While using the following code:
import pyspark
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql import SparkSession
from pyspark.sql.types import Row
from datetime import datetime
sc = SparkContext()
spark = SparkSession(sc)
simple_data = sc.parallelize([1, "Nissan Versa", 12])
simple_data.count()
I get the following error:
--------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
Cell In[10], line 1
----> 1 simple_data.count()
File ~\anaconda3\Lib\site-packages\pyspark\rdd.py:2316, in RDD.count(self)
2295 def count(self) -> int:
2296 """
2297 Return the number of elements in this RDD.
2298
(...)
2314 3
2315 """
-> 2316 return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
File ~\anaconda3\Lib\site-packages\pyspark\rdd.py:2291, in RDD.sum(self)
2270 def sum(self: "RDD[NumberOrArray]") -> "NumberOrArray":
2271 """
2272 Add up the elements in this RDD.
2273
(...)
2289 6.0
2290 """
-> 2291 return self.mapPartitions(lambda x: [sum(x)]).fold( # type: ignore[return-value]
2292 0, operator.add
2293 )
File ~\anaconda3\Lib\site-packages\pyspark\rdd.py:2044, in RDD.fold(self, zeroValue, op)
2039 yield acc
2041 # collecting result of mapPartitions here ensures that the copy of
2042 # zeroValue provided to each partition is unique from the one provided
2043 # to the final reduce call
-> 2044 vals = self.mapPartitions(func).collect()
2045 return reduce(op, vals, zeroValue)
File ~\anaconda3\Lib\site-packages\pyspark\rdd.py:1833, in RDD.collect(self)
1831 with SCCallSiteSync(self.context):
1832 assert self.ctx._jvm is not None
-> 1833 sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
1834 return list(_load_from_socket(sock_info, self._jrdd_deserializer))
File ~\anaconda3\Lib\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 ~\anaconda3\Lib\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 ~\anaconda3\Lib\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 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) (DESKTOP-JC7CP9I executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:203)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:109)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:124)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:67)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
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$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.net.SocketTimeoutException: Accept timed out
at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
at java.net.PlainSocketImpl.accept(Unknown Source)
at java.net.ServerSocket.implAccept(Unknown Source)
at java.net.ServerSocket.accept(Unknown Source)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:190)
... 17 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2856)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2792)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2791)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2791)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1247)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1247)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1247)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3060)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2994)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2983)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:989)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2398)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2419)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2438)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2463)
at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1049)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:410)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1048)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:195)
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: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 failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:203)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:109)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:124)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:67)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
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.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:190)
... 17 more
java version "1.8.0_421", Python 3.11.8, pyspark 3.5.1
I installed pyspark in anaconda powershell using "conda install -c conda-forge pyspark".
It is the first time I use spark in jupyter and I don't know how to fix it. What can I do to fix this?
