Recently I rewrote the code in WordCount example of hadoop, but when i run it on my virtual machine (ubuntu server 14.04 with both hadoop and java set), i got ClassNotFoundException ... I have already tired many solutions found on the Internet but they didn't work. Anything i can do to fix this?
and my code is :
package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class myhadoop
{
public static int total_number = 0;
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>
{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException
{
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens())
{
word.set(itr.nextToken());
context.write(word, one);
total_number = total_number + 1;
}
}
}
public static class IntSumCombiner extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException
{
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static class ResultCountReducer extends Reducer<Text,IntWritable,Text,FloatWritable> {
private FloatWritable result = new FloatWritable();
public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException
{
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
float frequncy = sum / total_number;
result.set(frequncy);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception
{
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2)
{
System.err.println("Usage: myhadoop <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "myhadoop");
job.setJarByClass(myhadoop.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumCombiner.class);
job.setReducerClass(ResultCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FloatWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
Solution From Comment: deleting the first line ie package import
'package org.apache.hadoop.examples;'
Change in code, replace
Job.setJarByClass(),
by
Job.setJar()
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.