Stelyus commented on pull request #35233:
URL: https://github.com/apache/spark/pull/35233#issuecomment-1014977463


   Tested with:
   
   ```
   val adselect_raw = spark.createDataFrame(Seq(("imp-1",1),("imp-2",2)))
       .cache()
   val adselect = adselect_raw.select(
           expr("uuid()").alias("userUuid"),
           expr("_1").alias("impressionUuid"),
           expr("_1").alias("accessDateTime"),
           expr("_1").alias("publisher"),
           expr("_1").alias("site"),
           expr("_1").alias("placement"),
           expr("_1").alias("advertiser"),
           expr("_1").alias("campaign"),
           expr("_1").alias("lineItem"),
           expr("_1").alias("creative"),
           expr("_1").alias("browserLanguage"),
           expr("_1").alias("geoLocode"),
           expr("_1").alias("osFamily"),
           expr("_1").alias("osName"),
           expr("_1").alias("browserName"),
           expr("_1").alias("referrerDomain"),
           expr("_1").alias("placementIabCategory"),
           expr("_1").alias("placementDeviceGroup"),
           expr("_1").alias("placementDevice"),
           expr("_1").alias("placementVideoType"),
           expr("_1").alias("placementSection"),
           expr("_1").alias("placementPlayer"),
           expr("_1").alias("demandType"),
           expr("_1").alias("techCosts"),
           expr("_1").alias("mediaCosts"),
           expr("_1").alias("directSPrice"),
           expr("_1").alias("network"),
           expr("_1").alias("deviceSetting"),
           expr("_1").alias("placementGroup"),
           expr("_1").alias("postalCode"),
           expr("_1").alias("householdId")
       )
   
   val adcount_raw = spark.createDataFrame(Seq(("imp-1", 1), ("imp-2", 2)))
   val adcount = adcount_raw.select(
           expr("_1").alias("impressionUuid"),
           expr("_2").alias("accessDateTime")
       )
   
   val result =  adselect.join(adcount, Seq("impressionUuid"))
   result.explain()
   ```
   
   On my side, I get an OOM


-- 
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

Reply via email to