Я пытаюсь загрузить модель логистической регрессии с помощью функции PipelineModel.load (), которая работала нормально 2 недели назад, но недавно показывает ошибку. Мое приложение докеризовано и не имело никаких изменений, но недавно оно перестало работать даже со старым входным файлом, который успешно выполнялся ранее. при индивидуальном запуске кодов я получил следующую ошибку, которую я полностью вставил.
Кто-нибудь недавно сталкивался с подобной ошибкой? любые идеи будут полезны.
model1 = PipelineModel.load(PicklePath)
model1 = PipelineModel.load(PicklePath)
Traceback (most recent call last):
File "<ipython-input-158-8b02a75116f5>", line 1, in <module>
model1 = PipelineModel.load(PicklePath)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\ml\util.py", line 362, in load
return cls.read().load(path)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\ml\pipeline.py", line 242, in load
return JavaMLReader(self.cls).load(path)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\ml\util.py", line 300, in load
java_obj = self._jread.load(path)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\py4j\java_gateway.py", line 1257, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\pyspark\sql\utils.py", line 63, in deco
return f(*a, **kw)
File "C:\Users\z026355\AppData\Local\Continuum\anaconda3\lib\site-packages\py4j\protocol.py", line 328, in get_return_value
format(target_id, ".", name), value)
Py4JJavaError: An error occurred while calling o1095.load.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 53.0 failed 1 times, most recent failure: Lost task 0.0 in stage 53.0 (TID 56, localhost, executor driver): TaskResultLost (result lost from block manager)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365)
at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.apache.spark.sql.Dataset.org$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$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3369)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2550)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2557)
at org.apache.spark.ml.classification.LogisticRegressionModel$LogisticRegressionModelReader.load(LogisticRegression.scala:1273)
at org.apache.spark.ml.classification.LogisticRegressionModel$LogisticRegressionModelReader.load(LogisticRegression.scala:1245)
at org.apache.spark.ml.util.DefaultParamsReader$.loadParamsInstance(ReadWrite.scala:652)
at org.apache.spark.ml.Pipeline$SharedReadWrite$$anonfun$4.apply(Pipeline.scala:274)
at org.apache.spark.ml.Pipeline$SharedReadWrite$$anonfun$4.apply(Pipeline.scala:272)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at org.apache.spark.ml.Pipeline$SharedReadWrite$.load(Pipeline.scala:272)
at org.apache.spark.ml.PipelineModel$PipelineModelReader.load(Pipeline.scala:348)
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)