Windows下Spark-mlib保存模型到本地报空指针解决方案
一、问题描述
在windows下用Spark mlib跑机器学习模型时，保存模型到本地，出现空指针异常。代码如下：
import org.apache.spark.mllib.classification.{LogisticRegressionWithLBFGS, SVMWithSGD}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.mllib.util.MLUtils;
object SVM {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local").setAppName("SVM")
val sc = new SparkContext(conf)
val data = MLUtils.loadLibSVMFile(sc,"D://spark/sample_libsvm_data.txt");
val splits = data.randomSplit(Array(0.6,0.4), seed = 11L)
val training = splits(0).cache()
val test = splits(1)
//training.foreach(println)
val numIterations = 100
val model = SVMWithSGD.train(training, numIterations)
//model.clearThreshold();
println("######## Threshold is : " + model.getThreshold)
val scoreAndLabels = test.map { point =>
val score = model.predict(point.features)
(score, point.label)
}
// Get evaluation metrics.
val metrics = new BinaryClassificationMetrics(scoreAndLabels)
val auROC = metrics.areaUnderROC()
println("Area under ROC = " + auROC)
model.save(sc, "file:///D://spark/SVMTrainingModel")
//val model = new LogisticRegressionWithLBFGS().setNumClasses(10).run(training)
}
}首先以下异常信息：
16/08/26 18:34:58 ERROR Shell: Failed to locate the winutils binary in the hadoop binary path
java.io.IOException: Could not locate executable null\bin\winutils.exe in the Hadoop binaries.
at org.apache.hadoop.util.Shell.getQualifiedBinPath(Shell.java:278)
at org.apache.hadoop.util.Shell.getWinUtilsPath(Shell.java:300)
at org.apache.hadoop.util.Shell.(Shell.java:293)
at org.apache.hadoop.util.StringUtils.(StringUtils.java:76)
at org.apache.hadoop.mapred.FileInputFormat.setInputPaths(FileInputFormat.java:362)
at org.apache.spark.SparkContext$$anonfun$hadoopFile$1$$anonfun$33.apply(SparkContext.scala:1015)
at org.apache.spark.SparkContext$$anonfun$hadoopFile$1$$anonfun$33.apply(SparkContext.scala:1015)
at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:176)
at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:176)
at scala.Option.map(Option.scala:145)
at org.apache.spark.rdd.HadoopRDD.getJobConf(HadoopRDD.scala:176)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:195)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1007)
at org.apache.spark.mllib.util.MLUtils$.loadLibSVMFile(MLUtils.scala:105)
at org.apache.spark.mllib.util.MLUtils$.loadLibSVMFile(MLUtils.scala:134)
at org.apache.spark.mllib.util.MLUtils$.loadLibSVMFile(MLUtils.scala:159)
at com.jd.risk.mlib.SVM$.main(SVM.scala:16)
at com.jd.risk.mlib.SVM.main(SVM.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$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$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1922)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1213)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.RDDOperationScope$.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.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1060)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply$mcV$sp(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.RDDOperationScope$.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.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:951)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply$mcV$sp(RDD.scala:1457)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
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.saveAsTextFile(RDD.scala:1436)
at org.apache.spark.mllib.classification.impl.GLMClassificationModel$SaveLoadV1_0$.save(GLMClassificationModel.scala:61)
at org.apache.spark.mllib.classification.SVMModel.save(SVM.scala:84)
at com.jd.risk.mlib.SVM$.main(SVM.scala:39)
at com.jd.risk.mlib.SVM.main(SVM.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 com.intellij.rt.execution.application.AppMain.main(AppMain.java:140)
Caused by: java.lang.NullPointerException
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1010)
at org.apache.hadoop.util.Shell.runCommand(Shell.java:404)
at org.apache.hadoop.util.Shell.run(Shell.java:379)
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:589)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:678)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:661)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:639)
at org.apache.hadoop.fs.FilterFileSystem.setPermission(FilterFileSystem.java:468)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:456)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:424)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:905)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:798)
at org.apache.hadoop.mapred.TextOutputFormat.getRecordWriter(TextOutputFormat.java:123)
at org.apache.spark.SparkHadoopWriter.open(SparkHadoopWriter.scala:91)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1193)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1185)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$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)二、解决办法
- 下载编译好的winutils.exe，该文章里讲述了出错的原因；
- 把该执行文件放置在某个路径下，如 c:\\winutils\\bin；
- 在代码中加入这句话：System.setProperty("hadoop.home.dir","C:\\winutils")
三、原因
在上述引用的文章中，大致讲了一个意思：在Windows操作系统中，Hadoop中初始发行版本中的bug，导致Hadoop中用于评估文件权限的功能不能正常运行。在执行作业的时候，存储到HDFS的路径依旧是可达的，（上述错误虽然存在，但依旧在相应路径下保存了spark mlib跑出来的模型，只不过是没有数据），但是map/reduce作业会执行失败。
这个异常是属于Hadoop在Windows上的bug所致，在Linux下不会报错，也不用加上那句话。