我正在尝试运行第7章中的helloworld示例。我在eclipse中创建了以下内容,然后将其打包到jar:-
package com.mycode.mahout
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.mahout.clustering.WeightedVectorWritable;
import org.apache.mahout.clustering.kmeans.Cluster;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.common.distance.EuclideanDistanceMeasure;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;
public class SimpleKMeansClustering {
public static final double[][] points = { {1, 1}, {2, 1}, {1, 2},
{2, 2}, {3, 3}, {8, 8},
{9, 8}, {8, 9}, {9, 9}};
public static void writePointsToFile(List<Vector> points,
String fileName,
FileSystem fs,
Configuration conf) throws IOException {
Path path = new Path(fileName);
SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
path, LongWritable.class, VectorWritable.class);
long recNum = 0;
VectorWritable vec = new VectorWritable();
for (Vector point : points) {
vec.set(point);
writer.append(new LongWritable(recNum++), vec);
}
writer.close();
}
public static List<Vector> getPoints(double[][] raw) {
List<Vector> points = new ArrayList<Vector>();
for (int i = 0; i < raw.length; i++) {
double[] fr = raw[i];
Vector vec = new RandomAccessSparseVector(fr.length);
vec.assign(fr);
points.add(vec);
}
return points;
}
public static void main(String args[]) throws Exception {
int k = 2;
List<Vector> vectors = getPoints(points);
File testData = new File("testdata");
if (!testData.exists()) {
testData.mkdir();
}
testData = new File("testdata/points");
if (!testData.exists()) {
testData.mkdir();
}
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
writePointsToFile(vectors, "testdata/points/file1", fs, conf);
Path path = new Path("testdata/clusters/part-00000");
SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
path, Text.class, Cluster.class);
for (int i = 0; i < k; i++) {
Vector vec = vectors.get(i);
Cluster cluster = new Cluster(vec, i, new EuclideanDistanceMeasure());
writer.append(new Text(cluster.getIdentifier()), cluster);
}
writer.close();
KMeansDriver.run(conf, new Path("testdata/points"), new Path("testdata/clusters"),
new Path("output"), new EuclideanDistanceMeasure(), 0.001, 10,
true, false);
SequenceFile.Reader reader = new SequenceFile.Reader(fs,
new Path("output/" + Cluster.CLUSTERED_POINTS_DIR
+ "/part-m-00000"), conf);
IntWritable key = new IntWritable();
WeightedVectorWritable value = new WeightedVectorWritable();
while (reader.next(key, value)) {
System.out.println(value.toString() + " belongs to cluster "
+ key.toString());
}
reader.close();
}
}
我把它打包成myjob.jar
现在我该如何在我的集群上执行这个呢?
我试过了following:-
hadoop jar myjob.jar com.mycode.mahout.SimpleKMeansClustering
java -jar myjob.jar
java -cp myjob.jar
我跟在后面error:-
[root@node1 tmp]# hadoop jar mahoutfirst.jar com.mahout.emc.SimpleKMeansClustering
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/mahout/math/Vector`
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.math.Vector
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:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 3 more
请告知使用mahout编写的代码的正确运行方式。
2条答案
按热度按时间iaqfqrcu1#
虽然已经很晚了,但我也遇到了类似的问题,下面的方法确实对我有用,因为我不想使用maven:
1) 转到mahout安装目录并查找*job.jar作为
2) 将mahout-examples-0.5-cdh3u3-job.jar复制到代码所在的目录
3) 使用mahout提供的“job”jar文件。它打包了所有依赖项。你也需要添加你的类。当您使用hadoop和mahout库编译类时,您已经准备好了.class文件。
4) 将类文件添加到目录中的job jar mahout-core-0.5-cdh3u3-job.jar:
4) 使用您的代码运行hadoop jar:
5) 在Map缩小作业的末尾,您可以看到:
col17t5w2#
查看上面的not class defind异常,您可能需要在hadoop作业中包含mahout相关的jar(我猜是mahout-core.jar)。
要在整个集群中将jar传递给Map器,可能需要使用distributedcache或
-libjar
hadoop选项。后面的想法在这里解释。