spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Alexandr Dzhagriev <dzh...@gmail.com>
Subject Re: Failed to 'collect_set' with dataset in spark 1.6
Date Mon, 01 Feb 2016 17:09:55 GMT
Hello again,

Also I've tried the following snippet with concat_ws:

val dataset = sc.parallelize(Seq(
  RecordExample(1, "apple"),
  RecordExample(1, "banana"),
  RecordExample(2, "orange"))
).toDS().groupBy($"a").agg(concat_ws(",", $"b").as[String])

dataset.take(10).foreach(println)


which also fails

Exception in thread "main" org.apache.spark.sql.AnalysisException:
expression 'b' is neither present in the group by, nor is it an aggregate
function. Add to group by or wrap in first() (or first_value) if you don't
care which value you get.;
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:38)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$
1.org
$apache$spark$sql$catalyst$analysis$CheckAnalysis$class$$anonfun$$checkValidAggregateExpression$1(CheckAnalysis.scala:130)

Thanks, Alex.

On Mon, Feb 1, 2016 at 6:03 PM, Alexandr Dzhagriev <dzhagr@gmail.com> wrote:

> Hi Ted,
>
> That doesn't help neither as one method delegates to another as far as I
> can see:
>
> def collect_list(columnName: String): Column = collect_list(Column(columnName))
>
>
> Thanks, Alex
>
> On Mon, Feb 1, 2016 at 5:55 PM, Ted Yu <yuzhihong@gmail.com> wrote:
>
>> bq. agg(collect_list("b")
>>
>> Have you tried:
>>
>> agg(collect_list($"b")
>>
>> On Mon, Feb 1, 2016 at 8:50 AM, Alexandr Dzhagriev <dzhagr@gmail.com>
>> wrote:
>>
>>> Hello,
>>>
>>> I'm trying to run the following example code:
>>>
>>> import org.apache.spark.sql.hive.HiveContext
>>> import org.apache.spark.{SparkContext, SparkConf}
>>> import org.apache.spark.sql.functions._
>>>
>>>
>>> case class RecordExample(a: Int, b: String)
>>>
>>> object ArrayExample {
>>>   def main(args: Array[String]) {
>>>     val conf = new SparkConf()
>>>
>>>     val sc = new SparkContext(conf)
>>>     val sqlContext = new HiveContext(sc)
>>>
>>>     import sqlContext.implicits._
>>>
>>>     val dataset = sc.parallelize(Seq(RecordExample(1, "apple"), RecordExample(2,
"orange"))).toDS()
>>>
>>>     dataset.groupBy($"a").agg(collect_list("b").as[List[String]])
>>>
>>>     dataset.collect()
>>>
>>>   }
>>>
>>> }
>>>
>>>
>>> and it fails with the following (please see the whole stack trace below):
>>>
>>>  Exception in thread "main" java.lang.ClassCastException:
>>> org.apache.spark.sql.types.ArrayType cannot be cast to
>>> org.apache.spark.sql.types.StructType
>>>
>>>
>>> Could please someone point me to the proper way to do that or confirm
>>> it's a bug?
>>>
>>> Thank you and here is the whole stacktrace:
>>>
>>> Exception in thread "main" java.lang.ClassCastException:
>>> org.apache.spark.sql.types.ArrayType cannot be cast to
>>> org.apache.spark.sql.types.StructType
>>> at org.apache.spark.sql.catalyst.expressions.GetStructField.org
>>> $apache$spark$sql$catalyst$expressions$GetStructField$$field$lzycompute(complexTypeExtractors.scala:107)
>>> at org.apache.spark.sql.catalyst.expressions.GetStructField.org
>>> $apache$spark$sql$catalyst$expressions$GetStructField$$field(complexTypeExtractors.scala:107)
>>> at
>>> org.apache.spark.sql.catalyst.expressions.GetStructField.dataType(complexTypeExtractors.scala:109)
>>> at
>>> org.apache.spark.sql.catalyst.analysis.ResolveUpCast$$anonfun$apply$24.applyOrElse(Analyzer.scala:1214)
>>> at
>>> org.apache.spark.sql.catalyst.analysis.ResolveUpCast$$anonfun$apply$24.applyOrElse(Analyzer.scala:1211)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:243)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:243)
>>> at
>>> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:53)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:242)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:265)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:305)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:265)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:305)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4$$anonfun$apply$9.apply(TreeNode.scala:294)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at scala.collection.immutable.List.foreach(List.scala:381)
>>> at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
>>> at scala.collection.immutable.List.map(List.scala:285)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:292)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:305)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4$$anonfun$apply$9.apply(TreeNode.scala:294)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at
>>> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
>>> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
>>> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:292)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:305)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:265)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:305)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:248)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:75)
>>> at org.apache.spark.sql.catalyst.plans.QueryPlan.org
>>> $apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:85)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$1.apply(QueryPlan.scala:89)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at
>>> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
>>> at scala.collection.immutable.List.foreach(List.scala:381)
>>> at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
>>> at scala.collection.immutable.List.map(List.scala:285)
>>> at org.apache.spark.sql.catalyst.plans.QueryPlan.org
>>> $apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:89)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:93)
>>> at scala.collection.Iterator$$anon$11.next(Iterator.scala:370)
>>> at scala.collection.Iterator$class.foreach(Iterator.scala:742)
>>> at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
>>> at
>>> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
>>> at
>>> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
>>> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308)
>>> at scala.collection.AbstractIterator.to(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300)
>>> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194)
>>> at
>>> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287)
>>> at scala.collection.AbstractIterator.toArray(Iterator.scala:1194)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:93)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:64)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$transformAllExpressions$1.applyOrElse(QueryPlan.scala:134)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$transformAllExpressions$1.applyOrElse(QueryPlan.scala:133)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:243)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:243)
>>> at
>>> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:53)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:242)
>>> at
>>> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:233)
>>> at
>>> org.apache.spark.sql.catalyst.plans.QueryPlan.transformAllExpressions(QueryPlan.scala:133)
>>> at
>>> org.apache.spark.sql.catalyst.analysis.ResolveUpCast$.apply(Analyzer.scala:1211)
>>> at
>>> org.apache.spark.sql.catalyst.analysis.ResolveUpCast$.apply(Analyzer.scala:1195)
>>> at
>>> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:83)
>>> at
>>> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:80)
>>> at
>>> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
>>> at scala.collection.immutable.List.foldLeft(List.scala:84)
>>> at
>>> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:80)
>>> at
>>> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:72)
>>> at scala.collection.immutable.List.foreach(List.scala:381)
>>> at
>>> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:72)
>>> at
>>> org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.resolve(ExpressionEncoder.scala:253)
>>> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:78)
>>> at
>>> org.apache.spark.sql.GroupedDataset.aggUntyped(GroupedDataset.scala:240)
>>> at org.apache.spark.sql.GroupedDataset.agg(GroupedDataset.scala:253)
>>> at ArrayExample$.main(ArrayExample.scala:22)
>>> at ArrayExample.main(ArrayExample.scala)
>>> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
>>> at
>>> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
>>> at
>>> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
>>> at java.lang.reflect.Method.invoke(Method.java:497)
>>> at
>>> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
>>> at
>>> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
>>> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
>>> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
>>> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
>>>
>>>
>>>
>>>
>>
>

Mime
View raw message