Hi,
Why am I getting this error which prevents my KMeans clustering algorithm to
work inside of Spark? I'm trying to run a sample Scala model found in
Databricks website on my Cloudera-Spark 1-node local VM. For completeness, the
Scala program is as follows: Thx
import org.apache.spark.mllib.clustering.KMeans
import org.apache.spark.mllib.linalg.Vectors
// Load and parse the data
val data = sc.textFile("/path/to/file")
.map(s => Vectors.dense(s.split(',').map(_.toDouble)))
// Cluster the data into three classes using KMeans
val numIterations = 20
val numClusters = 3
val kmeansModel = KMeans.train(data, numClusters, numIterations)
5/09/23 19:38:11 WARN clustering.KMeans: The input data is not directly cached,
which may hurt performance if its parent RDDs are also uncached.
java.io.IOException: No FileSystem for scheme: c
at
org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2584)
at
org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2591)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:91)
at
org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2630)
at
org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2612)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:370)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:296)
at
org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:256)
at
org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:228)
at
org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:313)
at
org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:203)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
at
org.apache.spark.rdd.ZippedPartitionsBaseRDD.getPartitions(ZippedPartitionsRDD.scala:55)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
at
org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1517)
at org.apache.spark.rdd.RDD.count(RDD.scala:1006)
at org.apache.spark.rdd.RDD.takeSample(RDD.scala:428)
at
org.apache.spark.mllib.clustering.KMeans.initKMeansParallel(KMeans.scala:288)
at
org.apache.spark.mllib.clustering.KMeans.runAlgorithm(KMeans.scala:162)
at org.apache.spark.mllib.clustering.KMeans.run(KMeans.scala:139)
at
org.apache.spark.mllib.clustering.KMeans$.train(KMeans.scala:420)
at
org.apache.spark.mllib.clustering.KMeans$.train(KMeans.scala:430)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:29)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:38)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:40)
at $iwC$$iwC$$iwC.<init>(<console>:42)
at $iwC$$iwC.<init>(<console>:44)
at $iwC.<init>(<console>:46)
at <init>(<console>:48)
at .<init>(<console>:52)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
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:856)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:901)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:813)
at
org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:656)
at
org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:664)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:669)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:996)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:944)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:944)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:944)
at
org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1058)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:569)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:166)
at
org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:189)
at
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:110)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
