天天看點
傳回

Hadoop-Mapreduce實戰（兩表join）

兩表Join

  • 未優化版本
    • Bean.java 
import org.apache.hadoop.io.WritableComparable;

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

/*
 * 人員和位址的通用bean
 */
public class Bean implements WritableComparable<Bean> {
    private String userNo = "";
    private String userName = "";
    private String addreNo = "";
    private String addreName = "";
    private int flag;

    public Bean(Bean bean) {
        this.userName = bean.getUserName();
        this.userNo = bean.getUserNo();
        this.addreName = bean.getAddreName();
        this.addreNo = bean.getAddreNo();
        this.flag = bean.getFlag();
    }

    public Bean() {
        super();
        // TODO Auto-generated constructor stub
    }

    public Bean(String userNo, String userName, String addreNo,
                String addreName, int flag) {
        super();
        this.userNo = userNo;
        this.userName = userName;
        this.addreNo = addreNo;
        this.addreName = addreName;
        this.flag = flag;
    }

    public String getUserNo() {
        return userNo;
    }

    public void setUserNo(String userNo) {
        this.userNo = userNo;
    }

    public String getUserName() {
        return userName;
    }

    public void setUserName(String userName) {
        this.userName = userName;
    }

    public String getAddreNo() {
        return addreNo;
    }

    public void setAddreNo(String addreNo) {
        this.addreNo = addreNo;
    }

    public String getAddreName() {
        return addreName;
    }

    public void setAddreName(String addreName) {
        this.addreName = addreName;
    }

    public int getFlag() {
        return flag;
    }

    public void setFlag(int flag) {
        this.flag = flag;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(userNo);
        out.writeUTF(userName);
        out.writeUTF(addreNo);
        out.writeUTF(addreName);
        out.writeInt(flag);

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.userNo = in.readUTF();
        this.userName = in.readUTF();
        this.addreNo = in.readUTF();
        this.addreName = in.readUTF();
        this.flag = in.readInt();

    }

    @Override
    public int compareTo(Bean arg0) {
        // TODO Auto-generated method stub
        return 0;
    }

    @Override
    public String toString() {
        return "userNo=" + userNo + ", userName=" + userName + ", addreNo="
                + addreNo + ", addreName=" + addreName;
    }

}

PersonAddrMap.java

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

import java.io.IOException;

public class PersonAddrMap extends Mapper<LongWritable, Text, IntWritable, Bean> {
    @Override
    protected void map(LongWritable key, Text value,
                       Mapper<LongWritable, Text, IntWritable, Bean>.Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String str[] = line.split(" ");
        if (str.length == 2) { //地區資訊表
            Bean bean = new Bean();
            bean.setAddreNo(str[0]);
            bean.setAddreName(str[1]);
            bean.setFlag(0); // 0表示地區
            context.write(new IntWritable(Integer.parseInt(str[0])), bean);
        } else { //人員資訊表
            Bean bean = new Bean();
            bean.setUserNo(str[0]);
            bean.setUserName(str[1]);
            bean.setAddreNo(str[2]);
            bean.setFlag(1); // 1表示人員表
            context.write(new IntWritable(Integer.parseInt(str[2])), bean);
        }
    }
}

PersonAddreRedu.java

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

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class PersonAddreRedu extends Reducer<IntWritable, Bean, NullWritable,Text> {
    @Override
    protected void reduce(IntWritable key, Iterable<Bean> values,
                          Reducer<IntWritable, Bean, NullWritable, Text>.Context context)
            throws IOException, InterruptedException {
        Bean Addre = null;
        List<Bean> peoples = new ArrayList<Bean>();
		/*
		 * 如果values的第一個元素資訊就是位址Addre的資訊的話,
		 * 我們就不再需要一個List來緩存person資訊了,values後面的全是人員資訊
		 * 将減少巨大的記憶體空間
		 */
		/*
		 * partitioner和shuffer的過程：
		 * partitioner的主要功能是根據reduce的數量将map輸出的結果進行分塊,将資料送入到相應的reducer.
		 * 所有的partitioner都必須實作partitioner接口并實作getPartition方法,該方法的傳回值為int類型，并且取值範圍在0~(numOfReducer-1),
		 * 進而能将map的輸出輸入到對應的reducer中,對于某個mapreduce過程,hadoop架構定義了預設的partitioner為HashPartioner,
		 * 該partitioner使用key的hashCode來決定将該key輸送到哪個reducer;
		 * shuffle将每個partitioner輸出的結果根據key進行group以及排序,将具有相同key的value構成一個values的疊代器,并根據key進行排序分别調用
		 * 開發者定義的reduce方法進行排序,是以mapreducer的是以key必須實作comparable接口的compareto()方法進而能實作兩個key對象的比較
		 */
		/*
		 * 我們需要自定義key的資料結構(shuffle按照key進行分組)來滿足共同addreNo的情況下位址表的更小需求
		 *
		 */
        for (Bean bean : values) {
            if (bean.getFlag() == 0) { // 表示地區表
                Addre = new Bean(bean);
            } else {
                peoples.add(new Bean(bean)); //添加到peoplelist中
            }
        }
        for (Bean peo : peoples) { // 給peoplelist添加地區名字
            peo.setAddreName(Addre.getAddreName());
            context.write(NullWritable.get(), new Text(peo.toString()));
        }
    }
}

