需要被统计流量的文件内容如下:
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
其中各个字段的解释如下,要统计手机号的上行流量,下行流量和总流量,其中总流量=上行流量+下行流量
代码如下:
FlowBean:
package com.gec.demo.bean; import org.apache.hadoop.io.Writable; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; /* * 序列化的类 * */ public class FlowBean implements Writable { //上行流量 private long upFlow; //下行流量 private long downFlow; //总流量 private long sumFlow; public FlowBean() { } public FlowBean(long upFlow, long downFlow, long sumFlow) { this.upFlow = upFlow; this.downFlow = downFlow; this.sumFlow = sumFlow; } public void setFlowData(long upFlow, long downFlow) { this.upFlow=upFlow; this.downFlow=downFlow; sumFlow=this.upFlow+this.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; } public long getSumFlow() { return sumFlow; } public void setSumFlow(long sumFlow) { this.sumFlow = sumFlow; } //序列化处理 @Override public void write(DataOutput out) throws IOException { out.writeLong(this.getUpFlow()); out.writeLong(this.getDownFlow()); out.writeLong(this.getSumFlow()); } //反列化处理 @Override public void readFields(DataInput in) throws IOException { setUpFlow(in.readLong()); setDownFlow(in.readLong()); setSumFlow(in.readLong()); } @Override public String toString() { return getUpFlow()+"\t"+getDownFlow()+"\t"+getSumFlow(); } }
Mapper:
package com.gec.demo; import com.gec.demo.bean.FlowBean; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.util.StringUtils; import java.io.IOException; /*< KEYIN VALUEIN KEYOUT VALUEOUT */ public class PhoneFlowMapper extends Mapper<LongWritable, Text,Text, FlowBean> { private FlowBean flowBean=new FlowBean(); private Text keyText=new Text(); @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { //获取行内容 String line=value.toString(); String []fields=StringUtils.split(line,‘\t‘); //获取手机号 String phoneNum=fields[1]; //获取上传流量数据 long upflow=Long.parseLong(fields[fields.length-3]); //获取下载流量数据 long downflow=Long.parseLong(fields[fields.length-2]); flowBean.setFlowData(upflow,downflow); keyText.set(phoneNum); context.write(keyText,flowBean); } }
Reducer:
package com.gec.demo; import com.gec.demo.bean.FlowBean; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; public class PhoneFlowReducer extends Reducer<Text, FlowBean,Text, FlowBean> { private FlowBean flowBean=new FlowBean(); /** *key:phonenum(电话号码) *values: */ @Override protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException { long sumDownFlow=0; long sumUpFlow=0; //统计每台手机所耗的总流量 for (FlowBean value : values) { sumUpFlow+=value.getUpFlow(); sumDownFlow+=value.getDownFlow(); } flowBean.setFlowData(sumUpFlow,sumDownFlow); context.write(key,flowBean); } }
Driver:
package com.gec.demo; import com.gec.demo.bean.FlowBean; 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.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import java.io.IOException; public class PhoneFlowApp { public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration configuration=new Configuration(); Job job=Job.getInstance(configuration); job.setJarByClass(PhoneFlowApp.class); //job.setJar(""); job.setMapperClass(PhoneFlowMapper.class); job.setReducerClass(PhoneFlowReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(FlowBean.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(FlowBean.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); //指定要处理的数据所在的位置 FileInputFormat.setInputPaths(job, "hdfs://hadoop-001:9000/flowcount/input/HTTP_20130313143750.dat"); //指定处理完成之后的结果所保存的位置 FileOutputFormat.setOutputPath(job, new Path("hdfs://hadoop-001:9000/flowcount/output/")); //向yarn集群提交这个job boolean res = job.waitForCompletion(true); System.exit(res?0:1); } }
生成文件的结果如下:
手机号 上行流量 下行流量 总流量
如果要按总流量的多少排序,并按手机号输出到六个不同的文件,有如下代码:
FlowBean:要实现WritableComparable接口
