java使用hadoop实现关联商品统计

package com; 
 
import java.io.IOException; 
import java.util.HashMap; 
import java.util.Map.Entry; 
 
import org.apache.hadoop.conf.Configuration; 
import org.apache.hadoop.conf.Configured; 
import org.apache.hadoop.fs.Path; 
import org.apache.hadoop.io.IntWritable; 
import org.apache.hadoop.io.LongWritable; 
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; 
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; 
import org.apache.hadoop.util.Tool; 
import org.apache.hadoop.util.ToolRunner; 
 
public class Test extends Configured implements Tool{ 
 
  /** 
   * map类，实现数据的预处理 
   * 输出结果key为商品A value为关联商品B 
   * @author lulei 
   */ 
  public static class MapT extends Mapper { 
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException{ 
      String line = value.toString(); 
      if (!(line == null || "".equals(line))) { 
        //分割商品 
        String []vs = line.split(","); 
        //两两组合，构成一条记录 
        for (int i = 0; i < (vs.length - 1); i++) { 
          if ("".equals(vs[i])) {//排除空记录 
            continue; 
          } 
          for (int j = i+1; j < vs.length; j++) { 
            if ("".equals(vs[j])) { 
              continue; 
            } 
            //输出结果 
            context.write(new Text(vs[i]), new Text(vs[j])); 
            context.write(new Text(vs[j]), new Text(vs[i])); 
          } 
        } 
      }  
    } 
  } 
   
  /** 
   * reduce类，实现数据的计数 
   * 输出结果key 为商品A|B value为该关联次数 
   * @author lulei 
   */ 
  public static class ReduceT extends Reducer { 
    private int count; 
     
    /** 
     * 初始化 
     */ 
    public void setup(Context context) { 
      //从参数中获取最小记录个数 
      String countStr = context.getConfiguration().get("count"); 
      try { 
        this.count = Integer.parseInt(countStr); 
      } catch (Exception e) { 
        this.count = 0; 
      } 
    } 
    public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException{ 
      String keyStr = key.toString(); 
      HashMap hashMap = new HashMap(); 
      //利用hash统计B商品的次数 
      for (Text value : values) { 
        String valueStr = value.toString(); 
        if (hashMap.containsKey(valueStr)) { 
          hashMap.put(valueStr, hashMap.get(valueStr) + 1); 
        } else { 
          hashMap.put(valueStr, 1); 
        } 
      } 
      //将结果输出 
      for (Entry entry : hashMap.entrySet()) { 
        if (entry.getValue() >= this.count) {//只输出次数不小于最小值的 
          context.write(new Text(keyStr + "|" + entry.getKey()), new IntWritable(entry.getValue())); 
        } 
      } 
    } 
  } 
   
  @Override 
  public int run(String[] arg0) throws Exception { 
    // TODO Auto-generated method stub 
    Configuration conf = getConf(); 
    conf.set("count", arg0[2]); 
     
    Job job = new Job(conf); 
    job.setJobName("jobtest"); 
     
    job.setOutputFormatClass(TextOutputFormat.class); 
    job.setOutputKeyClass(Text.class); 
    job.setOutputValueClass(Text.class); 
     
    job.setMapperClass(MapT.class); 
    job.setReducerClass(ReduceT.class); 
     
    FileInputFormat.addInputPath(job, new Path(arg0[0])); 
    FileOutputFormat.setOutputPath(job, new Path(arg0[1])); 
     
    job.waitForCompletion(true); 
     
    return job.isSuccessful() ? 0 : 1; 
     
  } 
   
  /** 
   * @param args 
   */ 
  public static void main(String[] args) { 
    // TODO Auto-generated method stub 
    if (args.length != 3) { 
      System.exit(-1); 
    } 
    try { 
      int res = ToolRunner.run(new Configuration(), new Test(), args); 
      System.exit(res); 
    } catch (Exception e) { 
      // TODO Auto-generated catch block 
      e.printStackTrace(); 
    } 
  } 
 
}