Hadoop实现关联规则算法--二项集挖掘

近期看mahout的关联规则源码，颇为头痛，本来打算写一个系列分析关联规则的源码的，但是后面看到有点乱了，可能是稍微有点复杂吧，所以就打算先实现最简单的二项集关联规则。

算法的思想还是参考上次的图片：

这里实现分为五个步骤：

1. 针对原始输入计算每个项目出现的次数；
2. 按出现次数从大到小（排除出现次数小于阈值的项目）生成frequence list file;
3. 针对原始输入的事务进行按frequence list file进行排序并剪枝；
4. 生成二项集规则；
5. 计算二项集规则出现的次数，并删除小于阈值的二项集规则；

第一步的实现：包括步骤1和步骤2，代码如下：

GetFlist.java:

package org.fansy.date1108.fpgrowth.twodimension;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.Comparator;
import java.util.Iterator;
import java.util.List;
import java.util.PriorityQueue;
import java.util.regex.Pattern;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
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;

//  the specific comparator
class MyComparator implements Comparator<String>{
	private String splitter=",";
	public MyComparator(String splitter){
		this.splitter=splitter;
	}
	@Override
	public int compare(String o1, String o2) {
		// TODO Auto-generated method stub
		String[] str1=o1.toString().split(splitter);
		String[] str2=o2.toString().split(splitter);
		int num1=Integer.parseInt(str1[1]);
		int num2=Integer.parseInt(str2[1]);
		if(num1>num2){
			return -1;
		}else if(num1<num2){
			return 1;
		}else{
			return str1[0].compareTo(str2[0]);
		}
	}
}

public class GetFList {
	/**
	 *  the program is based on the picture 
	 */
	// Mapper
	public static class  MapperGF extends Mapper<LongWritable ,Text ,Text,IntWritable>{
		private Pattern splitter=Pattern.compile("[ ]*[ ,|\t]");
		private final IntWritable newvalue=new IntWritable(1);
		public void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
			String [] items=splitter.split(value.toString());
			for(String item:items){
				context.write(new Text(item), newvalue);
			}
		}
	}
	// Reducer
	public static class ReducerGF extends Reducer<Text,IntWritable,Text ,IntWritable>{
		public void reduce(Text key,Iterable<IntWritable> value,Context context) throws IOException, InterruptedException{
			int temp=0;
			for(IntWritable v:value){
				temp+=v.get();
			}
			context.wri