Search in sources :

Example 1 with AveragerFactory

use of org.apache.druid.query.movingaverage.averagers.AveragerFactory in project druid by druid-io.

the class MovingAverageQueryRunner method run.

@Override
public Sequence<Row> run(QueryPlus<Row> query, ResponseContext responseContext) {
    MovingAverageQuery maq = (MovingAverageQuery) query.getQuery();
    List<Interval> intervals;
    final Period period;
    // Get the largest bucket from the list of averagers
    Optional<Integer> opt = maq.getAveragerSpecs().stream().map(AveragerFactory::getNumBuckets).max(Integer::compare);
    int buckets = opt.orElse(0);
    // Extend the interval beginning by specified bucket - 1
    if (maq.getGranularity() instanceof PeriodGranularity) {
        period = ((PeriodGranularity) maq.getGranularity()).getPeriod();
        int offset = buckets <= 0 ? 0 : (1 - buckets);
        intervals = maq.getIntervals().stream().map(i -> new Interval(i.getStart().withPeriodAdded(period, offset), i.getEnd())).collect(Collectors.toList());
    } else {
        throw new ISE("Only PeriodGranulaity is supported for movingAverage queries");
    }
    Sequence<Row> resultsSeq;
    DataSource dataSource = maq.getDataSource();
    if (maq.getDimensions() != null && !maq.getDimensions().isEmpty() && (dataSource instanceof TableDataSource || dataSource instanceof UnionDataSource || dataSource instanceof QueryDataSource)) {
        // build groupBy query from movingAverage query
        GroupByQuery.Builder builder = GroupByQuery.builder().setDataSource(dataSource).setInterval(intervals).setDimFilter(maq.getFilter()).setGranularity(maq.getGranularity()).setDimensions(maq.getDimensions()).setAggregatorSpecs(maq.getAggregatorSpecs()).setPostAggregatorSpecs(maq.getPostAggregatorSpecs()).setContext(maq.getContext());
        GroupByQuery gbq = builder.build();
        ResponseContext gbqResponseContext = ResponseContext.createEmpty();
        gbqResponseContext.merge(responseContext);
        gbqResponseContext.putQueryFailDeadlineMs(System.currentTimeMillis() + QueryContexts.getTimeout(gbq));
        Sequence<ResultRow> results = gbq.getRunner(walker).run(QueryPlus.wrap(gbq), gbqResponseContext);
        try {
            // use localhost for remote address
            requestLogger.logNativeQuery(RequestLogLine.forNative(gbq, DateTimes.nowUtc(), "127.0.0.1", new QueryStats(ImmutableMap.of("query/time", 0, "query/bytes", 0, "success", true))));
        } catch (Exception e) {
            throw Throwables.propagate(e);
        }
        resultsSeq = results.map(row -> row.toMapBasedRow(gbq));
    } else {
        // no dimensions, so optimize this as a TimeSeries
        TimeseriesQuery tsq = new TimeseriesQuery(dataSource, new MultipleIntervalSegmentSpec(intervals), false, null, maq.getFilter(), maq.getGranularity(), maq.getAggregatorSpecs(), maq.getPostAggregatorSpecs(), 0, maq.getContext());
        ResponseContext tsqResponseContext = ResponseContext.createEmpty();
        tsqResponseContext.merge(responseContext);
        tsqResponseContext.putQueryFailDeadlineMs(System.currentTimeMillis() + QueryContexts.getTimeout(tsq));
        Sequence<Result<TimeseriesResultValue>> results = tsq.getRunner(walker).run(QueryPlus.wrap(tsq), tsqResponseContext);
        try {
            // use localhost for remote address
            requestLogger.logNativeQuery(RequestLogLine.forNative(tsq, DateTimes.nowUtc(), "127.0.0.1", new QueryStats(ImmutableMap.of("query/time", 0, "query/bytes", 0, "success", true))));
        } catch (Exception e) {
            throw Throwables.propagate(e);
        }
        resultsSeq = Sequences.map(results, new TimeseriesResultToRow());
    }
    // Process into period buckets
    Sequence<RowBucket> bucketedMovingAvgResults = Sequences.simple(new RowBucketIterable(resultsSeq, intervals, period));
    // Apply the windows analysis functions
    Sequence<Row> movingAvgResults = Sequences.simple(new MovingAverageIterable(bucketedMovingAvgResults, maq.getDimensions(), maq.getAveragerSpecs(), maq.getPostAggregatorSpecs(), maq.getAggregatorSpecs()));
    // Apply any postAveragers
    Sequence<Row> movingAvgResultsWithPostAveragers = Sequences.map(movingAvgResults, new PostAveragerAggregatorCalculator(maq));
    // remove rows outside the reporting window
    List<Interval> reportingIntervals = maq.getIntervals();
    movingAvgResults = Sequences.filter(movingAvgResultsWithPostAveragers, row -> reportingIntervals.stream().anyMatch(i -> i.contains(row.getTimestamp())));
    // Apply any having, sorting, and limits
    movingAvgResults = maq.applyLimit(movingAvgResults);
    return movingAvgResults;
}
Also used : QueryPlus(org.apache.druid.query.QueryPlus) MapBasedRow(org.apache.druid.data.input.MapBasedRow) AveragerFactory(org.apache.druid.query.movingaverage.averagers.AveragerFactory) TimeseriesResultValue(org.apache.druid.query.timeseries.TimeseriesResultValue) Row(org.apache.druid.data.input.Row) QueryStats(org.apache.druid.server.QueryStats) Interval(org.joda.time.Interval) PeriodGranularity(org.apache.druid.java.util.common.granularity.PeriodGranularity) Map(java.util.Map) QueryRunner(org.apache.druid.query.QueryRunner) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) GroupByQuery(org.apache.druid.query.groupby.GroupByQuery) QuerySegmentWalker(org.apache.druid.query.QuerySegmentWalker) Sequences(org.apache.druid.java.util.common.guava.Sequences) Nullable(javax.annotation.Nullable) DateTimes(org.apache.druid.java.util.common.DateTimes) Sequence(org.apache.druid.java.util.common.guava.Sequence) Period(org.joda.time.Period) Function(com.google.common.base.Function) ImmutableMap(com.google.common.collect.ImmutableMap) ResponseContext(org.apache.druid.query.context.ResponseContext) ResultRow(org.apache.druid.query.groupby.ResultRow) DataSource(org.apache.druid.query.DataSource) Throwables(com.google.common.base.Throwables) TimeseriesQuery(org.apache.druid.query.timeseries.TimeseriesQuery) RequestLogger(org.apache.druid.server.log.RequestLogger) ISE(org.apache.druid.java.util.common.ISE) Collectors(java.util.stream.Collectors) QueryContexts(org.apache.druid.query.QueryContexts) TableDataSource(org.apache.druid.query.TableDataSource) QueryDataSource(org.apache.druid.query.QueryDataSource) Result(org.apache.druid.query.Result) List(java.util.List) UnionDataSource(org.apache.druid.query.UnionDataSource) RequestLogLine(org.apache.druid.server.RequestLogLine) Optional(java.util.Optional) PeriodGranularity(org.apache.druid.java.util.common.granularity.PeriodGranularity) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) Result(org.apache.druid.query.Result) GroupByQuery(org.apache.druid.query.groupby.GroupByQuery) ResponseContext(org.apache.druid.query.context.ResponseContext) ISE(org.apache.druid.java.util.common.ISE) ResultRow(org.apache.druid.query.groupby.ResultRow) TimeseriesQuery(org.apache.druid.query.timeseries.TimeseriesQuery) Period(org.joda.time.Period) UnionDataSource(org.apache.druid.query.UnionDataSource) DataSource(org.apache.druid.query.DataSource) TableDataSource(org.apache.druid.query.TableDataSource) QueryDataSource(org.apache.druid.query.QueryDataSource) UnionDataSource(org.apache.druid.query.UnionDataSource) TableDataSource(org.apache.druid.query.TableDataSource) QueryDataSource(org.apache.druid.query.QueryDataSource) QueryStats(org.apache.druid.server.QueryStats) MapBasedRow(org.apache.druid.data.input.MapBasedRow) Row(org.apache.druid.data.input.Row) ResultRow(org.apache.druid.query.groupby.ResultRow) Interval(org.joda.time.Interval)