package com.gec.demo.Bean; import org.apache.hadoop.io.Writable; import org.apache.hadoop.io.WritableComparable; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; public class FlowBean implements WritableComparable<FlowBean> { //上行流量 private long upFlow; //下行流量 private long downFlow; //总流量 private long sumFlow; public FlowBean() { } 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; } public long getSumFlow() { return sumFlow; } public void setSumFlow(long sumFlow) { this.sumFlow = sumFlow; } public FlowBean(long upFlow, long downFlow, long sumFlow) { this.upFlow = upFlow; this.downFlow = downFlow; this.sumFlow = sumFlow; } public void setFlowData(long upFlow,long downFlow){ this.upFlow=upFlow; this.downFlow=downFlow; this.sumFlow=this.upFlow+this.downFlow; } @Override public String toString() { return getUpFlow()+" "+getDownFlow()+" "+getSumFlow(); } //序列化处理 @Override public void write(DataOutput dataOutput) throws IOException { dataOutput.writeLong(this.getUpFlow()); dataOutput.writeLong(this.getDownFlow()); dataOutput.writeLong(this.getSumFlow()); } //反序列化处理 @Override public void readFields(DataInput dataInput) throws IOException { setUpFlow(dataInput.readLong()); setDownFlow(dataInput.readLong()); setSumFlow(dataInput.readLong()); } @Override public int compareTo(FlowBean o) { if (o.getSumFlow()>this.getSumFlow()){ return 1; }else return -1; } }
//FlowPartitioner类继承Partitioner类,可以定义以什么开头的手机号输出到哪个文件
package com.gec.demo.partitioner; import com.gec.demo.Bean.FlowBean; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Partitioner; public class FlowPartitioner extends Partitioner<FlowBean,Text> { @Override public int getPartition(FlowBean flowBean, Text text, int i) { String phoneNum=text.toString(); String headThreePhoneNum=phoneNum.substring(0,3); if(headThreePhoneNum.equals("134")){ return 0; }else if(headThreePhoneNum.equals("135")){ return 1; }else if(headThreePhoneNum.equals("136")){ return 2; }else if(headThreePhoneNum.equals("137")){ return 3; }else if(headThreePhoneNum.equals("138")){ return 4; }else{ return 5; } } }
package com.gec.demo; import com.gec.demo.Bean.FlowBean; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.util.StringUtils; import org.mortbay.util.StringUtil; import java.io.IOException; public class PhoneFlowMapper extends Mapper<LongWritable, Text,FlowBean,Text> { private FlowBean flowBean=new FlowBean(); private Text text=new Text(); @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line=value.toString(); String[] fields= StringUtils.split(line,‘\t‘); String phoneNum=fields[1]; long upFlow=Long.parseLong(fields[fields.length-3]); long downFlow=Long.parseLong(fields[fields.length-2]); flowBean.setFlowData(upFlow,downFlow); flowBean.setSumFlow(upFlow+downFlow); text.set(phoneNum); context.write(flowBean,text); } }
package com.gec.demo; import com.gec.demo.Bean.FlowBean; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; public class PhoneFlowReducer extends Reducer<FlowBean,Text,Text,FlowBean> { private FlowBean flowBean=new FlowBean(); @Override protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException { //有没有分组合并操作? context.write(values.iterator().next(),key); } }
package com.gec.demo; import com.gec.demo.Bean.FlowBean; import com.gec.demo.partitioner.FlowPartitioner; 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.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import java.io.IOException; public class PhoneFlowApp { public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration configuration=new Configuration(); Job job=Job.getInstance(configuration); job.setJarByClass(PhoneFlowApp.class); job.setMapperClass(PhoneFlowMapper.class); job.setReducerClass(PhoneFlowReducer.class); job.setMapOutputKeyClass(FlowBean.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(FlowBean.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setPartitionerClass(FlowPartitioner.class); job.setNumReduceTasks(6); //指定要处理的数据所在的位置 FileInputFormat.setInputPaths(job, "D://Bigdata//4、mapreduce//day02//HTTP_20130313143750.dat"); //指定处理完成之后的结果所保存的位置 FileOutputFormat.setOutputPath(job, new Path("D://Bigdata//4、mapreduce//day02//output")); //向yarn集群提交这个job boolean res = job.waitForCompletion(true); System.exit(res?0:1); } }
原文地址:https://www.cnblogs.com/Transkai/p/10485257.html