统计每一个手机号全年的总话费(注意,虚拟网包月费属于赠送费,不计入在内)。
数据准备:
流程:
(1)读取一行数据,切分字段;
(2)抽取手机号、套餐基本费、语音通信费、短信彩信费、流量费;
(3)以手机号为key,bean对象为value输出,即context.write(手机号,bean)。
Reduce阶段:
(1)累加套餐基本费、语音通信费、短信彩信费、流量费得到总花费;
(2)实现自定义的bean来封装流量信息,并将bean作为map输出的key来传输;
(3) MR程序在处理数据的过程中会对数据排序(map输出的kv对传输到reduce之前,会排序),排序的依据是map输出的key。
程序设计:
(1)编写流量统计的bean对象
package com.csdn.TelFee;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class Phone implements Writable {
private int baseFee;//基础费用
private int viceFee;//语音费用
private int msgFee;//短信费用
private int floeFee;//流量费用
private int sumFee;//共计费用
public Phone() {
}
public Phone(int baseFee, int viceFee, int msgFee, int floeFee) {
this.baseFee = baseFee;
this.viceFee = viceFee;
this.msgFee = msgFee;
this.floeFee = floeFee;
this.sumFee = baseFee+viceFee+msgFee+floeFee;
}
public int getBaseFee() {
return baseFee;
}
public void setBaseFee(int baseFee) {
this.baseFee = baseFee;
}
public int getViceFee() {
return viceFee;
}
public void setViceFee(int viceFee) {
this.viceFee = viceFee;
}
public int getMsgFee() {
return msgFee;
}
public void setMsgFee(int msgFee) {
this.msgFee = msgFee;
}
public int getFloeFee() {
return floeFee;
}
public void setFloeFee(int floeFee) {
this.floeFee = floeFee;
}
public int getSumFee() {
return sumFee;
}
public void setSumFee(int sumFee) {
this.sumFee = sumFee;
}
public void write(DataOutput out) throws IOException {
out.writeInt(baseFee);
out.writeInt(viceFee);
out.writeInt(msgFee);
out.writeInt(floeFee);
out.writeInt(sumFee);
}
public void readFields(DataInput in) throws IOException {
baseFee=in.readInt();
viceFee=in.readInt();
msgFee=in.readInt();
floeFee=in.readInt();
sumFee=in.readInt();
}
@Override
public String toString() {
return baseFee+"\t"+viceFee+"\t"+msgFee+"\t"+floeFee+"\t"+sumFee;
}
}
(2)编写mapper
package com.csdn.TelFee;
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,Text,Phone> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
A 13939119984 3 5 7 8 20 201901
String[] allArr = line.split("\t");
String num=allArr[1];
Phone phone =new Phone(
Integer.parseInt(allArr[2]),//基础费
Integer.parseInt(allArr[3]),//语音费
Integer.parseInt(allArr[4]),//短信
Integer.parseInt(allArr[5]));//流量
context.write(new Text(num),phone);
}
}
(3)编写reducer
package com.csdn.TelFee;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class myReducer extends Reducer<Text,Phone,Text,Phone> {
@Override
protected void reduce(Text key, Iterable<Phone> values, Context context) throws IOException, InterruptedException {
int baseSum=0;
int viceSum=0;
int msgSum=0;
int flowSum=0;
for (Phone value : values) {
baseSum+=value.getBaseFee();
viceSum+=value.getViceFee();
msgSum+=value.getMsgFee();
flowSum+=value.getFloeFee();
}
Phone phone = new Phone(baseSum,viceSum,msgSum,flowSum);
context.write(key,phone);
}
}
(4)编写驱动
package com.csdn.TelFee;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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 myDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(myDriver.class);
job.setMapperClass(myMapper.class);
job.setReducerClass(myReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Phone.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Phone.class);
FileInputFormat.setInputPaths(job,new Path("F:\\int\\phoneFee.txt"));
FileSystem fs = FileSystem.get(conf);
Path outPath= new Path("F:\\out\\free");
boolean b = fs.exists(outPath);
if (b) fs.delete(outPath,true);
FileOutputFormat.setOutputPath(job,outPath);
job.submit();
}
}
数据处理后的结果: