提交到集群测试
- 用maven打jar包,需要添加的打包插件依赖:
maven-compiler-plugin
3.6.1
1.8
1.8
maven-assembly-plugin
jar-with-dependencies
make-assembly
package
single
;
-
将程序打成jar包
-
修改不带依赖的jar包名称为wc.jar,并拷贝该jar包到Hadoop集群的/opt/module/hadoop-3.1.3路径。
-
启动Hadoop集群
sbin/start-dfs.sh
sbin/start-yarn.sh
-
执行WordCount程序
hadoop jar wc.jar com.atguigu.mapreduce.wordcount.WordCountDriver /user/atguigu/input /user/atguigu/output
序列化概述
- 什么是序列化
- 序列化就是把内存中的对象,转换成字节序列(或其他数据传输协议)以便于存储到磁盘(持久化)和网络传输。
- 反序列化就是将收到字节序列(或其他数据传输协议)或者是磁盘的持久化数据,转换成内存中的对象。
- 为社么要序列化
- 序列化可以存储“活动的对象”,可以将“活的”对象发送到远程计算机。
- 为社么不用java的序列化
- Java的序列化是一个重量级序列化框架(Serializable),一个对象被序列化后,会附带很多额外的信息(各种校验信息,Header,继承体系等),不便于在网络中高效传输。所以,Hadoop自己开发了一套序列化机制(Writable)。
- hadoop序列化的特点:紧凑,快速,互操作。
mapreduce序列化案例实操
-
统计每一个手机号耗费的总上行流量、总下行流量、总流量
-
编写mapreduce程序
-
编写流量统计的Bean对象
package com.atguigu.mapreduce.writable;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
//1 继承Writable接口
public class FlowBean implements Writable {
private long upFlow; //上行流量
private long downFlow; //下行流量
private long sumFlow; //总流量
//2 提供无参构造
public FlowBean() {
}
//3 提供三个参数的getter和setter方法
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;
}
public void setSumFlow() {
this.sumFlow = this.upFlow + this.downFlow;
}
//4 实现序列化和反序列化方法,注意顺序一定要保持一致
@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 重写ToString
@Override
public String toString() {
return upFlow + "t" + downFlow + "t" + sumFlow;
}
}
;
-
编写Mapper类
package com.atguigu.mapreduce.writable;
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 {
private Text outK = new Text();
private FlowBean outV = new FlowBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//1 获取一行数据,转成字符串
String line = value.toString();
//2 切割数据
String[] split = line.split("t");
//3 抓取我们需要的数据:手机号,上行流量,下行流量
String phone = split[1];
String up = split[split.length - 3];
String down = split[split.length - 2];
//4 封装outK outV
outK.set(phone);
outV.setUpFlow(Long.parseLong(up));
outV.setDownFlow(Long.parseLong(down));
outV.setSumFlow();
//5 写出outK outV
context.write(outK, outV);
}
}
;
-
编写Reducer类
package com.atguigu.mapreduce.writable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class FlowReducer extends Reducer {
private FlowBean outV = new FlowBean();
@Override
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
long totalUp = 0;
long totalDown = 0;
//1 遍历values,将其中的上行流量,下行流量分别累加
for (FlowBean flowBean : values) {
totalUp += flowBean.getUpFlow();
totalDown += flowBean.getDownFlow();
}
//2 封装outKV
outV.setUpFlow(totalUp);
outV.setDownFlow(totalDown);
outV.setSumFlow();
//3 写出outK outV
context.write(key,outV);
}
}
;
-
package com.atguigu.mapreduce.writable;
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 {
//1 获取job对象
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 关联本Driver类
job.setJarByClass(FlowDriver.class);
//3 关联Mapper和Reducer
job.setMapperClass(FlowMapper.class);
job.setReducerClass(FlowReducer.class);
//4 设置Map端输出KV类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
//5 设置程序最终输出的KV类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
//6 设置程序的输入输出路径
FileInputFormat.setInputPaths(job, new Path("D:\inputflow"));
FileOutputFormat.setOutputPath(job, new Path("D:\flowoutput"));
//7 提交Job
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
maven-compiler-plugin 3.6.1 1.8 1.8 maven-assembly-plugin jar-with-dependencies make-assembly package single
;
将程序打成jar包
修改不带依赖的jar包名称为wc.jar,并拷贝该jar包到Hadoop集群的/opt/module/hadoop-3.1.3路径。
启动Hadoop集群
sbin/start-dfs.sh
sbin/start-yarn.sh
执行WordCount程序 hadoop jar wc.jar com.atguigu.mapreduce.wordcount.WordCountDriver /user/atguigu/input /user/atguigu/output
- 序列化就是把内存中的对象,转换成字节序列(或其他数据传输协议)以便于存储到磁盘(持久化)和网络传输。
- 反序列化就是将收到字节序列(或其他数据传输协议)或者是磁盘的持久化数据,转换成内存中的对象。
- 序列化可以存储“活动的对象”,可以将“活的”对象发送到远程计算机。
- Java的序列化是一个重量级序列化框架(Serializable),一个对象被序列化后,会附带很多额外的信息(各种校验信息,Header,继承体系等),不便于在网络中高效传输。所以,Hadoop自己开发了一套序列化机制(Writable)。
统计每一个手机号耗费的总上行流量、总下行流量、总流量
编写mapreduce程序
编写流量统计的Bean对象
package com.atguigu.mapreduce.writable;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
//1 继承Writable接口
public class FlowBean implements Writable {
private long upFlow; //上行流量
private long downFlow; //下行流量
private long sumFlow; //总流量
//2 提供无参构造
public FlowBean() {
}
//3 提供三个参数的getter和setter方法
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;
}
public void setSumFlow() {
this.sumFlow = this.upFlow + this.downFlow;
}
//4 实现序列化和反序列化方法,注意顺序一定要保持一致
@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 重写ToString
@Override
public String toString() {
return upFlow + "t" + downFlow + "t" + sumFlow;
}
}
;
编写Mapper类
package com.atguigu.mapreduce.writable; 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{ private Text outK = new Text(); private FlowBean outV = new FlowBean(); @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { //1 获取一行数据,转成字符串 String line = value.toString(); //2 切割数据 String[] split = line.split("t"); //3 抓取我们需要的数据:手机号,上行流量,下行流量 String phone = split[1]; String up = split[split.length - 3]; String down = split[split.length - 2]; //4 封装outK outV outK.set(phone); outV.setUpFlow(Long.parseLong(up)); outV.setDownFlow(Long.parseLong(down)); outV.setSumFlow(); //5 写出outK outV context.write(outK, outV); } }
;
编写Reducer类
package com.atguigu.mapreduce.writable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; public class FlowReducer extends Reducer{ private FlowBean outV = new FlowBean(); @Override protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { long totalUp = 0; long totalDown = 0; //1 遍历values,将其中的上行流量,下行流量分别累加 for (FlowBean flowBean : values) { totalUp += flowBean.getUpFlow(); totalDown += flowBean.getDownFlow(); } //2 封装outKV outV.setUpFlow(totalUp); outV.setDownFlow(totalDown); outV.setSumFlow(); //3 写出outK outV context.write(key,outV); } }
;
package com.atguigu.mapreduce.writable;
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 {
//1 获取job对象
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//2 关联本Driver类
job.setJarByClass(FlowDriver.class);
//3 关联Mapper和Reducer
job.setMapperClass(FlowMapper.class);
job.setReducerClass(FlowReducer.class);
//4 设置Map端输出KV类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
//5 设置程序最终输出的KV类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
//6 设置程序的输入输出路径
FileInputFormat.setInputPaths(job, new Path("D:\inputflow"));
FileOutputFormat.setOutputPath(job, new Path("D:\flowoutput"));
//7 提交Job
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}



