Question

我有一个带有以下示例条目的火花数据框。

当我尝试计算数据帧中的行数时，我得到了一个Keyerror。谁能说出我为什么会收到此错误？

下面是扩展的数据砖堆栈跟踪，显示有一个Keyerror。

    ---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-42-c51951771cc1> in <module>()
----> 1 projdf.count()

/databricks/spark/python/pyspark/sql/dataframe.py in count(self)
    267         2
    268         """
--> 269         return int(self._jdf.count())
    270 
    271     @ignore_unicode_prefix

/databricks/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:

/databricks/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()

/databricks/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 o877.count.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 208.0 failed 1 times, most recent failure: Lost task 1.0 in stage 208.0 (TID 11930, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/databricks/spark/python/pyspark/worker.py", line 111, in main
    process()
  File "/databricks/spark/python/pyspark/worker.py", line 106, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/databricks/spark/python/pyspark/serializers.py", line 263, in dump_stream
    vs = list(itertools.islice(iterator, batch))
  File "/databricks/spark/python/pyspark/sql/functions.py", line 1563, in <lambda>
    func = lambda _, it: map(lambda x: returnType.toInternal(f(*x)), it)
  File "<ipython-input-16-b98f0196f4a3>", line 66, in <lambda>
KeyError: u''

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:129)
    at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:125)
    at org.apache.spark.InterruptibleIterator.next(InterruptibleIterator.scala:43)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:504)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    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:1835)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1861)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1932)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
    at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:166)
    at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174)
    at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1538)
    at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1538)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
    at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2125)
    at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1537)
    at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1544)
    at org.apache.spark.sql.DataFrame$$anonfun$count$1.apply(DataFrame.scala:1554)
    at org.apache.spark.sql.DataFrame$$anonfun$count$1.apply(DataFrame.scala:1553)
    at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2138)
    at org.apache.spark.sql.DataFrame.count(DataFrame.scala:1553)
    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:497)
    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: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/databricks/spark/python/pyspark/worker.py", line 111, in main
    process()
  File "/databricks/spark/python/pyspark/worker.py", line 106, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/databricks/spark/python/pyspark/serializers.py", line 263, in dump_stream
    vs = list(itertools.islice(iterator, batch))
  File "/databricks/spark/python/pyspark/sql/functions.py", line 1563, in <lambda>
    func = lambda _, it: map(lambda x: returnType.toInternal(f(*x)), it)
  File "<ipython-input-16-b98f0196f4a3>", line 66, in <lambda>
KeyError: u''

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:129)
    at org.apache.spark.api.python.PythonRunner$$anon$1.next(PythonRDD.scala:125)
    at org.apache.spark.InterruptibleIterator.next(InterruptibleIterator.scala:43)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:504)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95)
    at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    ... 1 more

Answer 1

谢谢@zsxwing！我发现在生成projdf数据帧的代码中存在一个问题，导致数据帧有很多无效数据条目。然而，我收到的错误在调试根本原因方面没有多大意义。

在尝试对Spark数据帧进行计数时的Keyerror

1 个答案: