hadoop?詳解如何實(shí)現(xiàn)數(shù)據(jù)排序

更新時(shí)間：2024年10月11日 12:02:35 作者：YinJuan791739156

在很多業(yè)務(wù)場(chǎng)景下,需要對(duì)原始的數(shù)據(jù)讀取分析后,將輸出的結(jié)果按照指定的業(yè)務(wù)字段進(jìn)行排序輸出,方便上層應(yīng)用對(duì)結(jié)果數(shù)據(jù)進(jìn)行展示或使用,減少二次排序的成本

一、全排序

全排序是指最終只產(chǎn)生一個(gè)輸出文件，數(shù)據(jù)在文件內(nèi)部有序。

1、輸入數(shù)據(jù)

13470253144	180	180	360
13509468723	7335	110349	117684
13560439638	918	4938	5856
13568436656	3597	25635	29232
13590439668	1116	954	2070
13630577991	6960	690	7650
13682846555	1938	2910	4848
13729199489	240	0	240
13736230513	2481	24681	27162
13768778790	120	120	240
13846544121	264	0	264
13956435636	132	1512	1644
13966251146	240	0	240
13975057813	11058	48243	59301
13992314666	3008	3720	6728
15043685818	3659	3538	7197
15910133277	3156	2936	6092
15959002129	1938	180	2118
18271575951	1527	2106	3633
18390173782	9531	2412	11943
84188413	4116	1432	5548

2、Bean對(duì)象

繼承WritabelComparable，并實(shí)現(xiàn)方法compareTo。WritabelComparable起始就是兩個(gè)接口的綜合，Writable是Hadoop自定義序列化數(shù)據(jù)需要實(shí)現(xiàn)的接口，而Coparable是比較排序需要實(shí)現(xiàn)的接口。

package cn.nuwa.hap.cp;

import lombok.Data;
import lombok.NoArgsConstructor;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;


@Data
@NoArgsConstructor
public class FlowBean implements WritableComparable<FlowBean> {
    private long upFlow; //上行流量
    private long downFlow; //下行流量
    private long sumFlow; //總流量

    public void setSumFlow() {
        this.sumFlow = this.upFlow + this.downFlow;
    }

    //4 實(shí)現(xiàn)序列化和反序列化方法,注意順序一定要保持一致
    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(sumFlow);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.upFlow = dataInput.readLong();
        this.downFlow = dataInput.readLong();
        this.sumFlow = dataInput.readLong();
    }

    //5 重寫(xiě)ToString
    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }

    @Override
    public int compareTo(FlowBean  o) {
        //按照總流量比較,倒序排列
        if(this.sumFlow > o.getSumFlow()){
            return -1;
        }else if(this.sumFlow < o.getSumFlow()){
            return 1;
        }else {
            return 0;
        }
    }
}

3、Mapper類(lèi)

package cn.nuwa.hap.cp;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;


public class FlowMapper extends Mapper<LongWritable, Text, FlowBean, Text> {
    private FlowBean outK = new FlowBean();
    private Text outV = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1 獲取一行數(shù)據(jù)
        String line = value.toString();

        //2 按照"\t",切割數(shù)據(jù)
        String[] split = line.split("\t");

        //3 封裝outK outV
        outK.setUpFlow(Long.parseLong(split[1]));
        outK.setDownFlow(Long.parseLong(split[2]));
        outK.setSumFlow();
        outV.set(split[0]);

        //4 寫(xiě)出outK outV
        context.write(outK,outV);
    }
}

4、Reduce類(lèi)

package cn.nuwa.hap.cp;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;


public class FlowReducer extends Reducer<FlowBean, Text, Text, FlowBean> {

    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

        //遍歷values集合,循環(huán)寫(xiě)出,避免總流量相同的情況
        for (Text value : values) {
            //調(diào)換KV位置,反向?qū)懗?
            context.write(value, key);
        }
    }
}

5、Dirver類(lèi)

package cn.nuwa.hap.cp;

import cn.nuwa.hap.wb.FlowBean;
import cn.nuwa.hap.wb.ProvincePartitioner;
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 FlowDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        //1 獲取job對(duì)象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2 關(guān)聯(lián)本Driver類(lèi)
        job.setJarByClass(FlowDriver.class);

