我正在关注AWS ec2 AMI，Docker，Jupiter Notebook，PySpark教程https://www.guru99.com/pyspark-tutorial.html
我已经完成了本教程显示的所有操作。 我在以下部分收到错误消息：
from time import *
start_time = time()
# Create 5-fold CrossValidator
cv = CrossValidator(estimator=lr,
estimatorParamMaps=paramGrid,
evaluator=evaluator, numFolds=5)
# Run cross validations
cvModel = cv.fit(train_data)
# likely take a fair amount of time
end_time = time()
elapsed_time = end_time - start_time
print("Time to train model: %.3f seconds" % elapsed_time)
错误消息：
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-60-f9ae20e6d18e> in <module>
8
9 # Run cross validations
---> 10 cvModel = cv.fit(train_data)
11 # likely take a fair amount of time
12 end_time = time()
/usr/local/spark/python/pyspark/ml/base.py in fit(self, dataset, params)
130 return self.copy(params)._fit(dataset)
131 else:
--> 132 return self._fit(dataset)
133 else:
134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/usr/local/spark/python/pyspark/ml/tuning.py in _fit(self, dataset)
302
303 tasks = _parallelFitTasks(est, train, eva, validation, epm, collectSubModelsParam)
--> 304 for j, metric, subModel in pool.imap_unordered(lambda f: f(), tasks):
305 metrics[j] += (metric / nFolds)
306 if collectSubModelsParam:
/opt/conda/lib/python3.7/multiprocessing/pool.py in next(self, timeout)
746 if success:
747 return value
--> 748 raise value
749
750 __next__ = next # XXX
/opt/conda/lib/python3.7/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
119 job, i, func, args, kwds = task
120 try:
--> 121 result = (True, func(*args, **kwds))
122 except Exception as e:
123 if wrap_exception and func is not _helper_reraises_exception:
/usr/local/spark/python/pyspark/ml/tuning.py in <lambda>(f)
302
303 tasks = _parallelFitTasks(est, train, eva, validation, epm, collectSubModelsParam)
--> 304 for j, metric, subModel in pool.imap_unordered(lambda f: f(), tasks):
305 metrics[j] += (metric / nFolds)
306 if collectSubModelsParam:
/usr/local/spark/python/pyspark/ml/tuning.py in singleTask()
51 def singleTask():
52 index, model = next(modelIter)
---> 53 metric = eva.evaluate(model.transform(validation, epm[index]))
54 return index, metric, model if collectSubModel else None
55
/usr/local/spark/python/pyspark/ml/evaluation.py in evaluate(self, dataset, params)
69 return self.copy(params)._evaluate(dataset)
70 else:
---> 71 return self._evaluate(dataset)
72 else:
73 raise ValueError("Params must be a param map but got %s." % type(params))
/usr/local/spark/python/pyspark/ml/evaluation.py in _evaluate(self, dataset)
99 """
100 self._transfer_params_to_java()
--> 101 return self._java_obj.evaluate(dataset._jdf)
102
103 def isLargerBetter(self):
/usr/local/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/usr/local/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o1467.evaluate.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 264.0 failed 1 times, most recent failure: Lost task 0.0 in stage 264.0 (TID 2192, localhost, executor driver): java.net.SocketException: Broken pipe (Write failed)
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.write(BufferedOutputStream.java:122)
at java.io.DataOutputStream.write(DataOutputStream.java:107)
at java.io.FilterOutputStream.write(FilterOutputStream.java:97)
at org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:212)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:224)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:224)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:148)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:224)
at org.apache.spark.api.python.PythonRunner$$anon$2.writeIteratorToStream(PythonRunner.scala:557)
at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:345)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1945)
at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:194)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
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:2110)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
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.mllib.evaluation.BinaryClassificationMetrics.x$4$lzycompute(BinaryClassificationMetrics.scala:192)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.x$4(BinaryClassificationMetrics.scala:146)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.confusions$lzycompute(BinaryClassificationMetrics.scala:148)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.confusions(BinaryClassificationMetrics.scala:148)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.createCurve(BinaryClassificationMetrics.scala:223)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.roc(BinaryClassificationMetrics.scala:86)
at org.apache.spark.mllib.evaluation.BinaryClassificationMetrics.areaUnderROC(BinaryClassificationMetrics.scala:97)
at org.apache.spark.ml.evaluation.BinaryClassificationEvaluator.evaluate(BinaryClassificationEvaluator.scala:87)
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: Broken pipe (Write failed)
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.write(BufferedOutputStream.java:122)
at java.io.DataOutputStream.write(DataOutputStream.java:107)
at java.io.FilterOutputStream.write(FilterOutputStream.java:97)
at org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:212)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:224)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:224)
at scala.collection.Iterator$class.foreach(Iterator.scala:891)
at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:148)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:224)
at org.apache.spark.api.python.PythonRunner$$anon$2.writeIteratorToStream(PythonRunner.scala:557)
at org.apache.spark.api.python.BasePythonRunner$WriterThread$$anonfun$run$1.apply(PythonRunner.scala:345)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1945)
at org.apache.spark.api.python.BasePythonRunner$WriterThread.run(PythonRunner.scala:194)
我已经看过类似的堆栈溢出文章，但是代码正在运行，只需要修改即可：