Examples with FilteredAggregatorFactory io.druid.query.aggregation.FilteredAggregatorFactory used on opensource projects

Example 6 with FilteredAggregatorFactory

use of io.druid.query.aggregation.FilteredAggregatorFactory in project druid by druid-io.

the class TimeseriesQueryRunnerTest method testTimeSeriesWithFilteredAgg.

@Test
public void testTimeSeriesWithFilteredAgg() {
    TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).intervals(QueryRunnerTestHelper.firstToThird).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new CountAggregatorFactory("filteredAgg"), Druids.newSelectorDimFilterBuilder().dimension(QueryRunnerTestHelper.marketDimension).value("spot").build()))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).descending(descending).build();
    Iterable<Result<TimeseriesResultValue>> actualResults = Sequences.toList(runner.run(query, CONTEXT), Lists.<Result<TimeseriesResultValue>>newArrayList());
    List<Result<TimeseriesResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-04-01"), new TimeseriesResultValue(ImmutableMap.<String, Object>of("filteredAgg", 18L, "addRowsIndexConstant", 12486.361190795898d, "index", 12459.361190795898d, "uniques", 9.019833517963864d, "rows", 26L))));
    assertExpectedResults(expectedResults, actualResults);
}

Example 7 with FilteredAggregatorFactory

use of io.druid.query.aggregation.FilteredAggregatorFactory in project druid by druid-io.

the class QuantileSqlAggregatorTest method testQuantileOnComplexColumn.

@Test
public void testQuantileOnComplexColumn() throws Exception {
    try (final DruidPlanner planner = plannerFactory.createPlanner(null)) {
        final String sql = "SELECT\n" + "APPROX_QUANTILE(hist_m1, 0.01),\n" + "APPROX_QUANTILE(hist_m1, 0.5, 50),\n" + "APPROX_QUANTILE(hist_m1, 0.98, 200),\n" + "APPROX_QUANTILE(hist_m1, 0.99),\n" + "APPROX_QUANTILE(hist_m1, 0.99) FILTER(WHERE dim1 = 'abc'),\n" + "APPROX_QUANTILE(hist_m1, 0.999) FILTER(WHERE dim1 <> 'abc'),\n" + "APPROX_QUANTILE(hist_m1, 0.999) FILTER(WHERE dim1 = 'abc')\n" + "FROM foo";
        final PlannerResult plannerResult = planner.plan(sql);
        // Verify results
        final List<Object[]> results = Sequences.toList(plannerResult.run(), new ArrayList<Object[]>());
        final List<Object[]> expectedResults = ImmutableList.of(new Object[] { 1.0, 3.0, 5.880000114440918, 5.940000057220459, 6.0, 4.994999885559082, 6.0 });
        Assert.assertEquals(expectedResults.size(), results.size());
        for (int i = 0; i < expectedResults.size(); i++) {
            Assert.assertArrayEquals(expectedResults.get(i), results.get(i));
        }
        // Verify query
        Assert.assertEquals(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE1).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).aggregators(ImmutableList.of(new ApproximateHistogramFoldingAggregatorFactory("a0:agg", "hist_m1", null, null, null, null), new ApproximateHistogramFoldingAggregatorFactory("a2:agg", "hist_m1", 200, null, null, null), new FilteredAggregatorFactory(new ApproximateHistogramFoldingAggregatorFactory("a4:agg", "hist_m1", null, null, null, null), new SelectorDimFilter("dim1", "abc", null)), new FilteredAggregatorFactory(new ApproximateHistogramFoldingAggregatorFactory("a5:agg", "hist_m1", null, null, null, null), new NotDimFilter(new SelectorDimFilter("dim1", "abc", null))))).postAggregators(ImmutableList.<PostAggregator>of(new QuantilePostAggregator("a0", "a0:agg", 0.01f), new QuantilePostAggregator("a1", "a0:agg", 0.50f), new QuantilePostAggregator("a2", "a2:agg", 0.98f), new QuantilePostAggregator("a3", "a0:agg", 0.99f), new QuantilePostAggregator("a4", "a4:agg", 0.99f), new QuantilePostAggregator("a5", "a5:agg", 0.999f), new QuantilePostAggregator("a6", "a4:agg", 0.999f))).context(ImmutableMap.<String, Object>of("skipEmptyBuckets", true)).build(), Iterables.getOnlyElement(queryLogHook.getRecordedQueries()));
    }
}

Example 8 with FilteredAggregatorFactory

use of io.druid.query.aggregation.FilteredAggregatorFactory in project druid by druid-io.

the class TimeseriesBenchmark method setupQueries.

