[
https://issues.apache.org/jira/browse/SPARK-10361?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14723621#comment-14723621
]
Velu nambi commented on SPARK-10361:
------------------------------------
Thanks [~srowen].
Is this a known issue, any suggestions ?
> model.predictAll() fails at user_product.first()
> ------------------------------------------------
>
> Key: SPARK-10361
> URL: https://issues.apache.org/jira/browse/SPARK-10361
> Project: Spark
> Issue Type: Bug
> Components: MLlib, PySpark
> Affects Versions: 1.3.1, 1.4.1, 1.5.0
> Environment: Windows 10, Python 2.7 and with all the three versions
> of Spark
> Reporter: Velu nambi
>
> This code, adapted from the documentation, fails when calling PredictAll()
> after an ALS.train()
> 15/08/31 00:11:45 ERROR PythonRDD: Python worker exited unexpectedly (crashed)
> java.net.SocketException: Connection reset by peer: socket write error
> at java.net.SocketOutputStream.socketWrite0(Native Method)
> at java.net.SocketOutputStream.socketWrite(Unknown Source)
> at java.net.SocketOutputStream.write(Unknown Source)
> at java.io.BufferedOutputStream.write(Unknown Source)
> at java.io.DataOutputStream.write(Unknown Source)
> at java.io.FilterOutputStream.write(Unknown Source)
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:413)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at
> org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:248)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
> 15/08/31 00:11:45 ERROR PythonRDD: This may have been caused by a prior
> exception:
> java.net.SocketException: Connection reset by peer: socket write error
> at java.net.SocketOutputStream.socketWrite0(Native Method)
> at java.net.SocketOutputStream.socketWrite(Unknown Source)
> at java.net.SocketOutputStream.write(Unknown Source)
> at java.io.BufferedOutputStream.write(Unknown Source)
> at java.io.DataOutputStream.write(Unknown Source)
> at java.io.FilterOutputStream.write(Unknown Source)
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:413)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at
> org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:248)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
> 15/08/31 00:11:45 ERROR Executor: Exception in task 0.0 in stage 187.0 (TID
> 85)
> java.net.SocketException: Connection reset by peer: socket write error
> at java.net.SocketOutputStream.socketWrite0(Native Method)
> at java.net.SocketOutputStream.socketWrite(Unknown Source)
> at java.net.SocketOutputStream.write(Unknown Source)
> at java.io.BufferedOutputStream.write(Unknown Source)
> at java.io.DataOutputStream.write(Unknown Source)
> at java.io.FilterOutputStream.write(Unknown Source)
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:413)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at
> org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:248)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
> 15/08/31 00:11:45 WARN TaskSetManager: Lost task 0.0 in stage 187.0 (TID 85,
> localhost): java.net.SocketException: Connection reset by peer: socket write
> error
> at java.net.SocketOutputStream.socketWrite0(Native Method)
> at java.net.SocketOutputStream.socketWrite(Unknown Source)
> at java.net.SocketOutputStream.write(Unknown Source)
> at java.io.BufferedOutputStream.write(Unknown Source)
> at java.io.DataOutputStream.write(Unknown Source)
> at java.io.FilterOutputStream.write(Unknown Source)
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:413)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at
> org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:248)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
> 15/08/31 00:11:45 ERROR TaskSetManager: Task 0 in stage 187.0 failed 1 times;
> aborting job
> 15/08/31 00:11:45 INFO TaskSchedulerImpl: Removed TaskSet 187.0, whose tasks
> have all completed, from pool
> 15/08/31 00:11:45 INFO TaskSchedulerImpl: Cancelling stage 187
> 15/08/31 00:11:45 INFO DAGScheduler: ResultStage 187 (runJob at
> PythonRDD.scala:366) failed in 0.427 s
> 15/08/31 00:11:45 INFO DAGScheduler: Job 16 failed: runJob at
> PythonRDD.scala:366, took 0.434198 s
> Traceback (most recent call last):
> File "C:\Program Files (x86)\JetBrains\PyCharm Community Edition
> 4.5.3\helpers\pydev\pydevd.py", line 2358, in <module>
> globals = debugger.run(setup['file'], None, None, is_module)
> File "C:\Program Files (x86)\JetBrains\PyCharm Community Edition
> 4.5.3\helpers\pydev\pydevd.py", line 1778, in run
> pydev_imports.execfile(file, globals, locals) # execute the script
> File "C:/Users/thirumalaiv1/PycharmProjects/MovieLensALS/MovieLensALS.py",
> line 137, in <module>
> validationRmse = computeRmse(model, validation, numValidation)
> File "C:/Users/thirumalaiv1/PycharmProjects/MovieLensALS/MovieLensALS.py",
> line 49, in computeRmse
> predictions = model.predictAll(data).map(lambda x: ((x[0], x[1]), x[2]))
> File "C:\spark-1.4.1\python\pyspark\mllib\recommendation.py", line 126, in
> predictAll
> first = user_product.first()
> File "C:\spark-1.4.1\python\pyspark\rdd.py", line 1295, in first
> rs = self.take(1)
> File "C:\spark-1.4.1\python\pyspark\rdd.py", line 1277, in take
> res = self.context.runJob(self, takeUpToNumLeft, p, True)
> File "C:\spark-1.4.1\python\pyspark\context.py", line 897, in runJob
> allowLocal)
> File
> "C:\Users\thirumalaiv1\PyCharmVirtualEnv\MovieLensALSVirtEnv\lib\site-packages\py4j\java_gateway.py",
> line 813, in __call__
> answer, self.gateway_client, self.target_id, self.name)
> File
> "C:\Users\thirumalaiv1\PyCharmVirtualEnv\MovieLensALSVirtEnv\lib\site-packages\py4j\protocol.py",
> line 308, in get_return_value
> format(target_id, ".", name), value)
> py4j.protocol.Py4JJavaError: An error occurred while calling
> z:org.apache.spark.api.python.PythonRDD.runJob.
> : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
> in stage 187.0 failed 1 times, most recent failure: Lost task 0.0 in stage
> 187.0 (TID 85, localhost): java.net.SocketException: Connection reset by
> peer: socket write error
> at java.net.SocketOutputStream.socketWrite0(Native Method)
> at java.net.SocketOutputStream.socketWrite(Unknown Source)
> at java.net.SocketOutputStream.write(Unknown Source)
> at java.io.BufferedOutputStream.write(Unknown Source)
> at java.io.DataOutputStream.write(Unknown Source)
> at java.io.FilterOutputStream.write(Unknown Source)
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:413)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:425)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at
> org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:425)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:248)
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1772)
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1273)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1264)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1263)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1263)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
> at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
> at scala.Option.foreach(Option.scala:236)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1457)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1418)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
--
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
