MLlib-Kmeans遇到的异常

最新推荐文章于 2024-08-16 10:07:57 发布

-ROOT-

最新推荐文章于 2024-08-16 10:07:57 发布

阅读量1.7k

点赞数 2

分类专栏： MLlib 文章标签：异常 MLlib Kmeans spark

本文链接：https://blog.csdn.net/github_36869152/article/details/53414753

版权

MLlib 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

在用MLlib跑KMeans的时候死活跑不起来，由于造训练数据和测试数据的时候是我亲自造的，始终坚信我的数据绝对没有问题，回想起来造数据的时候使用过CV大法，在最后确认数据之后发现最后一条数据和其他的数据不同，没有做处理造成了下面的结果，真是piapia打脸那，果然程序是不会骗你的。。

造成此问题的原因是数据源的维度不同导致的非法参数异常。

以下是在stackoverflow中查到的答案：
http://stackoverflow.com/questions/30737361/getting-java-lang-illegalargumentexception-requirement-failed-while-calling-spa

附上异常的样子~

Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 2.0 failed 4 times, most recent failure: Lost task 1.3 in stage 2.0 (TID 8, s12180): java.lang.IllegalArgumentException: requirement failed
    at scala.Predef$.require(Predef.scala:221)
    at org.apache.spark.mllib.util.MLUtils$.fastSquaredDistance(MLUtils.scala:330)
    at org.apache.spark.mllib.clustering.KMeans$.fastSquaredDistance(KMeans.scala:595)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$findClosest$1.apply(KMeans.scala:569)
	at org.apache.spark.mllib.clustering.KMeans$$anonfun$findClosest$1.apply(KMeans.scala:563)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.mllib.clustering.KMeans$.findClosest(KMeans.scala:563)
    at org.apache.spark.mllib.clustering.KMeans$.pointCost(KMeans.scala:586)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply$mcDI$sp(KMeans.scala:400)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply(KMeans.scala:399)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply(KMeans.scala:399)
    at scala.Array$.tabulate(Array.scala:331)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1.apply(KMeans.scala:399)
	at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1.apply(KMeans.scala:398)
    at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
    at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:285)
    at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
	at scala.Option.foreach(Option.scala:236)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1843)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1963)
    at org.apache.spark.rdd.RDD$$anonfun$aggregate$1.apply(RDD.scala:1114)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
	at org.apache.spark.rdd.RDD.aggregate(RDD.scala:1107)
	at org.apache.spark.mllib.clustering.KMeans.initKMeansParallel(KMeans.scala:404)
	at org.apache.spark.mllib.clustering.KMeans.runAlgorithm(KMeans.scala:249)
	at org.apache.spark.mllib.clustering.KMeans.run(KMeans.scala:213)
	at org.apache.spark.mllib.clustering.KMeans$.train(KMeans.scala:528)
	at org.apache.spark.mllib.clustering.KMeans$.train(KMeans.scala:551)
	at KMeansRun$.main(KMeansRun.scala:24)
	at KMeansRun.main(KMeansRun.scala)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalArgumentException: requirement failed
    at scala.Predef$.require(Predef.scala:221)
    at org.apache.spark.mllib.util.MLUtils$.fastSquaredDistance(MLUtils.scala:330)
    at org.apache.spark.mllib.clustering.KMeans$.fastSquaredDistance(KMeans.scala:595)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$findClosest$1.apply(KMeans.scala:569)
	at org.apache.spark.mllib.clustering.KMeans$$anonfun$findClosest$1.apply(KMeans.scala:563)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.mllib.clustering.KMeans$.findClosest(KMeans.scala:563)
    at org.apache.spark.mllib.clustering.KMeans$.pointCost(KMeans.scala:586)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply$mcDI$sp(KMeans.scala:400)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply(KMeans.scala:399)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1$$anonfun$apply$3.apply(KMeans.scala:399)
    at scala.Array$.tabulate(Array.scala:331)
    at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1.apply(KMeans.scala:399)
	at org.apache.spark.mllib.clustering.KMeans$$anonfun$initKMeansParallel$1.apply(KMeans.scala:398)
    at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
    at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:285)
    at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
    at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)