Examples with Sessions org.apache.beam.sdk.transforms.windowing.Sessions used on opensource projects

Example 1 with Sessions

use of org.apache.beam.sdk.transforms.windowing.Sessions in project beam by apache.

the class BeamAggregationRel method explainTerms.

@Override
public RelWriter explainTerms(RelWriter pw) {
    super.explainTerms(pw);
    if (this.windowFn != null) {
        WindowFn windowFn = this.windowFn;
        String window = windowFn.getClass().getSimpleName() + "($" + String.valueOf(windowFieldIndex);
        if (windowFn instanceof FixedWindows) {
            FixedWindows fn = (FixedWindows) windowFn;
            window = window + ", " + fn.getSize().toString() + ", " + fn.getOffset().toString();
        } else if (windowFn instanceof SlidingWindows) {
            SlidingWindows fn = (SlidingWindows) windowFn;
            window = window + ", " + fn.getPeriod().toString() + ", " + fn.getSize().toString() + ", " + fn.getOffset().toString();
        } else if (windowFn instanceof Sessions) {
            Sessions fn = (Sessions) windowFn;
            window = window + ", " + fn.getGapDuration().toString();
        } else {
            throw new UnsupportedOperationException("Unknown window function " + windowFn.getClass().getSimpleName());
        }
        window = window + ")";
        pw.item("window", window);
    }
    return pw;
}

Example 2 with Sessions

use of org.apache.beam.sdk.transforms.windowing.Sessions in project beam by apache.

the class FlinkPartialReduceFunction method combine.

@Override
public void combine(Iterable<WindowedValue<KV<K, InputT>>> elements, Collector<WindowedValue<KV<K, AccumT>>> out) throws Exception {
    PipelineOptions options = serializedOptions.get();
    FlinkSideInputReader sideInputReader = new FlinkSideInputReader(sideInputs, getRuntimeContext());
    AbstractFlinkCombineRunner<K, InputT, AccumT, AccumT, W> reduceRunner;
    if (groupedByWindow) {
        reduceRunner = new SingleWindowFlinkCombineRunner<>();
    } else {
        if (windowingStrategy.needsMerge() && windowingStrategy.getWindowFn() instanceof Sessions) {
            reduceRunner = new SortingFlinkCombineRunner<>();
        } else {
            reduceRunner = new HashingFlinkCombineRunner<>();
        }
    }
    reduceRunner.combine(new AbstractFlinkCombineRunner.PartialFlinkCombiner<>(combineFn), windowingStrategy, sideInputReader, options, elements, out);
}

Example 3 with Sessions

use of org.apache.beam.sdk.transforms.windowing.Sessions in project DataflowJavaSDK-examples by GoogleCloudPlatform.

the class GameStats method main.

public static void main(String[] args) throws Exception {
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    // Enforce that this pipeline is always run in streaming mode.
    options.setStreaming(true);
    ExampleUtils exampleUtils = new ExampleUtils(options);
    Pipeline pipeline = Pipeline.create(options);
    // Read Events from Pub/Sub using custom timestamps
    PCollection<GameActionInfo> rawEvents = pipeline.apply(PubsubIO.readStrings().withTimestampAttribute(TIMESTAMP_ATTRIBUTE).fromTopic(options.getTopic())).apply("ParseGameEvent", ParDo.of(new ParseEventFn()));
    // Extract username/score pairs from the event stream
    PCollection<KV<String, Integer>> userEvents = rawEvents.apply("ExtractUserScore", MapElements.into(TypeDescriptors.kvs(TypeDescriptors.strings(), TypeDescriptors.integers())).via((GameActionInfo gInfo) -> KV.of(gInfo.getUser(), gInfo.getScore())));
    // Calculate the total score per user over fixed windows, and
    // cumulative updates for late data.
    final PCollectionView<Map<String, Integer>> spammersView = userEvents.apply("FixedWindowsUser", Window.<KV<String, Integer>>into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("CalculateSpammyUsers", new CalculateSpammyUsers()).apply("CreateSpammersView", View.<String, Integer>asMap());
    // [START DocInclude_FilterAndCalc]
    // Calculate the total score per team over fixed windows,
    // and emit cumulative updates for late data. Uses the side input derived above-- the set of
    // suspected robots-- to filter out scores from those users from the sum.
    // Write the results to BigQuery.
    rawEvents.apply("WindowIntoFixedWindows", Window.<GameActionInfo>into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("FilterOutSpammers", ParDo.of(new DoFn<GameActionInfo, GameActionInfo>() {

        @ProcessElement
        public void processElement(ProcessContext c) {
            // If the user is not in the spammers Map, output the data element.
            if (c.sideInput(spammersView).get(c.element().getUser().trim()) == null) {
                c.output(c.element());
            }
        }
    }).withSideInputs(spammersView)).apply("ExtractTeamScore", new ExtractAndSumScore("team")).apply("WriteTeamSums", new WriteWindowedToBigQuery<KV<String, Integer>>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_team", configureWindowedWrite()));
    // [START DocInclude_SessionCalc]
    // Detect user sessions-- that is, a burst of activity separated by a gap from further
    // activity. Find and record the mean session lengths.
    // This information could help the game designers track the changing user engagement
    // as their set of games changes.
    userEvents.apply("WindowIntoSessions", Window.<KV<String, Integer>>into(Sessions.withGapDuration(Duration.standardMinutes(options.getSessionGap()))).withTimestampCombiner(TimestampCombiner.END_OF_WINDOW)).apply(Combine.perKey(x -> 0)).apply("UserSessionActivity", ParDo.of(new UserSessionInfoFn())).apply("WindowToExtractSessionMean", Window.<Integer>into(FixedWindows.of(Duration.standardMinutes(options.getUserActivityWindowDuration())))).apply(Mean.<Integer>globally().withoutDefaults()).apply("WriteAvgSessionLength", new WriteWindowedToBigQuery<Double>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_sessions", configureSessionWindowWrite()));
    // [END DocInclude_Rewindow]
    // Run the pipeline and wait for the pipeline to finish; capture cancellation requests from the
    // command line.
    PipelineResult result = pipeline.run();
    exampleUtils.waitToFinish(result);
}

