Py4JJavaError Traceback (most recent call last) in 19 isp_data["isp"], 20 CONCAT_WS("-", year, LPAD(month, 2, "0"), LPAD(day, 2, "0")) ---> 21 """, spark_config=SPARK_CONFIG) /srv/home/neilpquinn-wmf/pkg/wmfdata/wmfdata/hive.py in run(cmds, fmt, spark_master, app_name, spark_config) 29 result_DF = cmd_result 30 if fmt == 'pandas': ---> 31 result = result_DF.toPandas() 32 else: 33 result = result_DF.collect() /usr/lib/spark2/python/pyspark/sql/dataframe.py in toPandas(self) 2141 2142 # Below is toPandas without Arrow optimization. -> 2143 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns) 2144 2145 dtype = {} /usr/lib/spark2/python/pyspark/sql/dataframe.py in collect(self) 532 """ 533 with SCCallSiteSync(self._sc) as css: --> 534 sock_info = self._jdf.collectToPython() 535 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer()))) 536 /usr/lib/spark2/python/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: /usr/lib/spark2/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() /usr/lib/spark2/python/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 o275.collectToPython. : org.apache.spark.SparkException: Job 3 cancelled because SparkContext was shut down at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:932) at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:930) at scala.collection.mutable.HashSet.foreach(HashSet.scala:78) at org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:930) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:2128) at org.apache.spark.util.EventLoop.stop(EventLoop.scala:84) at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:2041) at org.apache.spark.SparkContext$$anonfun$stop$6.apply$mcV$sp(SparkContext.scala:1949) at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1340) at org.apache.spark.SparkContext.stop(SparkContext.scala:1948) at org.apache.spark.SparkContext$$anon$3.run(SparkContext.scala:1903) 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$$anonfun$collect$1.apply(RDD.scala:945) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) at org.apache.spark.rdd.RDD.withScope(RDD.scala:363) at org.apache.spark.rdd.RDD.collect(RDD.scala:944) at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.bulkListLeafFiles(InMemoryFileIndex.scala:237) at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.listLeafFiles(InMemoryFileIndex.scala:126) at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.refresh0(InMemoryFileIndex.scala:91) at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.(InMemoryFileIndex.scala:67) at org.apache.spark.sql.execution.datasources.PrunedInMemoryFileIndex.(CatalogFileIndex.scala:118) at org.apache.spark.sql.execution.datasources.CatalogFileIndex.filterPartitions(CatalogFileIndex.scala:84) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$$anonfun$apply$1.applyOrElse(PruneFileSourcePartitions.scala:63) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$$anonfun$apply$1.applyOrElse(PruneFileSourcePartitions.scala:27) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:259) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:259) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:258) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:264) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:264) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.transformDown(AnalysisHelper.scala:149) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$.apply(PruneFileSourcePartitions.scala:27) at org.apache.spark.sql.execution.datasources.PruneFileSourcePartitions$.apply(PruneFileSourcePartitions.scala:26) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66) at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76) at scala.collection.immutable.List.foreach(List.scala:392) at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:66) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:66) at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:72) at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:68) at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:77) at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:77) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3365) at org.apache.spark.sql.Dataset.collectToPython(Dataset.scala:3260) 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: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)