PersonAddreMain.java

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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;

public class PersonAddreMain {
    public static void main(String[] args) throws Exception {

        args = new String[] { "F:\\A\\join\\", "F:\\A\\out" };

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(PersonAddreMain.class);

        job.setMapperClass(PersonAddrMap.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(Bean.class);

        job.setReducerClass(PersonAddreRedu.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

已優化版本

  • Bean.java 
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/*
 * 人員和位址的通用bean
 * 用作map輸出的value
 */
public class Bean implements WritableComparable<Bean> {
    private String userNo = " ";
    private String userName = " ";
    private String addreNo = " ";
    private String addreName = " ";

    public Bean(Bean bean) {
        this.userName = bean.getUserName();
        this.userNo = bean.getUserNo();
        this.addreName = bean.getAddreName();
        this.addreNo = bean.getAddreNo();
    }

    public Bean() {
        super();
        // TODO Auto-generated constructor stub
    }

    public Bean(String userNo, String userName, String addreNo,
                String addreName, int flag) {
        super();
        this.userNo = userNo;
        this.userName = userName;
        this.addreNo = addreNo;
        this.addreName = addreName;
    }
    
           
public String getUserNo() {
        return userNo;
    }

    public void setUserNo(String userNo) {
        this.userNo = userNo;
    }

    public String getUserName() {
        return userName;
    }

    public void setUserName(String userName) {
        this.userName = userName;
    }

    public String getAddreNo() {
        return addreNo;
    }

    public void setAddreNo(String addreNo) {
        this.addreNo = addreNo;
    }

    public String getAddreName() {
        return addreName;
    }

    public void setAddreName(String addreName) {
        this.addreName = addreName;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeUTF(userNo);
        out.writeUTF(userName);
        out.writeUTF(addreNo);
        out.writeUTF(addreName);

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.userNo = in.readUTF();
        this.userName = in.readUTF();
        this.addreNo = in.readUTF();
        this.addreName = in.readUTF();
    }

    @Override
    public int compareTo(Bean arg0) {
        // TODO Auto-generated method stub
        return 0;
    }

    @Override
    public String toString() {
        return "userNo=" + userNo + ", userName=" + userName + ", addreNo="
                + addreNo + ", addreName=" + addreName;
    }
}

BeanKey.java

import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/*
 * map輸出的key
 */
public class BeanKey implements WritableComparable<BeanKey> {
    private int AddreNo;
    private boolean isPrimary; // true：address false：person

    public BeanKey(int addreNo, boolean isPrimary) {
        super();
        this.AddreNo = addreNo;
        this.isPrimary = isPrimary;
    }

    public BeanKey() {
        super();
        // TODO Auto-generated constructor stub
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(AddreNo);
        out.writeBoolean(isPrimary);

    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.AddreNo = in.readInt();
        this.isPrimary = in.readBoolean();

    }

    // partitioner執行時調用hashcode()方法和compareTo()方法
    // compareTo()方法作為shuffle排序的預設方法
    @Override
    public int hashCode() {
        return this.AddreNo; // 按AddreNo進行分組
    }

