I have a weird spark RDD, I am not sure what is wrong or how to go about troubleshooting. I am running Spark 1.6.2 with python 3.4.3 through an ipython notebook.
Here is how I am pulling in the data:
sqlContext = SQLContext(sc)
hdfs = 'hdfs://192.168.1.213:54310/TEMP/*'
def make_Row(item):
temp = {}
if 'desc' in item:
temp['desc']=str(item['desc']).lower()
if 'cat' in item:
temp['cat']= parse_cats(str(item['cat']).lower())
if 'cat' in temp and 'desc' in temp:
return Row(**temp)
raw_data = sc.wholeTextFiles(hdfs, 15).map(lambda x: json.loads(x[1])).flatMap(lambda x: x).map(lambda d: make_Row(d)).cache()
raw_data.count()
This brings me the count of the data:
Weird parts:
raw_data.show()gives the following exception. I checked 'PipelinedRDD' object has no attribute 'toDF' in PySpark, but I do have sqlContext defined.AttributeErrorTraceback (most recent call last) in () ----> 1 raw_data.show()
AttributeError: 'PipelinedRDD' object has no attribute 'show'
raw_data.toDF().show()works fine.raw_data.toDF().columnsshows:['cat', 'desc'], butraw_data.toDF().describe('cat').show()throws the following:Py4JJavaErrorTraceback (most recent call last) <ipython-input-110-45e3ce9b4e4b> in <module>() ----> 1 raw_data.toDF().describe('cat').show() /apps/spark/python/pyspark/sql/dataframe.py in describe(self, *cols) 772 if len(cols) == 1 and isinstance(cols[0], list): 773 cols = cols[0] --> 774 jdf = self._jdf.describe(self._jseq(cols)) 775 return DataFrame(jdf, self.sql_ctx) 776 /apps/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args) 811 answer = self.gateway_client.send_command(command) 812 return_value = get_return_value( --> 813 answer, self.gateway_client, self.target_id, self.name) 814 815 for temp_arg in temp_args: /apps/spark/python/pyspark/sql/utils.py in deco(*a, **kw) 43 def deco(*a, **kw): 44 try: ---> 45 return f(*a, **kw) 46 except py4j.protocol.Py4JJavaError as e: 47 s = e.java_exception.toString() /apps/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name) 306 raise Py4JJavaError( 307 "An error occurred while calling {0}{1}{2}.\n". --> 308 format(target_id, ".", name), value) 309 else: 310 raise Py4JError( Py4JJavaError: An error occurred while calling o1689.describe. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 68.0 failed 4 times, most recent failure: Lost task 2.3 in stage 68.0 (TID 352, solrmain): java.lang.NullPointerException at org.apache.spark.api.python.SerDeUtil$$anonfun$toJavaArray$1.apply(SerDeUtil.scala:102) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.processCurrentSortedGroup(SortBasedAggregationIterator.scala:122) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.next(SortBasedAggregationIterator.scala:152) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.next(SortBasedAggregationIterator.scala:29) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:149) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:212) at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165) at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505) at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375) at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374) at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099) at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374) at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1383) at org.apache.spark.sql.DataFrame$$anonfun$describe$1.apply(DataFrame.scala:1352) at org.apache.spark.sql.DataFrame$$anonfun$describe$1.apply(DataFrame.scala:1335) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$withPlan(DataFrame.scala:2126) at org.apache.spark.sql.DataFrame.describe(DataFrame.scala:1335) 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:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381) 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:209) at java.lang.Thread.run(Thread.java:745) Caused by: java.lang.NullPointerException at org.apache.spark.api.python.SerDeUtil$$anonfun$toJavaArray$1.apply(SerDeUtil.scala:102) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.processCurrentSortedGroup(SortBasedAggregationIterator.scala:122) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.next(SortBasedAggregationIterator.scala:152) at org.apache.spark.sql.execution.aggregate.SortBasedAggregationIterator.next(SortBasedAggregationIterator.scala:29) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:149) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) ... 1 more
Thanks in advance
