MapReduce实例

数据去重：

import java.io.IOException;

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 Dedup {
    public static class Map extends Mapper<Object, Text, Text, Text>{
        private static Text line=new Text();
        
        public void  map(Object key,Text value,Context context) throws IOException, InterruptedException {
            line=value;
            context.write(line, new Text(""));
        }
    }
    
    public static class Reduce extends Reducer<Text, Text, Text, Text>{
        public void  ruduce(Text key,Iterable<Text> values,Context context) throws IOException, InterruptedException {
            context.write(key, new Text(""));
        }
    }
    
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: DataAverage <input path> <output path>");
            System.exit(-1);
        }
        Job job = new Job();
        job.setJobName("Dedup");
        job.setJarByClass(Dedup.class);
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reducer.class);
        job.setReducerClass(Reducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

排序：

import java.io.IOException;

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 Sort {
    public static class Map extends Mapper<Object, Text, IntWritable, IntWritable>{
        private static IntWritable data= new IntWritable();
        public void map(Object key,Text value,Context context) throws IOException, InterruptedException {
            String lineString=value.toString();
            data.set(Integer.parseInt(lineString));
            context.write(data, new IntWritable(1));
        }
    }
    
    public static class Reduce extends Reducer<IntWritable ,IntWritable,IntWritable,IntWritable>{
        private static IntWritable linenum=new IntWritable(1);
        public void reduce(IntWritable key,Iterable< IntWritable> values,Context context) throws IOException, InterruptedException {
            for(IntWritable value:values){
                context.write(linenum, key);
                linenum=new IntWritable(linenum.get()+1);
            }
        }
    }
    
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: DataAverage <input path> <output path>");
            System.exit(-1);
        }
        Job job = new Job();
        job.setJobName("Sort");
        job.setJarByClass(Sort.class);
        
        job.setMapperClass(Map.class);
        job.setReducerClass(Reducer.class);
        
        job.setOutputKeyClass(IntWritable.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);
    }
}

求平均值：

import java.io.IOException;
import java.util.StringTokenizer;

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 Score {
    public static class Map extends Mapper<Object, Text, Text, IntWritable>{
        public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
            String lineString =value.toString();
            StringTokenizer stringTokenizer=new StringTokenizer(lineString,"
");
            while (stringTokenizer.hasMoreElements()) {
                StringTokenizer tokenizerLine = new StringTokenizer(stringTokenizer.nextToken());
                String strName=tokenizerLine.nextToken();
                String strScore=tokenizerLine.nextToken();
                Text name=new Text(strName);
                int score=Integer.parseInt(strScore);
                context.write(name, new IntWritable(score));
            }
        }
    }
    
    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable>{
        public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
            int sum=0;
            int count=0;
            while (values.iterator().hasNext()) {
                sum+=values.iterator().next().get();
                count++;
            }
            int averate=(int)sum/count;
            context.write(key, new IntWritable(averate));
        }
    }
    
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: DataAverage <input path> <output path>");
            System.exit(-1);
        }
        Job job = new Job();
        job.setJobName("Score");
        job.setJarByClass(Score.class);
        
        job.setMapperClass(Map.class);
        job.setReducerClass(Reducer.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);
    }
}