写在开头:OPEN_MR在数加平台上可用,ODPS_MR我还没跑出结果,先给大家演示一下OPEN_MR的简单使用。
首先,建立一个Hadoop项目,可以使用御膳房的文档搭建环境(目的使代码能够编译通过),后面附一份我的御膳房项目(配置maven后可直接导入eclipse使用)。
使用御膳房的文档搭建环境
http://setting.tenant.yushanfang.com/portal/help/doc.html?spm=0.0.0.0.LBzMEE&file=MrUdfLocalDev
下载源码
http://download.csdn.net/detail/q383700092/9551145
附上示例代码:
package hadoop.TianChiMapreduce;
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;
public class WordCount {
public static class TokenizerMapper extends MapperBase {
private Record word;
private Record one;
@Override
public void setup(TaskContext context) throws IOException {
word = context.createMapOutputKeyRecord();
one = context.createMapOutputValueRecord();
one.set(new Object[] { 1L });
System.out.println("TaskID:" + context.getTaskID().toString());
}
@Override
public void map(long recordNum, Record record, TaskContext context)
throws IOException {
for (int i = 0; i < record.getColumnCount(); i++) {
word.set(new Object[] { record.get(0).toString() });
context.write(word, one);
}
}
}
/**
* A combiner class that combines map output by sum them.
**/
public static class SumCombiner extends ReducerBase {
private Record count;
@Override
public void setup(TaskContext context) throws IOException {
count = context.createMapOutputValueRecord();
}
@Override
public void reduce(Record key, Iterator<Record> values, TaskContext context)
throws IOException {
long c = 0;
while (values.hasNext()) {
Record val = values.next();
c += (Long) val.get(0);
}
count.set(0, c);
context.write(key, count);
}
}
/**
* A reducer class that just emits the sum of the input values.
**/
public static class SumReducer 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 {
long count = 0;
while (values.hasNext()) {
Record val = values.next();
count += (Long) val.get(0);
}
result.set(0, key.get(0));
result.set(1, count);
context.write(result);
}
}
public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: WordCount <in_table> <out_table>");
System.exit(2);
}
JobConf job = new JobConf();
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(SumCombiner.class);
job.setReducerClass(SumReducer.class);
job.setMapOutputKeySchema(SchemaUtils.fromString("word:string"));
job.setMapOutputValueSchema(SchemaUtils.fromString("count:bigint"));
InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
JobClient.runJob(job);
}
}
项目结构如下:
留一个标红的代码就行,其他没用。
点击WordCount.java右键export导出Jar
打开数加平台点击上传资源
拖动OPEN_MR组件到右侧空白
双击组件-按如下填写,前两个是你需要运行的jar,mapper和reducer是你要运行的map类和reudce类,输出表要提前创建好,key和value对应输出表的字段
建表sql:create table if not exists wcout1 (key string,cnt bigint);
保存运行即可
wcout1的表结构和结果