        //3 關(guān)聯(lián)Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4 設(shè)置Map端輸出KV類(lèi)型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(cn.nuwa.hap.wb.FlowBean.class);

        //5 設(shè)置程序最終輸出的KV類(lèi)型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //6 設(shè)置程序的輸入輸出路徑
        FileInputFormat.setInputPaths(job, new Path("C:\\Users\\Dell\\Desktop\\hadoop\\inputFlow"));
        FileOutputFormat.setOutputPath(job, new Path("C:\\Users\\Dell\\Desktop\\hadoop\\outputFlow"));

        //8 指定自定義分區(qū)器
        job.setPartitionerClass(ProvincePartitioner.class);

        //9 同時(shí)指定相應(yīng)數(shù)量的ReduceTask
        job.setNumReduceTasks(5);

        //7 提交Job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

6、最終結(jié)果

13509468723	7335	110349	117684
13975057813	11058	48243	59301
13568436656	3597	25635	29232
13736230513	2481	24681	27162
18390173782	9531	2412	11943
13630577991	6960	690	7650
15043685818	3659	3538	7197
13992314666	3008	3720	6728
15910133277	3156	2936	6092
13560439638	918	4938	5856
84188413	4116	1432	5548
13682846555	1938	2910	4848
18271575951	1527	2106	3633
15959002129	1938	180	2118
13590439668	1116	954	2070
13956435636	132	1512	1644
13470253144	180	180	360
13846544121	264	0	264
13729199489	240	0	240
13768778790	120	120	240
13966251146	240	0	240

二、分區(qū)排序

分區(qū)排序的本質(zhì)是：

數(shù)據(jù)分區(qū)
區(qū)內(nèi)數(shù)據(jù)有序

只需要在全排序的基礎(chǔ)上加上分區(qū)的代碼即可

1、分區(qū)類(lèi)

package cn.nuwa.hap.cp;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;


public class ProvincePartitioner extends Partitioner< FlowBean, Text> {

    @Override
    public int getPartition(FlowBean flowBean, Text text, int numPartitions) {
        //獲取手機(jī)號(hào)前三位
        String phone = text.toString();
        String prePhone = phone.substring(0, 3);

        //定義一個(gè)分區(qū)號(hào)變量partition,根據(jù)prePhone設(shè)置分區(qū)號(hào)
        int partition;
        if("136".equals(prePhone)){
            partition = 0;
        }else if("137".equals(prePhone)){
            partition = 1;
        }else if("138".equals(prePhone)){
            partition = 2;
        }else if("139".equals(prePhone)){
            partition = 3;
        }else {
            partition = 4;
        }

        //最后返回分區(qū)號(hào)partition
        return partition;
    }
}

2、Driver類(lèi)新增分區(qū)配置

  // 設(shè)置自定義分區(qū)器
  job.setPartitionerClass(ProvincePartitioner.class);

  // 設(shè)置對(duì)應(yīng)的ReduceTask的個(gè)數(shù)
  job.setNumReduceTasks(5);

3、結(jié)果

part-r-00000

13630577991	6960	690	7650
13682846555	1938	2910	4848

part-r-00001

13736230513	2481	24681	27162
13729199489	240	0	240
13768778790	120	120	240

part-r-00002

13846544121	264	0	264

part-r-00003

13975057813	11058	48243	59301
13992314666	3008	3720	6728
13956435636	132	1512	1644
13966251146	240	0	240

part-r-00004

13509468723	7335	110349	117684
13568436656	3597	25635	29232
18390173782	9531	2412	11943
15043685818	3659	3538	7197
15910133277	3156	2936	6092
13560439638	918	4938	5856
84188413	4116	1432	5548
18271575951	1527	2106	3633
15959002129	1938	180	2118
13590439668	1116	954	2070
13470253144	180	180	360

到此這篇關(guān)于hadoop 詳解如何實(shí)現(xiàn)數(shù)據(jù)排序的文章就介紹到這了,更多相關(guān)hadoop 數(shù)據(jù)排序內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: