[
https://issues.apache.org/jira/browse/SPARK-17709?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15573512#comment-15573512
]
Ashish Shrowty commented on SPARK-17709:
----------------------------------------
[~smilegator] I compiled with the added debug information and here is the
output -
{code:java}
scala> val d1 = spark.sql("select * from testext2")
d1: org.apache.spark.sql.DataFrame = [productid: int, price: float ... 2 more
fields]
scala> val df1 =
d1.groupBy("companyid","productid").agg(sum("price").as("price"))
df1: org.apache.spark.sql.DataFrame = [companyid: int, productid: int ... 1
more field]
scala> val df2 =
d1.groupBy("companyid","productid").agg(sum("count").as("count"))
df2: org.apache.spark.sql.DataFrame = [companyid: int, productid: int ... 1
more field]
scala> df1.join(df2, Seq("companyid", "productid")).show
org.apache.spark.sql.AnalysisException: using columns ['companyid,'productid]
can not be resolved given input columns: [companyid, productid, price, count] ;;
'Join UsingJoin(Inner,List('companyid, 'productid))
:- Aggregate [companyid#121, productid#122], [companyid#121, productid#122,
sum(cast(price#123 as double)) AS price#166]
: +- Project [productid#122, price#123, count#124, companyid#121]
: +- SubqueryAlias testext2
: +- Relation[productid#122,price#123,count#124,companyid#121] parquet
+- Aggregate [companyid#121, productid#122], [companyid#121, productid#122,
sum(cast(count#124 as bigint)) AS count#177L]
+- Project [productid#122, price#123, count#124, companyid#121]
+- SubqueryAlias testext2
+- Relation[productid#122,price#123,count#124,companyid#121] parquet
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:40)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:58)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:174)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:67)
at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:126)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:67)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:58)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2589)
at org.apache.spark.sql.Dataset.join(Dataset.scala:641)
at org.apache.spark.sql.Dataset.join(Dataset.scala:614)
... 48 elided
{code}
> spark 2.0 join - column resolution error
> ----------------------------------------
>
> Key: SPARK-17709
> URL: https://issues.apache.org/jira/browse/SPARK-17709
> Project: Spark
> Issue Type: Bug
> Affects Versions: 2.0.0
> Reporter: Ashish Shrowty
> Labels: easyfix
>
> If I try to inner-join two dataframes which originated from the same initial
> dataframe that was loaded using spark.sql() call, it results in an error -
> // reading from Hive .. the data is stored in Parquet format in Amazon S3
> val d1 = spark.sql("select * from <hivetable>")
> val df1 = d1.groupBy("key1","key2")
> .agg(avg("totalprice").as("avgtotalprice"))
> val df2 = d1.groupBy("key1","key2")
> .agg(avg("itemcount").as("avgqty"))
> df1.join(df2, Seq("key1","key2")) gives error -
> org.apache.spark.sql.AnalysisException: using columns ['key1,'key2] can
> not be resolved given input columns: [key1, key2, avgtotalprice, avgqty];
> If the same Dataframe is initialized via spark.read.parquet(), the above code
> works. This same code above worked with Spark 1.6.2
--
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
