Spark，流量统计案例

最新推荐文章于 2025-12-10 22:10:48 发布

原创最新推荐文章于 2025-12-10 22:10:48 发布 · 427 阅读

8 ·

CC 4.0 BY-SA版权

文章标签：

#spark #大数据 #分布式

拥有一个文件，其中文件内容(内容随便写符合规矩即可)分别为电话号码上行流量下行流量(第一行是写给大家看的注释不用写出来)

提前创好一个文件夹分为四个类

FlowBean中的代码内容为：

package org.example.flow;

import org.apache.hadoop.io.Writable;

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

//hadoop 序列化
//三个属性：手机号，上行流量，下行流量
public class FlowBean implements Writable {
private String phone;
private Long upFlow;
private Long downFlow;

public FlowBean(String phone, Long upFlow, Long downFlow) {
this.phone = phone;
this.upFlow = upFlow;
this.downFlow = downFlow;
}
//定义get/set方法
public String getPhone() {
return phone;
}
public void setPhone(String phone) {
this.phone = phone;
}
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;
}

//定义无参结构
public FlowBean() {}
//定义一个获取总流量的方法
public Long getTotalFlow(){
return upFlow+downFlow;
}

@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeUTF(phone);
dataOutput.writeLong(upFlow);
dataOutput.writeLong(downFlow);

}

@Override
public void readFields(DataInput dataInput) throws IOException {
phone = dataInput.readUTF();
upFlow = dataInput.readLong();
downFlow = dataInput.readLong();

}
}