大数据学习（八）：mapreduce编程案例-计算每个手机号访问网站请求流量、相应流量和流量总和根据手机号判断省份进行分类
数据类型
作者：qq_33252988
数据顺序依次为:时间戳、手机号、mark地址、ip地址、访问地址、网站类型、请求时间、响应时间、请求流量、响应流量、状态
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
自定义数据类型如何实现hadoop的序列化接口？
1、实现Writable接口
2、保留空参构造函数
3、write方法中输出字段二进制数据的顺序要与readFields方法读取数据的顺序一致
package com.bigdata.mapreduce.flow;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
/**
* 自定义数据类型如何实现hadoop的序列化接口
* 1、实现Writable接口
* 2、保留空参构造函数
* 3、write方法中输出字段二进制数据的顺序要与readFields方法读取数据的顺序一致
* @author 90669
*
*/
public class FlowBean implements Writable{
//请求流量
private int upFlow;
//响应流量
private int dFlow;
//电话
private String phone;
//总流量
private int amountFlow;
public FlowBean(){}
public FlowBean(String phone, int upFlow, int dFlow) {
this.phone = phone;
this.upFlow = upFlow;
this.dFlow = dFlow;
this.amountFlow = upFlow + dFlow;
}
public String getPhone() {
return phone;
}
public void setPhone(String phone) {
this.phone = phone;
}
public int getUpFlow() {
return upFlow;
}
public void setUpFlow(int upFlow) {
this.upFlow = upFlow;
}
public int getdFlow() {
return dFlow;
}
public void setdFlow(int dFlow) {
this.dFlow = dFlow;
}
public int getAmountFlow() {
return amountFlow;
}
public void setAmountFlow(int amountFlow) {
this.amountFlow = amountFlow;
}
/**
* hadoop系统在序列化该类的对象时要调用的方法
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeInt(upFlow);
out.writeUTF(phone);
out.writeInt(dFlow);
out.writeInt(amountFlow);
}
/**
* hadoop系统在反序列化该类的对象时要调用的方法
*/
@Override
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readInt();
this.phone = in.readUTF();
this.dFlow = in.readInt();
this.amountFlow = in.readInt();
}
@Override
public String toString() {
return this.phone + ","+this.upFlow +","+ this.dFlow +"," + this.amountFlow;
}
}
package com.bigdata.mapreduce.flow;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class FlowCountMapper extends Mapper {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] fields = line.split("\t");
// 电话
String phone = fields[1];
int upFlow = Integer.parseInt(fields[fields.length - 3]);
int dFlow = Integer.parseInt(fields[fields.length - 2]);
context.write(new Text(phone), new FlowBean(phone, upFlow, dFlow));
}
}
package com.bigdata.mapreduce.flow;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowCountReducer extends Reducer{
@Override
protected void reduce(Text key, Iterable values, Context context)
throws IOException, InterruptedException {
int upSum = 0;
int dSum = 0;
for (FlowBean flowBean : values) {
upSum+=flowBean.getUpFlow();
dSum+=flowBean.getdFlow();
}
context.write(new Text(key), new FlowBean(key.toString(),upSum,dSum));
}
}
package com.bigdata.mapreduce.flow;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
public class JobSubmitter {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(JobSubmitter.class);
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
FileInputFormat.setInputPaths(job, new Path("D:\\mrdata\\flow\\input"));
FileOutputFormat.setOutputPath(job, new Path("D:\\mrdata\\flow\\output"));
job.waitForCompletion(true);
}
}
运算结果
13480253104 13480253104,180,180,360
13502468823 13502468823,7335,110349,117684
13560436666 13560436666,1116,954,2070
13560439658 13560439658,2034,5892,7926
13602846565 13602846565,1938,2910,4848
13660577991 13660577991,6960,690,7650
13719199419 13719199419,240,0,240
13726230503 13726230503,2481,24681,27162
13726238888 13726238888,2481,24681,27162
13760778710 13760778710,120,120,240
13826544101 13826544101,264,0,264
13922314466 13922314466,3008,3720,6728
13925057413 13925057413,11058,48243,59301
13926251106 13926251106,240,0,240
13926435656 13926435656,132,1512,1644
15013685858 15013685858,3659,3538,7197
15920133257 15920133257,3156,2936,6092
15989002119 15989002119,1938,180,2118
18211575961 18211575961,1527,2106,3633
18320173382 18320173382,9531,2412,11943
84138413 84138413,4116,1432,5548
案例:根据手机号判断省并进行分组
package com.bigdata.mapreduce.flow;
import java.util.HashMap;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
/**
* 本类是提供给MapTask用的
* MapTask通过这个类的getPartition方法，来计算它所产生的每一对kv数据该分发给哪一个reduce task
* @author ThinkPad
*
*/
public class ProvincePartitioner extends Partitioner{
static HashMap codeMap = new HashMap();
static{
codeMap.put("135", 0);
codeMap.put("136", 1);
codeMap.put("137", 2);
codeMap.put("138", 3);
codeMap.put("139", 4);
}
@Override
public int getPartition(Text key, FlowBean value, int numPartitions) {
//获取手机号前三位进行比对进行分类
Integer code = codeMap.get(key.toString().substring(0, 3));
return code==null?5:code;
}
}
package com.bigdata.mapreduce.flow;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
public class JobSubmitter {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(JobSubmitter.class);
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
// 设置参数：maptask在做数据分区时，用哪个分区逻辑类 （如果不指定，它会用默认的HashPartitioner）
job.setPartitionerClass(ProvincePartitioner.class);
// 由于我们的ProvincePartitioner可能会产生6种分区号，所以，需要有6个reduce task来接收
job.setNumReduceTasks(6);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
FileInputFormat.setInputPaths(job, new Path("D:\\mrdata\\flow\\input"));
FileOutputFormat.setOutputPath(job, new Path("D:\\mrdata\\flow\\province-output"));
job.waitForCompletion(true);
}
}
输出结果
13502468823 13502468823,7335,110349,117684
13560436666 13560436666,1116,954,2070
13560439658 13560439658,2034,5892,7926
作者：qq_33252988