    //用于排序,将相同的AddressNo的位址表和人員表,将位址表放到首位
    @Override
    public int compareTo(BeanKey o) {
        if (this.AddreNo == o.getAddreNo()) { // 如果是同一個AddressNo的資料則判斷是Person還是Address表
            if (this.isPrimary == o.isPrimary()) {  //如果屬性相同屬于同種類型的表,傳回0
                return 0;
            } else {
                return this.isPrimary ? -1 : 1; // true表示Address表 傳回更小的值,将排至values隊首
            }
        } else {
            return this.AddreNo - o.getAddreNo() > 0 ? 1 : -1;  //按AddressNo排序
        }
    }

    public int getAddreNo() {
        return AddreNo;
    }

    public void setAddreNo(int addreNo) {
        AddreNo = addreNo;
    }

    public boolean isPrimary() {
        return isPrimary;
    }

    public void setPrimary(boolean isPrimary) {
        this.isPrimary = isPrimary;
    }
}

PersonAddrMap.java

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

/*
 * map類使key,value分别進行處理
 */
public class PersonAddreMap extends Mapper<LongWritable, Text, BeanKey, Bean> {
    @Override
    protected void map(LongWritable key, Text value,
                       Mapper<LongWritable, Text, BeanKey, Bean>.Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String str[] = line.split(" ");
        if (str.length == 2) {
            // Addre表
            Bean Addre = new Bean();
            Addre.setAddreNo(str[0]);
            Addre.setAddreName(str[1]);

            BeanKey AddreKey = new BeanKey();
            AddreKey.setAddreNo(Integer.parseInt(str[0]));
            AddreKey.setPrimary(true); // true表示地區表
            context.write(AddreKey, Addre);
        } else {
            // Person表
            Bean Person = new Bean();
            Person.setUserNo(str[0]);
            Person.setUserName(str[1]);
            Person.setAddreNo(str[2]);

            BeanKey PerKey = new BeanKey();
            PerKey.setAddreNo(Integer.parseInt(str[2]));
            PerKey.setPrimary(false);// false表示人員表
            context.write(PerKey, Person);

        }
    }

}

PersonAddreRedu.java

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

import java.io.IOException;

public class PersonAddreReduce extends Reducer<BeanKey, Bean, NullWritable, Text> {
    @Override
    protected void reduce(BeanKey key, Iterable<Bean> values,
                          Reducer<BeanKey, Bean, NullWritable, Text>.Context context)
            throws IOException, InterruptedException {
        Bean Addre = null;
        int num = 0;
        for (Bean bean : values) {
            if (num == 0) {
                Addre = new Bean(bean); // Address位址表為values的第一個值
                num++;
            } else {
                // 其餘全為person表
                // 沒有list數組,節省大量記憶體空間
                bean.setAddreName(Addre.getAddreName());
                context.write(NullWritable.get(), new Text(bean.toString()));
            }
        }
    }
}

PKFKCompartor.java

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

/*
 * 實作Group分組
 * shuffle的group過程預設的是使用的key(BeanKey)的compareTo()方法
 * 剛才我們添加的自定義的Key沒有辦法将具有相同AddressNo的位址和人員放到同一個group中(因為從compareTo()方法中可以看出他們是不相等的)
 * 我們需要的就是自己定義一個groupComparer就可以
 * 實作比較器
 */
public class PKFKCompartor extends WritableComparator {

    protected PKFKCompartor() {
        super(BeanKey.class, true);
    }

    //兩個BeanKey進行比較排序
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        BeanKey a1 = (BeanKey) a;
        BeanKey b1 = (BeanKey) b;
        if (a1.getAddreNo() == b1.getAddreNo()) {
            return 0;
        } else {
            return a1.getAddreNo() > b1.getAddreNo() ? 1 : -1;
        }
    }
}

PersonAddreMain.java

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;

public class PersonAddreMain {
    public static void main(String[] args) throws Exception {

        args = new String[]{"F:\\A\\join\\", "F:\\A\\out_Andy1"};

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(PersonAddreMain.class);

        //設定自定義的group
        job.setGroupingComparatorClass(PKFKCompartor.class);

        job.setMapperClass(PersonAddreMap.class);
        job.setMapOutputKeyClass(BeanKey.class);
        job.setMapOutputValueClass(Bean.class);

        job.setReducerClass(PersonAddreRedu.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}
hadoop java mapreduce 大資料
上一篇: Hadoop-mapreduce案例-兩表join
下一篇: hadoop二次排序應用，實作兩表連接配接join操作

繼續閱讀