流量汇总程序案例
需求1:统计手机号耗费的总上行流量、下行流量、总流量(序列化)
1)需求:
统计每一个手机号耗费的总上行流量、下行流量、总流量
2)数据准备
phone_data.txt
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 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 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 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 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 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 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 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 2 2 120 120 200
1363157985066 13726238888 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157993055 13560436666 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
输入数据格式:
1363157993055 13560436666 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
手机号码 上行流量 下行流量
输出数据格式
13560436666 1116 954 2070
手机号码 上行流量 下行流量 总流量
3)分析
基本思路:
Map阶段:
(1)读取一行数据,切分字段
(2)抽取手机号、上行流量、下行流量
(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)累加上行流量和下行流量得到总流量。
(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
所以,我们如果要实现自己需要的排序规则,则可以考虑将排序因素放到key中,让key实现接口:WritableComparable。
然后重写key的compareTo方法。
4)编写mapreduce程序
(1)编写流量统计的bean对象
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
// bean对象要实例化
public class FlowBean implements Writable {
private long upFlow;
private long downFlow;
private long sumFlow;
// 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;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = 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;
}
/**
* 序列化方法
* @param out
* @throws IOException
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
/**
* 反序列化方法
* 注意反序列化的顺序和序列化的顺序完全一致
* @param in
* @throws IOException
*/
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
downFlow = in.readLong();
sumFlow = in.readLong();
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
}
(2)编写mapreduce主程序
FlowMapper:
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
FlowBean bean = new FlowBean();
Text k = new Text();
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// 1 获取一行数据
String line = value.toString();
// 2 截取字段
String[] fields = line.split("\t");
// 3 封装bean对象以及获取电话号
String phoneNum = fields[1];
long upFlow = Long.parseLong(fields[fields.length - 3]);
long downFlow = Long.parseLong(fields[fields.length - 2]);
bean.set(upFlow, downFlow);
k.set(phoneNum);
// 4 写出去
context.write(k, bean);
}
}
FlowReducer:
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context)
throws IOException, InterruptedException {
// 1 计算总的流量
long sum_upFlow = 0;
long sum_downFlow = 0;
for (FlowBean bean : values) {
sum_upFlow += bean.getUpFlow();
sum_downFlow += bean.getDownFlow();
}
// 2 输出
context.write(key, new FlowBean(sum_upFlow, sum_downFlow));
}
}
FlowDriver:
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 FlowDriver {
public static void main(String[] args) throws Exception {
// 1 获取job信息
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 获取jar的存储路径
job.setJarByClass(FlowDriver.class);
// 3 关联map和reduce的class类
job.setMapperClass(FlowMapper.class);
job.setReducerClass(FlowReducer.class);
// 4 设置map阶段输出的key和value类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
// 5 设置最后输出数据的key和value类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
// 6 设置输入数据的路径 和输出数据的路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
(3)将程序打成jar包,然后拷贝到hadoop集群中。
(4)启动hadoop集群
(5)执行flowcount程序
hadoop jar flowcount.jar com.atguigu.mr.flowsum.FlowDriver /user/atguigu/flowcount/input/ /user/atguigu/flowcount/output
(6)查看结果
hadoop fs -cat /user/atguigu/flowcount/output/part-r-00000
13480253104 FlowBean upFlow=180 downFlow=180 sumFlow=360
13502468823 FlowBean upFlow=7335 downFlow=110349 sumFlow=117684
13560436666 FlowBean upFlow=1116 downFlow=954 sumFlow=2070
13560439658 FlowBean upFlow=2034 downFlow=5892 sumFlow=7926
13602846565 FlowBean upFlow=1938 downFlow=2910 sumFlow=4848
需求2:将统计结果按照手机归属地不同省份输出到不同文件中(Partitioner)
0)需求:将统计结果按照手机归属地不同省份输出到不同文件中(分区)
1)数据准备
phone_data.txt
2)分析
(1)Mapreduce中会将map输出的kv对,按照相同key分组,然后分发给不同的reducetask。默认的分发规则为:根据key的hashcode%reducetask数来分发
(2)如果要按照我们自己的需求进行分组,则需要改写数据分发(分组)组件Partitioner
自定义一个CustomPartitioner继承抽象类:Partitioner
(3)在job驱动中,设置自定义partitioner: job.setPartitionerClass(CustomPartitioner.class)
3)在需求1的基础上,增加一个分区类
