我只是想运行下面的代码来学习 Pyspark 中拆分列的概念，但我遇到了错误
data = [("John,Doe", 30),
("Jane,Smith", 25),
("Tom,Hanks", 40)]
# Create a DataFrame
df1 = spark.createDataFrame(data, ["name_age", "other_column"])
df1.show()
然后我收到以下错误：
Py4JJavaError Traceback (most recent call last)
Cell In[45], line 8
5 # Create a DataFrame
6 df1 = spark.createDataFrame(data, ["name_age", "other_column"])
----> 8 df1.show()
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\pyspark\sql\dataframe.py:959, in DataFrame.show(self, n, truncate, vertical)
953 raise PySparkTypeError(
954 error_class="NOT_BOOL",
955 message_parameters={"arg_name": "vertical", "arg_type": type(vertical).__name__},
956 )
958 if isinstance(truncate, bool) and truncate:
--> 959 print(self._jdf.showString(n, 20, vertical))
960 else:
961 try:
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\py4j\java_gateway.py:1322, in JavaMember.__call__(self, *args)
1316 command = proto.CALL_COMMAND_NAME +\
1317 self.command_header +\
1318 args_command +\
1319 proto.END_COMMAND_PART
1321 answer = self.gateway_client.send_command(command)
-> 1322 return_value = get_return_value(
1323 answer, self.gateway_client, self.target_id, self.name)
1325 for temp_arg in temp_args:
1326 if hasattr(temp_arg, "_detach"):
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\pyspark\errors\exceptions\captured.py:179, in capture_sql_exception.<locals>.deco(*a, **kw)
177 def deco(*a: Any, **kw: Any) -> Any:
178 try:
--> 179 return f(*a, **kw)
180 except Py4JJavaError as e:
181 converted = convert_exception(e.java_exception)
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\py4j\protocol.py:326, in get_return_value(answer, gateway_client, target_id, name)
324 value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
325 if answer[1] == REFERENCE_TYPE:
--> 326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
331 "An error occurred while calling {0}{1}{2}. Trace:\n{3}\n".
332 format(target_id, ".", name, value))
Py4JJavaError: An error occurred while calling o320.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 31.0 failed 1 times, most recent failure: Lost task 0.0 in stage 31.0 (TID 73) (LAPTOP-29NB2SLE.Home executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:612)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:594)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:789)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:766)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:525)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:491)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:890)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:890)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:623)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:774)
... 26 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2844)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2780)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2779)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2779)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1242)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1242)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1242)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3048)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2982)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2971)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:984)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2398)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2419)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2438)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:61)
at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:4344)
at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:3326)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4334)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4332)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4332)
at org.apache.spark.sql.Dataset.head(Dataset.scala:3326)
at org.apache.spark.sql.Dataset.take(Dataset.scala:3549)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:280)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:315)
at sun.reflect.GeneratedMethodAccessor179.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:612)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$1.applyOrElse(PythonRunner.scala:594)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:38)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:789)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:766)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:525)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:491)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:890)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:890)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:364)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:328)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:161)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:623)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
... 1 more
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$3.read(PythonRunner.scala:774)
... 26 more
我无法理解这个问题是什么以及为什么会引起它。
我尝试在聊天 gpt 上查找此错误，但仍未解决问题，如何解决此问题。
如果您的 python>=3.12，请尝试 python3.11.x。这对我有用！
来源：[https://stackoverflow.com/questions/77369508/python-worker-keeps-on-crashing-in-pyspark][1]