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

Example 16 with FilteredAggregatorFactory

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

the class QuantileSqlAggregatorTest method testQuantileOnFloatAndLongs.

@Test
public void testQuantileOnFloatAndLongs() throws Exception {
    try (final DruidPlanner planner = plannerFactory.createPlanner(null)) {
        final String sql = "SELECT\n" + "APPROX_QUANTILE(m1, 0.01),\n" + "APPROX_QUANTILE(m1, 0.5, 50),\n" + "APPROX_QUANTILE(m1, 0.98, 200),\n" + "APPROX_QUANTILE(m1, 0.99),\n" + "APPROX_QUANTILE(m1, 0.99) FILTER(WHERE dim1 = 'abc'),\n" + "APPROX_QUANTILE(m1, 0.999) FILTER(WHERE dim1 <> 'abc'),\n" + "APPROX_QUANTILE(m1, 0.999) FILTER(WHERE dim1 = 'abc'),\n" + "APPROX_QUANTILE(cnt, 0.5)\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, 1.0 });
        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 ApproximateHistogramAggregatorFactory("a0:agg", "m1", null, null, null, null), new ApproximateHistogramAggregatorFactory("a2:agg", "m1", 200, null, null, null), new FilteredAggregatorFactory(new ApproximateHistogramAggregatorFactory("a4:agg", "m1", null, null, null, null), new SelectorDimFilter("dim1", "abc", null)), new FilteredAggregatorFactory(new ApproximateHistogramAggregatorFactory("a5:agg", "m1", null, null, null, null), new NotDimFilter(new SelectorDimFilter("dim1", "abc", null))), new ApproximateHistogramAggregatorFactory("a7:agg", "cnt", null, null, null, 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), new QuantilePostAggregator("a7", "a7:agg", 0.50f))).context(ImmutableMap.<String, Object>of("skipEmptyBuckets", true)).build(), Iterables.getOnlyElement(queryLogHook.getRecordedQueries()));
    }
}

Example 17 with FilteredAggregatorFactory

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

the class FilteredAggregatorBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schema);
    BenchmarkDataGenerator gen = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    incIndex = makeIncIndex(schemaInfo.getAggsArray());
    filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new JavaScriptDimFilter("dimSequential", "function(x) { return false }", null, JavaScriptConfig.getEnabledInstance()), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Arrays.asList("X"), null)));
    filteredMetrics = new AggregatorFactory[1];
    filteredMetrics[0] = new FilteredAggregatorFactory(new CountAggregatorFactory("rows"), filter);
    incIndexFilteredAgg = makeIncIndex(filteredMetrics);
    inputRows = new ArrayList<>();
    for (int j = 0; j < rowsPerSegment; j++) {
        InputRow row = gen.nextRow();
        if (j % 10000 == 0) {
            log.info(j + " rows generated.");
        }
        incIndex.add(row);
        inputRows.add(row);
    }
    tmpDir = Files.createTempDir();
    log.info("Using temp dir: " + tmpDir.getAbsolutePath());
    indexFile = INDEX_MERGER_V9.persist(incIndex, tmpDir, new IndexSpec());
    qIndex = INDEX_IO.loadIndex(indexFile);
    factory = new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(QueryBenchmarkUtil.NoopIntervalChunkingQueryRunnerDecorator()), new TimeseriesQueryEngine(), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
    BenchmarkSchemaInfo basicSchema = BenchmarkSchemas.SCHEMA_MAP.get("basic");
    QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
    List<AggregatorFactory> queryAggs = new ArrayList<>();
    queryAggs.add(filteredMetrics[0]);
    query = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
}

Example 18 with FilteredAggregatorFactory

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

the class GroupByQueryRunnerTest method testSubqueryWithOuterFilterAggregator.

@Test
public void testSubqueryWithOuterFilterAggregator() {
    final GroupByQuery subquery = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.fullOnInterval).setDimensions(Lists.<DimensionSpec>newArrayList(new DefaultDimensionSpec("market", "market"), new DefaultDimensionSpec("quality", "quality"))).setAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.rowsCount, new LongSumAggregatorFactory("index", "index"))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    final DimFilter filter = new SelectorDimFilter("market", "spot", null);
    final GroupByQuery query = GroupByQuery.builder().setDataSource(subquery).setQuerySegmentSpec(QueryRunnerTestHelper.fullOnInterval).setDimensions(Lists.<DimensionSpec>newArrayList()).setAggregatorSpecs(ImmutableList.<AggregatorFactory>of(new FilteredAggregatorFactory(QueryRunnerTestHelper.rowsCount, filter))).setGranularity(QueryRunnerTestHelper.allGran).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("1970-01-01", "rows", 837L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}

Example 19 with FilteredAggregatorFactory

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

the class GroupByQueryRunnerTest method testSubqueryWithOuterTimeFilter.

@Test
public void testSubqueryWithOuterTimeFilter() {
    final GroupByQuery subquery = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.fullOnInterval).setDimensions(Lists.<DimensionSpec>newArrayList(new DefaultDimensionSpec("market", "market"), new DefaultDimensionSpec("quality", "quality"))).setAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.rowsCount, new LongSumAggregatorFactory("index", "index"))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    final DimFilter fridayFilter = new SelectorDimFilter(Column.TIME_COLUMN_NAME, "Friday", new TimeFormatExtractionFn("EEEE", null, null, null, false));
    final DimFilter firstDaysFilter = new InDimFilter(Column.TIME_COLUMN_NAME, ImmutableList.of("1", "2", "3"), new TimeFormatExtractionFn("d", null, null, null, false));
    final GroupByQuery query = GroupByQuery.builder().setDataSource(subquery).setQuerySegmentSpec(QueryRunnerTestHelper.fullOnInterval).setDimensions(Lists.<DimensionSpec>newArrayList()).setDimFilter(firstDaysFilter).setAggregatorSpecs(ImmutableList.<AggregatorFactory>of(new FilteredAggregatorFactory(QueryRunnerTestHelper.rowsCount, fridayFilter))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-02-01", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-02-02", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-02-03", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-03-01", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-03-02", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-03-03", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "rows", 13L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "rows", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-03", "rows", 0L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}