向MapReduce转换：生成用户向量

Posted 2020-06-14 杨鑫newlfe

分两部分：

<span style="font-size:18px;">/***
 * @author YangXin
 * @date 2016/2/21
 * @ info 主要功能是mahout实现解析Wikipedia链接文件的Mapper接口
 */
package unitSix;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.mahout.math.VarLongWritable;

public class WikipediaToItemPrefsMapper extends Mapper<LongWritable, Text, VarLongWritable, VarLongWritable>{
	private static final Pattern NUMBERS = Pattern.compile("(\\d+)");
	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException{
		String line = value.toString();
		Matcher m = NUMBERS.matcher(line);
		//定位用户ID
		m.find();                              
		VarLongWritable userID = new VarLongWritable(Long.parseLong(m.group()));
		VarLongWritable itemID = new VarLongWritable();
		while(m.find()){
			itemID.set(Long.parseLong(m.group()));
			//为每个物品ID生成用户-物品对
			context.write(userID, itemID);
		}
	}
}</span>

<strong><span style="font-size:18px;">/***
 * @author YangXin
 * @info 功能是mahout实现从用户物品偏好中生成Vector的reducer接口
 */
package unitSix;
import java.io.IOException;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.VarLongWritable;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

public class WikipediaToUserVectorReducer extends Reducer<VarLongWritable, VarLongWritable, VarLongWritable, VectorWritable>{
	public void reduce(VarLongWritable userID, Iterable<VarLongWritable> itemPrefs, Context context) throws IOException, InterruptedException{
		Vector userVector = new RandomAccessSparseVector(Integer.MAX_VALUE, 100);
		for(VarLongWritable itemPref : itemPrefs){
			userVector.set((int)itemPref.get(), 1.0f);
		}
		context.write(userID, new VectorWritable(userVector));
	}
}
</span></strong>