Hello tout le monde ,

je rencontre un petit soucis sur pyspark que je viens partager avec vous. J'essaye de rajouter une nouvelle colonne à un spark DataFrame qui renvoie le rang du temps ( colonne POSIXct ) par l'ID mais j'ai un problème au niveau de la fonction Window de HiveContext . vous trouverez ci dessous le bout de code et l'erreur.
En vous remerciant d'avance

Code pyspark :*

window=Window.partitionBy("ID").orderBy("POSIXct")
test2=df.withColumn("rang",fn.rank().over(window))*
test2.select("KruxUserID","numpage","POSIXct").show()*

Erreur :*


Py4JJavaErrorTraceback (most recent call last)
<ipython-input-246-892cec191f70> in <module>()
----> 1 test.show()

/usr/iop/current/spark-client/python/pyspark/sql/dataframe.py in show(self, n, truncate)
254 +---+-----+
255 """
--> 256 print(self._jdf.showString(n, truncate))
257
258 def __repr__(self):

/usr/iop/current/spark-client/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:

/usr/iop/current/spark-client/python/pyspark/sql/utils.py 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()

/usr/iop/current/spark-client/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 o5850.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 67 in stage 7.0 failed 4 times, most recent failure: Lost task 67.3 in stage 7.0 (TID 127, nom_du_server): java.lang.ArrayIndexOutOfBoundsException

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:1822)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1835)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:215)
at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:207)
at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1385)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1903)
at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1384)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1314)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1377)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
at sun.reflect.GeneratedMethodAccessor70.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
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: java.lang.ArrayIndexOutOfBoundsException