Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Py4JJavaError Traceback (most recent call last)
- <ipython-input-22-9a60a1cb581c> in <module>()
- ----> 1 jaccard_sims = rdd2.map(lambda x: jacc_sim(x)).collect()
- /opt/spark/python/pyspark/rdd.py in collect(self)
- 806 """
- 807 with SCCallSiteSync(self.context) as css:
- --> 808 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
- 809 return list(_load_from_socket(port, self._jrdd_deserializer))
- 810
- /opt/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args)
- 1131 answer = self.gateway_client.send_command(command)
- 1132 return_value = get_return_value(
- -> 1133 answer, self.gateway_client, self.target_id, self.name)
- 1134
- 1135 for temp_arg in temp_args:
- /opt/spark/python/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()
- /opt/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
- 317 raise Py4JJavaError(
- 318 "An error occurred while calling {0}{1}{2}.\n".
- --> 319 format(target_id, ".", name), value)
- 320 else:
- 321 raise Py4JError(
- Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
- : org.apache.spark.SparkException: Job 2 cancelled because SparkContext was shut down
- at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:808)
- at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:806)
- at scala.collection.mutable.HashSet.foreach(HashSet.scala:78)
- at org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:806)
- at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:1668)
- at org.apache.spark.util.EventLoop.stop(EventLoop.scala:83)
- at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:1587)
- at org.apache.spark.SparkContext$$anonfun$stop$8.apply$mcV$sp(SparkContext.scala:1833)
- at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1283)
- at org.apache.spark.SparkContext.stop(SparkContext.scala:1832)
- at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend$MonitorThread.run(YarnClientSchedulerBackend.scala:108)
- at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
- at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925)
- at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938)
- at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951)
- at org.apache.spark.SparkContext.runJob(SparkContext.scala:1965)
- at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:936)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
- at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
- at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
- at org.apache.spark.rdd.RDD.collect(RDD.scala:935)
- at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
- 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:244)
- at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
- at py4j.Gateway.invoke(Gateway.java:280)
- at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
- at py4j.commands.CallCommand.execute(CallCommand.java:79)
- at py4j.GatewayConnection.run(GatewayConnection.java:214)
- at java.lang.Thread.run(Thread.java:748)
Add Comment
Please, Sign In to add comment