apache-spark - 在PredictionIO应用中获取事件总数时出错

标签 apache-spark elasticsearch predictionio

我是使用v0.11-incubating版本(spark-2.6.1，Hbase-1.2.6，ElasticSearch-5.2.1)来PredictionIO的新手。使用./pio-start-all启动Prediction Server，并检查pio status正常运行。然后，我创建了一个应用程序'testApp'，并将一些事件导入了该PredictionIO应用程序。现在，为了验证导入事件的数量，我运行了以下命令:

  • pio-shell --with-spark
  • import org.apache.predictionio.data.store.PEventStore
  • val eventsRDD = PEventStore.find(appName="testApp")(sc)

    • 我得到了错误:
    ERROR Storage$: Error initializing storage client for source ELASTICSEARCH
java.lang.ClassNotFoundException: elasticsearch.StorageClient
    at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    at java.lang.Class.forName0(Native Method)
    at java.lang.Class.forName(Class.java:264)
    at org.apache.predictionio.data.storage.Storage$.getClient(Storage.scala:228)
    at org.apache.predictionio.data.storage.Storage$.org$apache$predictionio$data$storage$Storage$$updateS2CM(Storage.scala:254)
    at org.apache.predictionio.data.storage.Storage$$anonfun$sourcesToClientMeta$1.apply(Storage.scala:215)
    at org.apache.predictionio.data.storage.Storage$$anonfun$sourcesToClientMeta$1.apply(Storage.scala:215)
    at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:189)
    at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:91)
    at org.apache.predictionio.data.storage.Storage$.sourcesToClientMeta(Storage.scala:215)
    at org.apache.predictionio.data.storage.Storage$.getDataObject(Storage.scala:284)
    at org.apache.predictionio.data.storage.Storage$.getDataObjectFromRepo(Storage.scala:269)
    at org.apache.predictionio.data.storage.Storage$.getMetaDataApps(Storage.scala:387)
    at org.apache.predictionio.data.store.Common$.appsDb$lzycompute(Common.scala:27)
    at org.apache.predictionio.data.store.Common$.appsDb(Common.scala:27)
    at org.apache.predictionio.data.store.Common$.appNameToId(Common.scala:32)
    at org.apache.predictionio.data.store.PEventStore$.find(PEventStore.scala:71)
    at $line19.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28)
    at $line19.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:33)
    at $line19.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
    at $line19.$read$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
    at $line19.$read$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
    at $line19.$read$$iwC$$iwC$$iwC.<init>(<console>:41)
    at $line19.$read$$iwC$$iwC.<init>(<console>:43)
    at $line19.$read$$iwC.<init>(<console>:45)
    at $line19.$read.<init>(<console>:47)
    at $line19.$read$.<init>(<console>:51)
    at $line19.$read$.<clinit>(<console>)
    at $line19.$eval$.<init>(<console>:7)
    at $line19.$eval$.<clinit>(<console>)
    at $line19.$eval.$print(<console>)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
    at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
    at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
    at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
    at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
    at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
    at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
    at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
    at org.apache.spark.repl.Main$.main(Main.scala:31)
    at org.apache.spark.repl.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$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)
org.apache.predictionio.data.storage.StorageClientException: Data source ELASTICSEARCH was not properly initialized.
    at org.apache.predictionio.data.storage.Storage$$anonfun$10.apply(Storage.scala:285)
    at org.apache.predictionio.data.storage.Storage$$anonfun$10.apply(Storage.scala:285)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.predictionio.data.storage.Storage$.getDataObject(Storage.scala:284)
    at org.apache.predictionio.data.storage.Storage$.getDataObjectFromRepo(Storage.scala:269)
    at org.apache.predictionio.data.storage.Storage$.getMetaDataApps(Storage.scala:387)
    at org.apache.predictionio.data.store.Common$.appsDb$lzycompute(Common.scala:27)
    at org.apache.predictionio.data.store.Common$.appsDb(Common.scala:27)
    at org.apache.predictionio.data.store.Common$.appNameToId(Common.scala:32)
    at org.apache.predictionio.data.store.PEventStore$.find(PEventStore.scala:71)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:33)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
    at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
    at $iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
    at $iwC$$iwC$$iwC.<init>(<console>:41)
    at $iwC$$iwC.<init>(<console>:43)
    at $iwC.<init>(<console>:45)
    at <init>(<console>:47)
    at .<init>(<console>:51)
    at .<clinit>(<console>)
    at .<init>(<console>:7)
    at .<clinit>(<console>)
    at $print(<console>)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
    at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
    at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
    at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
    at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
    at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
    at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
    at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
    at org.apache.spark.repl.Main$.main(Main.scala:31)
    at org.apache.spark.repl.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.spark.deploy.SparkSubmit$.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)

    我已经通过pio status和ElasticSearch运行状况命令验证了 flex 搜索服务器正在运行。有人可以告诉我如何解决此问题吗？

    最佳答案

    通过将ForecastIO版本从0.11.0升级到0.12.0解决了此问题

    关于apache-spark - 在PredictionIO应用中获取事件总数时出错，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/47288425/

    上一篇：php - 在浏览器中播放动态声音片段

    下一篇：powershell - 测试 WinRM/WSMan 连接？

    相关文章：

    elasticsearch - Elasticsearch索引在集群中的位置

    elasticsearch - 如何在Kibana中的两个过滤器之间汇总数据？

    predictionio - 坚持创建新的预测应用程序

    java - Spark 2.0.0 : Read from Cassandra in Cluster mode

    elasticsearch - 如何使用Elasticsearch 7对字段进行排序

    java - EasyRec vs PredictionIO vs Apache Mahout

    hadoop - 首选推荐系统

    scala - Spark Streaming dropDuplicates

    scala - 从 Spark 数据帧生成字段数组

    java - 如何在 Java Spark 中将单行拆分为多行

    ©2024 IT工具网  联系我们