Example 2 with AveragerFactory

use of org.apache.druid.query.movingaverage.averagers.AveragerFactory in project druid by druid-io.

the class MovingAverageIterableTest method testWithFilteredAggregation.

@Test
public void testWithFilteredAggregation() {
    Map<String, Object> event1 = new HashMap<>();
    Map<String, Object> event2 = new HashMap<>();
    List<DimensionSpec> ds = new ArrayList<>();
    ds.add(new DefaultDimensionSpec("gender", "gender"));
    event1.put("gender", "m");
    event1.put("pageViews", 10L);
    Row row1 = new MapBasedRow(JAN_1, event1);
    event2.put("gender", "m");
    event2.put("pageViews", 20L);
    Row row2 = new MapBasedRow(JAN_4, event2);
    Sequence<RowBucket> seq = Sequences.simple(Arrays.asList(new RowBucket(JAN_1, Collections.singletonList(row1)), new RowBucket(JAN_2, Collections.emptyList()), new RowBucket(JAN_3, Collections.emptyList()), new RowBucket(JAN_4, Collections.singletonList(row2))));
    AveragerFactory averagerfactory = new LongMeanAveragerFactory("movingAvgPageViews", 4, 1, "pageViews");
    AggregatorFactory aggregatorFactory = new LongSumAggregatorFactory("pageViews", "pageViews");
    DimFilter filter = new SelectorDimFilter("gender", "m", null);
    FilteredAggregatorFactory filteredAggregatorFactory = new FilteredAggregatorFactory(aggregatorFactory, filter);
    Iterator<Row> iter = new MovingAverageIterable(seq, ds, Collections.singletonList(averagerfactory), Collections.emptyList(), Collections.singletonList(filteredAggregatorFactory)).iterator();
    Assert.assertTrue(iter.hasNext());
    Row result = iter.next();
    Assert.assertEquals("m", (result.getDimension("gender")).get(0));
    Assert.assertEquals(2.5f, result.getMetric("movingAvgPageViews").floatValue(), 0.0f);
    Assert.assertTrue(iter.hasNext());
    result = iter.next();
    Assert.assertEquals("m", (result.getDimension("gender")).get(0));
    Assert.assertEquals(2.5f, result.getMetric("movingAvgPageViews").floatValue(), 0.0f);
    Assert.assertTrue(iter.hasNext());
    result = iter.next();
    Assert.assertEquals("m", (result.getDimension("gender")).get(0));
    Assert.assertEquals(2.5f, result.getMetric("movingAvgPageViews").floatValue(), 0.0f);
    Assert.assertTrue(iter.hasNext());
    result = iter.next();
    Assert.assertEquals("m", (result.getDimension("gender")).get(0));
    Assert.assertEquals(7.5f, result.getMetric("movingAvgPageViews").floatValue(), 0.0f);
    Assert.assertFalse(iter.hasNext());
}
Also used : FilteredAggregatorFactory(org.apache.druid.query.aggregation.FilteredAggregatorFactory) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) DimensionSpec(org.apache.druid.query.dimension.DimensionSpec) HashMap(java.util.HashMap) ArrayList(java.util.ArrayList) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) FilteredAggregatorFactory(org.apache.druid.query.aggregation.FilteredAggregatorFactory) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) ConstantAveragerFactory(org.apache.druid.query.movingaverage.averagers.ConstantAveragerFactory) AveragerFactory(org.apache.druid.query.movingaverage.averagers.AveragerFactory) LongMeanAveragerFactory(org.apache.druid.query.movingaverage.averagers.LongMeanAveragerFactory) MapBasedRow(org.apache.druid.data.input.MapBasedRow) LongMeanAveragerFactory(org.apache.druid.query.movingaverage.averagers.LongMeanAveragerFactory) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) MapBasedRow(org.apache.druid.data.input.MapBasedRow) Row(org.apache.druid.data.input.Row) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) DimFilter(org.apache.druid.query.filter.DimFilter) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Aggregations

MapBasedRow (org.apache.druid.data.input.MapBasedRow)2 Row (org.apache.druid.data.input.Row)2 AveragerFactory (org.apache.druid.query.movingaverage.averagers.AveragerFactory)2 Function (com.google.common.base.Function)1 Throwables (com.google.common.base.Throwables)1 ImmutableMap (com.google.common.collect.ImmutableMap)1 ArrayList (java.util.ArrayList)1 HashMap (java.util.HashMap)1 List (java.util.List)1 Map (java.util.Map)1 Optional (java.util.Optional)1 Collectors (java.util.stream.Collectors)1 Nullable (javax.annotation.Nullable)1 DateTimes (org.apache.druid.java.util.common.DateTimes)1 ISE (org.apache.druid.java.util.common.ISE)1 PeriodGranularity (org.apache.druid.java.util.common.granularity.PeriodGranularity)1 Sequence (org.apache.druid.java.util.common.guava.Sequence)1 Sequences (org.apache.druid.java.util.common.guava.Sequences)1 DataSource (org.apache.druid.query.DataSource)1 QueryContexts (org.apache.druid.query.QueryContexts)1