I can execute java program by build it with maven on hadoop-cluster.
source-code of my program
package com.ait.summer.clusterermapreduce;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.mahout.clustering.canopy.CanopyDriver;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.distance.EuclideanDistanceMeasure;
public class ClustererMapReduce {
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
FileSystem hdfs = FileSystem.get(conf);
Path ProjectFolder = new Path (args[0]);
Path InputDir = new Path(args[0], "in");
Path OutputDir = new Path(args[0], "out");
Path canopyCentroids = new Path(args[0], "canopyCentroids");
HadoopUtil.delete(conf, OutputDir);
double clusterClassificationThreshold = 0.5;
double t1 = 20;
double t2 = 30;
// how to set up correctly param?
CanopyDriver.run(conf, InputDir, canopyCentroids, new EuclideanDistanceMeasure(),
t1, t2, false, clusterClassificationThreshold, false);
KMeansDriver.run(conf, InputDir, new Path(canopyCentroids, "clusters-0"), OutputDir, new EuclideanDistanceMeasure(), 0.5 , 5, true, 0.5 , false);
}
}
my pom.xml file
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.ait.summer</groupId>
<artifactId>ClustererMapReduce</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>jar</packaging>
<repositories>
<repository>
<id>apache.snapshots</id>
<name>Apache Snapshot Repository</name>
<url>http://repository.apache.org/snapshots</url>
<releases>
<enabled>false</enabled>
</releases>
</repository>
<repository>
<id>cdh.repo</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
<name>Cloudera Repositories</name>
<snapshots>
<enabled>false</enabled>
</snapshots>
</repository>
<repository>
<id>cdh.snapshots.repo</id>
<url>https://repository.cloudera.com/artifactory/libs-snapshot-local</url>
<name>Cloudera Snapshots Repository</name>
<snapshots>
<enabled>true</enabled>
</snapshots>
<releases>
<enabled>false</enabled>
</releases>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.0.0-cdh4.7.0</version>
<type>jar</type>
</dependency>
<dependency>
<groupId>org.apache.mahout</groupId>
<artifactId>mahout-core</artifactId>
<version>0.7-cdh4.7.0</version>
<type>jar</type>
</dependency>
<dependency>
<groupId>jfree</groupId>
<artifactId>jfreechart</artifactId>
<version>1.0.8a</version>
</dependency>
</dependencies>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.7</maven.compiler.source>
<maven.compiler.target>1.7</maven.compiler.target>
</properties>
</project>
after compiling this code from command line (i situated in project dir)
$ mvn install
I run it with
$ hadoop jar
and received this error-log
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/mahout/common/distance/DistanceMeasure
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:270)
at org.apache.hadoop.util.RunJar.main(RunJar.java:201)
Caused by: java.lang.ClassNotFoundException: org.apache.mahout.common.distance.DistanceMeasure
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
... 3 more
I use CDH-4.7.0 JDK 1.7.0.65 use NetBeans IDE 8.0
What might be cause of this problem?
