JustPaste.it - Share Text & Images the Easy Way

Spark assembly has been built with Hive, including Datanucleus jars on classpath
[Stage 0:> (0 + 4) / 4]15/03/17 11:09:05 ERROR Executor: Exception in task 1.0 in stage 0.0 (TID 1)
org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/worker.py", line 90, in main
command = pickleSer._read_with_length(infile)
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/serializers.py", line 151, in _read_with_length
return self.loads(obj)
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/serializers.py", line 400, in loads
return cPickle.loads(obj)
ImportError: No module named work

at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:137)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:96)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:280)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:247)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:200)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
15/03/17 11:09:05 ERROR TaskSetManager: Task 2 in stage 0.0 failed 1 times; aborting job
Traceback (most recent call last):
File "/Users/poiuytrez/Documents/DB/programs/bdutil-1.1.0/../../datascience/dunnhumby/main2.py", line 18, in <module>
processing(dist_data)
File "/Users/poiuytrez/Documents/DB/datascience/dunnhumby/work.py", line 6, in processing
sum_of_elements = dist_data.map(add_1).sum()
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/rdd.py", line 820, in sum
return self.mapPartitions(lambda x: [sum(x)]).reduce(operator.add)
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/rdd.py", line 725, in reduce
vals = self.mapPartitions(func).collect()
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/rdd.py", line 686, in collect
bytesInJava = self._jrdd.collect().iterator()
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py", line 538, in __call__
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line 300, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o25.collect.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 0.0 failed 1 times, most recent failure: Lost task 2.0 in stage 0.0 (TID 2, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/worker.py", line 90, in main
command = pickleSer._read_with_length(infile)
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/serializers.py", line 151, in _read_with_length
return self.loads(obj)
File "/Users/poiuytrez/Documents/DB/programs/spark-1.2.1/python/pyspark/serializers.py", line 400, in loads
return cPickle.loads(obj)
ImportError: No module named work

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)