Исправлена ​​ошибка Py4JJavaError при попытке преобразовать pyspark df размером 1,7 lac в pandas df - PullRequest
0 голосов
/ 18 июня 2019
> Py4JJavaError: An error occurred while calling o342.collectToPython. :
> org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 36 in stage 14.0 failed 1 times, most recent failure: Lost task
> 36.0 in stage 14.0 (TID 675, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent
> call last):   File
> "C:\Users\MUM1342\Desktop\spark\spark-2.4.3-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\worker.py",
> line 362, in main   File
> "C:\Users\MUM1342\Desktop\spark\spark-2.4.3-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\serializers.py",
> line 715, in read_int
>     length = stream.read(4)   File "C:\ProgramData\Anaconda2\lib\socket.py", line 384, in read
>     data = self._sock.recv(left) timeout: timed out
> 
>   at
> org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:452)
>   at
> org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81)
>   at
> org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64)
>   at
> org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:406)
>   at
> org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
>   at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)   at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)    at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)    at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage7.processNext(Unknown
> Source)   at
> org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
>   at
> org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
>   at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
>   at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
>   at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:836)
>   at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:836)
>   at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
>   at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
>   at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)     at
> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)    at
> org.apache.spark.scheduler.Task.run(Task.scala:121)   at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
>   at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
>   at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
>   at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
>   at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
>   at java.lang.Thread.run(Unknown Source)
> 
> Driver stacktrace:    at
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
>   at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
>   at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
>   at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
>   at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
>   at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
>   at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
>   at
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
>   at scala.Option.foreach(Option.scala:257)   at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
>   at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
>   at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
>   at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
>   at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
>   at
> org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)    at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)     at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)     at
> org.apache.spark.SparkContext.runJob(SparkContext.scala:2126)     at
> org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945)  at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
>   at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
>   at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)    at
> org.apache.spark.rdd.RDD.collect(RDD.scala:944)   at
> org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:299)
>   at
> org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3257)
>   at
> org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3254)
>   at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3364)
>   at
> org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
>   at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
>   at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3363)  at
> org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:3254)  at
> sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)   at
> sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)   at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)   at
> java.lang.reflect.Method.invoke(Unknown Source)   at
> py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)  at
> py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)    at
> py4j.Gateway.invoke(Gateway.java:282)     at
> py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
>   at py4j.commands.CallCommand.execute(CallCommand.java:79)   at
> py4j.GatewayConnection.run(GatewayConnection.java:238)    at
> java.lang.Thread.run(Unknown Source) Caused by:
> org.apache.spark.api.python.PythonException: Traceback (most recent
> call last):   File
> "C:\Users\MUM1342\Desktop\spark\spark-2.4.3-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\worker.py",
> line 362, in main   File
> "C:\Users\MUM1342\Desktop\spark\spark-2.4.3-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\serializers.py",
> line 715, in read_int
>     length = stream.read(4)   File "C:\ProgramData\Anaconda2\lib\socket.py", line 384, in read
>     data = self._sock.recv(left) timeout: timed out
> 
>   at
> org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:452)
>   at
> org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81)
>   at
> org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64)
>   at
> org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:406)
>   at
> org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
>   at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)   at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)    at
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)    at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage7.processNext(Unknown
> Source)   at
> org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
>   at
> org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
>   at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
>   at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
>   at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:836)
>   at
> org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:836)
>   at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
>   at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
>   at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)     at
> org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)    at
> org.apache.spark.scheduler.Task.run(Task.scala:121)   at
> org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
>   at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
>   at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
>   at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
>   at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
> 1 more
...