WordCount实验

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：

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

买家id 商品数量
10181 1
20001 2
20042 1
20054 6
20055 1
20056 12
20064 1
20067 1
20076 5

代码：

 1 package mapreduce;
 2 import java.io.IOException;  
 3 
 4 import java.util.StringTokenizer;  
 5 import org.apache.hadoop.fs.Path;  
 6 import org.apache.hadoop.io.IntWritable;  
 7 import org.apache.hadoop.io.Text;  
 8 import org.apache.hadoop.mapreduce.Job;  
 9 import org.apache.hadoop.mapreduce.Mapper;  
10 import org.apache.hadoop.mapreduce.Reducer;  
11 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;  
12 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
13 
14 public class WordCount {
15      public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{  
16             //第一个Object表示输入key的类型；第二个Text表示输入value的类型；第三个Text表示表示输出键的类型；第四个IntWritable表示输出值的类型  
17             public static final IntWritable one = new IntWritable(1);  
18                     public static Text word = new Text();  
19                     @Override  
20                     protected void map(Object key, Text value, Context context) throws IOException, InterruptedException  //抛出异常  
21                     {  
22                         StringTokenizer tokenizer = new StringTokenizer(value.toString(),"	");  
23                       //StringTokenizer是Java工具包中的一个类，用于将字符串进行拆分  
24                        word.set(tokenizer.nextToken());  
25                              //返回当前位置到下一个分隔符之间的字符串  
26                             context.write(word, one);  
27                              //将word存到容器中，记一个数  
28                       }
29          }             
30      public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{  
31             //参数同Map一样，依次表示是输入键类型，输入值类型，输出键类型，输出值类型  
32             private IntWritable result = new IntWritable();  
33                     @Override  
34                     protected void reduce(Text key, Iterable<IntWritable> values, Context context)  
35                 throws IOException, InterruptedException {  
36                 int sum = 0;  
37                 for (IntWritable value : values) {  
38                 sum += value.get();  
39                 }  
40                 //for循环遍历，将得到的values值累加  
41                 result.set(sum);  
42                 context.write(key, result);  
43                 }  
44                 } 
45      public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {  
46             Job job = Job.getInstance();  
47             job.setJobName("WordCount");  
48             job.setJarByClass(WordCount.class);  
49             job.setMapperClass(doMapper.class);  
50             job.setReducerClass(doReducer.class);  
51             job.setOutputKeyClass(Text.class);  
52             job.setOutputValueClass(IntWritable.class);  
53             Path in = new Path("hdfs://localhost:9000/mymapreduce1/in");  
54             Path out = new Path("hdfs://localhost:9000/mymapreduce1/out");  
55             FileInputFormat.addInputPath(job, in);  
56             FileOutputFormat.setOutputPath(job, out);  
57             System.exit(job.waitForCompletion(true) ? 0 : 1);  
58         }  
59 }

最终结果截图：