I am using PySpark with IPython notebook. <pre> data = sc.parallelize(range(1000), 10)
#successful data.map(lambda x: x+1).collect() #Error data.count() </pre> Something similar:http://apache-spark-user-list.1001560.n3.nabble.com/Exception-on-simple-pyspark-script-td3415.html But it does not figure out how to solve it. Any one help? <pre> --------------------------------------------------------------------------- Py4JJavaError Traceback (most recent call last) <ipython-input-10-0106b6ff8a89> in <module>() ----> 1 data.count() /home/workspace/spark-1.0.2-bin-hadoop2/python/pyspark/rdd.pyc in count(self) 735 3 736 """ --> 737 return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum() 738 739 def stats(self): /home/workspace/spark-1.0.2-bin-hadoop2/python/pyspark/rdd.pyc in sum(self) 726 6.0 727 """ --> 728 return self.mapPartitions(lambda x: [sum(x)]).reduce(operator.add) 729 730 def count(self): /home/workspace/spark-1.0.2-bin-hadoop2/python/pyspark/rdd.pyc in reduce(self, f) 646 if acc is not None: 647 yield acc --> 648 vals = self.mapPartitions(func).collect() 649 return reduce(f, vals) 650 /home/workspace/spark-1.0.2-bin-hadoop2/python/pyspark/rdd.pyc in collect(self) 610 """ 611 with _JavaStackTrace(self.context) as st: --> 612 bytesInJava = self._jrdd.collect().iterator() 613 return list(self._collect_iterator_through_file(bytesInJava)) 614 /home/workspace/spark-1.0.2-bin-hadoop2/python/lib/py4j-0.8.1-src.zip/py4j/java_gateway.py in __call__(self, *args) 535 answer = self.gateway_client.send_command(command) 536 return_value = get_return_value(answer, self.gateway_client, --> 537 self.target_id, self.name) 538 539 for temp_arg in temp_args: /home/workspace/spark-1.0.2-bin-hadoop2/python/lib/py4j-0.8.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name) 298 raise Py4JJavaError( 299 'An error occurred while calling {0}{1}{2}.\n'. --> 300 format(target_id, '.', name), value) 301 else: 302 raise Py4JError( ---------------------------- org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/home/workspace/spark-0.9.1-bin-hadoop2/python/pyspark/worker.py", line 77, in main serializer.dump_stream(func(split_index, iterator), outfile) File "/home/workspace/spark-0.9.1-bin-hadoop2/python/pyspark/serializers.py", line 182, in dump_stream self.serializer.dump_stream(self._batched(iterator), stream) File "/home/workspace/spark-0.9.1-bin-hadoop2/python/pyspark/serializers.py", line 117, in dump_stream for obj in iterator: File "/home/workspace/spark-0.9.1-bin-hadoop2/python/pyspark/serializers.py", line 171, in _batched for item in iterator: File "/home/workspace/spark-1.0.2-bin-hadoop2/python/pyspark/rdd.py", line 642, in func TypeError: an integer is required org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:115) org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:145) org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:78) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:183) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603) java.lang.Thread.run(Thread.java:722) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1049) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1033) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1031) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1031) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:635) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1234) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386) 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) </pre> -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/PySpark-Python-2-7-8-Spark-1-0-2-count-with-TypeError-an-integer-is-required-tp12643.html Sent from the Apache Spark User List mailing list archive at Nabble.com. --------------------------------------------------------------------- To unsubscribe, e-mail: user-unsubscr...@spark.apache.org For additional commands, e-mail: user-h...@spark.apache.org
