MapReduce自定义数据类型案列

案例需求：

统计每个手机号的总上行流量和总下行流量以及总流量（总上行流量+总下行流量）

输入：

 输出：

导包：

 <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.10.0</version>
        </dependency>

    </dependencies>

自定义数据类：

注意的是：

1实现Writable接口，实现序列化方法，序列化和反序列化顺序必须一致

2实现空参构造函数

import org.apache.hadoop.io.Writable;

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

public class FlowBean implements Writable {
    long upFlow;//上行流量
    long downFlow;//下行流量
    long totalFlow;//总流量
    public FlowBean() {
        super();
    }

    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeLong(upFlow);
        dataOutput.writeLong(downFlow);
        dataOutput.writeLong(totalFlow);

    }

    public void readFields(DataInput dataInput) throws IOException {
        upFlow=dataInput.readLong();
        downFlow=dataInput.readLong();
        totalFlow=dataInput.readLong();
    }

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

    public void setTotalFlow(long totalFlow) {
        this.totalFlow = totalFlow;
    }



}

MyMapper类：

以电话号码为key

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

import java.io.IOException;

public class MyMapper extends Mapper<LongWritable,Text,LongWritable, FlowBean> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line=value.toString();
        String[] s = line.split("\\t");

        FlowBean v = new FlowBean();
        LongWritable k = new LongWritable();
        k.set(Long.parseLong(s[0]));
        v.setUpFlow(Long.parseLong(s[1]));
        v.setDownFlow(Long.parseLong(s[2]));
        v.setTotalFlow(v.getDownFlow()+v.getUpFlow());

        context.write(k,v);


    }
}

MyReducer类：

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

import java.io.IOException;

public class MyReducer extends Reducer<LongWritable,FlowBean,LongWritable,FlowBean> {

    FlowBean v = new FlowBean();
    @Override
    protected void reduce(LongWritable key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        long totalUpFlow=0L;
        long totalDownFlow=0L;
       
        for (FlowBean value : values) {
            totalUpFlow+=value.getUpFlow();
            totalDownFlow=value.getDownFlow();
        }

        v.setUpFlow(totalUpFlow);
        v.setDownFlow(totalDownFlow);
        v.setTotalFlow(v.getDownFlow()+v.getUpFlow());

        context.write(key,v);
    }
}

MyDriver类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 MyDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(MyDriver.class);

        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

//        job.setMapOutputKeyClass(LongWritable.class);
//        job.setMapOutputValueClass(FlowBean.class);

        job.setOutputKeyClass(LongWritable.class);
        job.setOutputValueClass(FlowBean.class);

        FileInputFormat.addInputPath(job,new Path("/home/hadoop/temp/phone_info.txt"));
        FileOutputFormat.setOutputPath(job,new Path("/home/hadoop/temp/phone_info_RES"));

        FileSystem.get(conf).delete(new Path("/home/hadoop/temp/phone_info_RES"),true);


        boolean b = job.waitForCompletion(true);

        System.exit(b?0:1);
    }
}

遇到的坑：

1 导包要导对，hadoop里面有好多相似的包

2 遇到reducer不工作的原因是a:map时没写context.write()   b:context.write()后部分数据不符合reducer接受要求 c:各个节点通讯有问题导致无法copy数据到reducer节点