组合部分标签向量并累加成完整向量

Posted 2020-06-18 杨鑫newlfe

<strong><span style="font-size:18px;">/***
 * @author YangXin
 * @info K-Means算法会对向量元素进行多次顺序的遍历，上次表示最适合于这种访问模式。
 * 利用Mapper输出的部分向量，Reducer通过简单的拼接得到一个完整的向量。
 */
package unitTwelve;

import java.io.IOException;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.mahout.math.NamedVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

public class VectorReducer extends Reducer<Text, VectorWritable, Text, VectorWritable>{
	private VectorWritable writer = new VectorWritable();
	protected void reduce(Text tag, Iterable<VectorWritable> values, Context context) throws IOException, InterruptedException{
		Vector vector = null;
		for(VectorWritable partialVector : values){
			if(vector == null){
				vector = partialVector.get().like();
			}
			partialVector.get().addTo(vector);
		}
		NamedVector namedVector = new NamedVector(vector, tag.toString());
		writer.set(namedVector);
		context.write(tag, writer);
	}
	
}
</span></strong>