ueshin commented on code in PR #45701:
URL: https://github.com/apache/spark/pull/45701#discussion_r1543431051
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala:
##########
@@ -3338,7 +3358,25 @@ class Dataset[T] private[sql] (
}
def observe(name: String, expr: Column, exprs: Column*): Dataset[T] = {
Review Comment:
Don't we need to annotate this with `@varargs` for Java client?
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/Dataset.scala:
##########
@@ -3338,7 +3358,25 @@ class Dataset[T] private[sql] (
}
def observe(name: String, expr: Column, exprs: Column*): Dataset[T] = {
- throw new UnsupportedOperationException("observe is not implemented.")
+ sparkSession.newDataset(agnosticEncoder, getObservationsMapOpt) { builder
=>
+ builder.getCollectMetricsBuilder
+ .setInput(plan.getRoot)
+ .setName(name)
+ .addAllMetrics((expr +: exprs).map(_.expr).asJava)
+ }
+ }
+
+ def observe(observation: Observation, expr: Column, exprs: Column*):
Dataset[T] = {
Review Comment:
ditto.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
