Github user cloud-fan commented on a diff in the pull request:

    https://github.com/apache/spark/pull/15544#discussion_r139188790
  
    --- Diff: 
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxCountDistinctForIntervals.scala
 ---
    @@ -0,0 +1,248 @@
    +/*
    + * 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.spark.sql.catalyst.expressions.aggregate
    +
    +import java.util
    +
    +import org.apache.spark.sql.catalyst.InternalRow
    +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
    +import 
org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure, 
TypeCheckSuccess}
    +import org.apache.spark.sql.catalyst.expressions.{AttributeReference, 
ExpectsInputTypes, Expression, ExpressionDescription}
    +import org.apache.spark.sql.catalyst.util.{ArrayData, GenericArrayData, 
HyperLogLogPlusPlusHelper}
    +import org.apache.spark.sql.types._
    +
    +/**
    + * This function counts the approximate number of distinct values (ndv) in
    + * intervals constructed from endpoints specified in 
`endpointsExpression`. The endpoints will be
    + * sorted into ascending order. To count ndv's in these intervals, apply 
the HyperLogLogPlusPlus
    + * algorithm in each of them.
    + * @param child to estimate the ndv's of.
    + * @param endpointsExpression to construct the intervals.
    + * @param relativeSD The maximum estimation error allowed in the 
HyperLogLogPlusPlus algorithm.
    + */
    +@ExpressionDescription(
    --- End diff --
    
    we don't need this if it's an internal func


---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to