MapReduce之Partition分区实例操作

1.需求:
将统计结果按照手机归属地不同省份输出到不同文件中(分区)
2.案例数据:
phone_data.txt
如下:

1363157985066 	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157995052 	13826544101	5C-0E-8B-C7-F1-E0:CMCC	120.197.40.4			4	0	264	0	200
1363157991076 	13926435656	20-10-7A-28-CC-0A:CMCC	120.196.100.99			2	4	132	1512	200
1363154400022 	13926251106	5C-0E-8B-8B-B1-50:CMCC	120.197.40.4			4	0	240	0	200
1363157993044 	18211575961	94-71-AC-CD-E6-18:CMCC-EASY	120.196.100.99	iface.qiyi.com	视频网站	15	12	1527	2106	200
1363157995074 	84138413	5C-0E-8B-8C-E8-20:7DaysInn	120.197.40.4	122.72.52.12		20	16	4116	1432	200
1363157993055 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157995033 	15920133257	5C-0E-8B-C7-BA-20:CMCC	120.197.40.4	sug.so.360.cn	信息安全	20	20	3156	2936	200
1363157983019 	13719199419	68-A1-B7-03-07-B1:CMCC-EASY	120.196.100.82			4	0	240	0	200
1363157984041 	13660577991	5C-0E-8B-92-5C-20:CMCC-EASY	120.197.40.4	s19.cnzz.com	站点统计	24	9	6960	690	200
1363157973098 	15013685858	5C-0E-8B-C7-F7-90:CMCC	120.197.40.4	rank.ie.sogou.com	搜索引擎	28	27	3659	3538	200
1363157986029 	15989002119	E8-99-C4-4E-93-E0:CMCC-EASY	120.196.100.99	www.umeng.com	站点统计	3	3	1938	180	200
1363157992093 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			15	9	918	4938	200
1363157986041 	13480253104	5C-0E-8B-C7-FC-80:CMCC-EASY	120.197.40.4			3	3	180	180	200
1363157984040 	13602846565	5C-0E-8B-8B-B6-00:CMCC	120.197.40.4	2052.flash2-http.qq.com	综合门户	15	12	1938	2910	200
1363157995093 	13922314466	00-FD-07-A2-EC-BA:CMCC	120.196.100.82	img.qfc.cn		12	12	3008	3720	200
1363157982040 	13502468823	5C-0A-5B-6A-0B-D4:CMCC-EASY	120.196.100.99	y0.ifengimg.com	综合门户	57	102	7335	110349	200
1363157986072 	18320173382	84-25-DB-4F-10-1A:CMCC-EASY	120.196.100.99	input.shouji.sogou.com	搜索引擎	21	18	9531	2412	200
1363157990043 	13925057413	00-1F-64-E1-E6-9A:CMCC	120.196.100.55	t3.baidu.com	搜索引擎	69	63	11058	48243	200
1363157988072 	13760778710	00-FD-07-A4-7B-08:CMCC	120.196.100.82			2	2	120	120	200
1363157985066 	13560436666	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200

3.分析:
(1)Mapreduce 中会将 map 输出的 kv 对,按照相同 key 分组,然后分发给不同的 reducetask。默认的分发规则为:根据 key 的 hashcode%reducetask 数来分发。
(2)如果要按照自己的需求进行分组,则需要改写数据分发(分组)组件Partitioner。
自定义一个 CustomPartitioner 继承抽象类:Partitioner
(3)在 job 驱动中,设置自定义 partitioner:
job.setPartitionerClass(CustomPartitioner.class)
(4)在统计流量案例的基础上,增加一个分区类。
流量统计详细操作见

package com.kgc.mapreduce.flowcount;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
public class ProvincePartitioner extends Partitioner<Text,FlowBean> {
    @Override
    public int getPartition(Text text, FlowBean flowBean, int i) {
        //1 获取电话号码前三位
        String preNum = text.toString().substring(0,3);
        int partition=4;
        //2 判断哪个省
        if("136".equals(preNum)){
            partition=0;
        }else if("137".equals(preNum)){
            partition=1;
        }else if("138".equals(preNum)){
            partition=2;
        }else if("139".equals(preNum)) {
            partition = 3;
        }
        return partition;  
    }
}

(5)在驱动函数中增加自定义数据分区设置和 reduce task 设置。

package com.kgc.mapreduce.flowcount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;

public class PartitionerDriver {
    public static void main(String[] args) throws IllegalArgumentException, IOException,ClassNotFoundException,InterruptedException {
        //1 获取配置信息,获取job对象实例
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        //2 指定本程序的 jar 包所在的本地路径
        job.setJarByClass(FlowBean.class);
        //3 指定本业务 job 要使用的 mapper/Reducer 业务类
        job.setMapperClass(FlowCountMapper.class);
        job.setReducerClass(FlowCountReducer.class);
        //4 指定 mapper 输出数据的 kv 类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //5 指定最终输出的数据的 kv 类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //6 指定自定义数据分区
        job.setPartitionerClass(ProvincePartitioner.class);
        //7 同时指定相应数量的 reduce task
        job.setNumReduceTasks(5);
        //8 指定 job 的输入原始文件所在目录以及输出目录
        FileInputFormat.setInputPaths(job,new Path("e:/phone_data.txt"));
        FileOutputFormat.setOutputPath(job,new Path("e:/partition"));
        //9 将 job 中配置的相关参数,以及 job 所用的 java 类所在的 jar 包,提交给 yarn 去运行
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}

你可能感兴趣的:(MapReduce,hadoop)