mayankshriv commented on a change in pull request #7226:
URL: https://github.com/apache/pinot/pull/7226#discussion_r683866618
##########
File path:
pinot-core/src/test/java/org/apache/pinot/queries/InterSegmentAggregationSingleValueQueriesTest.java
##########
@@ -412,6 +412,186 @@ public void testPercentileEst99() {
new String[]{"2146232405", "999309554"});
}
+ @Test
+ public void testPercentileRawEst50() {
+ ExpectedQueryResult expectedQueryResultsBasic =
+ new ExpectedQueryResult(120000L, 0L, 240000L, 120000L, new
String[]{"1107310944", "1082130431"});
Review comment:
These are probably brittle tests since we are hardcoding the expected
results? We should probably test that results are within a certain error margin
of the accurate percentile?
##########
File path:
pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/PercentileRawEstAggregationFunction.java
##########
@@ -0,0 +1,137 @@
+/**
+ * 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.pinot.core.query.aggregation.function;
+
+import java.util.Map;
+import org.apache.pinot.common.request.context.ExpressionContext;
+import org.apache.pinot.common.utils.DataSchema.ColumnDataType;
+import org.apache.pinot.core.common.BlockValSet;
+import org.apache.pinot.core.query.aggregation.AggregationResultHolder;
+import org.apache.pinot.core.query.aggregation.groupby.GroupByResultHolder;
+import org.apache.pinot.segment.local.customobject.QuantileDigest;
+import org.apache.pinot.segment.local.utils.CustomSerDeUtils;
+import org.apache.pinot.segment.spi.AggregationFunctionType;
+import org.apache.pinot.spi.utils.BytesUtils;
+
+
+public class PercentileRawEstAggregationFunction extends
BaseSingleInputAggregationFunction<QuantileDigest, String> {
+ private final PercentileEstAggregationFunction
_percentileRawEstAggregationFunction;
+
+ public PercentileRawEstAggregationFunction(ExpressionContext
expressionContext, double percentile) {
+ this(expressionContext, new
PercentileEstAggregationFunction(expressionContext, percentile));
+ }
+
+ public PercentileRawEstAggregationFunction(ExpressionContext
expressionContext, int percentile) {
+ this(expressionContext, new
PercentileEstAggregationFunction(expressionContext, percentile));
+ }
+
+ PercentileRawEstAggregationFunction(ExpressionContext expression,
+ PercentileEstAggregationFunction percentileRawEstAggregationFunction) {
+ super(expression);
+ _percentileRawEstAggregationFunction = percentileRawEstAggregationFunction;
+ }
+
+ @Override
+ public AggregationFunctionType getType() {
+ return AggregationFunctionType.PERCENTILERAWEST;
+ }
+
+ @Override
+ public String getColumnName() {
+ final double percentile = _percentileRawEstAggregationFunction._percentile;
+ final int version = _percentileRawEstAggregationFunction._version;
+ final String type = getType().getName();
+
+ return version == 0 ? type + (int) percentile + "_" + _expression : type +
percentile + "_" + _expression;
+ }
+
+ @Override
+ public String getResultColumnName() {
+ final double percentile = _percentileRawEstAggregationFunction._percentile;
+ final int version = _percentileRawEstAggregationFunction._version;
+ final String type = getType().getName().toLowerCase();
+
+ return version == 0 ? type + (int) percentile + "(" + _expression + ")"
+ : type + "(" + _expression + ", " + percentile + ")";
+ }
+
+ @Override
+ public AggregationResultHolder createAggregationResultHolder() {
+ return
_percentileRawEstAggregationFunction.createAggregationResultHolder();
+ }
+
+ @Override
+ public GroupByResultHolder createGroupByResultHolder(int initialCapacity,
int maxCapacity) {
+ return
_percentileRawEstAggregationFunction.createGroupByResultHolder(initialCapacity,
maxCapacity);
+ }
+
+ @Override
+ public void aggregate(int length, AggregationResultHolder
aggregationResultHolder,
+ Map<ExpressionContext, BlockValSet> blockValSetMap) {
+ _percentileRawEstAggregationFunction.aggregate(length,
aggregationResultHolder, blockValSetMap);
+ }
+
+ @Override
+ public void aggregateGroupBySV(int length, int[] groupKeyArray,
GroupByResultHolder groupByResultHolder,
+ Map<ExpressionContext, BlockValSet> blockValSetMap) {
+ _percentileRawEstAggregationFunction.aggregateGroupBySV(length,
groupKeyArray, groupByResultHolder, blockValSetMap);
+ }
+
+ @Override
+ public void aggregateGroupByMV(int length, int[][] groupKeysArray,
GroupByResultHolder groupByResultHolder,
+ Map<ExpressionContext, BlockValSet> blockValSetMap) {
+ _percentileRawEstAggregationFunction
+ .aggregateGroupByMV(length, groupKeysArray, groupByResultHolder,
blockValSetMap);
+ }
+
+ @Override
+ public QuantileDigest extractAggregationResult(AggregationResultHolder
aggregationResultHolder) {
+ return
_percentileRawEstAggregationFunction.extractAggregationResult(aggregationResultHolder);
+ }
+
+ @Override
+ public QuantileDigest extractGroupByResult(GroupByResultHolder
groupByResultHolder, int groupKey) {
+ return
_percentileRawEstAggregationFunction.extractGroupByResult(groupByResultHolder,
groupKey);
+ }
+
+ @Override
+ public QuantileDigest merge(QuantileDigest intermediateResult1,
QuantileDigest intermediateResult2) {
+ return _percentileRawEstAggregationFunction.merge(intermediateResult1,
intermediateResult2);
+ }
+
+ @Override
+ public boolean isIntermediateResultComparable() {
+ return
_percentileRawEstAggregationFunction.isIntermediateResultComparable();
+ }
+
+ @Override
+ public ColumnDataType getIntermediateResultColumnType() {
+ return
_percentileRawEstAggregationFunction.getIntermediateResultColumnType();
+ }
+
+ @Override
+ public ColumnDataType getFinalResultColumnType() {
+ return ColumnDataType.STRING;
+ }
+
+ @Override
+ public String extractFinalResult(QuantileDigest intermediateResult) {
+ return
BytesUtils.toHexString(CustomSerDeUtils.QUANTILE_DIGEST_SER_DE.serialize(intermediateResult));
Review comment:
We can do this outside this PR. Perhaps provide a wrapper to
encode/decode these bytes, and share it in the client side library. Once we
have a wrapper, we can do all sorts of things like compression etc. One reason
why we did String was so UI can show it without breaking. Would have to
evaluate that as well.
--
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: commits-unsubscr...@pinot.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org
