I am using PySpark through JupyterLab using the Spark distibution provided
with *conda install pyspark*. So I run Spark locally.
I started using pyspark 2.4.0 but I had a Socket issue which I solved with
downgrading the package to 2.3.2.
So I am using pyspark 2.3.2 at the moment.
I am trying to do an orderBy on one of my dataframe.
That way : dfRequestwithTime = dfRequestwithTime.orderBy('time', ascending =
False)
but I get the following error. (I am sure that this is that line which is
the issue since without I do not get any error.)
This dataframe contains 2 columns:
- a column "request" containing strings
- a column "time" which is in fact a duration containing integers
Here the first 2 rows.
[Row(request='SELECT XXX FROM XXX WHERE XXX ', time=4),
Row(request='SELECT XXX FROM XXX WHERE XXX ', time=1)]
I am getting my duration thanks to RegEx collected earlier in the notebook.
I casted my "time" column to Integer and droped NaN on my dataset.
I get the same following error if I try to do an orderBy on my 'request'
column.
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-461-17cd191c67c0> in <module>
----> 1 dfRequestwithTime.head(5)
~\Anaconda3\lib\site-packages\pyspark\sql\dataframe.py in head(self, n)
1132 rs = self.head(1)
1133 return rs[0] if rs else None
-> 1134 return self.take(n)
1135
1136 @ignore_unicode_prefix
~\Anaconda3\lib\site-packages\pyspark\sql\dataframe.py in take(self, num)
502 [Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
503 """
--> 504 return self.limit(num).collect()
505
506 @since(1.3)
~\Anaconda3\lib\site-packages\pyspark\sql\dataframe.py in collect(self)
464 """
465 with SCCallSiteSync(self._sc) as css:
--> 466 sock_info = self._jdf.collectToPython()
467 return list(_load_from_socket(sock_info,
BatchedSerializer(PickleSerializer())))
468
~\Anaconda3\lib\site-packages\py4j\java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
~\Anaconda3\lib\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
~\Anaconda3\lib\site-packages\py4j\protocol.py in get_return_value(answer,
gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o5404.collectToPython.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 26
in stage 190.0 failed 1 times, most recent failure: Lost task 26.0 in stage
190.0 (TID 4856, localhost, executor driver):
org.apache.spark.api.python.PythonException: Traceback (most recent call
last):
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 253, in main
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 248, in process
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 331, in dump_stream
self.serializer.dump_stream(self._batched(iterator), stream)
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 140, in dump_stream
for obj in iterator:
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 320, in _batched
for item in iterator:
File "<string>", line 1, in <lambda>
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 76, in <lambda>
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\util.py",
line 55, in wrapper
return f(*args, **kwargs)
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 68, in <lambda>
File "<ipython-input-454-e809ef90d785>", line 1, in <lambda>
File "C:\Users\tryck\Anaconda3\lib\re.py", line 191, in sub
return _compile(pattern, flags).sub(repl, string, count)
TypeError: expected string or bytes-like object
at
org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:330)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:83)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:66)
at
org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:284)
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$$anon$11.hasNext(Iterator.scala:409)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1124)
at
scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1130)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
at
org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:223)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$2.writeIteratorToStream(PythonUDFRunner.scala:52)
at
org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:247)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1992)
at
org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:170)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1651)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1639)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1638)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1638)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1872)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1821)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1810)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2131)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1035)
at
org.apache.spark.rdd.RDDOperationScope$.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.reduce(RDD.scala:1017)
at org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1.apply(RDD.scala:1439)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.takeOrdered(RDD.scala:1426)
at
org.apache.spark.sql.execution.TakeOrderedAndProjectExec.executeCollect(limit.scala:135)
at
org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3200)
at
org.apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:3197)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3259)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3258)
at org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:3197)
at sun.reflect.GeneratedMethodAccessor84.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
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(Thread.java:748)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most
recent call last):
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 253, in main
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 248, in process
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 331, in dump_stream
self.serializer.dump_stream(self._batched(iterator), stream)
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 140, in dump_stream
for obj in iterator:
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\serializers.py",
line 320, in _batched
for item in iterator:
File "<string>", line 1, in <lambda>
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 76, in <lambda>
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\util.py",
line 55, in wrapper
return f(*args, **kwargs)
File
"C:\Users\tryck\Anaconda3\Lib\site-packages\pyspark\python\lib\pyspark.zip\pyspark\worker.py",
line 68, in <lambda>
File "<ipython-input-454-e809ef90d785>", line 1, in <lambda>
File "C:\Users\tryck\Anaconda3\lib\re.py", line 191, in sub
return _compile(pattern, flags).sub(repl, string, count)
TypeError: expected string or bytes-like object
at
org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:330)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:83)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:66)
at
org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:284)
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$$anon$11.hasNext(Iterator.scala:409)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1124)
at
scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1130)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
at
org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:223)
at
org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$2.writeIteratorToStream(PythonUDFRunner.scala:52)
at
org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:247)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1992)
at
org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:170)
--
Sent from: http://apache-spark-user-list.1001560.n3.nabble.com/
---------------------------------------------------------------------
To unsubscribe e-mail: [email protected]
