问题
我正在尝试使用pySpark在Jupyter笔记本中运行Python DEAP遗传算法进行并行化。通过一些研究，我了解到要点是注册一个基于spark的映射函数到工具箱中，以允许spark进行适应度评估（下面是代码）。
我的问题是，我该如何为SparkContext公开creator函数？与SCOOP和多进程相比，Spark是否需要任何特殊处理？
代码
我正在运行的代码的要点如下，其中已经创建了SparContext（sc）：
import deap as ea
from deap import creator, base, tools, algorithms
ea.creator.create("FitnessMin", ea.base.Fitness, weights=(-1.0,))
ea.creator.create("Individual", list, fitness=ea.creator.FitnessMin)
toolbox = ea.base.Toolbox()
def sparkMap(algorithm, *population):
return sc.parallelize(population).map(algorithm)
toolbox.register("map", sparkMap) #Set DEAP to run on a machine cluster using Spark
hallOfFame = tools.HallOfFame(2)
population = toolbox.population(n=POPULATION_SIZE)
tools.initIterate(list, partial(sample, range(MAX_NUMBER_OF_CLUSTERS), MAX_NUMBER_OF_CLUSTERS))
gen = 0;
while gen < NUMBER_OF_GENERATOINS:
# Update population
population = toolbox.select(population, k=len(population))
population = [toolbox.clone(ind) for ind in population]
population = ea.algorithms.varAnd(population, toolbox, cxpb=cxpb, mutpb=mutpb, )
offspring = [individual for individual in population if not individual.fitness.valid]
fits = toolbox.map(toolbox.evaluate, offspring).collect()
for fit, ind in zip(fits, offspring):
ind.fitness.values = fit
#Update hall of fame to ensure we always know the best found solution
hallOfFame.update(offspring)
gen += 1
best = hallOfFame[0]
然而，这会导致一个错误，指出：
AttributeError: 无法从'/gpfs/fs01/user/s093-7b1ca9741d3405-545a66b5b986/.local/lib/python3.5/site-packages/deap/creator.py'中的'module'deap.creator'获取属性'Individual'
我的理解是，在其他并行设置（如SCOOP和Python parallel）中，deap.creator方法必须是全局范围的一部分。由于我在JUpyter笔记本上工作，因此下面的代码应该是这种情况。 此外，“％who”显示，在许多其他内容中，这些内容列在全局范围内：
creator ea sparkMap toolbox
错误信息
完整的错误信息：
--------------------------------------------------------------------------- Py4JJavaError Traceback (most recent call last) <ipython-input-45-49c0cc9cf0b4> in <module>()
28
29 offspring = [individual for individual in population if not individual.fitness.valid]
---> 30 fits = toolbox.map(toolbox.evaluate, offspring).collect()
31 #print('---------------------------------------------------------------------')
32 #print('fits',fits)
/usr/local/src/spark21master/spark/python/pyspark/rdd.py in collect(self)
806 """
807 with SCCallSiteSync(self.context) as css:
--> 808 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
809 return list(_load_from_socket(port, self._jrdd_deserializer))
810
/usr/local/src/spark21master/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args) 1131 answer = self.gateway_client.send_command(command) 1132 return_value
= get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name) 1134 1135 for temp_arg in temp_args:
/usr/local/src/spark21master/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/src/spark21master/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
321 raise Py4JError(
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 1 in stage 1.0 failed 10 times, most recent failure: Lost task
1.9 in stage 1.0 (TID 21, yp-spark-dal09-env5-0024, executor 6679c417-036c-45c6-9b7e-92e96c9751eb): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/worker.py", line 171, in main
process() File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/worker.py", line 166, in process
serializer.dump_stream(func(split_index, iterator), outfile) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 268, in dump_stream
vs = list(itertools.islice(iterator, batch)) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 144, in load_stream
yield self._read_with_length(stream) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 169, in _read_with_length
return self.loads(obj) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 455, in loads
return pickle.loads(obj, encoding=encoding) AttributeError: Can't get attribute 'Individual' on <module 'deap.creator' from '/gpfs/fs01/user/s093-7b1ca9741d3405-545a66b5b986/.local/lib/python3.5/site-packages/deap/creator.py'>
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193) at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:326) at org.apache.spark.rdd.RDD.iterator(RDD.scala:290) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:326) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1153) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) at java.lang.Thread.run(Thread.java:785)
Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1442) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1430) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1429) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1429) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:803) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:803) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:803) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1657) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1612) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1601) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at java.lang.Thread.getStackTrace(Thread.java:1117) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:629) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1941) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1954) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1967) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1981) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:956) 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:381) at org.apache.spark.rdd.RDD.collect(RDD.scala:955) at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453) at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:95) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:55) at java.lang.reflect.Method.invoke(Method.java:507) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:280) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:214) at java.lang.Thread.run(Thread.java:785) Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/worker.py", line 171, in main
process() File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/worker.py", line 166, in process
serializer.dump_stream(func(split_index, iterator), outfile) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 268, in dump_stream
vs = list(itertools.islice(iterator, batch)) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 144, in load_stream
yield self._read_with_length(stream) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 169, in _read_with_length
return self.loads(obj) File "/usr/local/src/spark21master/spark-2.1.2-bin-2.7.3/python/lib/pyspark.zip/pyspark/serializers.py", line 455, in loads
return pickle.loads(obj, encoding=encoding) AttributeError: Can't get attribute 'Individual' on <module 'deap.creator' from '/gpfs/fs01/user/s093-7b1ca9741d3405-545a66b5b986/.local/lib/python3.5/site-packages/deap/creator.py'>
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193) at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:326) at org.apache.spark.rdd.RDD.iterator(RDD.scala:290) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87) at org.apache.spark.scheduler.Task.run(Task.scala:99) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:326) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1153) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) ... 1 more