Examples with TopNQueryBuilder io.druid.query.topn.TopNQueryBuilder used on opensource projects

Example 11 with TopNQueryBuilder

use of io.druid.query.topn.TopNQueryBuilder in project druid by druid-io.

the class VarianceTopNQueryTest method testFullOnTopNOverUniques.

@Test
public void testFullOnTopNOverUniques() {
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(QueryRunnerTestHelper.marketDimension).metric(QueryRunnerTestHelper.uniqueMetric).threshold(3).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.<AggregatorFactory>newArrayList(Iterables.concat(VarianceTestHelper.commonPlusVarAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<TopNResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>builder().put("market", "spot").put("rows", 837L).put("index", 95606.57232284546D).put("addRowsIndexConstant", 96444.57232284546D).put("uniques", QueryRunnerTestHelper.UNIQUES_9).put("maxIndex", 277.2735290527344D).put("minIndex", 59.02102279663086D).put("index_var", 439.3851694586573D).build(), ImmutableMap.<String, Object>builder().put("market", "total_market").put("rows", 186L).put("index", 215679.82879638672D).put("addRowsIndexConstant", 215866.82879638672D).put("uniques", QueryRunnerTestHelper.UNIQUES_2).put("maxIndex", 1743.9217529296875D).put("minIndex", 792.3260498046875D).put("index_var", 27679.900887366413D).build(), ImmutableMap.<String, Object>builder().put("market", "upfront").put("rows", 186L).put("index", 192046.1060180664D).put("addRowsIndexConstant", 192233.1060180664D).put("uniques", QueryRunnerTestHelper.UNIQUES_2).put("maxIndex", 1870.06103515625D).put("minIndex", 545.9906005859375D).put("index_var", 79699.9780741607D).build()))));
    assertExpectedResults(expectedResults, query);
}

Example 12 with TopNQueryBuilder

use of io.druid.query.topn.TopNQueryBuilder in project druid by druid-io.

the class ApproximateHistogramTopNQueryTest method testTopNWithApproximateHistogramAgg.

@Test
public void testTopNWithApproximateHistogramAgg() {
    ApproximateHistogramAggregatorFactory factory = new ApproximateHistogramAggregatorFactory("apphisto", "index", 10, 5, Float.NEGATIVE_INFINITY, Float.POSITIVE_INFINITY);
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(QueryRunnerTestHelper.marketDimension).metric(QueryRunnerTestHelper.dependentPostAggMetric).threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.<AggregatorFactory>newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"), factory)))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant, QueryRunnerTestHelper.dependentPostAgg, new QuantilePostAggregator("quantile", "apphisto", 0.5f))).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<TopNResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.marketDimension, "total_market").put("rows", 186L).put("index", 215679.82879638672D).put("addRowsIndexConstant", 215866.82879638672D).put(QueryRunnerTestHelper.dependentPostAggMetric, 216053.82879638672D).put("uniques", QueryRunnerTestHelper.UNIQUES_2).put("maxIndex", 1743.9217529296875D).put("minIndex", 792.3260498046875D).put("quantile", 1085.6775f).put("apphisto", new Histogram(new float[] { 554.4271240234375f, 792.3260498046875f, 1030.2249755859375f, 1268.1239013671875f, 1506.0228271484375f, 1743.9217529296875f }, new double[] { 0.0D, 39.42073059082031D, 103.29110717773438D, 34.93659591674805D, 8.351564407348633D })).build(), ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.marketDimension, "upfront").put("rows", 186L).put("index", 192046.1060180664D).put("addRowsIndexConstant", 192233.1060180664D).put(QueryRunnerTestHelper.dependentPostAggMetric, 192420.1060180664D).put("uniques", QueryRunnerTestHelper.UNIQUES_2).put("maxIndex", 1870.06103515625D).put("minIndex", 545.9906005859375D).put("quantile", 880.9881f).put("apphisto", new Histogram(new float[] { 214.97299194335938f, 545.9906005859375f, 877.0081787109375f, 1208.0257568359375f, 1539.0433349609375f, 1870.06103515625f }, new double[] { 0.0D, 67.53287506103516D, 72.22068786621094D, 31.984678268432617D, 14.261756896972656D })).build(), ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.marketDimension, "spot").put("rows", 837L).put("index", 95606.57232284546D).put("addRowsIndexConstant", 96444.57232284546D).put(QueryRunnerTestHelper.dependentPostAggMetric, 97282.57232284546D).put("uniques", QueryRunnerTestHelper.UNIQUES_9).put("maxIndex", 277.2735290527344D).put("minIndex", 59.02102279663086D).put("quantile", 101.78856f).put("apphisto", new Histogram(new float[] { 4.457897186279297f, 59.02102279663086f, 113.58415222167969f, 168.14727783203125f, 222.7104034423828f, 277.2735290527344f }, new double[] { 0.0D, 462.4309997558594D, 357.5404968261719D, 15.022850036621094D, 2.0056631565093994D })).build()))));
    HashMap<String, Object> context = new HashMap<String, Object>();
    TestHelper.assertExpectedResults(expectedResults, runner.run(query, context));
}

Example 13 with TopNQueryBuilder

use of io.druid.query.topn.TopNQueryBuilder in project druid by druid-io.

the class TopNTypeInterfaceBenchmark method setupQueries.

