@SuppressWarnings("serial")
public static void main(String[] args) throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Vertex<Long, Double>> pages = getPagesDataSet(env);
DataSet<Edge<Long, Double>> links = getLinksDataSet(env);
Graph<Long, Double, Double> network = new Graph<Long, Double, Double>(pages, links, env);
DataSet<Tuple2<Long, Long>> vertexOutDegrees = network.outDegrees();
// assign the transition probabilities as the edge weights
Graph<Long, Double, Double> networkWithWeights =
network.joinWithEdgesOnSource(
vertexOutDegrees,
new MapFunction<Tuple2<Double, Long>, Double>() {
public Double map(Tuple2<Double, Long> value) {
return value.f0 / value.f1;
}
});
DataSet<Vertex<Long, Double>> pageRanks =
networkWithWeights
.run(new PageRank<Long>(numPages, DAMPENING_FACTOR, maxIterations))
.getVertices();
pageRanks.print();
env.execute();
}
@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();
}
}
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();
}
}
@Override
protected void testProgram() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Record> initialInput =
env.readFile(new PointInFormat(), this.dataPath).setParallelism(1);
IterativeDataSet<Record> iteration = initialInput.iterate(2);
DataSet<Record> result = iteration.union(iteration).map(new IdentityMapper());
iteration.closeWith(result).write(new PointOutFormat(), this.resultPath);
env.execute();
}
@Test(expected = ExpressionException.class)
public void testOnlyFieldRefInAs() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
TableEnvironment tableEnv = new TableEnvironment();
DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env);
Table in = tableEnv.fromDataSet(ds, "a, b as c, d");
DataSet<Row> resultSet = tableEnv.toDataSet(in, Row.class);
resultSet.writeAsText(resultPath, FileSystem.WriteMode.OVERWRITE);
env.execute();
expected = "sorry bro";
}
@Test(expected = ExpressionException.class)
public void testAsWithAmbiguousFields() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
TableEnvironment tableEnv = new TableEnvironment();
DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env);
Table in = tableEnv.fromDataSet(ds, "a, b, c, b");
DataSet<Row> resultSet = tableEnv.toDataSet(in, Row.class);
resultSet.writeAsText(resultPath, FileSystem.WriteMode.OVERWRITE);
env.execute();
expected = " today's not your day ";
}
@Test
public void testSimpleSelectAllWithAs() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
TableEnvironment tableEnv = new TableEnvironment();
DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env);
Table in = tableEnv.fromDataSet(ds, "a,b,c");
Table result = in.select("a, b, c");
DataSet<Row> resultSet = tableEnv.toDataSet(result, Row.class);
resultSet.writeAsText(resultPath, FileSystem.WriteMode.OVERWRITE);
env.execute();
expected =
"1,1,Hi\n"
+ "2,2,Hello\n"
+ "3,2,Hello world\n"
+ "4,3,Hello world, "
+ "how are you?\n"
+ "5,3,I am fine.\n"
+ "6,3,Luke Skywalker\n"
+ "7,4,"
+ "Comment#1\n"
+ "8,4,Comment#2\n"
+ "9,4,Comment#3\n"
+ "10,4,Comment#4\n"
+ "11,5,"
+ "Comment#5\n"
+ "12,5,Comment#6\n"
+ "13,5,Comment#7\n"
+ "14,5,Comment#8\n"
+ "15,5,"
+ "Comment#9\n"
+ "16,6,Comment#10\n"
+ "17,6,Comment#11\n"
+ "18,6,Comment#12\n"
+ "19,"
+ "6,Comment#13\n"
+ "20,6,Comment#14\n"
+ "21,6,Comment#15\n";
}
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();
}
}
@Override
protected void testProgram() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
env.setDegreeOfParallelism(4);
DataSet<Integer> data = env.fromElements(1, 2, 3, 4, 5, 6, 7, 8);
IterativeDataSet<Integer> iteration = data.iterate(10);
DataSet<Integer> result =
data.reduceGroup(new PickOneAllReduce()).withBroadcastSet(iteration, "bc");
final List<Integer> resultList = new ArrayList<Integer>();
iteration.closeWith(result).output(new LocalCollectionOutputFormat<Integer>(resultList));
env.execute();
Assert.assertEquals(8, resultList.get(0).intValue());
}
@Test
public void testSimpleSelectWithNaming() throws Exception {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
TableEnvironment tableEnv = new TableEnvironment();
DataSet<Tuple3<Integer, Long, String>> ds = CollectionDataSets.get3TupleDataSet(env);
Table in = tableEnv.fromDataSet(ds);
Table result = in.select("f0 as a, f1 as b").select("a, b");
DataSet<Row> resultSet = tableEnv.toDataSet(result, Row.class);
resultSet.writeAsText(resultPath, FileSystem.WriteMode.OVERWRITE);
env.execute();
expected =
"1,1\n" + "2,2\n" + "3,2\n" + "4,3\n" + "5,3\n" + "6,3\n" + "7,4\n" + "8,4\n" + "9,4\n"
+ "10,4\n" + "11,5\n" + "12,5\n" + "13,5\n" + "14,5\n" + "15,5\n" + "16,6\n" + "17,6\n"
+ "18,6\n" + "19,6\n" + "20,6\n" + "21,6\n";
}
public static void main(String[] args) throws Exception {
final String jarFile = args[0];
final String host = args[1];
final int port = Integer.parseInt(args[2]);
ExecutionEnvironment env = ExecutionEnvironment.createRemoteEnvironment(host, port, jarFile);
DataSet<Integer> data = env.createInput(new CustomInputFormat());
data.map(
new MapFunction<Integer, Tuple2<Integer, Double>>() {
@Override
public Tuple2<Integer, Double> map(Integer value) {
return new Tuple2<Integer, Double>(value, value * 0.5);
}
})
.output(new DiscardingOutputFormat<Tuple2<Integer, Double>>());
env.execute();
}
