Я пытаюсь запустить пример, приведенный в https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark. sql .functions.pandas_udf :
from pyspark.sql import SparkSession
from pyspark.sql.functions import pandas_udf, PandasUDFType
spark = SparkSession.builder.getOrCreate()
df = spark.createDataFrame(
[(1, 1.0), (1, 2.0), (2, 3.0), (2, 5.0), (2, 10.0)],
("id", "v"))
@pandas_udf("id long, v double", PandasUDFType.GROUPED_MAP) def normalize(pdf):
v = pdf.v
return pdf.assign(v=(v - v.mean()) / v.std())
df.groupby("id").apply(normalize).show()
Но я получаю исключение (полная трассировка стека ниже) .
Я пробовал предлагаемое решение здесь , но это не помогло.
Я пытался экспортировать переменные окружения PYSPARK_PYTHON и PYSPARK_DRIVER_PYTHON раньше запуск python (указывает на тот же интерпретатор python), но это не помогло.
Я выполняю это на MacOS в виртуальной среде, созданной с помощью venv. Список установленных пакетов выглядит следующим образом:
f$ pip list
Package Version Location
------------------ --------------------------- ----------------------------------------------------------------------
-andas 0.25.3
appnope 0.1.0
attrs 19.3.0
backcall 0.1.0
boto3 1.12.31
botocore 1.15.31
cffi 1.14.0
cycler 0.10.0
Cython 0.29.16
decorator 4.4.2
docutils 0.15.2
filelock 3.0.12
fsspec 0.7.0
importlib-metadata 1.6.0
ipython 7.13.0
ipython-genutils 0.2.0
jedi 0.16.0
Jinja2 2.11.1
jmespath 0.9.5
joblib 0.14.1
kiwisolver 1.1.0
MarkupSafe 1.1.1
matplotlib 3.2.1
more-itertools 8.2.0
numpy 1.18.2
packaging 20.3
pandas 0.25.3
parso 0.6.2
patsy 0.5.1
pexpect 4.8.0
pickleshare 0.7.5
pip 20.0.2
pluggy 0.13.1
prompt-toolkit 3.0.5
ptyprocess 0.6.0
py 1.8.1
py4j 0.10.7
pyarrow 0.14.1
pycparser 2.20
Pygments 2.6.1
pyodbc 4.0.30
pyparsing 2.4.6
pyspark 2.4.5
pytest 5.4.1
python-dateutil 2.8.1
python-dotenv 0.12.0
pytz 2019.3
rpy2 3.0.0
s3fs 0.4.1
s3transfer 0.3.3
scikit-learn 0.22.1
scipy 1.4.1
seaborn 0.10.0
setuptools 41.2.0
simplegeneric 0.8.1
six 1.14.0
statsmodels 0.11.1
tqdm 4.44.1
traitlets 4.3.3
tzlocal 2.0.0
urllib3 1.25.8
wcwidth 0.1.9
zipp 3.1.0
Трассировка стека выглядит следующим образом:
[Stage 7:=======================================================>(99 + 1) / 100]objc[81337]: +[__NSPlaceholderDictionary initialize] may have been in progress in another thread when fork() was called.
objc[81337]: +[__NSPlaceholderDictionary initialize] may have been in progress in another thread when fork() was called. We cannot safely call it or ignore it in the fork() child process. Crashing instead. Set a breakpoint on objc_initializeAfterForkError to debug.
20/03/30 09:33:53 ERROR Executor: Exception in task 44.0 in stage 7.0 (TID 136)
org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:490)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:479)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:178)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:159)
... 26 more
20/03/30 09:33:53 WARN TaskSetManager: Lost task 44.0 in stage 7.0 (TID 136, localhost, executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:490)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:479)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:178)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:159)
... 26 more
20/03/30 09:33:53 ERROR TaskSetManager: Task 44 in stage 7.0 failed 1 times; aborting job
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-3-fc7502e65cf8> in <module>
----> 1 df.groupby("id").apply(normalize).show()
~/Work/lodging-brain-mod-lever/scripts/Python/godfather/venv/lib/python3.7/site-packages/pyspark/sql/dataframe.py in show(self, n, truncate, vertical)
378 """
379 if isinstance(truncate, bool) and truncate:
--> 380 print(self._jdf.showString(n, 20, vertical))
381 else:
382 print(self._jdf.showString(n, int(truncate), vertical))
~/Work/lodging-brain-mod-lever/scripts/Python/godfather/venv/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
~/Work/lodging-brain-mod-lever/scripts/Python/godfather/venv/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
~/Work/lodging-brain-mod-lever/scripts/Python/godfather/venv/lib/python3.7/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o53.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 44 in stage 7.0 failed 1 times, most recent failure: Lost task 44.0 in stage 7.0 (TID 136, localhost, executor driver): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:490)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:479)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:178)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:159)
... 26 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1891)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1878)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1878)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2112)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2061)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2050)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3389)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3370)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3369)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2550)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2764)
at org.apache.spark.sql.Dataset.getRows(Dataset.scala:254)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:291)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:490)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator$$anonfun$3.applyOrElse(PythonRunner.scala:479)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:178)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage3.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:255)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:247)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:858)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:346)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:310)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:123)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:159)
... 26 more