云原生大数据计算服务 MaxCompute：PageRank

基本原理

算法的基本原理如下：

• 初始化：点值表示PageRank的rank值（DOUBLE类型）。初始时，所有点取值为1/TotalNumVertices。

• 迭代公式：PageRank(i)=0.15/TotalNumVertices+0.85*sum。其中sum为所有指向i点的点（设为j）PageRank(j)/out_degree(j)的累加值。

由算法基本原理可以看出，此算法非常适合使用MaxCompute Graph程序进行求解。每个点j维护其PageRank值，每一轮迭代都将PageRank(j)/out_degree(j)发给其邻接点（向其投票）。下一轮迭代时，每个点根据迭代公式重新计算PageRank取值。

前提条件

您已通过编写Graph完成测试所需的环境配置。

测试准备

本测试是在MaxCompute客户端，提交作业到集群进行测试。您也可以先进行本地测试，详情请参见本地调试。

1. 准备好测试程序的JAR包，假设名字为graph-examples.jar，本地存放路径为MaxCompute客户端bin目录下data\resources。

2. 准备好PageRank的测试表和资源。

   1. 创建测试表。

      CREATE TABLE pagerank_in(vertex STRING, des_1 STRING, des_2 STRING);
      CREATE TABLE pagerank_out(vertex_id STRING, vertex_value DOUBLE);

   2. 添加测试资源。

      -- 首次添加忽略-f覆盖指令。
      add jar data\resources\graph-examples.jar -f;

3. 使用Tunnel将MaxCompute客户端bin目录下data.txt导入pagerank_in表中。

   tunnel upload data.txt pagerank_in;

   data.txt数据如下：

   1,2,4
   2,1,3
   4,2,3
   3,1,2

测试步骤

在MaxCompute客户端中执行PageRank测试。

jar -resources graph-examples.jar -classpath data\resources\graph-examples.jar
com.aliyun.odps.graph.PageRank pagerank_in pagerank_out

预期结果

作业成功结束后，输出表pagerank_out中的内容如下。

+------------+--------------+
| vertex_id  | vertex_value |
+------------+--------------+
| 1          | 0.2781238395149928 |
| 2          | 0.3245614688676814 |
| 3          | 0.24161225195637787 |
| 4          | 0.155702636559485 |
+------------+--------------+

代码示例

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");
  }
}