Example 4 with Sessions

use of org.apache.beam.sdk.transforms.windowing.Sessions in project beam by apache.

the class GameStats method main.

public static void main(String[] args) throws Exception {
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    // Enforce that this pipeline is always run in streaming mode.
    options.setStreaming(true);
    ExampleUtils exampleUtils = new ExampleUtils(options);
    Pipeline pipeline = Pipeline.create(options);
    // Read Events from Pub/Sub using custom timestamps
    PCollection<GameActionInfo> rawEvents = pipeline.apply(PubsubIO.readStrings().withTimestampAttribute(GameConstants.TIMESTAMP_ATTRIBUTE).fromTopic(options.getTopic())).apply("ParseGameEvent", ParDo.of(new ParseEventFn()));
    // Extract username/score pairs from the event stream
    PCollection<KV<String, Integer>> userEvents = rawEvents.apply("ExtractUserScore", MapElements.into(TypeDescriptors.kvs(TypeDescriptors.strings(), TypeDescriptors.integers())).via((GameActionInfo gInfo) -> KV.of(gInfo.getUser(), gInfo.getScore())));
    // Calculate the total score per user over fixed windows, and
    // cumulative updates for late data.
    final PCollectionView<Map<String, Integer>> spammersView = userEvents.apply("FixedWindowsUser", Window.into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("CalculateSpammyUsers", new CalculateSpammyUsers()).apply("CreateSpammersView", View.asMap());
    // [START DocInclude_FilterAndCalc]
    // Calculate the total score per team over fixed windows,
    // and emit cumulative updates for late data. Uses the side input derived above-- the set of
    // suspected robots-- to filter out scores from those users from the sum.
    // Write the results to BigQuery.
    rawEvents.apply("WindowIntoFixedWindows", Window.into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("FilterOutSpammers", ParDo.of(new DoFn<GameActionInfo, GameActionInfo>() {

        @ProcessElement
        public void processElement(ProcessContext c) {
            // If the user is not in the spammers Map, output the data element.
            if (c.sideInput(spammersView).get(c.element().getUser().trim()) == null) {
                c.output(c.element());
            }
        }
    }).withSideInputs(spammersView)).apply("ExtractTeamScore", new ExtractAndSumScore("team")).apply("WriteTeamSums", new WriteWindowedToBigQuery<>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_team", configureWindowedWrite()));
    // [START DocInclude_SessionCalc]
    // Detect user sessions-- that is, a burst of activity separated by a gap from further
    // activity. Find and record the mean session lengths.
    // This information could help the game designers track the changing user engagement
    // as their set of games changes.
    userEvents.apply("WindowIntoSessions", Window.<KV<String, Integer>>into(Sessions.withGapDuration(Duration.standardMinutes(options.getSessionGap()))).withTimestampCombiner(TimestampCombiner.END_OF_WINDOW)).apply(Combine.perKey(x -> 0)).apply("UserSessionActivity", ParDo.of(new UserSessionInfoFn())).apply("WindowToExtractSessionMean", Window.into(FixedWindows.of(Duration.standardMinutes(options.getUserActivityWindowDuration())))).apply(Mean.<Integer>globally().withoutDefaults()).apply("WriteAvgSessionLength", new WriteWindowedToBigQuery<>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_sessions", configureSessionWindowWrite()));
    // [END DocInclude_Rewindow]
    // Run the pipeline and wait for the pipeline to finish; capture cancellation requests from the
    // command line.
    PipelineResult result = pipeline.run();
    exampleUtils.waitToFinish(result);
}

Example 5 with Sessions

use of org.apache.beam.sdk.transforms.windowing.Sessions in project beam by apache.

the class FlinkMergingNonShuffleReduceFunction method reduce.

@Override
public void reduce(Iterable<WindowedValue<KV<K, InputT>>> elements, Collector<WindowedValue<KV<K, OutputT>>> out) throws Exception {
    PipelineOptions options = serializedOptions.get();
    FlinkSideInputReader sideInputReader = new FlinkSideInputReader(sideInputs, getRuntimeContext());
    AbstractFlinkCombineRunner<K, InputT, AccumT, OutputT, W> reduceRunner;
    if (windowingStrategy.getWindowFn() instanceof Sessions) {
        reduceRunner = new SortingFlinkCombineRunner<>();
    } else {
        reduceRunner = new HashingFlinkCombineRunner<>();
    }
    reduceRunner.combine(new AbstractFlinkCombineRunner.CompleteFlinkCombiner<>(combineFn), windowingStrategy, sideInputReader, options, elements, out);
}