scala - 在 spark 中读取 csv 文件时出现 ArrayIndexOutOfBoundsException

标签 scala csv apache-spark

我正在阅读使用 Spark 进行高级分析的第二章，第二版。我正在使用

val parsed = spark.read.csv("linkage")

并收到此错误:
18/01/16 12:09:32 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
java.lang.ArrayIndexOutOfBoundsException: 63
    at org.apache.spark.unsafe.types.UTF8String.numBytesForFirstByte(UTF8String.java:190)
    at org.apache.spark.unsafe.types.UTF8String.numChars(UTF8String.java:205)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
    at org.apache.spark.scheduler.Task.run(Task.scala:108)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
18/01/16 12:09:32 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.ArrayIndexOutOfBoundsException: 63
    at org.apache.spark.unsafe.types.UTF8String.numBytesForFirstByte(UTF8String.java:190)
    at org.apache.spark.unsafe.types.UTF8String.numChars(UTF8String.java:205)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
    at org.apache.spark.scheduler.Task.run(Task.scala:108)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
    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)

18/01/16 12:09:32 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.ArrayIndexOutOfBoundsException: 63
    at org.apache.spark.unsafe.types.UTF8String.numBytesForFirstByte(UTF8String.java:190)
    at org.apache.spark.unsafe.types.UTF8String.numChars(UTF8String.java:205)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
    at org.apache.spark.scheduler.Task.run(Task.scala:108)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
    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.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
  at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
  at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
  at scala.Option.foreach(Option.scala:257)
  at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
  at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062)
  at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336)
  at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
  at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2853)
  at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
  at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153)
  at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2837)
  at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
  at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2836)
  at org.apache.spark.sql.Dataset.head(Dataset.scala:2153)
  at org.apache.spark.sql.Dataset.take(Dataset.scala:2366)
  at org.apache.spark.sql.execution.datasources.csv.TextInputCSVDataSource$.infer(CSVDataSource.scala:147)
  at org.apache.spark.sql.execution.datasources.csv.CSVDataSource.inferSchema(CSVDataSource.scala:62)
  at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.inferSchema(CSVFileFormat.scala:57)
  at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$7.apply(DataSource.scala:177)
  at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$7.apply(DataSource.scala:177)
  at scala.Option.orElse(Option.scala:289)
  at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:176)
  at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:366)
  at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:178)
  at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:533)
  at org.apache.spark.sql.DataFrameReader.csv(DataFrameReader.scala:412)
  ... 48 elided
Caused by: java.lang.ArrayIndexOutOfBoundsException: 63
  at org.apache.spark.unsafe.types.UTF8String.numBytesForFirstByte(UTF8String.java:190)
  at org.apache.spark.unsafe.types.UTF8String.numChars(UTF8String.java:205)
  at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
  at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
  at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:395)
  at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
  at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
  at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
  at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
  at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
  at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
  at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
  at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
  at org.apache.spark.scheduler.Task.run(Task.scala:108)
  at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
  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)

一开始，我以为我的数据集有问题，所以我检查了所有文件的每一行的元素之间是否有相同数量的逗号。有11个逗号:
scala> import scala.io.Source
import scala.io.Source

scala> Source.fromFile("linkage/block_1.csv").getLines take 10 foreach println
"id_1","id_2","cmp_fname_c1","cmp_fname_c2","cmp_lname_c1","cmp_lname_c2","cmp_sex","cmp_bd","cmp_bm","cmp_by","cmp_plz","is_match"
37291,53113,0.833333333333333,?,1,?,1,1,1,1,0,TRUE
39086,47614,1,?,1,?,1,1,1,1,1,TRUE
70031,70237,1,?,1,?,1,1,1,1,1,TRUE
84795,97439,1,?,1,?,1,1,1,1,1,TRUE
36950,42116,1,?,1,1,1,1,1,1,1,TRUE
42413,48491,1,?,1,?,1,1,1,1,1,TRUE
25965,64753,1,?,1,?,1,1,1,1,1,TRUE
49451,90407,1,?,1,?,1,1,1,1,0,TRUE
39932,40902,1,?,1,?,1,1,1,1,1,TRUE

scala> val fileNames = (1 to 10) map (num => s"block_$num.csv")
fileNames: scala.collection.immutable.IndexedSeq[String] = Vector(block_1.csv, block_2.csv, block_3.csv, block_4.csv, block_5.csv, block_6.csv, block_7.csv, block_8.csv, block_9.csv, block_10.csv)

scala> fileNames foreach { fn =>
     | val lines = Source.fromFile(s"linkage/$fn").getLines.toList
     | val notMatching = lines filterNot (line => ((line count(c => c == ',')) == 11))
     | notMatching foreach println
     | println("\n")
     | }

其输出只是“\n”，因此每行的值之间总是有 11 个逗号。

我正在使用这些版本:
Spark version: 2.2.0
Scala version: 2.11.8
Hadoop version: 2.8.2

我正在像这样在本地机器上启动 spark shell:
spark-shell --master local[*] --driver-memory 2g

链接目录就在我启动 spark-shell 的地方。

有任何想法吗？也许我在做一些愚蠢的事情，因为这是我第一次使用 Spark/Scala。我也不熟悉 Java，如果那可能是问题的话。
谢谢你。

最佳答案

这是一个愚蠢的问题。我是这样读的:

val parsed = spark.read.csv("linkage")

什么时候应该是:
val parsed = spark.read.csv("linkage/block_*.csv")

这是因为还有另一个 csv 文件 (frequencies.csv) 中的逗号较少。这个文件只给出了一些列的频率，但不是全部。

关于scala - 在 spark 中读取 csv 文件时出现 ArrayIndexOutOfBoundsException，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/48289697/

上一篇：session - 在中间件中使用 .NET Core Session

下一篇：c - 链表 : Exception thrown: read access violation. B 为 0xCDCDCDCD

相关文章：

node.js - 如何在 Scala.js 中使用 Node 模块

Python CSV 写入对象

c# - 如何在 FileHelpers 中使用动态 CSV 定界符？

php - 使用 fgetcsv() 而不使用 fopen()、popen() 或 fsockopen()？

apache-spark - 如何在公司代理后面使用 Spark-Shell 解析外部包？

hadoop - RDD 拆分给出缺少的参数类型

scala - Scala Slick 3.0 中的随机行

scala - 非案例类的“复制”？

scala - 将SORM与Play Framework 2.3.8结合使用

apache-spark - 在scala中使用apache Spark更新数据集中的列

©2024 IT工具网  联系我们