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

Example 1 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 2 with FilteredAggregatorFactory

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

the class GroupByQueryRunnerTest method testGroupByWithAggregatorFilterAndExtractionFunction.

@Test
public void testGroupByWithAggregatorFilterAndExtractionFunction() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("automotive", "automotive0");
    extractionMap.put("business", "business0");
    extractionMap.put("entertainment", "entertainment0");
    extractionMap.put("health", "health0");
    extractionMap.put("mezzanine", "mezzanineANDnews");
    extractionMap.put("news", "mezzanineANDnews");
    extractionMap.put("premium", "premium0");
    extractionMap.put("technology", "technology0");
    extractionMap.put("travel", "travel0");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, "missing", true, false);
    DimFilter filter = new ExtractionDimFilter("quality", "mezzanineANDnews", lookupExtractionFn, null);
    GroupByQuery query = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.firstToThird).setDimensions(Lists.<DimensionSpec>newArrayList(new DefaultDimensionSpec("quality", "alias"))).setAggregatorSpecs(Arrays.asList(new FilteredAggregatorFactory(QueryRunnerTestHelper.rowsCount, filter), (AggregatorFactory) new FilteredAggregatorFactory(new LongSumAggregatorFactory("idx", "index"), filter))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "automotive", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "business", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "entertainment", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "health", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "premium", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "technology", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "travel", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "automotive", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "business", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "entertainment", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "health", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "mezzanine", "rows", 3L, "idx", 2447L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "news", "rows", 1L, "idx", 114L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "premium", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "technology", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "travel", "rows", 0L, "idx", 0L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}

Example 3 with FilteredAggregatorFactory

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

the class TopNQueryRunnerTest method testTopNWithExtractionFilterNoExistingValue.

@Test
public void testTopNWithExtractionFilterNoExistingValue() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("", "NULL");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, true);
    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 DoubleMaxAggregatorFactory("maxIndex", "index"),
    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);
    // Assert the optimization path as well
    final Sequence<Result<TopNResultValue>> retval = runWithPreMergeAndMerge(topNQueryWithNULLValueExtraction);
    TestHelper.assertExpectedResults(expectedResults, retval);
}

Example 4 with FilteredAggregatorFactory

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

the class TimeseriesQueryRunnerTest method testTimeSeriesWithFilteredAggInvertedNullValue.

@Test
public void testTimeSeriesWithFilteredAggInvertedNullValue() {
    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"), new NotDimFilter(Druids.newSelectorDimFilterBuilder().dimension(QueryRunnerTestHelper.marketDimension).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);
}

Example 5 with FilteredAggregatorFactory

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

the class TimeseriesQueryRunnerTest method testTimeSeriesWithFilteredAggValueNotPresent.

@Test
public void testTimeSeriesWithFilteredAggValueNotPresent() {
    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"), new NotDimFilter(Druids.newSelectorDimFilterBuilder().dimension(QueryRunnerTestHelper.marketDimension).value("LolLol").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);
}