Davies Liu created SPARK-13406:
----------------------------------
Summary: NPE in LazilyGeneratedOrdering
Key: SPARK-13406
URL: https://issues.apache.org/jira/browse/SPARK-13406
Project: Spark
Issue Type: Improvement
Components: SQL
Reporter: Davies Liu
Assignee: Josh Rosen
{code}
File
"/Users/davies/work/spark/python/lib/pyspark.zip/pyspark/sql/dataframe.py",
line ?, in pyspark.sql.dataframe.DataFrameStatFunctions.sampleBy
Failed example:
sampled.groupBy("key").count().orderBy("key").show()
Exception raised:
Traceback (most recent call last):
File "//anaconda/lib/python2.7/doctest.py", line 1315, in __run
compileflags, 1) in test.globs
File "<doctest
pyspark.sql.dataframe.DataFrameStatFunctions.sampleBy[3]>", line 1, in <module>
sampled.groupBy("key").count().orderBy("key").show()
File
"/Users/davies/work/spark/python/lib/pyspark.zip/pyspark/sql/dataframe.py",
line 217, in show
print(self._jdf.showString(n, truncate))
File
"/Users/davies/work/spark/python/lib/py4j-0.9.1-src.zip/py4j/java_gateway.py",
line 835, in __call__
answer, self.gateway_client, self.target_id, self.name)
File
"/Users/davies/work/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line
45, in deco
return f(*a, **kw)
File
"/Users/davies/work/spark/python/lib/py4j-0.9.1-src.zip/py4j/protocol.py", line
310, in get_return_value
format(target_id, ".", name), value)
Py4JJavaError: An error occurred while calling o681.showString.
: org.apache.spark.SparkDriverExecutionException: Execution error
at
org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1189)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1658)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1620)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1609)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:623)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1782)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:937)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:323)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:919)
at org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1.apply(RDD.scala:1318)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:323)
at org.apache.spark.rdd.RDD.takeOrdered(RDD.scala:1305)
at
org.apache.spark.sql.execution.TakeOrderedAndProject.executeCollect(limit.scala:94)
at
org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:157)
at
org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1520)
at
org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1520)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53)
at
org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1769)
at
org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1519)
at
org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1526)
at
org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1396)
at
org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1395)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:1782)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1395)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1477)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:167)
at sun.reflect.GeneratedMethodAccessor63.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:290)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.NullPointerException
at
org.apache.spark.sql.catalyst.expressions.codegen.LazilyGeneratedOrdering.compare(GenerateOrdering.scala:157)
at
org.apache.spark.sql.catalyst.expressions.codegen.LazilyGeneratedOrdering.compare(GenerateOrdering.scala:148)
at scala.math.Ordering$$anon$4.compare(Ordering.scala:111)
at java.util.PriorityQueue.siftUpUsingComparator(PriorityQueue.java:649)
at java.util.PriorityQueue.siftUp(PriorityQueue.java:627)
at java.util.PriorityQueue.offer(PriorityQueue.java:329)
at
org.apache.spark.util.BoundedPriorityQueue.$plus$eq(BoundedPriorityQueue.scala:47)
at
org.apache.spark.util.BoundedPriorityQueue$$anonfun$$plus$plus$eq$1.apply(BoundedPriorityQueue.scala:41)
at
org.apache.spark.util.BoundedPriorityQueue$$anonfun$$plus$plus$eq$1.apply(BoundedPriorityQueue.scala:41)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at
org.apache.spark.util.BoundedPriorityQueue.foreach(BoundedPriorityQueue.scala:31)
at
org.apache.spark.util.BoundedPriorityQueue.$plus$plus$eq(BoundedPriorityQueue.scala:41)
at
org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$apply$46.apply(RDD.scala:1319)
at
org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1$$anonfun$apply$46.apply(RDD.scala:1318)
at
org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:932)
at
org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:929)
at
org.apache.spark.scheduler.JobWaiter.taskSucceeded(JobWaiter.scala:57)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1185)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1658)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1620)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1609)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
