[
https://issues.apache.org/jira/browse/SPARK-41391?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ruifeng Zheng updated SPARK-41391:
----------------------------------
Description:
scala> val df = spark.range(1, 10).withColumn("value", lit(1))
df: org.apache.spark.sql.DataFrame = [id: bigint, value: int]
scala> df.createOrReplaceTempView("table")
scala> df.groupBy("id").agg(count_distinct($"value"))
res1: org.apache.spark.sql.DataFrame = [id: bigint, count(value): bigint]
scala> spark.sql(" SELECT id, COUNT(DISTINCT value) FROM table GROUP BY id ")
res2: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT value):
bigint]
scala> df.groupBy("id").agg(count_distinct($"*"))
res3: org.apache.spark.sql.DataFrame = [id: bigint, count(unresolvedstar()):
bigint]
scala> spark.sql(" SELECT id, COUNT(DISTINCT *) FROM table GROUP BY id ")
res4: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT id, value):
bigint]
> The output column name of `groupBy.agg(count_distinct)` is incorrect
> --------------------------------------------------------------------
>
> Key: SPARK-41391
> URL: https://issues.apache.org/jira/browse/SPARK-41391
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.2.0, 3.3.0, 3.4.0
> Reporter: Ruifeng Zheng
> Priority: Major
>
> scala> val df = spark.range(1, 10).withColumn("value", lit(1))
> df: org.apache.spark.sql.DataFrame = [id: bigint, value: int]
> scala> df.createOrReplaceTempView("table")
> scala> df.groupBy("id").agg(count_distinct($"value"))
> res1: org.apache.spark.sql.DataFrame = [id: bigint, count(value): bigint]
> scala> spark.sql(" SELECT id, COUNT(DISTINCT value) FROM table GROUP BY id ")
> res2: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT value):
> bigint]
> scala> df.groupBy("id").agg(count_distinct($"*"))
> res3: org.apache.spark.sql.DataFrame = [id: bigint, count(unresolvedstar()):
> bigint]
> scala> spark.sql(" SELECT id, COUNT(DISTINCT *) FROM table GROUP BY id ")
> res4: org.apache.spark.sql.DataFrame = [id: bigint, count(DISTINCT id,
> value): bigint]
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
