Bootstrap

Hadoop之mapreduce学习笔记,一天攻关过期末第二弹

序列化:这个意思就是把需要处理的数据转化为字节序列,以便于传输,java中有自己的序列化框架,但是java是重量级的框架,一个对象被序列化后,会附带很多额外信息(校验信息,继承体等),这些信息是mapreduce用不着的,所以只需要简单的序列化就行。

开发中往往常用的基本序列化类型不能满足所有需求比如Hadoop框架内部传递一个bean对象,那么该对象就需要实现序列化接口。

 

具体实现bean对象序列化步骤如下7步

(1)必须实现Writable接口

(2)反序列化时,需要反射调用空参构造函数,所以必须有空参构造

public FlowBean() {

super();

}

(3)重写序列化方法

@Override

public void write(DataOutput out) throws IOException {

out.writeLong(upFlow);

out.writeLong(downFlow);

out.writeLong(sumFlow);

}

(4)重写反序列化方法

@Override

public void readFields(DataInput in) throws IOException {

upFlow = in.readLong();

downFlow = in.readLong();

sumFlow = in.readLong();

}

(5)注意反序列化的顺序和序列化的顺序完全一致

(6)要想把结果显示在文件中,需要重写toString(),可用”\t”分开,方便后续用。

(7)如果需要将自定义的bean放在key中传输,则还需要实现Comparable接口,因为MapReduce框中的Shuffle过程要求对key必须能排序。

@Override

public int compareTo(FlowBean o) {

// 倒序排列,从大到小

return this.sumFlow > o.getSumFlow() ? -1 : 1;

}

 看一个案例:统计手机的上行流量、下行流量、总流量。难点在于KV值中,value需要定义为一个单独的对象,这样才能进行数据传输。

编写程序:

(1)编写流量统计的Bean对象

package com.atguigu.mapreduce.flowsum;

import java.io.DataInput;

import java.io.DataOutput;

import java.io.IOException;

import org.apache.hadoop.io.Writable;

// 1 实现writable接口

public class FlowBean implements Writable{

private long upFlow;

private long downFlow;

private long sumFlow;

//2  反序列化时,需要反射调用空参构造函数,所以必须有

public FlowBean() {

super();

}

public FlowBean(long upFlow, long downFlow) {

super();

this.upFlow = upFlow;

this.downFlow = downFlow;

this.sumFlow = upFlow + downFlow;

}

//3  写序列化方法

@Override

public void write(DataOutput out) throws IOException {

out.writeLong(upFlow);

out.writeLong(downFlow);

out.writeLong(sumFlow);

}

//4 反序列化方法

//5 反序列化方法读顺序必须和写序列化方法的写顺序必须一致

@Override

public void readFields(DataInput in) throws IOException {

this.upFlow  = in.readLong();

this.downFlow = in.readLong();

this.sumFlow = in.readLong();

}

// 6 编写toString方法,方便后续打印到文本

@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;

}

}

(2)编写Mapper类

package com.atguigu.mapreduce.flowsum;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean>{

FlowBean v = new FlowBean();

Text k = new Text();

@Override

protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

// 1 获取一行

String line = value.toString();

// 2 切割字段

String[] fields = line.split("\t");

// 3 封装对象

// 取出手机号码

String phoneNum = fields[1];

// 取出上行流量和下行流量

long upFlow = Long.parseLong(fields[fields.length - 3]);

long downFlow = Long.parseLong(fields[fields.length - 2]);

k.set(phoneNum);

v.set(downFlow, upFlow);

// 4 写出

context.write(k, v);

}

}

(3)编写Reducer类

package com.atguigu.mapreduce.flowsum;

import java.io.IOException;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Reducer;

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

@Override

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

long sum_upFlow = 0;

long sum_downFlow = 0;

// 1 遍历所用bean,将其中的上行流量,下行流量分别累加

for (FlowBean flowBean : values) {

sum_upFlow += flowBean.getUpFlow();

sum_downFlow += flowBean.getDownFlow();

}

// 2 封装对象

FlowBean resultBean = new FlowBean(sum_upFlow, sum_downFlow);

// 3 写出

context.write(key, resultBean);

}

}

(4)编写Driver驱动类

package com.atguigu.mapreduce.flowsum;

import java.io.IOException;

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;

public class FlowsumDriver {

public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {

// 输入输出路径需要根据自己电脑上实际的输入输出路径设置

args = new String[] { "e:/input/inputflow", "e:/output1" };

// 1 获取配置信息,或者job对象实例

Configuration configuration = new Configuration();

Job job = Job.getInstance(configuration);

// 6 指定本程序的jar包所在的本地路径

job.setJarByClass(FlowsumDriver.class);

// 2 指定本业务job要使用的mapper/Reducer业务类

job.setMapperClass(FlowCountMapper.class);

job.setReducerClass(FlowCountReducer.class);

// 3 指定mapper输出数据的kv类型

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(FlowBean.class);

// 4 指定最终输出的数据的kv类型

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(FlowBean.class);

// 5 指定job的输入原始文件所在目录

FileInputFormat.setInputPaths(job, new Path(args[0]));

FileOutputFormat.setOutputPath(job, new Path(args[1]));

// 7 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 result = job.waitForCompletion(true);

System.exit(result ? 0 : 1);

}

}

MapTask并行度决定机制

数据块:BlockHDFS物理把数据分成一块一块。

数据切片:数据切片只是在逻辑上对输入进行分片,并不会在磁盘上将其切分成片进行存储

  

;