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
public class FlowPartitioner extends Partitioner<Text, FlowBean>{
@Override
public int getPartition(Text key, FlowBean value, int numPartitions) {
// 1 需求:根据电话号码的前3位是几来分区
// 拿到电话号码的前3位
String phoneNum = key.toString().substring(0, 3);
int partitions = 4;
if ("135".equals(phoneNum)) {
partitions = 0;
}else if ("136".equals(phoneNum)) {
partitions = 1;
}else if ("137".equals(phoneNum)) {
partitions = 2;
}else if ("138".equals(phoneNum)) {
partitions = 3;
}
return partitions;
}
}
2)在驱动函数中增加自定义数据分区设置和reduce task设置
// 8 指定自定义数据分区
job.setPartitionerClass(ProvincePartitioner.class);
// 9 同时指定相应数量的reduce task
job.setNumReduceTasks(5);
3)将程序打成jar包,然后拷贝到hadoop集群中。
4)启动hadoop集群
5)执行flowcountPartitionser程序
hadoop jar flowcountPartitionser.jar com.atguigu.mr.partitioner.FlowCount /user/atguigu/flowcount/input /user/atguigu/flowcount/output
6)查看结果
hadoop fs -lsr /
/user/atguigu/flowcount/output/part-r-00000
/user/atguigu/flowcount/output/part-r-00001
/user/atguigu/flowcount/output/part-r-00002
/user/atguigu/flowcount/output/part-r-00003
/user/atguigu/flowcount/output/part-r-00004
需求3:将统计结果按照总流量倒序排序(排序)
0)需求
根据需求1产生的结果再次对总流量进行排序。
1)数据准备
phone_data.txt
2)分析
(1)把程序分两步走,第一步正常统计总流量,第二步再把结果进行排序
(2)context.write(总流量,手机号)
(3)FlowBean实现WritableComparable接口重写compareTo方法
@Override
public int compareTo(FlowBean o) {
// 倒序排列,从大到小
return this.sumFlow > o.getSumFlow() ? -1 : 1;
}
3)FlowBean对象在在需求1基础上增加了比较功能
FlowBean :
package com.atguigu.mapreduce.flowsort;
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; // 上行流量
private long downFlow; // 下行流量
private long sumFlow; // 总流量
// 反序列化时,需要空参构造
public FlowBean() {
super();
}
public FlowBean(long upFlow, long downFlow) {
super();
this.upFlow = upFlow;
this.downFlow = downFlow;
this.sumFlow = upFlow + downFlow;
}
public void set(long upFlow, long downFlow) {
this.upFlow = upFlow;
this.downFlow = downFlow;
this.sumFlow = upFlow + downFlow;
}
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;
}
// 序列化
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
// 反序列化
@Override
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readLong();
this.downFlow = in.readLong();
this.sumFlow = in.readLong();
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
// 排序
@Override
public int compareTo(FlowBean o) {
return this.sumFlow > o.getSumFlow() ? -1 : 1;
}
}
4)Map方法优化为一个对象,reduce方法则直接输出结果即可,驱动函数根据输入输出重写配置即可。
FlowSortMapper :
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
// 输入的数据:13480253104 180 180 360
public class FlowSortMapper extends Mapper<LongWritable, Text, FlowBean, Text>{
FlowBean bean = new FlowBean();
Text v = 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 截取字段
String[] fields = line.split("\t");
// 3 封装对象及获取电话号码
long upFlow = Long.parseLong(fields[1]);
long downFlow = Long.parseLong(fields[2]);
bean.set(upFlow, downFlow);
v.set(fields[0]);
// 4 写出去
context.write(bean, v);
}
}
FlowSortReducer:
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowSortReducer extends Reducer<FlowBean, Text, Text, FlowBean>{
@Override
protected void reduce(FlowBean bean, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
Text v = values.iterator().next();
context.write(v, bean);
}
}
FlowSortDriver:
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 FlowSortDriver {
public static void main(String[] args) throws Exception {
// 1 获取job信息
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 获取jar的存储路径
job.setJarByClass(FlowSortDriver.class);
// 3 关联map和reduce的class类
job.setMapperClass(FlowSortMapper.class);
job.setReducerClass(FlowSortReducer.class);
// 4 设置map阶段输出的key和value类型
job.setMapOutputKeyClass(FlowBean.class);
job.setMapOutputValueClass(Text.class);
// 5 设置最后输出数据的key和value类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
// 6 设置输入数据的路径 和输出数据的路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
5)将程序打成jar包,然后拷贝到hadoop集群中。
6)启动hadoop集群
7)执行flowcountsort程序
hadoop jar flowcountsort.jar com.atguigu.mr.sort.FlowCountSort /user/atguigu/flowcount/output /user/atguigu/flowcount/output_sort
8)查看结果
hadoop fs -cat /user/atguigu/flowcount/output_sort/part-r-00000
13502468823 7335 110349 117684
13925057413 11058 48243 59301
13726238888 2481 24681 27162
13726230503 2481 24681 27162
18320173382 9531 2412 11943