private void setupQueries() {
    // queries for the basic schema
    Map<String, TopNQueryBuilder> 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"));
        // Use an IdentityExtractionFn to force usage of DimExtractionTopNAlgorithm
        TopNQueryBuilder queryBuilderString = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension(new ExtractionDimensionSpec("dimSequential", "dimSequential", IdentityExtractionFn.getInstance())).metric("sumFloatNormal").intervals(intervalSpec).aggregators(queryAggs);
        // DimExtractionTopNAlgorithm is always used for numeric columns
        TopNQueryBuilder queryBuilderLong = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension("metLongUniform").metric("sumFloatNormal").intervals(intervalSpec).aggregators(queryAggs);
        TopNQueryBuilder queryBuilderFloat = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension("metFloatNormal").metric("sumFloatNormal").intervals(intervalSpec).aggregators(queryAggs);
        basicQueries.put("string", queryBuilderString);
        basicQueries.put("long", queryBuilderLong);
        basicQueries.put("float", queryBuilderFloat);
    }
    {
        // basic.numericSort
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        queryAggs.add(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"));
        TopNQueryBuilder queryBuilderA = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension("dimUniform").metric(new DimensionTopNMetricSpec(null, StringComparators.NUMERIC)).intervals(intervalSpec).aggregators(queryAggs);
        basicQueries.put("numericSort", queryBuilderA);
    }
    {
        // basic.alphanumericSort
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        queryAggs.add(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"));
        TopNQueryBuilder queryBuilderA = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension("dimUniform").metric(new DimensionTopNMetricSpec(null, StringComparators.ALPHANUMERIC)).intervals(intervalSpec).aggregators(queryAggs);
        basicQueries.put("alphanumericSort", queryBuilderA);
    }
    SCHEMA_QUERY_MAP.put("basic", basicQueries);
}

Example 14 with TopNQueryBuilder

use of io.druid.query.topn.TopNQueryBuilder in project druid by druid-io.

the class CachingClusteredClientTest method testTopNCachingTimeZone.

@Test
@SuppressWarnings("unchecked")
public void testTopNCachingTimeZone() throws Exception {
    final TopNQueryBuilder builder = new TopNQueryBuilder().dataSource(DATA_SOURCE).dimension(TOP_DIM).metric("imps").threshold(3).intervals(SEG_SPEC).filters(DIM_FILTER).granularity(PT1H_TZ_GRANULARITY).aggregators(AGGS).postAggregators(POST_AGGS).context(CONTEXT);
    QueryRunner runner = new FinalizeResultsQueryRunner(client, new TopNQueryQueryToolChest(new TopNQueryConfig(), QueryRunnerTestHelper.NoopIntervalChunkingQueryRunnerDecorator()));
    testQueryCaching(runner, builder.build(), new Interval("2011-11-04/2011-11-08"), makeTopNResultsWithoutRename(new DateTime("2011-11-04", TIMEZONE), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-11-05", TIMEZONE), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-11-06", TIMEZONE), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-11-07", TIMEZONE), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986));
    HashMap<String, List> context = new HashMap<String, List>();
    TestHelper.assertExpectedResults(makeRenamedTopNResults(new DateTime("2011-11-04", TIMEZONE), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-11-05", TIMEZONE), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-11-06", TIMEZONE), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-11-07", TIMEZONE), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986), runner.run(builder.intervals("2011-11-04/2011-11-08").metric("imps").aggregators(RENAMED_AGGS).postAggregators(DIFF_ORDER_POST_AGGS).build(), context));
}

Example 15 with TopNQueryBuilder

use of io.druid.query.topn.TopNQueryBuilder in project druid by druid-io.

the class CachingClusteredClientTest method testTopNCachingEmptyResults.

@Test
@SuppressWarnings("unchecked")
public void testTopNCachingEmptyResults() throws Exception {
    final TopNQueryBuilder builder = new TopNQueryBuilder().dataSource(DATA_SOURCE).dimension(TOP_DIM).metric("imps").threshold(3).intervals(SEG_SPEC).filters(DIM_FILTER).granularity(GRANULARITY).aggregators(AGGS).postAggregators(POST_AGGS).context(CONTEXT);
    QueryRunner runner = new FinalizeResultsQueryRunner(client, new TopNQueryQueryToolChest(new TopNQueryConfig(), QueryRunnerTestHelper.NoopIntervalChunkingQueryRunnerDecorator()));
    testQueryCaching(runner, builder.build(), new Interval("2011-01-01/2011-01-02"), makeTopNResultsWithoutRename(), new Interval("2011-01-02/2011-01-03"), makeTopNResultsWithoutRename(), new Interval("2011-01-05/2011-01-10"), makeTopNResultsWithoutRename(new DateTime("2011-01-05"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-01-06"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-07"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-08"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, new DateTime("2011-01-09"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983), new Interval("2011-01-05/2011-01-10"), makeTopNResultsWithoutRename(new DateTime("2011-01-05T01"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-01-06T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-07T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-08T01"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, new DateTime("2011-01-09T01"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983));
    HashMap<String, List> context = new HashMap<String, List>();
    TestHelper.assertExpectedResults(makeRenamedTopNResults(new DateTime("2011-01-05"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-01-05T01"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, new DateTime("2011-01-06"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-06T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-07"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-07T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, new DateTime("2011-01-08"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, new DateTime("2011-01-08T01"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, new DateTime("2011-01-09"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983, new DateTime("2011-01-09T01"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983), runner.run(builder.intervals("2011-01-01/2011-01-10").metric("imps").aggregators(RENAMED_AGGS).postAggregators(DIFF_ORDER_POST_AGGS).build(), context));
}