当前位置： 文江博客话题详情

scala一直报错：java.lang.NullPointerException

发布于 2022-09-30 23:10:28 字数 17687 浏览 48 评论 0

完整的错误是：

21/09/29 16:05:25 ERROR Executor: Exception in task 0.0 in stage 3.0 (TID 3)
java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
21/09/29 16:05:25 WARN TaskSetManager: Lost task 0.0 in stage 3.0 (TID 3) (iZbp19g1r31py4tg9gvzjhZ executor driver): java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)

21/09/29 16:05:25 ERROR TaskSetManager: Task 0 in stage 3.0 failed 1 times; aborting job
21/09/29 16:05:25 ERROR JobScheduler: Error running job streaming job 1632902720000 ms.0
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0 (TID 3) (iZbp19g1r31py4tg9gvzjhZ executor driver): java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2258)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2207)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2206)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2206)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1079)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1079)
    at scala.Option.foreach(Option.scala:407)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1079)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2445)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2387)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2376)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:868)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2196)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2261)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$1(RDD.scala:1012)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
    at org.apache.spark.rdd.RDD.foreach(RDD.scala:1010)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1(recommend.scala:58)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1$adapted(recommend.scala:48)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2(DStream.scala:629)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2$adapted(DStream.scala:629)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$2(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:417)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$1(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.Try$.apply(Try.scala:213)
    at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.$anonfun$run$1(JobScheduler.scala:256)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    ... 3 more
21/09/29 16:05:25 ERROR JobScheduler: Error running job streaming job 1632902725000 ms.0
java.lang.IllegalStateException: SparkContext has been shutdown
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2188)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2261)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$1(RDD.scala:1012)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
    at org.apache.spark.rdd.RDD.foreach(RDD.scala:1010)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1(recommend.scala:58)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1$adapted(recommend.scala:48)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2(DStream.scala:629)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2$adapted(DStream.scala:629)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$2(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:417)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$1(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.Try$.apply(Try.scala:213)
    at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.$anonfun$run$1(JobScheduler.scala:256)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0 (TID 3) (iZbp19g1r31py4tg9gvzjhZ executor driver): java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2258)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2207)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2206)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2206)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1079)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1079)
    at scala.Option.foreach(Option.scala:407)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1079)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2445)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2387)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2376)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:868)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2196)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2261)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$1(RDD.scala:1012)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
    at org.apache.spark.rdd.RDD.foreach(RDD.scala:1010)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1(recommend.scala:58)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1$adapted(recommend.scala:48)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2(DStream.scala:629)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2$adapted(DStream.scala:629)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$2(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:417)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$1(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.Try$.apply(Try.scala:213)
    at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.$anonfun$run$1(JobScheduler.scala:256)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NullPointerException
    at org.apache.spark.sql.SQLImplicits.localSeqToDatasetHolder(SQLImplicits.scala:231)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6(recommend.scala:87)
    at main.ylcx.mallRec.recommend$.$anonfun$main$6$adapted(recommend.scala:58)
    at scala.collection.Iterator.foreach(Iterator.scala:941)
    at scala.collection.Iterator.foreach$(Iterator.scala:941)
    at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2(RDD.scala:1012)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$2$adapted(RDD.scala:1012)
    at org.apache.spark.SparkContext.$anonfun$runJob$5(SparkContext.scala:2236)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    ... 3 more

奇怪的是我的输入数据没有null的
有人说是rdd嵌套使用的原因 我也改了不用rdd了

还是报这个错

谢谢大牛

如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论， 你可以免费 注册 一个本站的账号。

评论（1）

放我走吧 2022-10-07 23:10:28

兄弟有找到问题以及解决的办法吗，我也遇到这个错了

回复
~没有更多了~

关于作者

伤感在游骋

暂无简介

0 文章
0 评论
21 人气
发私信

相关话题

更多

热门标签

操作系统 程序设计 IT运维 Linux系统管理 JavaScript 服务器应用 solaris C/C++ PHP Shell BSD Vue.js aix Oracle Python HTML 系统管理 HTML5 CSS 前端
更多

推荐作者

花开柳相依

文章 0 评论 0

zyhello

文章 0 评论 0

故友

文章 0 评论 0

对风讲故事

文章 0 评论 0

Oo萌小芽oO

文章 0 评论 0

梦明

文章 0 评论 0

更多

友情链接

文江博客
    我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站，即表示您同意使用 Cookies 和您的相关数据。
    原文