我是Spark的新生，并尝试完成Spark教程：
指向教程的链接

在本地计算机（Win10 64，Python 3，Spark
2.4.0）上安装它并设置所有环境变量（HADOOP_HOME，SPARK_HOME等）后，我试图通过WordCount.py文件运行一个简单的Spark作业：

from pyspark import SparkContext,SparkConf

if __name__ == "__main__":
    conf = SparkConf().setAppName("word count").setMaster("local[2]")
    sc = SparkContext(conf = conf)

    lines = sc.textFile("C:/Users/mjdbr/Documents/BigData/python-spark-tutorial/in/word_count.text")
    words = lines.flatMap(lambda line: line.split(" "))
    wordCounts = words.countByValue()

    for word,count in wordCounts.items():
        print("{} : {}".format(word,count))

从终端运行后：

spark-submit WordCount.py

我得到以下错误。我检查（逐行注释）它在崩溃

wordCounts = words.countByValue()

知道我应该检查些什么才能使其正常工作吗？

Traceback (most recent call last):
  File "C:\Users\mjdbr\Anaconda3\lib\runpy.py",line 193,in _run_module_as_main
    "__main__",mod_spec)
  File "C:\Users\mjdbr\Anaconda3\lib\runpy.py",line 85,in _run_code
    exec(code,run_globals)
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\worker.py",line 25,in <module>
ModuleNotFoundError: No module named 'resource'
18/11/10 23:16:58 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
org.apache.spark.SparkException: Python worker failed to connect back.
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
        at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
        at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
        at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
        at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
        at org.apache.spark.scheduler.Task.run(Task.scala:121)
        at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
        at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
        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.net.SocketTimeoutException: Accept timed out
        at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
        at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
        at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
        at java.net.PlainSocketImpl.accept(Unknown Source)
        at java.net.ServerSocket.implAccept(Unknown Source)
        at java.net.ServerSocket.accept(Unknown Source)
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
        ... 14 more
18/11/10 23:16:58 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
Traceback (most recent call last):
  File "C:/Users/mjdbr/Documents/BigData/python-spark-tutorial/rdd/WordCount.py",line 19,in <module>
    wordCounts = words.countByValue()
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\rdd.py",line 1261,in countByValue
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\rdd.py",line 844,in reduce
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\pyspark.zip\pyspark\rdd.py",line 816,in collect
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\java_gateway.py",line 1257,in __call__
  File "C:\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\protocol.py",line 328,in get_return_value
py4j.protocol.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 0 in stage 0.0 failed 1 times,most recent failure:
Lost task 0.0 in stage 0.0 (TID 0,localhost,executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
        at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
        at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
        at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
        at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
        at org.apache.spark.scheduler.Task.run(Task.scala:121)
        at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
        at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        at java.lang.Thread.run(Unknown Source)
Caused by: java.net.SocketTimeoutException: Accept timed out
        at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
        at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
        at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
        at java.net.PlainSocketImpl.accept(Unknown Source)
        at java.net.ServerSocket.implAccept(Unknown Source)
        at java.net.ServerSocket.accept(Unknown Source)
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
        ... 14 more

Driver stacktrace:
        at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1887)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1875)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1874)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1874)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
        at scala.Option.foreach(Option.scala:257)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2108)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2057)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2046)
        at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
        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.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:166)
        at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.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: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(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker failed to connect back.
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
        at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
        at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
        at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
        at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
        at org.apache.spark.scheduler.Task.run(Task.scala:121)
        at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
        at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
        ... 1 more
Caused by: java.net.SocketTimeoutException: Accept timed out
        at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
        at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
        at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
        at java.net.PlainSocketImpl.accept(Unknown Source)
        at java.net.ServerSocket.implAccept(Unknown Source)
        at java.net.ServerSocket.accept(Unknown Source)
        at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
        ... 14 more

如鸭嘴兽所建议-检查“资源”模块是否可以直接从终端导入-显然不能：

>>> import resource
Traceback (most recent call last):
  File "<stdin>",line 1,in <module>
ModuleNotFoundError: No module named 'resource'

在安装资源方面-
我遵循了本教程中的说明：

1. 从Apache Spark网站下载了spark-2.4.0-bin-hadoop2.7.tgz
2. 解压缩到我的C盘
3. 已经安装了Python_3（Anaconda发行版）以及Java
4. 创建了本地“ C：\ hadoop \ bin”文件夹来存储winutils.exe
5. 创建了’C：\ tmp \ hive’文件夹，并授予了Spark访问权限
6. 添加了环境变量（SPARK_HOME，HADOOP_HOME等）

我应该安装任何额外的资源吗？

private void GetSomething(Action<IEnumerable<int>> completedAction)
{
    BackgroundWorker b = new BackgroundWorker();

    b.DoWork += (s,evt) => { throw new Exception(); evt.Result = new List<int> { 1,2,3 }; };

    b.RunWorkerCompleted += (s,evt) =>
    {
        if (evt.Error == null && completedAction != null)
        {
           completedAction((IEnumerable<int>)evt.Result);
        }
        else if(evt.Error != null)
        {
           throw evt.Error;
        }
    };

    b.RunWorkerAsync();
}

private void button3_Click(object sender,EventArgs e)
{
    try
    {
        GetSomething(list =>
        {
           foreach (int i in list)
           {
              listView1.Items.Add(new ListViewItem(i.ToString()));
           }
        });
    }
    catch (Exception ex)
    {
        MessageBox.Show(ex.Message);
    }
}

解决方法

private void GetSomething(Action<IEnumerable<int>> completedAction,Action<Exception> exceptionAction)
{
    BackgroundWorker b = new BackgroundWorker();

    b.DoWork += (s,evt) =>
    {
        if (evt.Error == null && completedAction != null)
            completedAction((IEnumerable<int>)evt.Result);
        else if(evt.Error != null)
            exceptionAction(evt.Error);
    };

    b.RunWorkerAsync();
}

Task<IEnumerable<int>> GetSomething()
{
    return Task.Factory.StartNew(() => { 
        Thread.Sleep(2000);
        throw new Exception(); 
        return (new List<int> { 1,3 }).AsEnumerable(); 
        });
}

private void button3_Click(object sender,EventArgs e)
    {
        GetSomething()
            .ContinueWith(task =>
                {
                    if (task.IsCanceled)
                    {
                    }
                    else if (task.IsFaulted)
                    {
                        var ex = task.Exception.InnerException;
                        MessageBox.Show(ex.Message);
                    }
                    else if (task.IsCompleted)
                    {
                        var list = task.Result;
                        foreach (int i in list)
                        {
                            listView1.Items.Add(new ListViewItem(i.ToString()));
                        }
                    }
                });
    }

private async void button3_Click(object sender,EventArgs e)
    {
        try
        {
            var list = await GetSomething();
            foreach (int i in list)
            {
                listView1.Items.Add(new ListViewItem(i.ToString()));
            }
        }
        catch (Exception ex)
        {
            MessageBox.Show(ex.Message);
        }
    }