[
https://issues.apache.org/jira/browse/SPARK-12491?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15073098#comment-15073098
]
Tristan commented on SPARK-12491:
---------------------------------
Confirmed: Second 'show' of the problematic query works fine.
{code}
scala> import com.pipeline.spark._
import com.pipeline.spark._
scala> sqlContext.udf.register("gm", new GeometricMean)
res0: org.apache.spark.sql.expressions.UserDefinedAggregateFunction =
com.pipeline.spark.GeometricMean@1b7a2459
scala> import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions._
scala> val ids = sqlContext.range(1, 20)
ids: org.apache.spark.sql.DataFrame = [id: bigint]
scala> ids.registerTempTable("ids")
scala> val df = sqlContext.sql("select id, id % 3 as group_id from ids")
df: org.apache.spark.sql.DataFrame = [id: bigint, group_id: bigint]
scala> df.registerTempTable("simple")
scala> sqlContext.sql("select group_id, gm(id) from simple group by
group_id").show()
+--------+---+
|group_id|_c1|
+--------+---+
| 0|0.0|
| 1|0.0|
| 2|0.0|
+--------+---+
scala> sqlContext.sql("select group_id, gm(id) from simple group by
group_id").show()
+--------+-----------------+
|group_id| _c1|
+--------+-----------------+
| 0|8.981385496571725|
| 1|7.301716979342118|
| 2|7.706253151292568|
+--------+-----------------+
scala> sqlContext.sql("select group_id, gm(id) as geomean from simple group by
group_id").show()
+--------+-----------------+
|group_id| geomean|
+--------+-----------------+
| 0|8.981385496571725|
| 1|7.301716979342118|
| 2|7.706253151292568|
+--------+-----------------+
{code}
> UDAF result differs in SQL if alias is used
> -------------------------------------------
>
> Key: SPARK-12491
> URL: https://issues.apache.org/jira/browse/SPARK-12491
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.2
> Reporter: Tristan
> Attachments: UDAF_GM.zip
>
>
> Using the GeometricMean UDAF example
> (https://databricks.com/blog/2015/09/16/spark-1-5-dataframe-api-highlights-datetimestring-handling-time-intervals-and-udafs.html),
> I found the following discrepancy in results:
> {code}
> scala> sqlContext.sql("select group_id, gm(id) from simple group by
> group_id").show()
> +--------+---+
> |group_id|_c1|
> +--------+---+
> | 0|0.0|
> | 1|0.0|
> | 2|0.0|
> +--------+---+
> scala> sqlContext.sql("select group_id, gm(id) as GeometricMean from simple
> group by group_id").show()
> +--------+-----------------+
> |group_id| GeometricMean|
> +--------+-----------------+
> | 0|8.981385496571725|
> | 1|7.301716979342118|
> | 2|7.706253151292568|
> +--------+-----------------+
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
