MapReduce之推荐算法实现

使用MapReduce实现推荐算法，进行迭代计算

Step 1：（去重）
第一次—Mapper

     static class Step1_Mapper extends Mapper<LongWritable, Text, Text, NullWritable>{
   

        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            if(key.get()!=0){
                context.write(value, NullWritable.get());
            }
        }
    }

第一次——Reducer

 static class Step1_Reducer extends Reducer<Text, IntWritable, Text, NullWritable>{
   

            protected void reduce(Text key, Iterable<IntWritable> i, Context context)
                    throws IOException, InterruptedException {
                context.write(key,NullWritable.get());
            }
        }

第一次——Main

    public static boolean run(Configuration config,Map<String, String> paths){
        try {
            FileSystem fs =FileSystem.get(config);
            Job job =Job.getInstance(config);
            job.setJobName("step1");
            job.setJarByClass(Step1.class);
            job.setMapperClass(Step1_Mapper.class);
            job.setReducerClass(Step1_Reducer.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(NullWritable.class);

            FileInputFormat.addInputPath(job, new Path(paths.get("Step1Input")));
            Path outpath=new Path(paths.get("Step1Output"));
            if(fs.exists(outpath)){
                fs.delete(outpath,true);
            }
            FileOutputFormat.setOutputPath(job, outpath);

            boolean f= job.waitForCompletion(true);
            return f;
        } catch (Exception e) {
            e.printStackTrace();
        }
        return false;
    }

Step 2：
/**
* 按用户分组，计算所有物品出现的组合列表，得到用户对物品的喜爱度得分矩阵
u13 i160:1,
u14 i25:1,i223:1,
u16 i252:1,i276:1,i201:3,
u21 i266:1,
u24 i64:1,i218:1,i185:1,
u26 i276:1,i201:1,i348:1,i321:1,i136:1,
* @author root
*
*/
第二次——Mapper

 static class Step2_Mapper extends Mapper<LongWritable, Text, Text, Text>{
   

         //如果使用：用户+物品，同时作为输出key，更优
        protected void map(LongWritable key, Text value,
                Context context)
                throws IOException, InterruptedException {
            String[]  tokens=value.toString().split(","); //定义一个token数组，并且使用，进行切割
            String item=tokens[0]; //找出item的位置在token[0]
            String user=tokens[1];//找出user的位置在token[1]
            String action =tokens[2];//找出action的位置在token[2]
            Integer rv =StartRun.R.get(action);         
            Text k= new Text(user);
//          if(rv!=null){
   
            Text v =new Text(item+":"+ rv.intValue());//讲rv的值定义为整型化
            context.write(k, v);
        }
    }

第二次Reducer：

static class Step2_Reducer extends Reducer<Text, Text, Text, Text>{
   

            protected void reduce(Text key, Iterable<Text> i,
                    Context context)
                    throws IOException, InterruptedException {

                Map<String, Integer> r =new HashMap<String, Integer>();

                for(Text value :i){
                    String[] vs =value.toString().split(":"); //定义一个中间数组，取名为vs
                    String item=vs[0];//找出item的位置是在vs[0]
                    Integer action=Integer.parseInt(vs[1]);//找出action的位置是在vs[1],并且对其进行整型化
                    action = ((Integer) (r.get(item)==null?  0:r.get(item))).intValue() + action;
                    r.put(item,action);//使用r把item和action合并，放到一起
                }
                StringBuffer sb =new StringBuffer();  //定义一个字符串缓冲区
                for(Entry<String, Integer> entry :r.entrySet() ){ //设置entry入口，并且进行遍历
                    sb.append(entry.getKey()+":"+entry.getValue().intValue()+",");//追加key、value的值
                }

                context.write(key,new Text(sb.toString()));
            }
        }

第二次——Main

    public static boolean run(Configuration config,Map<String, String> paths){
        try {
//          config.set("mapred.jar", "C:\\Users\\Administrator\\Desktop\\wc.jar");
            FileSystem fs =FileSystem.get(config);
            Job job =Job.getInstance(config);
            job.setJobName("step2");
            job.setJarByClass(StartRun.class);
            job.setMapperClass(Step2_Mapper.class);
            job.setReducerClass(Step2_Reducer.class);
//          
            job