尚硅谷大数据技术之Hadoop(MapReduce)(新)第7章 MapReduce扩展案例

发布时间:2018年10月26日作者:yafei浏览次数:825

7.2 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

2.需求分析

3.实现代码

(1)编写FlowBean类

package com.atguigu.mr.top;

 

import java.io.DataInput;

import java.io.DataOutput;

import java.io.IOException;

 

import org.apache.hadoop.io.WritableComparable;

 

public class FlowBean implements WritableComparable<FlowBean>{

 

private long upFlow;

private long downFlow;

private long sumFlow;

public FlowBean() {

super();

}

 

public FlowBean(long upFlow, long downFlow) {

super();

this.upFlow = upFlow;

this.downFlow = downFlow;

}

 

@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 {

upFlow = in.readLong();

downFlow = in.readLong();

sumFlow = in.readLong();

}

 

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 String toString() {

return upFlow + “\t” + downFlow + “\t” + sumFlow;

}

 

public void set(long downFlow2, long upFlow2) {

downFlow = downFlow2;

upFlow = upFlow2;

sumFlow = downFlow2 + upFlow2;

}

 

@Override

public int compareTo(FlowBean bean) {

int result;

if (this.sumFlow > bean.getSumFlow()) {

result = -1;

}else if (this.sumFlow < bean.getSumFlow()) {

result = 1;

}else {

result = 0;

}

return result;

}

}

(2)编写TopNMapper类

package com.atguigu.mr.top;

 

import java.io.IOException;

import java.util.Iterator;

import java.util.TreeMap;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

 

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

// 定义一个TreeMap作为存储数据的容器(天然按key排序)

private TreeMap<FlowBean, Text> flowMap = new TreeMap<FlowBean, Text>();

private FlowBean kBean;

@Override

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

kBean = new FlowBean();

Text v = new Text();

// 1 获取一行

String line = value.toString();

// 2 切割

String[] fields = line.split(“\t”);

// 3 封装数据

String phoneNum = fields[0];

long upFlow = Long.parseLong(fields[1]);

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

long sumFlow = Long.parseLong(fields[3]);

kBean.setDownFlow(downFlow);

kBean.setUpFlow(upFlow);

kBean.setSumFlow(sumFlow);

v.set(phoneNum);

// 4 向TreeMap中添加数据

flowMap.put(kBean, v);

// 5 限制TreeMap的数据量,超过10条就删除掉流量最小的一条数据

if (flowMap.size() > 10) {

// flowMap.remove(flowMap.firstKey());

flowMap.remove(flowMap.lastKey());

}

}

@Override

protected void cleanup(Context context) throws IOException, InterruptedException {

// 6 遍历treeMap集合,输出数据

Iterator<FlowBean> bean = flowMap.keySet().iterator();

 

while (bean.hasNext()) {

 

FlowBean k = bean.next();

 

context.write(k, flowMap.get(k));

}

}

}

(3)编写TopNReducer类

package com.atguigu.mr.top;

 

import java.io.IOException;

import java.util.Iterator;

import java.util.TreeMap;

 

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Reducer;

 

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

 

// 定义一个TreeMap作为存储数据的容器(天然按key排序)

TreeMap<FlowBean, Text> flowMap = new TreeMap<FlowBean, Text>();

 

@Override

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

 

for (Text value : values) {

 

 FlowBean bean = new FlowBean();

 bean.set(key.getDownFlow(), key.getUpFlow());

 

 // 1 向treeMap集合中添加数据

flowMap.put(bean, new Text(value));

 

// 2 限制TreeMap数据量,超过10条就删除掉流量最小的一条数据

if (flowMap.size() > 10) {

// flowMap.remove(flowMap.firstKey());

flowMap.remove(flowMap.lastKey());

}

}

}

 

@Override

protected void cleanup(Reducer<FlowBean, Text, Text, FlowBean>.Context context) throws IOException, InterruptedException {

 

// 3 遍历集合,输出数据

Iterator<FlowBean> it = flowMap.keySet().iterator();

 

while (it.hasNext()) {

 

FlowBean v = it.next();

 

context.write(new Text(flowMap.get(v)), v);

}

}

}

(4)编写TopNDriver类

package com.atguigu.mr.top;

 

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 TopNDriver {

 

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

args  = new String[]{“e:/output1″,”e:/output3”};

// 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(TopNDriver.class);

 

// 2 指定本业务job要使用的mapper/Reducer业务类

job.setMapperClass(TopNMapper.class);

job.setReducerClass(TopNReducer.class);

 

// 3 指定mapper输出数据的kv类型

job.setMapOutputKeyClass(FlowBean.class);

job.setMapOutputValueClass(Text.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);

}

}

 

 


上一篇:
下一篇:
相关课程

java培训 大数据培训 前端培训 UI/UE设计培训

关于尚硅谷
教育理念
名师团队
学员心声
资源下载
视频下载
资料下载
工具下载
加入我们
招聘岗位
岗位介绍
招贤纳师
联系我们
全国统一咨询电话:010-56253825
地址:北京市昌平区宏福科技园2号楼3层(北京校区)

深圳市宝安区西部硅谷大厦B座C区一层(深圳校区)

上海市松江区谷阳北路166号大江商厦6层(上海校区)

武汉市东湖高新开发区东湖网谷(武汉校区)

西安市高新区和发智能大厦(西安校区)