mapreduce in ubuntu

 

1. Start the HDFS services:

bash
start-dfs.sh

2. Start the YARN services:

bash
start-yarn.sh

Step 6: Write a MapReduce Program

1. Create your MapReduce program. Here’s a basic WordCount program (in Java):

java
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.util.GenericOptionsParser;

import java.io.IOException;
import java.util.StringTokenizer;

public class WordCount {

    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 tokenizer = new StringTokenizer(value.toString());
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer 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 void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        GenericOptionsParser parser = new GenericOptionsParser(conf, args);
        String[] remainingArgs = parser.getRemainingArgs();

        if (remainingArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }

        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(remainingArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(remainingArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

Step 7: Compile and Build the Program

Compile your Java program and create a .jar file.

bash
javac -classpath $(hadoop classpath) -d /path/to/output/WordCountClasses WordCount.java
jar -cvf wordcount.jar -C /path/to/output/WordCountClasses/ .

Step 8: Run the MapReduce Program

1. Upload input files to HDFS:

bash
hdfs dfs -mkdir /input
hdfs dfs -put /local/path/to/input_file /input

2. Run the program:

bash
hadoop jar wordcount.jar WordCount /input /output

3. View the output:

bash
hdfs dfs -cat /output/part-r-00000

Step 9: Stop Hadoop

When done, stop Hadoop services:

bash
stop-yarn.sh
stop-dfs.sh