BryanCutler commented on a change in pull request #24734:
[SPARK-27870][SQL][PySpark] Flush each batch for pandas UDF (for improving
pandas UDFs pipeline)
URL: https://github.com/apache/spark/pull/24734#discussion_r288754136
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowEvalPythonExec.scala
##########
@@ -86,28 +86,11 @@ case class ArrowEvalPythonExec(udfs: Seq[PythonUDF],
resultAttrs: Seq[Attribute]
sessionLocalTimeZone,
pythonRunnerConf).compute(batchIter, context.partitionId(), context)
- new Iterator[InternalRow] {
-
- private var currentIter = if (columnarBatchIter.hasNext) {
- val batch = columnarBatchIter.next()
- val actualDataTypes = (0 until batch.numCols()).map(i =>
batch.column(i).dataType())
- assert(outputTypes == actualDataTypes, "Invalid schema from
pandas_udf: " +
- s"expected ${outputTypes.mkString(", ")}, got
${actualDataTypes.mkString(", ")}")
- batch.rowIterator.asScala
- } else {
- Iterator.empty
- }
-
- override def hasNext: Boolean = currentIter.hasNext || {
- if (columnarBatchIter.hasNext) {
- currentIter = columnarBatchIter.next().rowIterator.asScala
- hasNext
- } else {
- false
- }
- }
-
- override def next(): InternalRow = currentIter.next()
+ columnarBatchIter.flatMap { batch =>
+ val actualDataTypes = (0 until batch.numCols()).map(i =>
batch.column(i).dataType())
+ assert(outputTypes == actualDataTypes, "Invalid schema from pandas_udf:
" +
+ s"expected ${outputTypes.mkString(", ")}, got
${actualDataTypes.mkString(", ")}")
+ batch.rowIterator.asScala
Review comment:
If I understand this correctly, you are saying that when the `Iterator` is
constructed, the first batch of rows is read and that is wrong? I think you are
right about that
----------------------------------------------------------------
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]
