Я получаю эту ошибку при обучении модели ALS на некоторых данных.
Я пробовал это Задание отменено, потому что SparkContext был закрыт , но это не сработало, я возникла эта проблема, так как я впервые попытался обучить модель, и это заняло много времени (более 5 часов), тогда у меня была эта проблема, но теперь, через 5 секунд, он получает эту ошибку.
Спасибо за помогая,
вся ошибка выглядит следующим образом:
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-7-640e082ca573> in <module>
----> 1 Model = als.fit(data_train)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\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, "
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\ml\wrapper.py in _fit(self, dataset)
293
294 def _fit(self, dataset):
--> 295 java_model = self._fit_java(dataset)
296 model = self._create_model(java_model)
297 return self._copyValues(model)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\ml\wrapper.py in _fit_java(self, dataset)
290 """
291 self._transfer_params_to_java()
--> 292 return self._java_obj.fit(dataset._jdf)
293
294 def _fit(self, dataset):
~\AppData\Local\Continuum\anaconda3\lib\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:
~\AppData\Local\Continuum\anaconda3\lib\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()
~\AppData\Local\Continuum\anaconda3\lib\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 o34.fit.
: org.apache.spark.SparkException: Job 18 cancelled because SparkContext was shut down
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:933)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$cleanUpAfterSchedulerStop$1.apply(DAGScheduler.scala:931)
at scala.collection.mutable.HashSet.foreach(HashSet.scala:78)
at org.apache.spark.scheduler.DAGScheduler.cleanUpAfterSchedulerStop(DAGScheduler.scala:931)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onStop(DAGScheduler.scala:2130)
at org.apache.spark.util.EventLoop.stop(EventLoop.scala:84)
at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:2043)
at org.apache.spark.SparkContext$$anonfun$stop$6.apply$mcV$sp(SparkContext.scala:1949)
at org.apache.spark.util.Utils$.tryLogNonFatalError(Utils.scala:1340)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1948)
at org.apache.spark.SparkContext$$anonfun$2.apply$mcV$sp(SparkContext.scala:575)
at org.apache.spark.util.SparkShutdownHook.run(ShutdownHookManager.scala:216)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ShutdownHookManager.scala:188)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(ShutdownHookManager.scala:188)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1$$anonfun$apply$mcV$sp$1.apply(ShutdownHookManager.scala:188)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1945)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply$mcV$sp(ShutdownHookManager.scala:188)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(ShutdownHookManager.scala:188)
at org.apache.spark.util.SparkShutdownHookManager$$anonfun$runAll$1.apply(ShutdownHookManager.scala:188)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.util.SparkShutdownHookManager.runAll(ShutdownHookManager.scala:188)
at org.apache.spark.util.SparkShutdownHookManager$$anon$2.run(ShutdownHookManager.scala:178)
at org.apache.hadoop.util.ShutdownHookManager$1.run(ShutdownHookManager.java:54)
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:2158)
at org.apache.spark.rdd.RDD$$anonfun$aggregate$1.apply(RDD.scala:1169)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:385)
at org.apache.spark.rdd.RDD.aggregate(RDD.scala:1162)
at org.apache.spark.ml.recommendation.ALS$.computeYtY(ALS.scala:1712)
at org.apache.spark.ml.recommendation.ALS$.org$apache$spark$ml$recommendation$ALS$$computeFactors(ALS.scala:1653)
at org.apache.spark.ml.recommendation.ALS$$anonfun$train$4.apply(ALS.scala:983)
at org.apache.spark.ml.recommendation.ALS$$anonfun$train$4.apply(ALS.scala:970)
at scala.collection.immutable.Range.foreach(Range.scala:160)
at org.apache.spark.ml.recommendation.ALS$.train(ALS.scala:970)
at org.apache.spark.ml.recommendation.ALS$$anonfun$fit$1.apply(ALS.scala:676)
at org.apache.spark.ml.recommendation.ALS$$anonfun$fit$1.apply(ALS.scala:658)
at org.apache.spark.ml.util.Instrumentation$$anonfun$11.apply(Instrumentation.scala:185)
at scala.util.Try$.apply(Try.scala:192)
at org.apache.spark.ml.util.Instrumentation$.instrumented(Instrumentation.scala:185)
at org.apache.spark.ml.recommendation.ALS.fit(ALS.scala:658)
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: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(Unknown Source)