You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Wenchen Fan (JIRA)" <ji...@apache.org> on 2016/03/22 01:24:25 UTC
[jira] [Updated] (SPARK-13320) Confusing error message for Dataset
API when using sum("*")
[ https://issues.apache.org/jira/browse/SPARK-13320?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Wenchen Fan updated SPARK-13320:
--------------------------------
Assignee: Xiao Li
> Confusing error message for Dataset API when using sum("*")
> -----------------------------------------------------------
>
> Key: SPARK-13320
> URL: https://issues.apache.org/jira/browse/SPARK-13320
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Reporter: Reynold Xin
> Assignee: Xiao Li
>
> {code}
> pagecounts4PartitionsDS
> .map(line => (line._1, line._3))
> .toDF()
> .groupBy($"_1")
> .agg(sum("*") as "sumOccurances")
> {code}
> {code}
> org.apache.spark.sql.AnalysisException: cannot resolve '_1' given input columns _1, _2;
> at org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
> at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:60)
> at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:57)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:319)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:319)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:53)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:318)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:107)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:117)
> at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:121)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:121)
> at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:125)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:125)
> at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:57)
> at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:50)
> at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:105)
> at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:50)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:44)
> at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:34)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
> at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
> at org.apache.spark.sql.GroupedData.toDF(GroupedData.scala:57)
> at org.apache.spark.sql.GroupedData.agg(GroupedData.scala:213)
> {code}
> The error is with sum("*"), not the resolution of group by "_1".
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org