Scribd
Upload
8 views4 pages

Map Reduce

MapReduce is a programming model for processing large datasets in a distributed system. The document discusses MapReduce and provides an example Java program that implements a word count algorithm using Hadoop MapReduce to count the frequency of words in a file. The program takes an input file and output location as parameters.

Uploaded by

chetanruparel07aws
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
8 views4 pages

Map Reduce

MapReduce is a programming model for processing large datasets in a distributed system. The document discusses MapReduce and provides an example Java program that implements a word count algorithm using Hadoop MapReduce to count the frequency of words in a file. The program takes an input file and output location as parameters.

Uploaded by

chetanruparel07aws
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Output

Map Reduce Programming in Java


MapReduce is a programming model and an associated implementation for processing and
generating large data sets with a parallel, distributed algorithm on a cluster. Conceptually
similar approaches have been very well known since 1995 with the Message Passing
Interface standard having reduce and scatter operations.

Running sample Word Count program in hadoop


1) Install Eclipse in ubuntu 14.04
2) Add all the external jar files from hadoop folder to eclipse project
3) Run the application giving input.txt and output parameters
Word Count program:
import java.io.*;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class WordCount extends Configured implements Tool {

public static class Map extends MapReduceBase implements Mapper<LongWritable, Text,


Text, IntWritable> {

static enum Counters { INPUT_WORDS }

private final static IntWritable one = new IntWritable(1);


private Text word = new Text();

private boolean caseSensitive = true;


private Set<String> patternsToSkip = new HashSet<String>();

private long numRecords = 0;


private String inputFile;

public void configure(JobConf job) {


caseSensitive = job.getBoolean("wordcount.case.sensitive", true);
inputFile = job.get("map.input.file");

if (job.getBoolean("wordcount.skip.patterns", false)) {
Path[] patternsFiles = new Path[0];
try {
patternsFiles = DistributedCache.getLocalCacheFiles(job);
} catch (IOException ioe) {
System.err.println("Caught exception while getting cached files: " +
StringUtils.stringifyException(ioe));
}
for (Path patternsFile : patternsFiles) {
parseSkipFile(patternsFile);
}
}
}

private void parseSkipFile(Path patternsFile) {


try {
BufferedReader fis = new BufferedReader(new FileReader(patternsFile.toString()));
String pattern = null;
while ((pattern = fis.readLine()) != null) {
patternsToSkip.add(pattern);
}
} catch (IOException ioe) {
System.err.println("Caught exception while parsing the cached file '" + patternsFile +
"' : " + StringUtils.stringifyException(ioe));
}
}

public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable>


output, Reporter reporter) throws IOException {
String line = (caseSensitive) ? value.toString() : value.toString().toLowerCase();

for (String pattern : patternsToSkip) {


line = line.replaceAll(pattern, "");
}

StringTokenizer tokenizer = new StringTokenizer(line);


while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
reporter.incrCounter(Counters.INPUT_WORDS, 1);
}

if ((++numRecords % 100) == 0) {
reporter.setStatus("Finished processing " + numRecords + " records " + "from the input
file: " + inputFile);
}
}
}

public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable,


Text, IntWritable> {
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();
}
output.collect(key, new IntWritable(sum));
}
}

public int run(String[] args) throws Exception {


JobConf conf = new JobConf(getConf(), WordCount.class);
conf.setJobName("wordcount");

conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);

conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);

List<String> other_args = new ArrayList<String>();


for (int i=0; i < args.length; ++i) {
if ("-skip".equals(args[i])) {
DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf);
conf.setBoolean("wordcount.skip.patterns", true);
} else {
other_args.add(args[i]);
}
}

FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));


FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

JobClient.runJob(conf);
return 0;
}

public static void main(String[] args) throws Exception {


int res = ToolRunner.run(new Configuration(), new WordCount(), args);
System.exit(res);
}
}

You might also like