MapReduce编程之流量分析
data_flow.dat文件内容如下:
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 游戏娱乐 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 jd.com 京东购物 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 taobao.com 淘宝购物 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 cnblogs.com 技术门户 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 未知 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 sougou.com 综合门户 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 baidu.com 综合搜索 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 zhilian.com 招聘门户 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 csdn.net 技术门户 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 图片大全 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 http://youku.com/ 视频网站 2 2 120 120 200
1363157985079 13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 img.qfc.cn 图片浏览 6 3 360 180 200
1363157985069 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 www.baidu.com 综合门户 18 138 1080 186852 200
1363157985059 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 www.baidu.com 综合门户 19 128 1177 16852 200
要求1:统计每个手机号的上行数据包总和,下行数据包总和,上行流量总和,下行流量总和
代码实现:
自定义数据类型:
package com.miao.flow;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
* @ClassName FlowBean1
* @Description TODO 自定义数据类型,用于封装上行和下行信息
* @Date 2021-04-28 19:59:05
* @Create By Miao
*/
public class FlowBean1 implements Writable {
private long upPack;
private long downPack;
private long upFlow;
private long downFlow;
public void setAll(long upPack, long downPack, long upFlow, long downFlow) {
this.setUpPack(upPack);
this.setDownPack(downPack);
this.setUpFlow(upFlow);
this.setDownFlow(downFlow);
}
public long getUpPack() {
return upPack;
}
public void setUpPack(long upPack) {
this.upPack = upPack;
}
public long getDownPack() {
return downPack;
}
public void setDownPack(long downPack) {
this.downPack = downPack;
}
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;
}
@Override
public String toString() {
return this.upPack + "\t" + this.downPack + "\t" + this.upFlow + "\t" + this.downFlow;
}
public void write(DataOutput out) throws IOException {
out.writeLong(this.upPack);
out.writeLong(this.downPack);
out.writeLong(this.upFlow);
out.writeLong(this.downFlow);
}
public void readFields(DataInput in) throws IOException {
this.upPack = in.r