mapReduce to get desired output - hadoop

Question

Kindly point me in a direction to get my desired output
Current outPut given:
Albania 3607 ++ Country minPopulation
Albania 418495 ++ Country maxPopulation
Desired Output
country city minPopulation
country city maxPopulation
Reducer Class:
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class Handson3Reducer extends Reducer<Text, IntWritable, Text, IntWritable> {
#Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int maxValue = Integer.MIN_VALUE;
int minValue = Integer.MAX_VALUE;
String line = key.toString();
String field[] = line.split(",");
for (IntWritable value : values) {
maxValue = Math.max(maxValue, value.get());
minValue = Math.min(minValue, value.get());
}
context.write(key, new IntWritable(minValue));
context.write(key, new IntWritable(maxValue));
}
}
Mapper class:
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class handson3Mapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private static final int MISSING = 9999;
#Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
int populationVal;
String line = value.toString();
String field[] = line.split(",");
String country = field[4].substring(1, field[4].length()-1);
String newString = country.concat(field[0].substring(1, field[0].length()-1));
String population = field[9].substring(1, field[9].length()-1);
String city = field[0].substring(1, field[0].length()-1);
if (!population.matches(".*\\d.*") || population.equals("")||
population.matches("([0-9].*)\\.([0-9].*)") ){
return;
}else{
populationVal = Integer.parseInt(population);
context.write(new Text(country),new IntWritable(populationVal));
}
}
}
Runner Class:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class handsonJobRunner {
public int run(String[] args) throws Exception {
if(args.length !=2) {
System.err.println("Usage: Handson3 <input path> <outputpath>");
System.exit(-1);
}
Job job = new Job();
job.setJarByClass(handsonJobRunner.class);
job.setJobName("Handson 3");
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.setMapperClass(handson3Mapper.class);
job.setReducerClass(Handson3Reducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true) ? 0:1);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
public static void main(String[] args) throws Exception {
handsonJobRunner driver = new handsonJobRunner();
driver.run(args);
}
}
Thank you in advance, any pointers would be much appreciated.

Answer 1

You should send both city and population as value to reducer and at reducer select the city with max and min population for each country.
Your mapper would be like this:
public class Handson3Mapper extends Mapper<LongWritable, Text, Text, Text> {
private static final int MISSING = 9999;
#Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
int populationVal;
String line = value.toString();
String field[] = line.split(",");
String country = field[4].substring(1, field[4].length() - 1);
String newString = country.concat(field[0].substring(1, field[0].length() - 1));
String population = field[9].substring(1, field[9].length() - 1);
String city = field[0].substring(1, field[0].length() - 1);
if (!population.matches(".*\\d.*") || population.equals("") ||
population.matches("([0-9].*)\\.([0-9].*)")) {
return;
} else {
populationVal = Integer.parseInt(population);
context.write(new Text(country), new Text(city + "-" + populationVal));
}
}
}
And Your reducer should change to this one:
public class Handson3Reducer extends Reducer<Text, Text, Text, IntWritable> {
#Override
public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
String maxPopulationCityName = "";
String minPopulationCityName = "";
int maxValue = Integer.MIN_VALUE;
int minValue = Integer.MAX_VALUE;
String line = key.toString();
String field[] = line.split(",");
for (IntWritable value : values) {
String[] array = value.toString().split("-");
int population = Integer.valueOf(array[1]);
if (population > maxValue) {
maxPopulationCityName = array[0];
maxValue = population;
}
if (population < minValue) {
minPopulationCityName = array[0];
minValue = population;
}
}
context.write(new Text(key + " " + minPopulationCityName), new IntWritable(minValue));
context.write(new Text(key + " " + maxPopulationCityName), new IntWritable(maxValue));
}
}