result<T> result : results) {
		assertEquals(score, result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #7
Source File: PageRankTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testWithRMatGraph() throws Exception {
	DataSet<Result<LongValue>> pr = new PageRank<LongValue, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.run(directedRMatGraph(10, 16));

	Map<Long, Result<LongValue>> results = new HashMap<>();
	for (Result<LongValue> result :  new Collect<Result<LongValue>>().run(pr).execute()) {
		results.put(result.getVertexId0().getValue(), result);
	}

	assertEquals(902, results.size());

	Map<Long, Double> expectedResults = new HashMap<>();
	// a pseudo-random selection of results, both high and low
	expectedResults.put(0L, 0.0271152394743);
	expectedResults.put(1L, 0.0132848430616);
	expectedResults.put(2L, 0.0121819700294);
	expectedResults.put(8L, 0.0115923214664);
	expectedResults.put(13L, 0.00183241122822);
	expectedResults.put(29L, 0.000848190646547);
	expectedResults.put(109L, 0.00030846825644);
	expectedResults.put(394L, 0.000828826945546);
	expectedResults.put(652L, 0.000683948671035);
	expectedResults.put(1020L, 0.000250442325034);

	for (Map.Entry<Long, Double> expected : expectedResults.entrySet()) {
		double value = results.get(expected.getKey()).getPageRankScore().getValue();

		assertEquals(expected.getValue(), value, ACCURACY);
	}
}
Example #8
Source File: PageRankTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
/**
 * Validate a test where each result has the same values.
 *
 * @param graph input graph
 * @param count number of results
 * @param score result PageRank score
 * @param <T> graph ID type
 * @throws Exception on error
 */
private static <T> void validate(Graph<T, NullValue, NullValue> graph, long count, double score) throws Exception {
	DataSet<Result<T>> pr = new PageRank<T, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.setIncludeZeroDegreeVertices(true)
		.run(graph);

	List<Result<T>> results = pr.collect();

	assertEquals(count, results.size());

	for (Result<T> result : results) {
		assertEquals(score, result.getPageRankScore().getValue(), ACCURACY);
	}
}
Example #9
Source File: PageRankTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testWithRMatGraph() throws Exception {
	DataSet<Result<LongValue>> pr = new PageRank<LongValue, NullValue, NullValue>(DAMPING_FACTOR, ACCURACY)
		.run(directedRMatGraph(10, 16));

	Map<Long, Result<LongValue>> results = new HashMap<>();
	for (Result<LongValue> result :  new Collect<Result<LongValue>>().run(pr).execute()) {
		results.put(result.getVertexId0().getValue(), result);
	}

	assertEquals(902, results.size());

	Map<Long, Double> expectedResults = new HashMap<>();
	// a pseudo-random selection of results, both high and low
	expectedResults.put(0L, 0.0271152394743);
	expectedResults.put(1L, 0.0132848430616);
	expectedResults.put(2L, 0.0121819700294);
	expectedResults.put(8L, 0.0115923214664);
	expectedResults.put(13L, 0.00183241122822);
	expectedResults.put(29L, 0.000848190646547);
	expectedResults.put(109L, 0.00030846825644);
	expectedResults.put(394L, 0.000828826945546);
	expectedResults.put(652L, 0.000683948671035);
	expectedResults.put(1020L, 0.000250442325034);

	for (Map.Entry<Long, Double> expected : expectedResults.entrySet()) {
		double value = results.get(expected.getKey()).getPageRankScore().getValue();

		assertEquals(expected.getValue(), value, ACCURACY);
	}
}
Example #10
Source File: PageRank.java    From Flink-CEPplus with Apache License 2.0 4 votes vote down vote up 
@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>()
			.setIncludeZeroDegreeVertices(includeZeroDegreeVertices)
			.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<>())
			.setParallelism(parallelism)
			.name("Extract source degree");

	// vertices with zero in-edges
	DataSet<Tuple2<K, DoubleValue>> sourceVertices = vertexDegree
		.flatMap(new InitializeSourceVertices<>())
			.setParallelism(parallelism)
			.name("Initialize source vertex scores");

	// s, initial pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> initialScores = vertexDegree
		.map(new InitializeVertexScores<>())
		.withBroadcastSet(vertexCount, VERTEX_COUNT)
			.setParallelism(parallelism)
			.name("Initialize scores");

	IterativeDataSet<Tuple2<K, DoubleValue>> iterative = initialScores
		.iterate(maxIterations)
		.setParallelism(parallelism);

	// s, projected pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> vertexScores = iterative
		.coGroup(edgeSourceDegree)
		.where(0)
		.equalTo(0)
		.with(new SendScore<>())
			.setParallelism(parallelism)
			.name("Send score")
		.groupBy(0)
		.reduce(new SumScore<>())
		.setCombineHint(CombineHint.HASH)
			.setParallelism(parallelism)
			.name("Sum");

