向MapReduce转换：计算共现关系

标签：

分两部分：

<strong><span style="font-size:18px;">/***
 * @author YangXin
 * @info 计算共现关系的Mapper
 */
package unitSix;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.mahout.math.VarLongWritable;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

public class UserVectorToCooccurrenceMapper extends Mapper<VarLongWritable, VectorWritable, IntWritable, IntWritable>{
	public void map(VarLongWritable userID, VectorWritable userVector, Context context) throws IOException, InterruptedException{
		Iterator<Vector.Element> it = userVector.get().nonZeroes().iterator();
		//双重循环遍历非零元素
		while(it.hasNext()){
			int index1 = it.next().index();
			Iterator<Vector.Element> it2 = userVector.get().nonZeroes().iterator();
			while(it2.hasNext()){
				int index2 = it2.next().index();
				//写入项目ID
				context.write(new IntWritable(index1), new IntWritable(index2));
			}
		}
	}
}</span></strong>

<strong><span style="font-size:18px;">/***
 * @author YangXin
 * @info Mahout实现计算共生关系的Reducer
 */
package unitSix;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

public class UserVectorToCooccurrenceReducer extends Reducer<IntWritable, IntWritable, IntWritable, VectorWritable>{
	public void reduce(IntWritable itemIndex1, Iterable<IntWritable> itemIndex2s, Context context) throws IOException, InterruptedException{
		Vector cooccurrenceRow = new RandomAccessSparseVector(Integer.MAX_VALUE, 100);
		for(IntWritable intWritable : itemIndex2s){
			int itemIndex2 = intWritable.get();
			cooccurrenceRow.set(itemIndex2, cooccurrenceRow.get(itemIndex2) + 1.0);
		}
		context.write(itemIndex1, new VectorWritable(cooccurrenceRow));
	}
}
</span></strong>

向MapReduce转换：计算共现关系

标签：

原文地址：http://blog.csdn.net/u012965373/article/details/50715192