MapReduce部分练习使用其API编程（用户推荐，协同过滤，同现矩阵等）

在MapReduce中reduce的格式个分区的格式一样，也就是和partition的个数是一样的。

1、

package com.sxt.hadoop.itemcf;

import java.util.HashMap;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;

public class StartRun {

	public static void main(String[] args) {
		Configuration conf = new Configuration();
		
		conf.set("mapreduce.app-submission.corss-paltform", "true");
		conf.set("mapreduce.framework.name", "local");
		
		//所有mr的输入和输出目录定义在map集合中
		Map<String, String> paths = new HashMap<String, String>();
		paths.put("Step1Input", "/data/itemcf/input/");
		paths.put("Step1Output", "/data/itemcf/output/step1");
		paths.put("Step2Input", paths.get("Step1Output"));
		paths.put("Step2Output", "/data/itemcf/output/step2");
		paths.put("Step3Input", paths.get("Step2Output"));
		paths.put("Step3Output", "/data/itemcf/output/step3");
		paths.put("Step4Input1", paths.get("Step2Output"));
		paths.put("Step4Input2", paths.get("Step3Output"));
		paths.put("Step4Output", "/data/itemcf/output/step4");
		paths.put("Step5Input", paths.get("Step4Output"));
		paths.put("Step5Output", "/data/itemcf/output/step5");
		paths.put("Step6Input", paths.get("Step5Output"));
		paths.put("Step6Output", "/data/itemcf/output/step6");

//		Step1.run(conf, paths);
//		Step2.run(conf, paths);
//		Step3.run(conf, paths);
//		Step4.run(conf, paths);
//		Step5.run(conf, paths);
		Step6.run(conf, paths);
	}

	public static Map<String, Integer> R = new HashMap<String, Integer>();
	static {
		R.put("click", 1);
		R.put("collect", 2);
		R.put("cart", 3);
		R.put("alipay", 4);
	}
}

2、

package com.sxt.hadoop.itemcf;

import java.io.IOException;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;
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.NullWritable;
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;

/**
 * 去重复
 * @author root
 *
 */
public class Step1 {

	
	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;
	}
	
	 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());
			}
		}
	}
	
	 
	 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());
			}
		}
}

3、

package com.sxt.hadoop.itemcf;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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;

/**
 * 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,
	u21	i266:1,
	u24	i64:1,i218:1,i185:1,
	u26