You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Michael Armbrust (JIRA)" <ji...@apache.org> on 2014/06/07 03:57:01 UTC
[jira] [Commented] (SPARK-2063) Creating a SchemaRDD via sql() does
not correctly resolve nested types
[ https://issues.apache.org/jira/browse/SPARK-2063?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14020641#comment-14020641 ]
Michael Armbrust commented on SPARK-2063:
-----------------------------------------
This seems to work for me:
{code}
scala> val popularTweets = sql("SELECT retweeted_status.text, MAX(retweeted_status.retweet_count) AS s FROM tweetTable WHERE retweeted_status is not NULL GROUP BY retweeted_status.text ORDER BY s DESC LIMIT 30")
popularTweets: org.apache.spark.sql.SchemaRDD =
SchemaRDD[13] at RDD at SchemaRDD.scala:117
== Query Plan ==
TakeOrdered 30, [s#26:1 DESC]
Aggregate false, [text#27], [text#27,MAX(PartialMax#30) AS s#26]
Exchange (HashPartitioning [text#27:0], 150)
Aggregate true, [retweeted_status#23.text AS text#27], [retweeted_status#23.text AS text#27,MAX(retweeted_status#23.retweet_count AS retweet_count#29) AS PartialMax#30]
Project [retweeted_status#23:23]
Filter IS NOT NULL retweeted_status#23:23
ExistingRdd [contributors#0,created_at#1,favorite_count#2,favorited#3,filter_level#4,id#5L,id_str#6,in_reply_to_screen_name#7,in_reply_to_status_id#8L,in_reply_to_status_id_str#9,in_reply_to_user_id#10,in_reply_to_user_id_str#11,lang#12,possibly_sensitive#13,retweet_count#14,retwee...
scala> popularTweets.collect()
res3: Array[org.apache.spark.sql.Row] = Array([Four more years. http://t.co/bAJE6Vom,793368], [388726,388726], [Thank you all for helping me through this time with your enormous love & support. Cory will forever be in my heart. http://t.co/XVlZnh9vOc,388719], [Yesss ! I'm 20 ! Wohooo ! No more teens!,369389], [Never been more happy in my life ! Thank you to everyone that has been so lovely about my engagement to my beautiful fiancé ! Big love z X,320358], [Note to self. Don't 'twerk'.,314666], [Harry wake up !! :D http://t.co/cuhD5bC5,311770], [In honor of Kim and Kanye's baby "North West" I will be naming my first son "Taco",311575], [ITS NIALL BITCH!! HAHA,283976], [what makes you so beautiful is that you dont know how beautiful you are... to me,279850], [279578,279578], [applied ...
{code}
> Creating a SchemaRDD via sql() does not correctly resolve nested types
> ----------------------------------------------------------------------
>
> Key: SPARK-2063
> URL: https://issues.apache.org/jira/browse/SPARK-2063
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.0.0
> Reporter: Aaron Davidson
> Assignee: Michael Armbrust
>
> For example, from the typical twitter dataset:
> {code}
> scala> val popularTweets = sql("SELECT retweeted_status.text, MAX(retweeted_status.retweet_count) AS s FROM tweets WHERE retweeted_status is not NULL GROUP BY retweeted_status.text ORDER BY s DESC LIMIT 30")
> scala> popularTweets.toString
> 14/06/06 21:27:48 INFO analysis.Analyzer: Max iterations (2) reached for batch MultiInstanceRelations
> 14/06/06 21:27:48 INFO analysis.Analyzer: Max iterations (2) reached for batch CaseInsensitiveAttributeReferences
> org.apache.spark.sql.catalyst.analysis.UnresolvedException: Invalid call to qualifiers on unresolved object, tree: 'retweeted_status.text
> at org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute.qualifiers(unresolved.scala:51)
> at org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute.qualifiers(unresolved.scala:47)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$2.apply(LogicalPlan.scala:67)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$2.apply(LogicalPlan.scala:65)
> at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
> at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
> at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolve(LogicalPlan.scala:65)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:100)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:97)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:165)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionDown$1(QueryPlan.scala:51)
> at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1$$anonfun$apply$1.apply(QueryPlan.scala:65)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:64)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:69)
> at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:40)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3.applyOrElse(Analyzer.scala:97)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3.applyOrElse(Analyzer.scala:94)
> at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:217)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:94)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:93)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:62)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:60)
> at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:60)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:52)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.apply(RuleExecutor.scala:52)
> at org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:265)
> at org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:265)
> at org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan$lzycompute(SQLContext.scala:266)
> at org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan(SQLContext.scala:266)
> at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:268)
> at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:268)
> at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:269)
> at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:269)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:272)
> at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:272)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:154)
> {code}
--
This message was sent by Atlassian JIRA
(v6.2#6252)