Mapreduce实例——WordCount

实验内容

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。

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：

1. 买家id   商品id    收藏日期  
2. 10181   1000481   2010-04-04 16:54:31  
3. 20001   1001597   2010-04-07 15:07:52  
4. 20001   1001560   2010-04-07 15:08:27  
5. 20042   1001368   2010-04-08 08:20:30  
6. 20067   1002061   2010-04-08 16:45:33  
7. 20056   1003289   2010-04-12 10:50:55  
8. 20056   1003290   2010-04-12 11:57:35  
9. 20056   1003292   2010-04-12 12:05:29  
10. 20054   1002420   2010-04-14 15:24:12  
11. 20055   1001679   2010-04-14 19:46:04  
12. 20054   1010675   2010-04-14 15:23:53  
13. 20054   1002429   2010-04-14 17:52:45  
14. 20076   1002427   2010-04-14 19:35:39  
15. 20054   1003326   2010-04-20 12:54:44  
16. 20056   1002420   2010-04-15 11:24:49  
17. 20064   1002422   2010-04-15 11:35:54  
18. 20056   1003066   2010-04-15 11:43:01  
19. 20056   1003055   2010-04-15 11:43:06  
20. 20056   1010183   2010-04-15 11:45:24  
21. 20056   1002422   2010-04-15 11:45:49  
22. 20056   1003100   2010-04-15 11:45:54  
23. 20056   1003094   2010-04-15 11:45:57  
24. 20056   1003064   2010-04-15 11:46:04  
25. 20056   1010178   2010-04-15 16:15:20  
26. 20076   1003101   2010-04-15 16:37:27  
27. 20076   1003103   2010-04-15 16:37:05  
28. 20076   1003100   2010-04-15 16:37:18  
29. 20076   1003066   2010-04-15 16:37:31  
30. 20054   1003103   2010-04-15 16:40:14  
31. 20054   1003100   2010-04-15 16:40:16  

要求编写MapReduce程序，统计每个买家收藏商品数量。

统计结果数据如下：

1. 买家id 商品数量  
2. 10181   1  
3. 20001   2  
4. 20042   1  
5. 20054   6  
6. 20055   1  
7. 20056   12  
8. 20064   1  
9. 20067   1  
10. 20076   5  

将linux本地/home/zhangwang/mapreduce1/buyer_favorite2，上传到HDFS上的/mapreduce/in目录下。

 代码:

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 WordCount {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance();
        job.setJobName("WordCount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(doMapper.class);
        job.setReducerClass(doReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        Path in = new Path("hdfs://localhost:9000/mapreduce/in/buyer_favourite2");
        Path out = new Path("hdfs://localhost:9000/mapreduce/out2");
        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();

        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();

        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);
        }
    }
}

运行结果: