zhengruifeng commented on code in PR #53232:
URL: https://github.com/apache/spark/pull/53232#discussion_r2567946545
##########
mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala:
##########
@@ -1142,4 +1143,31 @@ private[spark] object ReadWriteUtils {
spark.read.parquet(path).as[T].collect()
}
}
+
+ def saveDataFrame(path: String, df: DataFrame): Unit = {
+ if (localSavingModeState.get()) {
+ val filePath = Paths.get(path)
+ Files.createDirectories(filePath.getParent)
+
+ df match {
+ case d: org.apache.spark.sql.classic.DataFrame =>
+ ArrowFileReadWrite.save(d, path)
+ case _ => throw new UnsupportedOperationException("Unsupported
dataframe type")
+ }
+ } else {
+ df.write.parquet(path)
+ }
+ }
+
+ def loadDataFrame(path: String, spark: SparkSession): DataFrame = {
+ if (localSavingModeState.get()) {
+ spark match {
+ case s: org.apache.spark.sql.classic.SparkSession =>
+ ArrowFileReadWrite.load(s, path)
+ case _ => throw new UnsupportedOperationException("Unsupported session
type")
+ }
+ } else {
+ spark.read.parquet(path)
+ }
+ }
Review Comment:
we can read/write parquet with arrow, but it requires a new dependency
```
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-arrow</artifactId>
</dependency>
```
otherwise, I am not sure whether we have utils to read/write parquet.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
