✅ PART 1: Install Java and Hadoop on Ubuntu
🧰 Step 1: Install Java (JDK)
sudo apt update
sudo apt install openjdk-11-jdk -y
java -version
📦 Step 2: Download and Configure Hadoop (Standalone Mode)
🔽 Download Hadoop
cd ~
wget https://downloads.apache.org/hadoop/common/hadoop-3.3.6/hadoop-3.3.6.tar.gz
tar -xzf hadoop-3.3.6.tar.gz
mv hadoop-3.3.6 hadoop
🔧 Set Environment Variables
Edit ~/.bashrc:
nano ~/.bashrc
Add these at the end:
export HADOOP_HOME=~/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
export JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64
export HADOOP_CLASSPATH=$JAVA_HOME/lib/tools.jar
Apply the changes:
source ~/.bashrc
✅ Test:
hadoop version
✅ PART 2: Write the WordCount Java Code
Create a folder and Java file:
mkdir ~/wordcount
cd ~/wordcount
nano WordCount.java
import java.io.IOException;
import java.util.StringTokenizer;
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;
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 itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.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();
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(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
✅ PART 3: Compile and Run the Program
🔧 Step 1: Compile
mkdir classes
javac -classpath
"$HADOOP_HOME/share/hadoop/common/*:$HADOOP_HOME/share/hadoop/mapreduce/*" -d
classes WordCount.java
📦 Step 2: Create a JAR
jar -cvf wordcount.jar -C classes/ .
✅ PART 4: Run WordCount Job (Standalone)
📁 Step 1: Create Input File
mkdir input
echo "hadoop mapreduce hadoop word count word count" > input/test.txt
▶️ Step 2: Run MapReduce Job
hadoop jar wordcount.jar WordCount input output
📄 Step 3: View Output
cat output/part-r-00000
count 2
hadoop 2
mapreduce 1
word 2
