LAB 10.

LAB 11.1
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().toLowerCase().replaceAll("[^a-z]",
""));
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); // Optional optimization

job.setReducerClass(IntSumReducer.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);

FileInputFormat.addInputPath(job, new Path("input"));

FileOutputFormat.setOutputPath(job, new Path("output"));

System.exit(job.waitForCompletion(true) ? 0 : 1);

}
KeyWordSearch.java
import java.io.IOException;
import java.util.StringTokenizer;
import java.util.HashSet;
import java.util.Set;
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 KeywordSearch {
public static class KeywordMapper extends Mapper<Object, Text, Text,
IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private static final Set<String> keywords = new HashSet<>();
protected void setup(Context context) {
keywords.add("hadoop");
keywords.add("data");
keywords.add("processing");
}
public void map(Object key, Text value, Context context) throws
IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
String token =
itr.nextToken().toLowerCase().replaceAll("[^a-z]", "");
if (keywords.contains(token)) {
word.set(token);
context.write(word, one);
}
}
}
 }
public static class KeywordReducer 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, "keyword search");
job.setJarByClass(KeywordSearch.class);
job.setMapperClass(KeywordMapper.class);
job.setCombinerClass(KeywordReducer.class);
job.setReducerClass(KeywordReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path("input"));
FileOutputFormat.setOutputPath(job, new Path("output"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
 LAB 12.1

WeatherAnalysis.java
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 WeatherAnalysis {
public static class WeatherMapper extends Mapper<Object, Text, Text,
Text> {
private Text date = new Text();
private Text condition = new Text();
public void map(Object key, Text value, Context context) throws
IOException, InterruptedException {
String[] fields = value.toString().split(",");
if (fields.length == 2) {
String day = fields[0];
int temperature = Integer.parseInt(fields[1]);
date.set(day);
if (temperature > 30) {
condition.set("HOT");
} else {
condition.set("COOL");
}
context.write(date, condition);
}
}
}
public static class WeatherReducer extends Reducer<Text, Text, Text,
Text> {
public void reduce(Text key, Iterable<Text> values, Context
context)
throws IOException, InterruptedException {
for (Text val : values) {
 context.write(key, val);
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "weather analysis");
job.setJarByClass(WeatherAnalysis.class);
job.setMapperClass(WeatherMapper.class);
job.setReducerClass(WeatherReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path("input"));
FileOutputFormat.setOutputPath(job, new Path("output"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}