MapReduce用户行为数据之购买率最高的商品

需求分析：
商品的购买率可以反映用户群体对商品的忠诚度和对商品描述的接受程度，利用Map统计出所有的商品，在Reduce中统计出每种商品的点击数和购买数，通过公式购买率=购买数/(点击数+购买数)来进行记录，在cleanup阶段统计出Top3。
测试数据：


结果：

可视化如下图3：

部分代码分析：
clean up阶段按升序输出Top5，则return的数据应为int型且大于0。为实现return的数据为int型，将购买率（float型）*1000相减后并转换为int型。即只比较到小数点后4位。

完整代码：
map阶段

package rateofpurchase;
import java.io.IOException;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable>{
    Text k = new Text();
    IntWritable v = new IntWritable();
    @Override
    protected void map(LongWritable key, Text value, Context context) 
            throws IOException, InterruptedException {
        //1 获取一行
        String line = value.toString();
        
        //2 切割单词
        String[] fields = line.split("\t");
        
        //3 ite_ID为key,act_ID为value
        k.set(fields[2]);
        v.set(Integer.valueOf(fields[4]));
        
        //4 写出
        context.write(k, v);
    }
}

reduce阶段：

package rateofpurchase;
import java.io.IOException;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.TreeMap;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text,IntWritable,Text,FloatWritable>{
    FloatWritable v = new FloatWritable();
  
    Map<String,Float> map=new HashMap<String,Float>();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int buy=0;
        int click=0;
        float rate=0;
        // 1 累加求和
        for (IntWritable value : values) {            
            if(value.get()==1){
                buy+=1;
            }else{
                click+=1;
            }
        }
        
        rate=(float)buy/(float)(buy+click);    
   
        // 2 写出
//        context.write(key, new DoubleWritable(rate));
        String k=key.toString();
//        map.put(k, v);
        map.put(k,rate);
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        //这里将map.entrySet()转换成list
        List<Map.Entry<String,Float>> list=new LinkedList<Map.Entry<String,Float>>(map.entrySet());
        //通过比较器来实现排序
        Collections.sort(list, new Comparator<Map.Entry<String, Float>>(){
            //升序排序
            //例0.1278与0.2878比较 1278-2878<0 
            //例0.25783与0.25782比较 int(2578.3-2578.2)= 0 return 0;相等，即只比较到小数点后4位。 
            @Override
            public int compare(Map.Entry<String, Float> o1, Map.Entry<String, Float> o2) {
                return (int)((10000*o2.getValue())-(10000*o1.getValue()));
            }
        });
        
        for(int i=0;i<3;i++){
            context.write(new Text(list.get(i).getKey()),new FloatWritable(list.get(i).getValue()));
        }

    }
}

driver:

package rateofpurchase;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class RateOfPurchase {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException{
        Configuration conf = new Configuration();
        
        //1 获取job对象
        Job job = Job.getInstance(conf);
        
        //2 设置jar存储位置
        job.setJarByClass(RateOfPurchase.class);
        
        //3 关联map和reduce类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        
        //4 设置Mapper阶段输出数据的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        
        //5 设置最终数据输出的key和value类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FloatWritable.class);
        
        //6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        //7 提交job
        //job.submit();
        boolean result = job.waitForCompletion(true);
        System.exit(result? 0 : 1);
    }
    
}