Hadoop multiple inputs

Question

I am using hadoop map reduce and I want to compute two files. My first Map/Reduce iteration is giving me an a file with a pair ID number like this:

A 30
D 20

My goal is to use that ID from the file to associate with another file and have another output with a trio: ID, Number, Name, like this:

A ABC 30
D EFGH 20

But I am not sure whether using Map Reduce is the best way to do this. Would it be better for example to use a File Reader to Read the second input file and get the Name by ID? Or can I do it with Map Reduce?

If so, I'm trying to find out how. I tried a MultipleInput solution:

MultipleInputs.addInputPath(job2, new Path(args[1]+"-tmp"),
    TextInputFormat.class, FlightsByCarrierMapper2.class);
MultipleInputs.addInputPath(job2, new Path("inputplanes"),
    TextInputFormat.class, FlightsModeMapper.class); 

But I can't think of any solution to combine the two and get the output I want. The way I have right now is just giving me the list like this example:

A ABC
A 30
B ABCD
C ABCDEF
D EFGH
D 20

After my Last Reduce I am getting this:

N125DL  767-332
N125DL  7   , 
N126AT  737-76N
N126AT  19  , 
N126DL  767-332
N126DL  1   , 
N127DL  767-332
N127DL  7   , 
N128DL  767-332
N128DL  3

I want this: N127DL 7 767-332. And also, I don't want the ones which do not combine.

And this is my reduce class:

public class FlightsByCarrierReducer2 extends Reducer {

String merge = "";
protected void reduce(Text token, Iterable<Text> values, Context context) 
                            throws IOException, InterruptedException {

    int i = 0;  
    for(Text value:values)
    {
        if(i == 0){
            merge = value.toString()+",";
        }
        else{
            merge += value.toString();
        }
        i++;
    }

        context.write(token, new Text(merge));

}

}

Update:

http://stat-computing.org/dataexpo/2009/the-data.html this is the example I'm using.

I'm trying with: TailNum and Cancelled which is (1 or 0) get the model name that corresponds to the TailNum. My file with model has a TailNumb, Model and other stuff. My current output is:

N193JB ERJ 190-100 IGW

N194DN 767-332

N19503 EMB-135ER

N19554 EMB-145LR

N195DN 767-332

N195DN 2

First comes the key, second the model, the keys that has flights cancelled, apperas below the model

And I would like a trio Key,Model Number of Cancelled, Because I want number of Cancellations per model

Answer 1

You can join them using ID as key for both mapper. You can write your map task as something like this

public void map(LongWritable k, Text value, Context context) throws IOException, InterruptedException
{
    //Get the line
    //split the line to get ID seperate
    //word1 = A 
    //word2 = 30
                //Likewise for A ABC
                   //word1 = A 
                  //word2 = ABC
    context.write(word1, word2);
}

I think you can resuse the same Map task. And then write a commomn Reducer job where Hadoop Framework groups data on key basis. So you will be able to get ID as key. And You can cache one of the value and then concat.

String merge = "";
public void reduce(Text key, Iterable<Text> values, Context context)
{
    int i =0;
    for(Text value:values)
    {
        if(i == 0){
            merge = value.toString()+",";
        }
        else{
            merge += value.toString();
        }
        i++;
    }
    valEmit.set(merge);
    context.write(key, valEmit);
}

Finally you can write your Driver class

public int run(String[] args) throws Exception {
 Configuration c=new Configuration();
 String[] files=new GenericOptionsParser(c,args).getRemainingArgs();
 Path p1=new Path(files[0]);
 Path p2=new Path(files[1]);
 Path p3=new Path(files[2]);
 FileSystem fs = FileSystem.get(c);
 if(fs.exists(p3)){
  fs.delete(p3, true);
  }
 Job job = new Job(c,"Multiple Job");
 job.setJarByClass(MultipleFiles.class);
 MultipleInputs.addInputPath(job, p1, TextInputFormat.class, MultipleMap1.class);
 MultipleInputs.addInputPath(job,p2, TextInputFormat.class, MultipleMap2.class);
 job.setReducerClass(MultipleReducer.class);
 .
 .
}

You can find the example HERE

Hope this helps.

---

UPDATE

Input1

A 30
D 20

Input2

A ABC
D EFGH

Output

A ABC 30
D EFGH 20

Mapper.java

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * @author sreeveni
 *
 */
public class Mapper1 extends Mapper<LongWritable, Text, Text, Text> {
    Text keyEmit = new Text();
    Text valEmit = new Text();

    public void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String parts[] = line.split(" ");
        keyEmit.set(parts[0]);
        valEmit.set(parts[1]);
        context.write(keyEmit, valEmit);
    }
}

Reducer.java

import java.io.IOException;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * @author sreeveni
 *
 */
public class ReducerJoin extends Reducer<Text, Text, Text, Text> {

    Text valEmit = new Text();
    String merge = "";

    public void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        String character = "";
        String number = "";
        for (Text value : values) {
            // ordering output
            String val = value.toString();
            char myChar = val.charAt(0);

            if (Character.isDigit(myChar)) {
                number = val;
            } else {
                character = val;
            }
        }
        merge = character + " " + number;
        valEmit.set(merge);
        context.write(key, valEmit);
    }

}

Driver 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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * @author sreeveni
 *
 */
public class Driver extends Configured implements Tool {
    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        // checking the arguments count

        if (args.length != 3) {
            System.err
                    .println("Usage : <inputlocation>  <inputlocation>  <outputlocation> ");
            System.exit(0);
        }
        int res = ToolRunner.run(new Configuration(), new Driver(), args);
        System.exit(res);

    }

    @Override
    public int run(String[] args) throws Exception {
        // TODO Auto-generated method stub
        String source1 = args[0];
        String source2 = args[1];
        String dest = args[2];
        Configuration conf = new Configuration();
        conf.set("mapred.textoutputformat.separator", " "); // changing default
                                                            // delimiter to user
                                                            // input delimiter
        FileSystem fs = FileSystem.get(conf);
        Job job = new Job(conf, "Multiple Jobs");

        job.setJarByClass(Driver.class);
        Path p1 = new Path(source1);
        Path p2 = new Path(source2);
        Path out = new Path(dest);
        MultipleInputs.addInputPath(job, p1, TextInputFormat.class,
                Mapper1.class);
        MultipleInputs.addInputPath(job, p2, TextInputFormat.class,
                Mapper1.class);
        job.setReducerClass(ReducerJoin.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        job.setOutputFormatClass(TextOutputFormat.class);

        /*
         * delete if exist
         */
        if (fs.exists(out))
            fs.delete(out, true);

        TextOutputFormat.setOutputPath(job, out);
        boolean success = job.waitForCompletion(true);

        return success ? 0 : 1;
    }

}