Hadoop实战：MapReduce应用实例

参考：hadoop实战

一．ＷordCount

1. 任务：统计文件中单词的频率
2. 代码：

package mapreduce;


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

import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.*;

public class NewWordCount extends Configured implements Tool{
   

    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
   

        private final static IntWritable one = new IntWritable(1);

        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();

            StringTokenizer tokenizer = new StringTokenizer(line);

            while(tokenizer.hasMoreTokens()){
                word.set(tokenizer.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
   
        public void reduce(Text key, Iterator<IntWritable> values, Context context) throws IOException, InterruptedException {

            int sum = 0;

            while(values.hasNext()){
                sum += values.next().get();

            }

            context.write(key, new IntWritable(sum));
        }
    }

    public int run(String[] args) throws Exception {

        Job job = new Job(getConf());

        job.setJobName("wordcount");

        job .setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        boolean success = job.waitForCompletion(true);
        return success ? 0 : 1;
    }
    public static void main(String[] args) throws Exception {
        int ret = ToolRunner.run(new NewWordCount(), args);
        System.exit(ret);
    }
}

二．数据去重

1. 任务：去掉重复出现的数据
2. 代码：

package mapreduce;


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

import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.*;


/**
 * data deplicatioin removing_mapreduce
 * @author hadoop
 *
 */
public class Dedup extends Configured implements Tool{
   


    public static