spark FlatMapGroupsInPandasExec 源码

spark FlatMapGroupsInPandasExec 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/python/FlatMapGroupsInPandasExec.scala

/*
 * 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.execution.python

import org.apache.spark.api.python.{ChainedPythonFunctions, PythonEvalType}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.physical.{AllTuples, ClusteredDistribution, Distribution, Partitioning}
import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode}
import org.apache.spark.sql.execution.python.PandasGroupUtils._
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.util.ArrowUtils


/**
 * Physical node for [[org.apache.spark.sql.catalyst.plans.logical.FlatMapGroupsInPandas]]
 *
 * Rows in each group are passed to the Python worker as an Arrow record batch.
 * The Python worker turns the record batch to a `pandas.DataFrame`, invoke the
 * user-defined function, and passes the resulting `pandas.DataFrame`
 * as an Arrow record batch. Finally, each record batch is turned to
 * Iterator[InternalRow] using ColumnarBatch.
 *
 * Note on memory usage:
 * Both the Python worker and the Java executor need to have enough memory to
 * hold the largest group. The memory on the Java side is used to construct the
 * record batch (off heap memory). The memory on the Python side is used for
 * holding the `pandas.DataFrame`. It's possible to further split one group into
 * multiple record batches to reduce the memory footprint on the Java side, this
 * is left as future work.
 */
case class FlatMapGroupsInPandasExec(
    groupingAttributes: Seq[Attribute],
    func: Expression,
    output: Seq[Attribute],
    child: SparkPlan)
  extends SparkPlan with UnaryExecNode {

  private val sessionLocalTimeZone = conf.sessionLocalTimeZone
  private val pythonRunnerConf = ArrowUtils.getPythonRunnerConfMap(conf)
  private val pandasFunction = func.asInstanceOf[PythonUDF].func
  private val chainedFunc = Seq(ChainedPythonFunctions(Seq(pandasFunction)))

  override def producedAttributes: AttributeSet = AttributeSet(output)

  override def outputPartitioning: Partitioning = child.outputPartitioning

  override def requiredChildDistribution: Seq[Distribution] = {
    if (groupingAttributes.isEmpty) {
      AllTuples :: Nil
    } else {
      ClusteredDistribution(groupingAttributes) :: Nil
    }
  }

  override def requiredChildOrdering: Seq[Seq[SortOrder]] =
    Seq(groupingAttributes.map(SortOrder(_, Ascending)))

  override protected def doExecute(): RDD[InternalRow] = {
    val inputRDD = child.execute()

    val (dedupAttributes, argOffsets) = resolveArgOffsets(child.output, groupingAttributes)

    // Map grouped rows to ArrowPythonRunner results, Only execute if partition is not empty
    inputRDD.mapPartitionsInternal { iter => if (iter.isEmpty) iter else {

      val data = groupAndProject(iter, groupingAttributes, child.output, dedupAttributes)
        .map { case (_, x) => x }

      val runner = new ArrowPythonRunner(
        chainedFunc,
        PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
        Array(argOffsets),
        StructType.fromAttributes(dedupAttributes),
        sessionLocalTimeZone,
        pythonRunnerConf)

      executePython(data, output, runner)
    }}
  }

  override protected def withNewChildInternal(newChild: SparkPlan): FlatMapGroupsInPandasExec =
    copy(child = newChild)
}

相关信息

spark 源码目录

相关文章

spark AggregateInPandasExec 源码

spark ApplyInPandasWithStatePythonRunner 源码

spark ApplyInPandasWithStateWriter 源码

spark ArrowEvalPythonExec 源码

spark ArrowPythonRunner 源码

spark AttachDistributedSequenceExec 源码

spark BatchEvalPythonExec 源码

spark CoGroupedArrowPythonRunner 源码

spark EvalPythonExec 源码

spark EvaluatePython 源码