-1
Python을 사용하여 Apache Spark를 실습하는 동안 collect() 명령을 실행하는 동안 오류가 발생합니다. Jupyter 노트북에서 아래 코드를 시도하고 있습니다.PySpark에서 collect() 액션을 실행하는 중 오류가 발생했습니다.
vehicledata = sc.textFile("/home/newuser/Desktop/vehicle_data.csv")
vehicledata.collect()
[u'suzuki,gas,std,two,hatchback,fwd,four,69,4900,31,36,5118',
u'volvo,gas,std,two,hatchback,fwd,four,75,5400,37,40,3700',
u'chevrolet,gas,std,two,sedan,fwd,four,65,5600,30,32,4800',
u'toyota,gas,std,two,sedan,fwd,four,45,7800,45,47,3900',
u'tata,gas,std,two,hatchback,fwd,four,40,5900,50,52,7800',
u'tata,gas,std,four,hatchback,fwd,four,20,3100,30,35,2355',
u'suzuki,gas,std,four,hatchback,fwd,four,20,2500,28,30,6355',
u'chevrolet,gas,std,two,sedan,fwd,four,47,4900,23,27,2300',
u'hyundai,cell,std,two,SUV,fwd,four,55,6500,20,25,7000',
u'benz,gas,std,two,SUV,fwd,four,60,7300,26,30,7900',
u'']
여기서는 자동차 브랜드와 8 번째 필드 값을 나눠서 두 가지 값을 취하고 있습니다.
cyldata = vehicledata.map(lambda x: (x.split(",")[0], x.split(",")[7]))
cyldata.collect()
위의 collect() 명령을 실행할 때 다음 오류가 발생합니다. Spark의 새로운 기능이므로이 오류를 해결할 수 없었습니다.
부적절한 스파크 아나콘다 설치로 인해 코딩이나 오류가 발생했는지 알 수 있습니까?
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-9-795ae9e596f7> in <module>()
----> 1 cyldata.collect()
/home/newuser/spark/python/pyspark/rdd.pyc in collect(self)
771 """
772 with SCCallSiteSync(self.context) as css:
--> 773 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
774 return list(_load_from_socket(port, self._jrdd_deserializer))
775
/home/newuser/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
536 answer = self.gateway_client.send_command(command)
537 return_value = get_return_value(answer, self.gateway_client,
--> 538 self.target_id, self.name)
539
540 for temp_arg in temp_args:
/home/newuser/spark/python/pyspark/sql/utils.pyc in deco(*a, **kw)
34 def deco(*a, **kw):
35 try:
---> 36 return f(*a, **kw)
37 except py4j.protocol.Py4JJavaError as e:
38 s = e.java_exception.toString()
/home/newuser/spark/python/lib/py4j-0.8.2.1-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(
Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 2.0 failed 1 times, most recent failure: Lost task 1.0 in stage 2.0 (TID 5, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "<ipython-input-8-1adc0c950e09>", line 1, in <lambda>
IndexError: list index out of range
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:129)
at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:125)
at org.apache.spark.InterruptibleIterator.next(InterruptibleIterator.scala:43)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1921)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:909)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:310)
at org.apache.spark.rdd.RDD.collect(RDD.scala:908)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/newuser/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "<ipython-input-8-1adc0c950e09>", line 1, in <lambda>
IndexError: list index out of range
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:129)
at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:125)
at org.apache.spark.InterruptibleIterator.next(InterruptibleIterator.scala:43)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
허용 된 답변에 아무 것도 추가하지 않습니까? – mkl