283      阿裏雲

PageRank__示例程序_圖模型_大數據計算服務-阿裏雲

PageRank 算法是計算網頁排名的經典算法：輸入是一個有向圖 G，其中頂點表示網頁，如果存在網頁 A 到網頁 B 的鏈接，那麼存在聯接 A 到 B 的邊，算法基本原理：

• 初始化：點值表示 PageRank 的 rank 值（double 類型），初始時，所有點取值為 1/TotalNumVertices
• 迭代公式：PageRank(i)=0.15/TotalNumVertices+0.85*sum，其中 sum 為所有指向 i 點的點（設為 j） PageRank(j)/out_degree(j) 的累加值

從算法基本原理可以看出，這個算法非常適合使用 OPDS Graph 程序進行求解： 每個點 j 維護其 PageRank 值，每一輪迭代都將PageRank(j)/out_degree(j) 發給其鄰接點（向其投票），下一輪迭代時，每個點根據迭代公式重新計算 PageRank 取值。

源代碼

import java.io.IOException;
import org.apache.log4j.Logger;
import com.aliyun.odps.io.WritableRecord;
import com.aliyun.odps.graph.ComputeContext;
import com.aliyun.odps.graph.GraphJob;
import com.aliyun.odps.graph.GraphLoader;
import com.aliyun.odps.graph.MutationContext;
import com.aliyun.odps.graph.Vertex;
import com.aliyun.odps.graph.WorkerContext;
import com.aliyun.odps.io.DoubleWritable;
import com.aliyun.odps.io.LongWritable;
import com.aliyun.odps.io.NullWritable;
import com.aliyun.odps.data.TableInfo;
import com.aliyun.odps.io.Text;
import com.aliyun.odps.io.Writable;
public class PageRank {
  private final static Logger LOG = Logger.getLogger(PageRank.class);
  public static class PageRankVertex extends
      Vertex<Text, DoubleWritable, NullWritable, DoubleWritable> {
    @Override
    public void compute(
        ComputeContext<Text, DoubleWritable, NullWritable, DoubleWritable> context,
        Iterable<DoubleWritable> messages) throws IOException {
      if (context.getSuperstep() == 0) {
        setValue(new DoubleWritable(1.0 / context.getTotalNumVertices()));
      } else if (context.getSuperstep() >= 1) {
        double sum = 0;
        for (DoubleWritable msg : messages) {
          sum += msg.get();
        }
        DoubleWritable vertexValue = new DoubleWritable(
            (0.15f / context.getTotalNumVertices()) + 0.85f * sum);
        setValue(vertexValue);
      }
      if (hasEdges()) {
        context.sendMessageToNeighbors(this, new DoubleWritable(getValue()
            .get() / getEdges().size()));
      }
    }
    @Override
    public void cleanup(
        WorkerContext<Text, DoubleWritable, NullWritable, DoubleWritable> context)
        throws IOException {
      context.write(getId(), getValue());
    }
  }
  public static class PageRankVertexReader extends
      GraphLoader<Text, DoubleWritable, NullWritable, DoubleWritable> {
    @Override
    public void load(
        LongWritable recordNum,
        WritableRecord record,
        MutationContext<Text, DoubleWritable, NullWritable, DoubleWritable> context)
        throws IOException {
      PageRankVertex vertex = new PageRankVertex();
      vertex.setValue(new DoubleWritable(0));
      vertex.setId((Text) record.get(0));
      System.out.println(record.get(0));
      for (int i = 1; i < record.size(); i++) {
        Writable edge = record.get(i);
        System.out.println(edge.toString());
        if (!(edge.equals(NullWritable.get()))) {
          vertex.addEdge(new Text(edge.toString()), NullWritable.get());
        }
      }
      LOG.info("vertex edgs size: "
          + (vertex.hasEdges() ? vertex.getEdges().size() : 0));
      context.addVertexRequest(vertex);
    }
  }
  private static void printUsage() {
    System.out.println("Usage: <in> <out> [Max iterations (default 30)]");
    System.exit(-1);
  }
  public static void main(String[] args) throws IOException {
    if (args.length < 2)
      printUsage();
    GraphJob job = new GraphJob();
    job.setGraphLoaderClass(PageRankVertexReader.class);
    job.setVertexClass(PageRankVertex.class);
    job.addInput(TableInfo.builder().tableName(args[0]).build());
    job.addOutput(TableInfo.builder().tableName(args[1]).build());
    // default max iteration is 30
    job.setMaxIteration(30);
    if (args.length >= 3)
      job.setMaxIteration(Integer.parseInt(args[2]));
    long startTime = System.currentTimeMillis();
    job.run();
    System.out.println("Job Finished in "
        + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
  }
}