HyukjinKwon commented on a change in pull request #24997: [SPARK-28198][PYTHON] Add mapPartitionsInPandas to allow an iterator of DataFrames URL: https://github.com/apache/spark/pull/24997#discussion_r299020177
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/python/MapPartitionsInPandasExec.scala ########## @@ -0,0 +1,95 @@ +/* + * 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 scala.collection.JavaConverters._ + +import org.apache.spark.TaskContext +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._ +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.types.{StructField, StructType} +import org.apache.spark.sql.util.ArrowUtils +import org.apache.spark.sql.vectorized.{ArrowColumnVector, ColumnarBatch} + +/** + * A relation produced by applying a function that takes an iterator of pandas DataFrames + * and outputs an iterator of pandas DataFrames. + * + * This is somewhat similar with [[FlatMapGroupsInPandasExec]] and + * `org.apache.spark.sql.catalyst.plans.logical.MapPartitionsInRWithArrow` + * + */ +case class MapPartitionsInPandasExec( + func: Expression, + output: Seq[Attribute], + child: SparkPlan) + extends UnaryExecNode { + + private val pandasFunction = func.asInstanceOf[PythonUDF].func + + override def producedAttributes: AttributeSet = AttributeSet(output) + + private val batchSize = conf.arrowMaxRecordsPerBatch + + override def outputPartitioning: Partitioning = child.outputPartitioning Review comment: Hm, I just noticed other Python UDFs set it as unknown partitioning whereas `dapply` in R (without and with Arrow) and specify child output partitioning. I haven't taken a close look but matching it to `mapPartitions` should be fine. The partitioning and distribution looks not going to be affected because it converts one partition to the other but maybe I miss something. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
