Piotr Milanowski created SPARK-15293:
----------------------------------------
Summary: 'collect_list' function undefined
Key: SPARK-15293
URL: https://issues.apache.org/jira/browse/SPARK-15293
Project: Spark
Issue Type: Bug
Components: PySpark, SQL
Affects Versions: 2.0.0
Reporter: Piotr Milanowski
When using pyspark.sql.functions.collect_list function in sql queries, an error
occurs - Undefined function collect_list
Example:
{code}
>>> from pyspark.sql import Row
>>> #The same with HiveContext
>>> from pyspark.sql import SQLContext
>>> from pyspark.sql.functions import collect_list
>>> sql = SQLContext(sc)
>>> rows = [Row(age=20, job='Programmer', name='Alice'), Row(age=21,
>>> job='Programmer', name='Bob'), Row(age=30, job='Hacker', name='Fred'),
>>> Row(age=29, job='PM', name='Tom'), Row(age=50, job='CEO', name='Daisy')]
>>> df = sql.createDataFrame(rows)
>>> df.groupby(df.job).agg(df.job, collect_list(df.age))
Traceback (most recent call last):
File "/mnt/mfs/spark-2.0/python/pyspark/sql/utils.py", line 57, in deco
return f(*a, **kw)
File "/mnt/mfs/spark-2.0/python/lib/py4j-0.9.2-src.zip/py4j/protocol.py",
line 310, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o193.agg.
: org.apache.spark.sql.AnalysisException: Undefined function: 'collect_list'.
This function is neither a registered temporary function nor a permanent
function registered in the database 'default'.;
at
org.apache.spark.sql.catalyst.catalog.SessionCatalog.failFunctionLookup(SessionCatalog.scala:719)
at
org.apache.spark.sql.catalyst.catalog.SessionCatalog.lookupFunction(SessionCatalog.scala:781)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$6$$anonfun$applyOrElse$38.apply(Analyzer.scala:907)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$6$$anonfun$applyOrElse$38.apply(Analyzer.scala:907)
at
org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:48)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$6.applyOrElse(Analyzer.scala:906)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13$$anonfun$applyOrElse$6.applyOrElse(Analyzer.scala:894)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:265)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:265)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:68)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:270)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:270)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:307)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
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$class.to(TraversableOnce.scala:310)
at scala.collection.AbstractIterator.to(Iterator.scala:1336)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1336)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1336)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:356)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:270)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:156)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:166)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$1.apply(QueryPlan.scala:170)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:170)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$4.apply(QueryPlan.scala:175)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
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$class.to(TraversableOnce.scala:310)
at scala.collection.AbstractIterator.to(Iterator.scala:1336)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1336)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1336)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:175)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:144)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13.applyOrElse(Analyzer.scala:894)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$$anonfun$apply$13.applyOrElse(Analyzer.scala:892)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:68)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:60)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$.apply(Analyzer.scala:892)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveFunctions$.apply(Analyzer.scala:891)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:64)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:62)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:50)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:61)
at
org.apache.spark.sql.RelationalGroupedDataset.toDF(RelationalGroupedDataset.scala:55)
at
org.apache.spark.sql.RelationalGroupedDataset.agg(RelationalGroupedDataset.scala:211)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:290)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/mnt/mfs/spark-2.0/python/pyspark/sql/group.py", line 91, in agg
_to_seq(self.sql_ctx._sc, [c._jc for c in exprs[1:]]))
File "/mnt/mfs/spark-2.0/python/lib/py4j-0.9.2-src.zip/py4j/java_gateway.py",
line 836, in __call__
File "/mnt/mfs/spark-2.0/python/pyspark/sql/utils.py", line 63, in deco
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.AnalysisException: "Undefined function: 'collect_list'. This
function is neither a registered temporary function nor a permanent function
registered in the database 'default'.;"
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