private void setupQueries() {
    // queries for the basic schema
    Map<String, TimeseriesQuery> basicQueries = new LinkedHashMap<>();
    BenchmarkSchemaInfo basicSchema = BenchmarkSchemas.SCHEMA_MAP.get("basic");
    {
        // basic.A
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        queryAggs.add(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"));
        queryAggs.add(new LongMaxAggregatorFactory("maxLongUniform", "maxLongUniform"));
        queryAggs.add(new DoubleSumAggregatorFactory("sumFloatNormal", "sumFloatNormal"));
        queryAggs.add(new DoubleMinAggregatorFactory("minFloatZipf", "minFloatZipf"));
        queryAggs.add(new HyperUniquesAggregatorFactory("hyperUniquesMet", "hyper"));
        TimeseriesQuery queryA = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
        basicQueries.put("A", queryA);
    }
    {
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        LongSumAggregatorFactory lsaf = new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential");
        BoundDimFilter timeFilter = new BoundDimFilter(Column.TIME_COLUMN_NAME, "200000", "300000", false, false, null, null, StringComparators.NUMERIC);
        queryAggs.add(new FilteredAggregatorFactory(lsaf, timeFilter));
        TimeseriesQuery timeFilterQuery = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
        basicQueries.put("timeFilterNumeric", timeFilterQuery);
    }
    {
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        LongSumAggregatorFactory lsaf = new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential");
        BoundDimFilter timeFilter = new BoundDimFilter(Column.TIME_COLUMN_NAME, "200000", "300000", false, false, null, null, StringComparators.ALPHANUMERIC);
        queryAggs.add(new FilteredAggregatorFactory(lsaf, timeFilter));
        TimeseriesQuery timeFilterQuery = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
        basicQueries.put("timeFilterAlphanumeric", timeFilterQuery);
    }
    {
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(new Interval(200000, 300000)));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        LongSumAggregatorFactory lsaf = new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential");
        queryAggs.add(lsaf);
        TimeseriesQuery timeFilterQuery = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
        basicQueries.put("timeFilterByInterval", timeFilterQuery);
    }
    SCHEMA_QUERY_MAP.put("basic", basicQueries);
}

Example 9 with FilteredAggregatorFactory

use of io.druid.query.aggregation.FilteredAggregatorFactory in project druid by druid-io.

the class TopNQueryRunnerTest method testTopNWithExtractionFilterAndFilteredAggregatorCaseNoExistingValue.

@Test
public void testTopNWithExtractionFilterAndFilteredAggregatorCaseNoExistingValue() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("", "NULL");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
    DimFilter extractionFilter = new ExtractionDimFilter("null_column", "NULL", lookupExtractionFn, null);
    TopNQueryBuilder topNQueryBuilder = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension("null_column").metric(QueryRunnerTestHelper.indexMetric).threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new DoubleMaxAggregatorFactory("maxIndex", "index"), extractionFilter), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant));
    TopNQuery topNQueryWithNULLValueExtraction = topNQueryBuilder.filters(extractionFilter).build();
    Map<String, Object> map = Maps.newHashMap();
    map.put("null_column", null);
    map.put("rows", 1209L);
    map.put("index", 503332.5071372986D);
    map.put("addRowsIndexConstant", 504542.5071372986D);
    map.put("uniques", QueryRunnerTestHelper.UNIQUES_9);
    map.put("maxIndex", 1870.06103515625D);
    map.put("minIndex", 59.02102279663086D);
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.asList(map))));
    assertExpectedResults(expectedResults, topNQueryWithNULLValueExtraction);
}

Example 10 with FilteredAggregatorFactory

use of io.druid.query.aggregation.FilteredAggregatorFactory in project druid by druid-io.

the class TimeseriesQueryRunnerTest method testTimeSeriesWithFilteredAggDimensionNotPresentNullValue.

@Test
public void testTimeSeriesWithFilteredAggDimensionNotPresentNullValue() {
    TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).intervals(QueryRunnerTestHelper.firstToThird).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new CountAggregatorFactory("filteredAgg"), Druids.newSelectorDimFilterBuilder().dimension("abraKaDabra").value(null).build()))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).descending(descending).build();
    Iterable<Result<TimeseriesResultValue>> actualResults = Sequences.toList(runner.run(query, CONTEXT), Lists.<Result<TimeseriesResultValue>>newArrayList());
    List<Result<TimeseriesResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-04-01"), new TimeseriesResultValue(ImmutableMap.<String, Object>of("filteredAgg", 26L, "addRowsIndexConstant", 12486.361190795898d, "index", 12459.361190795898d, "uniques", 9.019833517963864d, "rows", 26L))));
    assertExpectedResults(expectedResults, actualResults);
}