Writing MapReduce Program
Writing wordcount Program
Scenario: There are a lot of files in which words are stored and one word occupies one line.
Task: How to count the number of occurrences of each word
Similar application scenarios:
Statistics of the most popular K search terms in search engines
Statistical search word frequency to help optimize search word prompts
- Edit pom.xml and add the jar package
maven adds jar packages to query: https://mvnrepository.com/
<!-- Add warehouse -->
<repositories>
<repository>
<id>apache</id>
<url>http://maven.apache.org</url>
</repository>
</repositories
<!-- Add dependency -->
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.2.1</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.0</version>
</dependency>
</dependencies>
- Writing Mapper classes
package com.bigdata.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 WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
// Receive each line of string
String line = value.toString();
// Segmentation data
String[] words = line.split(" ");
// Cyclic output, 1 for each word
for(String w: words) {
context.write(new Text(w), new LongWritable(1));
}
}
}
- Writing Reducer classes
package com.bigdata.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 WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key2, Iterable<LongWritable> value2s,
Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
// receive data
Text key3 = key2;
// Define a counter
long count = 0;
// Cyclic statistics value2s
for(LongWritable i: value2s) {
count += i.get();
}
// output
context.write(key3, new LongWritable(count));
}
}
- Write main classes and submit MR jobs
package com.bigdata.wordcount;
import org.apache.hadoop.conf.Configuration;
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.output.FileOutputFormat;
public class WordCount
{
public static void main( String[] args ) throws Exception
{
// Create jobs
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
job.setJobName("wordcount");
// Configuring map jobs
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path("/words.txt"));
// Configure reduce jobs
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileOutputFormat.setOutputPath(job, new Path("/wordcount"));
// Submit homework
System.exit(job.waitForCompletion(true)? 0 : 1);
}
}
- Export jar packages and submit hadoop runs