911      英雄聯盟

unique示例__示例程序_MapReduce_大數據計算服務-阿裏雲

（1）準備好測試程序jar包，假設名字為mapreduce-examples.jar;

（2）準備好Unique的測試表和資源；

• 創建表

  create table ss_in(key bigint, value bigint);
  create table ss_out(key bigint, value bigint);
  

• 添加資源

  add jar mapreduce-examples.jar -f;
  

（3）使用tunnel導入數據；

   tunnel upload data ss_in;

• 導入ss_in表的數據文件data內容為：

    1,1
    1,1
    2,2
    2,2

測試步驟

在odpscmd中執行Unique

jar -resources mapreduce-examples.jar -classpath mapreduce-examples.jar
    com.aliyun.odps.mapred.open.example.Unique ss_in ss_out key;

預期結果

作業成功結束。 輸出表ss_out中內容為：

+------------+------------+
| key        | value      |
+------------+------------+
| 1          |   1        |
| 2          |   2        |
+------------+------------+

代碼示例

    package com.aliyun.odps.mapred.open.example;

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

    import com.aliyun.odps.data.Record;
    import com.aliyun.odps.data.TableInfo;
    import com.aliyun.odps.mapred.JobClient;
    import com.aliyun.odps.mapred.MapperBase;
    import com.aliyun.odps.mapred.ReducerBase;
    import com.aliyun.odps.mapred.TaskContext;
    import com.aliyun.odps.mapred.conf.JobConf;
    import com.aliyun.odps.mapred.utils.InputUtils;
    import com.aliyun.odps.mapred.utils.OutputUtils;
    import com.aliyun.odps.mapred.utils.SchemaUtils;

    /**
     * Unique Remove duplicate words
     *
     **/
    public class Unique {

      public static class OutputSchemaMapper extends MapperBase {
        private Record key;
        private Record value;

        @Override
        public void setup(TaskContext context) throws IOException {
          key = context.createMapOutputKeyRecord();
          value = context.createMapOutputValueRecord();
        }

        @Override
        public void map(long recordNum, Record record, TaskContext context)
            throws IOException {
          long left = 0;
          long right = 0;

          if (record.getColumnCount() > 0) {
            left = (Long) record.get(0);
            if (record.getColumnCount() > 1) {
              right = (Long) record.get(1);
            }

            key.set(new Object[] { (Long) left, (Long) right });
            value.set(new Object[] { (Long) left, (Long) right });

            context.write(key, value);
          }
        }
      }

      public static class OutputSchemaReducer extends ReducerBase {
        private Record result = null;

        @Override
        public void setup(TaskContext context) throws IOException {
          result = context.createOutputRecord();
        }

        @Override
        public void reduce(Record key, Iterator<Record> values, TaskContext context)
            throws IOException {
          result.set(0, key.get(0));
          while (values.hasNext()) {
            Record value = values.next();
            result.set(1, value.get(1));
          }
          context.write(result);
        }
      }

      public static void main(String[] args) throws Exception {
        if (args.length > 3 || args.length < 2) {
          System.err.println("Usage: unique <in> <out> [key|value|all]");
          System.exit(2);
        }

        String ops = "all";
        if (args.length == 3) {
          ops = args[2];
        }

        // Key Unique
        if (ops.equals("key")) {
          JobConf job = new JobConf();

          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);

          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));

          job.setPartitionColumns(new String[] { "key" });
          job.setOutputKeySortColumns(new String[] { "key", "value" });
          job.setOutputGroupingColumns(new String[] { "key" });

          job.set("tablename2", args[1]);

          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);

          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);

          JobClient.runJob(job);
        }

        // Key&Value Unique
        if (ops.equals("all")) {
          JobConf job = new JobConf();

          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);

          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));

          job.setPartitionColumns(new String[] { "key" });
          job.setOutputKeySortColumns(new String[] { "key", "value" });
          job.setOutputGroupingColumns(new String[] { "key", "value" });

          job.set("tablename2", args[1]);

          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);

          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);

          JobClient.runJob(job);
        }

        // Value Unique
        if (ops.equals("value")) {
          JobConf job = new JobConf();

          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);

          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));

          job.setPartitionColumns(new String[] { "value" });
          job.setOutputKeySortColumns(new String[] { "value" });
          job.setOutputGroupingColumns(new String[] { "value" });

          job.set("tablename2", args[1]);

          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);

          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);

          JobClient.runJob(job);
        }

      }

    }

最後更新：2016-11-24 11:23:47

  上一篇： sleep示例__示例程序_MapReduce_大數據計算服務-阿裏雲

  下一篇： sort示例__示例程序_MapReduce_大數據計算服務-阿裏雲