Count Frequency of Character in Mapreduce Programme

Breadcrumb Abstract Shape
Breadcrumb Abstract Shape
Breadcrumb Abstract Shape
Breadcrumb Abstract Shape
Breadcrumb Abstract Shape
Breadcrumb Abstract Shape
  • User AvatarANKUSH THAVALI
  • 20 Dec, 2021
  • 0 Comments
  • 1 Min Read

Count Frequency of Character in Mapreduce Programme

Mapper Programe


package wordcount;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class AlphaMapper extends Mapper<Object, Text, Text, LongWritable> {
private final static LongWritable one = new LongWritable(1);
private Text character = new Text();

@Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String v = value.toString();
for (int i = 0; i < v.length(); i++) {
character.set(v.substring(i, i + 1));
context.write(character, one);
}
}
}

Reducer Programe

package wordcount;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 

public class AlphaReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
    private LongWritable result = new LongWritable();
 
    public void reduce(Text key, Iterable<LongWritable> values, Context context)
            throws IOException, InterruptedException {
        long sum = 0;
        for (LongWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

Driver Programe

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
 
// The driver program for mapreduce job.
public class AlphaCounter extends Configured implements Tool {
 
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new AlphaCounter(), args);
        System.exit(res);
    }
 
    @Override
    public int run(String[] args) throws Exception {
 
        Configuration conf = this.getConf();
 
        // Create job
        Job job = Job.getInstance(conf, "Alpha Counter Job");
        job.setJarByClass(AlphaCounter.class);
 
        job.setMapperClass(AlphaMapper.class);
        job.setReducerClass(AlphaReducer.class);
 
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
 
        FileInputFormat.addInputPath(job, new Path(args[0]));
        job.setInputFormatClass(TextInputFormat.class);
 
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.setOutputFormatClass(TextOutputFormat.class);
 
        return job.waitForCompletion(true) ? 0 : 1;
    }
}

Run Mapreduce Programe

hadoop jar count.jar wordcount.AlphaCounter /user/hive/input/wordcount.txt /user/hive/output/wordcount1



        14
I       1
a       10
c       2
d       4
e       9
g       6
h       2
i       5
l       3
m       7
n       4
o       8
p       4
r       9
s       3
u       3
w       2
y       2