MapReducer扩展案例---TopN案例

TopN案例
1．需求
对需求2.3输出结果进行加工，输出流量使用量在前10的用户信息
（1）输入数据

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）输出数据

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

注意在Notepad++中空格会显示有符号位的.

---

排序的时候按照流量进行排序,分组的时候我们希望所有的数据进入到同一个reducer,

---

按照流量取前十,第一件事情把流量放在Key的位置,map阶段,取前十要将所有的电话放到同一个组中取前十,

 <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>7</source>
                <target>7</target>
            </configuration>
        </plugin>
    </plugins>
</build>


    <dependencies>


        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
    </dependencies>

resource–>log4j.properties添加配置信息

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

---

代码

FlowBean

import org.apache.hadoop.io.WritableComparable;

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

public class FlowBean implements WritableComparable<FlowBean> {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }

    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }

    @Override
    public int compareTo(FlowBean o) { //比较  逆序,按照降序排列
        return Long.compare(o.sumFlow, this.sumFlow);
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }

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

FlowGroupingComparator

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

public class FlowGroupingComparator extends WritableComparator {
    protected FlowGroupingComparator() {
        super(FlowBean.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        return 0;  //返回0,让所有数据都相等
    }
}

FlowMapper

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 k = new FlowBean();
    private Text v = new Text();

    //ctrl + o 重写方法
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");  //按照/t进行切分
        v.set(fields[0]);
        k.setUpFlow(Long.parseLong(fields[1]));
        k.setDownFlow(Long.parseLong(fields[2]));
        k.setSumFlow(Long.parseLong(fields[3]));

        context.write(k, v);
    }
}

FlowReducer

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

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

public class FlowReducer extends Reducer<FlowBean, Text, Text, FlowBean> {//输入k,v,输出k,v

    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        //获取迭代器
        Iterator<Text> iterator = values.iterator();
        //取前十
        for (int i = 0; i < 10; i++) {
            context.write(iterator.next(), key);
        }
    }
}

FlowDriver

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, ClassNotFoundException, InterruptedException {
        //获取配置信息,或者job对象实例
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        //指定本程序的jar包所在的本地路径
        job.setJarByClass(FlowDriver.class);
        //指定本业务job要使用的mapper/Reducer业务类
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        job.setGroupingComparatorClass(FlowGroupingComparator.class);
        //指定mapper输出数据的kv类型
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);
        //指定最终输出的数据的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //指定job的输入原始文件所在目录
        FileInputFormat.setInputPaths(job, new Path("d:\\test1"));
        FileOutputFormat.setOutputPath(job, new Path("d:\\test1_finally"));
        //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 b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}