	// ignored ID, total pagerank
	DataSet<Tuple2<K, DoubleValue>> sumOfScores = vertexScores
		.reduce(new SumVertexScores<>())
			.setParallelism(parallelism)
			.name("Sum");

	// s, adjusted pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> adjustedScores = vertexScores
		.union(sourceVertices)
			.name("Union with source vertices")
		.map(new AdjustScores<>(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<>())
				.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<>())
			.setParallelism(parallelism)
			.name("Map result");
}
Example #11
Source File: PageRank.java    From Flink-CEPplus with Apache License 2.0 4 votes vote down vote up 
@Override
public Result<T> map(Tuple2<T, DoubleValue> value) throws Exception {
	output.setVertexId0(value.f0);
	output.setPageRankScore(value.f1);
	return output;
}
Example #12
Source File: PageRank.java    From flink with Apache License 2.0 4 votes vote down vote up 
@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>()
			.setIncludeZeroDegreeVertices(includeZeroDegreeVertices)
			.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<>())
			.setParallelism(parallelism)
			.name("Extract source degree");

	// vertices with zero in-edges
	DataSet<Tuple2<K, DoubleValue>> sourceVertices = vertexDegree
		.flatMap(new InitializeSourceVertices<>())
			.setParallelism(parallelism)
			.name("Initialize source vertex scores");

	// s, initial pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> initialScores = vertexDegree
		.map(new InitializeVertexScores<>())
		.withBroadcastSet(vertexCount, VERTEX_COUNT)
			.setParallelism(parallelism)
			.name("Initialize scores");

	IterativeDataSet<Tuple2<K, DoubleValue>> iterative = initialScores
		.iterate(maxIterations)
		.setParallelism(parallelism);

	// s, projected pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> vertexScores = iterative
		.coGroup(edgeSourceDegree)
		.where(0)
		.equalTo(0)
		.with(new SendScore<>())
			.setParallelism(parallelism)
			.name("Send score")
		.groupBy(0)
		.reduce(new SumScore<>())
		.setCombineHint(CombineHint.HASH)
			.setParallelism(parallelism)
			.name("Sum");

	// ignored ID, total pagerank
	DataSet<Tuple2<K, DoubleValue>> sumOfScores = vertexScores
		.reduce(new SumVertexScores<>())
			.setParallelism(parallelism)
			.name("Sum");

	// s, adjusted pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> adjustedScores = vertexScores
		.union(sourceVertices)
			.name("Union with source vertices")
		.map(new AdjustScores<>(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<>())
				.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<>())
			.setParallelism(parallelism)
			.name("Map result");
}
Example #13
Source File: PageRank.java    From flink with Apache License 2.0 4 votes vote down vote up 
@Override
public Result<T> map(Tuple2<T, DoubleValue> value) throws Exception {
	output.setVertexId0(value.f0);
	output.setPageRankScore(value.f1);
	return output;
}
Example #14
Source File: PageRank.java    From flink with Apache License 2.0 4 votes vote down vote up 
@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>()
			.setIncludeZeroDegreeVertices(includeZeroDegreeVertices)
			.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<>())
			.setParallelism(parallelism)
			.name("Extract source degree");

	// vertices with zero in-edges
	DataSet<Tuple2<K, DoubleValue>> sourceVertices = vertexDegree
		.flatMap(new InitializeSourceVertices<>())
			.setParallelism(parallelism)
			.name("Initialize source vertex scores");

	// s, initial pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> initialScores = vertexDegree
		.map(new InitializeVertexScores<>())
		.withBroadcastSet(vertexCount, VERTEX_COUNT)
			.setParallelism(parallelism)
			.name("Initialize scores");

	IterativeDataSet<Tuple2<K, DoubleValue>> iterative = initialScores
		.iterate(maxIterations)
		.setParallelism(parallelism);

	// s, projected pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> vertexScores = iterative
		.coGroup(edgeSourceDegree)
		.where(0)
		.equalTo(0)
		.with(new SendScore<>())
			.setParallelism(parallelism)
			.name("Send score")
		.groupBy(0)
		.reduce(new SumScore<>())
		.setCombineHint(CombineHint.HASH)
			.setParallelism(parallelism)
			.name("Sum");

	// ignored ID, total pagerank
	DataSet<Tuple2<K, DoubleValue>> sumOfScores = vertexScores
		.reduce(new SumVertexScores<>())
			.setParallelism(parallelism)
			.name("Sum");

	// s, adjusted pagerank(s)
	DataSet<Tuple2<K, DoubleValue>> adjustedScores = vertexScores
		.union(sourceVertices)
			.name("Union with source vertices")
		.map(new AdjustScores<>(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<>())
				.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<>())
			.setParallelism(parallelism)
			.name("Map result");
}
Example #15
Source File: PageRank.java    From flink with Apache License 2.0 4 votes vote down vote up 
@Override
public Result<T> map(Tuple2<T, DoubleValue> value) throws Exception {
	output.setVertexId0(value.f0);
	output.setPageRankScore(value.f1);
	return output;
}