Scribd
Upload
0 views4 pages

bigdata program

bigdata program

Uploaded by

Gayathri Meena G
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0 views4 pages

bigdata program

bigdata program

Uploaded by

Gayathri Meena G
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

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.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

class MatrixMultiplication {
public static class MatrixMultiplicationMapper extends Mapper<Object, Text, Text, IntWritable> {
private static final int A = 0;
private static final int B = 1;

@Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString().trim();
String[] elements = line.split("\\s+");
if (key.toString().contains("A")) {
for (int k = 0; k < elements.length; k++) {
context.write(new Text("A#" + key.toString().split("_")[0] + "," + k), new
IntWritable(Integer.parseInt(elements[k])));
}
} else if (key.toString().contains("B")) {
for (int j = 0; j < elements.length; j++) {
context.write(new Text("B#" + j + "," + key.toString().split("_")[1]), new
IntWritable(Integer.parseInt(elements[j])));
}
}
}
}

public static class MatrixMultiplicationReducer extends Reducer<Text, IntWritable, Text, IntWritable> {


@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException,
InterruptedException {
List<Integer> A_values = new ArrayList<>();
List<Integer> B_values = new ArrayList<>();

for (IntWritable value : values) {


String[] parts = key.toString().split("#");
String matrix = parts[0];
if (matrix.equals("A")) {
A_values.add(value.get());
} else if (matrix.equals("B")) {
B_values.add(value.get());
}
}

int sum = 0;
for (int i = 0; i < A_values.size(); i++) {
sum += A_values.get(i) * B_values.get(i);
}

context.write(key, new IntWritable(sum));


}
}

public static class MatrixMultiplicationDriver {


public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: MatrixMultiplication <input_path><output_path>");
System.exit(-1);
}

Configuration conf = new Configuration();


Job job = Job.getInstance(conf, "Matrix Multiplication");

job.setJarByClass(MatrixMultiplicationDriver.class);
job.setMapperClass(MatrixMultiplicationMapper.class);
job.setReducerClass(MatrixMultiplicationReducer.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);

FileInputFormat.addInputPath(job, new Path(args[0]));


FileOutputFormat.setOutputPath(job, new Path(args[1]));
}
}
}

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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.io.LongWritable;

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

class WordCountMapper implements Mapper<LongWritable, Text, Text, IntWritable> {


private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
@Override
public void configure(JobConf job) {}

@Override
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter
reporter) throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}

@Override
public void close() throws IOException {}
}

class WordCountReducer implements Reducer<Text, IntWritable, Text, IntWritable> {


private IntWritable result = new IntWritable();

@Override
public void configure(JobConf job) {}

@Override
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
result.set(sum);
output.collect(key, result);
}

@Override
public void close() throws IOException {}
}

public class WordCountDriver {


public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: WordCountDriver <input path> <output path>");
System.exit(-1);
}

Configuration conf = new Configuration();


JobConf job = new JobConf(conf, WordCountDriver.class);
job.setJobName("Word Count");

job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormat(TextInputFormat.class);
job.setOutputFormat(TextOutputFormat.class);

FileInputFormat.addInputPath(job, new Path(args[0]));


FileOutputFormat.setOutputPath(job, new Path(args[1]));

JobClient.runJob(job);
}
}

You might also like