Preprocessingon the whole pg100.txt

Assign2/Preprocessing_1/nb_output_records.txt

+114969
\ No newline at end of file

Assign2/src/Preprocessing/Preprocessing_1.java

@@ -20,6 +20,7 @@ import org.apache.hadoop.conf.Configured;
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.NullWritable;
 import org.apache.hadoop.io.Text;
 import org.apache.hadoop.mapreduce.Job;
 import org.apache.hadoop.mapreduce.Mapper;
@@ -38,10 +39,7 @@ public class Preprocessing_1 extends Configured implements Tool {
    public static void main(String[] args) throws Exception {
 	   
       System.out.println(Arrays.toString(args));
-      
-      
       int res = ToolRunner.run(new Configuration(), new Preprocessing_1(), args);
-      
       System.exit(res);
    }
    
@@ -50,7 +48,7 @@ public class Preprocessing_1 extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
       System.out.println(Arrays.toString(args));
-      Job job = new Job(getConf(), "Preprocessing_1_test (1)");
+      Job job = new Job(getConf(), "Preprocessing_1");
       job.setJarByClass(Preprocessing_1.class);
       job.setOutputKeyClass(LongWritable.class);
       job.setOutputValueClass(Text.class);
@@ -77,7 +75,6 @@ public class Preprocessing_1 extends Configured implements Tool {
 
       job.waitForCompletion(true);
 
-
       long counter = job.getCounters().findCounter(COUNTS.COUNT_LINES).getValue();
       Path countFile = new Path(new Path(args[1]),"nb_output_records.txt");
       File file = new File(countFile.toString());
@@ -88,11 +85,7 @@ public class Preprocessing_1 extends Configured implements Tool {
       
       return 0;
    }
-   
-
 
-
-   
    public static class Map extends Mapper<LongWritable, Text, LongWritable, Text> {
       
       private Text word = new Text();
@@ -116,7 +109,7 @@ public class Preprocessing_1 extends Configured implements Tool {
       }
    }
 
-   public static class Reduce extends Reducer<LongWritable, Text, LongWritable, Text> {
+   public static class Reduce extends Reducer<LongWritable, Text, NullWritable, Text> {
        
 	 private static HashMap<String,Integer> word_freq = new HashMap<String,Integer>();
 	 
@@ -180,7 +173,7 @@ public class Preprocessing_1 extends Configured implements Tool {
  
         if(!concat_words.toString().isEmpty()){
          context.getCounter(COUNTS.COUNT_LINES).increment(1);
-         context.write(key, new Text(concat_words.toString()));
+         context.write(NullWritable.get(), new Text(concat_words.toString()));
          }
          
        }