MapReduce编程小案例.1st—求取手机号码上下限及总流量
利用MapReduce处理一个小案例，如下是一批手机号码上网所保存在日志的流量信息：
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
设计Mapper类
package cn.edu360.mr.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<LongWritable, Text, Text, FlowBean>{
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] fields = line.split("\t");
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));
}
}
设计Reducer类
package cn.edu360.mr.flow;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Reducer<Text, FlowBean, Text, FlowBean>.Context context)
throws IOException, InterruptedException {
int upSum = 0;
int dSum = 0;
for (FlowBean value : values) {
upSum += value.getUpFlow();
dSum += value.getdFlow();
}
context.write(key, new FlowBean(key.toString(), upSum, dSum));
}
}
创建一个类封装【手机号码以及流量的信息】，要注意实现序列化
package cn.edu360.mr.flow;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class FlowBean implements Writable{
private int upFlow;
private int dFlow;
private String phone;
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 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 String getPhone() {
return phone;
}
public void setPhone(String phone) {
this.phone = phone;
}
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
*/
//反序列化
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readInt();
this.phone = in.readUTF();
this.dFlow = in.readInt();
this.amountFlow = in.readInt();
}
//序列化
public void write(DataOutput out) throws IOException {
out.writeInt(upFlow);
out.writeUTF(phone);
out.writeInt(dFlow);
out.writeInt(amountFlow);
}
@Override
public String toString() {
return this.phone + "," + this.upFlow + "," + this.dFlow + "," + this.amountFlow;
}
}
PS：添加一个新的功能，覆写一下MapTask分配kv给ReduceTask的规则
package cn.edu360.mr.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数据该分发哪一个reduce task
* @author Downey
*/
public class ProvincePartitioner extends Partitioner<Text, FlowBean>{
static HashMap<String, Integer> codeMap = new HashMap<String, Integer>();
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) {
Integer code = codeMap.get(key.toString().substring(0, 3));
return code == null?5:code;
}
}
最后实现JobSubmitter类的设计
package cn.edu360.mr.flow;
import java.io.IOException;
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 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(如果不指定的话，它会默认的HashPartitioner)
job.setPartitionerClass(ProvincePartitioner.class);
//由于我们的ProvincePartitioner可能会产生6种分区号，
job.setNumReduceTasks(6);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
FileInputFormat.setInputPaths(job, new Path("F:\\mrdata\\flow\\input"));
FileOutputFormat.setOutputPath(job, new Path("F:\\mrdata\\flow\\province-output"));
job.waitForCompletion(true);
}
}