报错内容:
C:\Python38\python.exe C:/untitled5/test1203.py
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
24/12/03 18:54:42 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:188)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:108)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:121)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:162)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:115)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.ExecutorTaskRunner.anonfun$run3(Executor.scala:506)
at org.apache.spark.util.Utils.tryWithSafeFinally(Utils.scala:1491)
at org.apache.spark.executor.ExecutorTaskRunner.run(Executor.scala:509)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutorWorker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: Accept timed out
at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:131)
at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:535)
at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:189)
at java.net.ServerSocket.implAccept(ServerSocket.java:545)
at java.net.ServerSocket.accept(ServerSocket.java:513)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:175)
... 19 more
24/12/03 18:54:42 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0) (Y9000P executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:188)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:108)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:121)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:162)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:115)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.ExecutorTaskRunner.anonfun$run3(Executor.scala:506)
at org.apache.spark.util.Utils.tryWithSafeFinally(Utils.scala:1491)
at org.apache.spark.executor.ExecutorTaskRunner.run(Executor.scala:509)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutorWorker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: Accept timed out
at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:131)
at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:535)
at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:189)
at java.net.ServerSocket.implAccept(ServerSocket.java:545)
at java.net.ServerSocket.accept(ServerSocket.java:513)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:175)
... 19 more
24/12/03 18:54:42 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
Traceback (most recent call last):
File "C:/untitled5/test1203.py", line 16, in <module>
words = doc.flatMap(lambda d:d).distinct().collect()
File "C:\Python38\lib\site-packages\pyspark\rdd.py", line 950, in collect
sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
File "C:\Python38\lib\site-packages\py4j\java_gateway.py", line 1321, in call
return_value = get_return_value(
File "C:\Python38\lib\site-packages\py4j\protocol.py", line 326, in get_return_value
raise Py4JJavaError(
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) (Y9000P executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:188)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:108)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:121)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:162)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:115)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.ExecutorTaskRunner.anonfun$run3(Executor.scala:506)
at org.apache.spark.util.Utils.tryWithSafeFinally(Utils.scala:1491)
at org.apache.spark.executor.ExecutorTaskRunner.run(Executor.scala:509)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutorWorker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.net.SocketTimeoutException: Accept timed out
at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:131)
at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:535)
at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:189)
at java.net.ServerSocket.implAccept(ServerSocket.java:545)
at java.net.ServerSocket.accept(ServerSocket.java:513)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:175)
... 19 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2454)
at org.apache.spark.scheduler.DAGScheduler.anonfunabortStage2(DAGScheduler.scala:2403)
at org.apache.spark.scheduler.DAGScheduler.anonfun$abortStage2adapted(DAGScheduler.scala:2402)
at scala.collection.immutable.List.foreach(List.scala:333)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2402)
at org.apache.spark.scheduler.DAGScheduler.anonfunhandleTaskSetFailed1(DAGScheduler.scala:1160)
at org.apache.spark.scheduler.DAGScheduler.anonfun$handleTaskSetFailed1adapted(DAGScheduler.scala:1160)
at scala.Option.foreach(Option.scala:437)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1160)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2642)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2584)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2573)
at org.apache.spark.util.EventLoop$$anon1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:938)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2214)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2235)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2254)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2279)
at org.apache.spark.rdd.RDD.anonfun$collect1(RDD.scala:1030)
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:414)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1029)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala:180)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Python worker failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:188)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:108)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:121)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:162)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:115)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.ExecutorTaskRunner.anonfun$run3(Executor.scala:506)
at org.apache.spark.util.Utils.tryWithSafeFinally(Utils.scala:1491)
at org.apache.spark.executor.ExecutorTaskRunner.run(Executor.scala:509)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutorWorker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.net.SocketTimeoutException: Accept timed out
at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
at java.net.DualStackPlainSocketImpl.socketAccept(DualStackPlainSocketImpl.java:131)
at java.net.AbstractPlainSocketImpl.accept(AbstractPlainSocketImpl.java:535)
at java.net.PlainSocketImpl.accept(PlainSocketImpl.java:189)
at java.net.ServerSocket.implAccept(ServerSocket.java:545)
at java.net.ServerSocket.accept(ServerSocket.java:513)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:175)
... 19 more
需要代码前面加入python地址:
python
import os # 导入os模块
os.environ['PYSPARK_PYTHON']='"C:\\Python38\\python.exe"'#本机电脑所使用的python编译器的地址
python
#测试内容:
import os # 导入os模块
os.environ['PYSPARK_PYTHON']='"C:\\Python38\\python.exe"'#本机电脑所使用的python编译器的地址
from pyspark import SparkContext
sc = SparkContext("local","Simple App")
doc = sc.parallelize([['a','b','c'],['b','d','d']])
words = doc.flatMap(lambda d:d).distinct().collect()
word_dict = {w:i for w,i in zip(words,range(len(words)))}
word_dict_b = sc.broadcast(word_dict)
def wordCountPerDoc(d):
dict={}
wd = word_dict_b.value
for w in d:
if dict.get(wd[w],0):
dict[wd[w]] +=1
else:
dict[wd[w]] = 1
return dict
print(doc.map(wordCountPerDoc).collect())
print("successful!")
C:\Python38\python.exe C:/untitled5/test1203.py
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
[{0: 1, 1: 1, 2: 1}, {1: 1, 3: 2}]
successful!
Process finished with exit code 0