Examples with TopNQuery org.apache.druid.query.topn.TopNQuery used on opensource projects

Example 26 with TopNQuery

use of org.apache.druid.query.topn.TopNQuery in project druid by druid-io.

the class StringTopNColumnAggregatesProcessor method scanAndAggregateWithCardinalityKnown.

private long scanAndAggregateWithCardinalityKnown(TopNQuery query, Cursor cursor, DimensionSelector selector, Aggregator[][] rowSelector) {
    long processedRows = 0;
    while (!cursor.isDone()) {
        final IndexedInts dimValues = selector.getRow();
        for (int i = 0, size = dimValues.size(); i < size; ++i) {
            final int dimIndex = dimValues.get(i);
            Aggregator[] aggs = rowSelector[dimIndex];
            if (aggs == null) {
                final Comparable<?> key = dimensionValueConverter.apply(selector.lookupName(dimIndex));
                aggs = aggregatesStore.computeIfAbsent(key, k -> BaseTopNAlgorithm.makeAggregators(cursor, query.getAggregatorSpecs()));
                rowSelector[dimIndex] = aggs;
            }
            for (Aggregator aggregator : aggs) {
                aggregator.aggregate();
            }
        }
        cursor.advance();
        processedRows++;
    }
    return processedRows;
}

Example 27 with TopNQuery

use of org.apache.druid.query.topn.TopNQuery in project druid by druid-io.

the class FixedBucketsHistogramTopNQueryTest method testTopNWithFixedHistogramAgg.

@Test
public void testTopNWithFixedHistogramAgg() {
    FixedBucketsHistogramAggregatorFactory factory = new FixedBucketsHistogramAggregatorFactory("histo", "index", 10, 0, 2000, FixedBucketsHistogram.OutlierHandlingMode.OVERFLOW, false);
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(QueryRunnerTestHelper.MARKET_DIMENSION).metric(QueryRunnerTestHelper.dependentPostAggMetric).threshold(4).intervals(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.COMMON_DOUBLE_AGGREGATORS, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"), factory)))).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT, QueryRunnerTestHelper.DEPENDENT_POST_AGG, new QuantilePostAggregator("quantile", "histo", 0.5f)).build();
    List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<TopNResultValue>(DateTimes.of("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.MARKET_DIMENSION, "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", 1135.238f).put("histo", new FixedBucketsHistogram(0, 2000, 10, FixedBucketsHistogram.OutlierHandlingMode.OVERFLOW, new long[] { 0, 0, 0, 1, 21, 105, 42, 12, 5, 0 }, 186, 1743.92175, 792.326066, 0, 0, 0).toString()).build(), ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.MARKET_DIMENSION, "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", 969.69696f).put("histo", new FixedBucketsHistogram(0, 2000, 10, FixedBucketsHistogram.OutlierHandlingMode.OVERFLOW, new long[] { 0, 0, 4, 33, 66, 35, 25, 11, 10, 2 }, 186, 1870.061029, 545.990623, 0, 0, 0).toString()).build(), ImmutableMap.<String, Object>builder().put(QueryRunnerTestHelper.MARKET_DIMENSION, "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", 100.23952f).put("histo", new FixedBucketsHistogram(0, 2000, 10, FixedBucketsHistogram.OutlierHandlingMode.OVERFLOW, new long[] { 835, 2, 0, 0, 0, 0, 0, 0, 0, 0 }, 837, 277.273533, 59.021022, 0, 0, 0).toString()).build()))));
    List<Result<TopNResultValue>> results = runner.run(QueryPlus.wrap(query)).toList();
    TestHelper.assertExpectedResults(expectedResults, results);
}

Example 28 with TopNQuery

use of org.apache.druid.query.topn.TopNQuery in project druid by druid-io.

the class SchemalessTestFullTest method testFilteredTopN.

/**
 * See {@link #runTests}
 */
@SuppressWarnings("unused")
private void testFilteredTopN(QueryRunner runner, List<Result<TopNResultValue>> expectedResults, String failMsg) {
    TopNQuery query = new TopNQueryBuilder().dataSource(dataSource).granularity(ALL_GRAN).dimension(marketDimension).filters(marketDimension, "spot").metric(indexMetric).threshold(3).intervals(fullOnInterval).aggregators(Lists.newArrayList(Iterables.concat(commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(addRowsIndexConstant).build();
    failMsg += " filtered topN ";
    Iterable<Result<TopNResultValue>> actualResults = runner.run(QueryPlus.wrap(query)).toList();
    TestHelper.assertExpectedResults(expectedResults, actualResults, failMsg);
}

Example 29 with TopNQuery

use of org.apache.druid.query.topn.TopNQuery in project druid by druid-io.

the class SchemalessTestFullTest method testFullOnTopN.

/**
 * See {@link #runTests}
 */
@SuppressWarnings("unused")
private void testFullOnTopN(QueryRunner runner, List<Result<TopNResultValue>> expectedResults, String failMsg) {
    TopNQuery query = new TopNQueryBuilder().dataSource(dataSource).granularity(ALL_GRAN).dimension(marketDimension).metric(indexMetric).threshold(3).intervals(fullOnInterval).aggregators(Lists.newArrayList(Iterables.concat(commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(addRowsIndexConstant).build();
    failMsg += " topN ";
    Iterable<Result<TopNResultValue>> actualResults = runner.run(QueryPlus.wrap(query)).toList();
    TestHelper.assertExpectedResults(expectedResults, actualResults, failMsg);
}

Example 30 with TopNQuery

use of org.apache.druid.query.topn.TopNQuery in project druid by druid-io.

the class CachingClusteredClientTest method testTopNCachingEmptyResults.

@Test
@SuppressWarnings("unchecked")
public void testTopNCachingEmptyResults() {
    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(getDefaultQueryRunner(), new TopNQueryQueryToolChest(new TopNQueryConfig()));
    testQueryCaching(runner, builder.randomQueryId().build(), Intervals.of("2011-01-01/2011-01-02"), makeTopNResultsWithoutRename(), Intervals.of("2011-01-02/2011-01-03"), makeTopNResultsWithoutRename(), Intervals.of("2011-01-05/2011-01-10"), makeTopNResultsWithoutRename(DateTimes.of("2011-01-05"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, DateTimes.of("2011-01-06"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-07"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-08"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, DateTimes.of("2011-01-09"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983), Intervals.of("2011-01-05/2011-01-10"), makeTopNResultsWithoutRename(DateTimes.of("2011-01-05T01"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, DateTimes.of("2011-01-06T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-07T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-08T01"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, DateTimes.of("2011-01-09T01"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983));
    TopNQuery query = builder.intervals("2011-01-01/2011-01-10").metric("imps").aggregators(RENAMED_AGGS).postAggregators(DIFF_ORDER_POST_AGGS).randomQueryId().build();
    TestHelper.assertExpectedResults(makeRenamedTopNResults(DateTimes.of("2011-01-05"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, DateTimes.of("2011-01-05T01"), "a", 50, 4994, "b", 50, 4993, "c", 50, 4992, DateTimes.of("2011-01-06"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-06T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-07"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-07T01"), "a", 50, 4991, "b", 50, 4990, "c", 50, 4989, DateTimes.of("2011-01-08"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, DateTimes.of("2011-01-08T01"), "a", 50, 4988, "b", 50, 4987, "c", 50, 4986, DateTimes.of("2011-01-09"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983, DateTimes.of("2011-01-09T01"), "a", 50, 4985, "b", 50, 4984, "c", 50, 4983), runner.run(QueryPlus.wrap(query)));
}