frankgrimes97 commented on code in PR #13887: URL: https://github.com/apache/druid/pull/13887#discussion_r1142530993
########## extensions-core/datasketches/src/test/java/org/apache/druid/query/aggregation/datasketches/tuple/sql/ArrayOfDoublesSketchSqlAggregatorTest.java: ########## @@ -0,0 +1,452 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +package org.apache.druid.query.aggregation.datasketches.tuple.sql; + +import com.google.common.collect.ImmutableList; +import com.google.common.collect.ImmutableMap; +import com.google.inject.Injector; +import org.apache.druid.data.input.InputRow; +import org.apache.druid.guice.DruidInjectorBuilder; +import org.apache.druid.java.util.common.StringUtils; +import org.apache.druid.java.util.common.granularity.Granularities; +import org.apache.druid.query.Druids; +import org.apache.druid.query.QueryRunnerFactoryConglomerate; +import org.apache.druid.query.aggregation.CountAggregatorFactory; +import org.apache.druid.query.aggregation.LongSumAggregatorFactory; +import org.apache.druid.query.aggregation.datasketches.tuple.ArrayOfDoublesSketchAggregatorFactory; +import org.apache.druid.query.aggregation.datasketches.tuple.ArrayOfDoublesSketchModule; +import org.apache.druid.query.aggregation.datasketches.tuple.ArrayOfDoublesSketchOperations; +import org.apache.druid.query.aggregation.datasketches.tuple.ArrayOfDoublesSketchSetOpPostAggregator; +import org.apache.druid.query.aggregation.datasketches.tuple.ArrayOfDoublesSketchToMetricsSumEstimatePostAggregator; +import org.apache.druid.query.aggregation.post.ExpressionPostAggregator; +import org.apache.druid.query.aggregation.post.FieldAccessPostAggregator; +import org.apache.druid.query.dimension.DefaultDimensionSpec; +import org.apache.druid.query.groupby.GroupByQuery; +import org.apache.druid.segment.IndexBuilder; +import org.apache.druid.segment.QueryableIndex; +import org.apache.druid.segment.column.ColumnType; +import org.apache.druid.segment.incremental.IncrementalIndexSchema; +import org.apache.druid.segment.join.JoinableFactoryWrapper; +import org.apache.druid.segment.virtual.ExpressionVirtualColumn; +import org.apache.druid.segment.writeout.OffHeapMemorySegmentWriteOutMediumFactory; +import org.apache.druid.sql.calcite.BaseCalciteQueryTest; +import org.apache.druid.sql.calcite.filtration.Filtration; +import org.apache.druid.sql.calcite.util.CalciteTests; +import org.apache.druid.sql.calcite.util.SpecificSegmentsQuerySegmentWalker; +import org.apache.druid.sql.calcite.util.TestDataBuilder; +import org.apache.druid.timeline.DataSegment; +import org.apache.druid.timeline.partition.LinearShardSpec; +import org.junit.Test; + +import java.io.IOException; +import java.util.List; +import java.util.stream.Collectors; + +public class ArrayOfDoublesSketchSqlAggregatorTest extends BaseCalciteQueryTest +{ + + private static final String DATA_SOURCE = "foo"; + + // built from ArrayOfDoublesUpdatableSketch.update("FEDCAB", new double[] {0.0}).compact() + private static final String COMPACT_BASE_64_ENCODED_SKETCH_FOR_INTERSECTION = "AQEJAwgBzJP/////////fwEAAAAAAAAAjFnadZuMrkgAAAAAAAAAAA=="; + + private static final List<InputRow> ROWS = ImmutableList.of( + ImmutableMap.<String, Object>builder() + .put("t", "2000-01-01") + .put("dim1", "CA") + .put("dim2", "FEDCAB") + .put("m1", 5) + .build(), + ImmutableMap.<String, Object>builder() + .put("t", "2000-01-01") + .put("dim1", "US") + .put("dim2", "ABCDEF") + .put("m1", 12) + .build(), + ImmutableMap.<String, Object>builder() + .put("t", "2000-01-02") + .put("dim1", "CA") + .put("dim2", "FEDCAB") + .put("m1", 3) + .build(), + ImmutableMap.<String, Object>builder() + .put("t", "2000-01-02") + .put("dim1", "US") + .put("dim2", "ABCDEF") + .put("m1", 8) + .build(), + ImmutableMap.<String, Object>builder() + .put("t", "2000-01-03") + .put("dim1", "US") + .put("dim2", "ABCDEF") + .put("m1", 2) + .build() + ).stream().map(TestDataBuilder::createRow).collect(Collectors.toList()); + + @Override + public void configureGuice(DruidInjectorBuilder builder) + { + super.configureGuice(builder); + builder.addModule(new ArrayOfDoublesSketchModule()); + } + + @Override + public SpecificSegmentsQuerySegmentWalker createQuerySegmentWalker( + final QueryRunnerFactoryConglomerate conglomerate, + final JoinableFactoryWrapper joinableFactory, + final Injector injector + ) throws IOException + { + ArrayOfDoublesSketchModule.registerSerde(); + + final QueryableIndex index = IndexBuilder.create() + .tmpDir(temporaryFolder.newFolder()) + .segmentWriteOutMediumFactory( + OffHeapMemorySegmentWriteOutMediumFactory.instance() + ) + .schema( + new IncrementalIndexSchema.Builder() + .withMetrics( + new CountAggregatorFactory("cnt"), + new ArrayOfDoublesSketchAggregatorFactory( + "tuplesketch_dim2", + "dim2", + null, + ImmutableList.of("m1"), + 1 + ), + new LongSumAggregatorFactory("m1", "m1") + ) + .withRollup(false) + .build() + ) + .rows(ROWS) + .buildMMappedIndex(); + + return new SpecificSegmentsQuerySegmentWalker(conglomerate).add( + DataSegment.builder() + .dataSource(DATA_SOURCE) + .interval(index.getDataInterval()) + .version("1") + .shardSpec(new LinearShardSpec(0)) + .size(0) + .build(), + index + ); + } + + @Test + public void testMetricsSumEstimate() + { + cannotVectorize(); + + final String sql = "SELECT\n" + + " dim1,\n" + + " SUM(cnt),\n" + + " ARRAY_OF_DOUBLES_SKETCH_METRICS_SUM_ESTIMATE(ARRAY_OF_DOUBLES_SKETCH(tuplesketch_dim2)),\n" + + " ARRAY_OF_DOUBLES_SKETCH_METRICS_SUM_ESTIMATE(ARRAY_OF_DOUBLES_SKETCH(dim2, m1)),\n" + + " ARRAY_OF_DOUBLES_SKETCH_METRICS_SUM_ESTIMATE(ARRAY_OF_DOUBLES_SKETCH(dim2, m1, 256))\n" Review Comment: I agree they may be a bit cumbersome to type, but the right tradeoff between explicit-ness and terseness can be difficult to find. N.B. The same could be said of some of the existing Theta Sketch SQL functions. e.g. - `theta_sketch_estimate_with_error_bounds` - `APPROX_COUNT_DISTINCT_DS_THETA` https://github.com/apache/druid/blob/master/extensions-core/datasketches/src/test/java/org/apache/druid/query/aggregation/datasketches/theta/sql/ThetaSketchSqlAggregatorTest.java -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
