在Jupyter笔记本中获取以下错误。不确定问题是与collect（）有关还是与任何兼容性问题有关

Question

data = sc.parallelize([1,2])

data.map(lambda x:x).collect()

我可以向您保证代码是正确的，因为它在命令行中正确运行。 不知道为什么它没有在木星上运行。 我使用的是spark版本3

第一行没有显示错误，因为我只运行了一行，它没有抛出任何错误

我们将非常感谢您的帮助

添加完整堆栈跟踪：

Py4JJavaError                             Traceback (most recent call last)
<ipython-input-2-72821d1d76cb> in <module>
      1 data = sc.parallelize([1,2])
      2 
----> 3 data.map(lambda x:x).collect()

~\OneDrive\Desktop\spark\spark-3.0.0-bin-hadoop2.7\python\pyspark\rdd.py in collect(self)
    887         """
    888         with SCCallSiteSync(self.context) as css:
--> 889             sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    890         return list(_load_from_socket(sock_info, self._jrdd_deserializer))
    891 

~\OneDrive\Desktop\spark\spark-3.0.0-bin-hadoop2.7\python\lib\py4j-0.10.9-src.zip\py4j\java_gateway.py in __call__(self, *args)
   1302 
   1303         answer = self.gateway_client.send_command(command)
-> 1304         return_value = get_return_value(
   1305             answer, self.gateway_client, self.target_id, self.name)
   1306 

~\OneDrive\Desktop\spark\spark-3.0.0-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
    129     def deco(*a, **kw):
    130         try:
--> 131             return f(*a, **kw)
    132         except py4j.protocol.Py4JJavaError as e:
    133             converted = convert_exception(e.java_exception)

~\OneDrive\Desktop\spark\spark-3.0.0-bin-hadoop2.7\python\lib\py4j-0.10.9-src.zip\py4j\protocol.py 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)

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 0.0 failed 1 times, most recent failure: Lost task 1.0 in stage 0.0 (TID 1, host.docker.internal, executor driver): java.net.SocketException: Connection reset by peer: socket write error
    at java.net.SocketOutputStream.socketWrite0(Native Method)
    at java.net.SocketOutputStream.socketWrite(SocketOutputStream.java:111)
    at java.net.SocketOutputStream.write(SocketOutputStream.java:155)
    at java.io.BufferedOutputStream.flushBuffer(BufferedOutputStream.java:82)
    at java.io.BufferedOutputStream.flush(BufferedOutputStream.java:140)
    at java.io.DataOutputStream.flush(DataOutputStream.java:123)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.$anonfun$run$1(PythonRunner.scala:386)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1932)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:218)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2023)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:1972)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:1971)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1971)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:950)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:950)
    at scala.Option.foreach(Option.scala:407)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:950)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2203)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2152)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2141)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:752)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2093)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2114)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2133)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2158)
    at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1004)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:388)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:1003)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:168)
    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: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)
Caused by: java.net.SocketException: Connection reset by peer: socket write error
    at java.net.SocketOutputStream.socketWrite0(Native Method)
    at java.net.SocketOutputStream.socketWrite(SocketOutputStream.java:111)
    at java.net.SocketOutputStream.write(SocketOutputStream.java:155)
    at java.io.BufferedOutputStream.flushBuffer(BufferedOutputStream.java:82)
    at java.io.BufferedOutputStream.flush(BufferedOutputStream.java:140)
    at java.io.DataOutputStream.flush(DataOutputStream.java:123)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.$anonfun$run$1(PythonRunner.scala:386)
    at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1932)
    at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:218)