Hi,
Can you try without creating sqlContext manually?
# sqlContext = SQLContext(sc)
Thanks,
moon
On Tue, Aug 4, 2015 at 8:20 AM Braden Callahan1 <brad...@us.ibm.com> wrote:
> I have an issue where I create a table in Python (pyspark) and the sql
> interpreter
> does not see the table. If I create it using scala both python and sql pick
> it up without an issue.
>
>
> Example:
>
> %pyspark
> sqlContext = SQLContext(sc)
>
> tweet = sqlContext.read.json("/temp/twitter_data_small/")
> tweet.registerTempTable("tweet")
>
>
>
> #this work fine:
> %pyspark
>
> print tweet.take(5)
>
>
> %sql
> select * from tweet
>
> java.lang.RuntimeException: Table Not Found: tweet at
> scala.sys.package$.error(package.scala:27) at
> org.apache.spark.sql.catalyst.analysis.SimpleCatalog$$anonfun$1.apply(Catalog.scala:115)
> at
> org.apache.spark.sql.catalyst.analysis.SimpleCatalog$$anonfun$1.apply(Catalog.scala:115)
> at scala.collection.MapLike$class.getOrElse(MapLike.scala:128) at
> scala.collection.AbstractMap.getOrElse(Map.scala:58) at
> org.apache.spark.sql.catalyst.analysis.SimpleCatalog.lookupRelation(Catalog.scala:115)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.getTable(Analyzer.scala:222)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:233)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:229)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:221)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:242)
> at scala.collection.Iterator$$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$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildrenDown(TreeNode.scala:272)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:227)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:212)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:229)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:219)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:61)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:59)
> at
> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
> at scala.collection.immutable.List.foldLeft(List.scala:84) at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:59)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:51)
> at scala.collection.immutable.List.foreach(List.scala:318) at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:51)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:922)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:922)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:920)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:131) at
> org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51) at
> org.apache.spark.sql.SQLContext.sql(SQLContext.scala:744) at
> org.apache.zeppelin.spark.SparkSqlInterpreter.interpret(SparkSqlInterpreter.java:133)
> at
> org.apache.zeppelin.interpreter.ClassloaderInterpreter.interpret(ClassloaderInterpreter.java:57)
> at
> org.apache.zeppelin.interpreter.LazyOpenInterpreter.interpret(LazyOpenInterpreter.java:93)
> at
> org.apache.zeppelin.interpreter.remote.RemoteInterpreterServer$InterpretJob.jobRun(RemoteInterpreterServer.java:276)
> at org.apache.zeppelin.scheduler.Job.run(Job.java:170) at
> org.apache.zeppelin.scheduler.FIFOScheduler$1.run(FIFOScheduler.java:118)
> at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
> at java.util.concurrent.FutureTask.run(FutureTask.java:262) at
> java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$201(ScheduledThreadPoolExecutor.java:178)
> at
> java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:292)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Took 0 seconds
>
