MapReduce——简单数据去重

　　MapReduce采用的是“分而治之”的思想，把对大规模数据集的操作，分发给一个主节点管理下的各个从节点共同完成，然后通过整合各个节点的中间结果，得到最终结果。简单来说，MapReduce就是”任务的分解与结果的汇总“。MapReduce可以把其处理过程高度抽象为Map与Reduce两个部分来进行阐述，其中Map部分负责把任务分解成多个子任务，Reduce部分负责把分解后多个子任务的处理结果汇总起来。下面举一个简单的例子：

　　现有某电商网站用户对商品的收藏数据，记录了用户收藏的商品id以及收藏日期，名为buyer_favorite1，包含：买家id，商品id，收藏日期这三个字段，数据以“ ”分割，样本数据及格式如下：

 要求编写MapReduce程序，统计每个买家收藏商品数量。

package org.apache.hadoop.examples;

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 WordCount2 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance();
        job.setJobName("WordCount");
        job.setJarByClass(WordCount2.class);
        job.setMapperClass(doMapper.class);
        job.setReducerClass(doReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/buyer_favorite1");
        Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

    public static class doMapper extends Mapper<Object, Text, Text, IntWritable> {
        public static final IntWritable one = new IntWritable(1);
        public static Text word = new Text();

        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer tokenizer = new StringTokenizer(value.toString(), " ");
            word.set(tokenizer.nextToken());
            context.write(word, one);
        }
    }

    public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
}