pom.xml
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<hadoop.version>2.7.3</hadoop.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>${hadoop.version}</version>
</dependency>
</dependencies>
流量统计
13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
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
84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
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
13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
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
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
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
13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
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
13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
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
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
13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200
13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 6 3 360 180 200
13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 18 138 1080 186852 200
mapreduce编程要使用javaBean作为map或reduce的输入(输出)的key-value的参数类型要使用hadoop的序列化机制
hadoop的序列化机制
跟jdk自带的比较起来,更加精简,只传递对象中的数据,而不传递如继承结构等额外信息
要想让自定义的数据类型在hadoop集群中传递,需要实现hadoop的序列化接口Writable或者 WritableComparable<T>
自定义的数据类型bean实现了Writable接口后,要实现其中的两个方法
public void write(DataOutput out) throws IOException ----序列化,将数据写入字节流
以及
public void readFields(DataInput in) throws IOException ----反序列化,从字节流中读出数据
注意:
写入数据和读出数据的顺序和类型要保持一致
FlowBean.java
package com.test.hadoop.mr.flowcount;
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 String phoneNbr;
private long up_flow;
private long d_flow;
private long sum_flow;
public FlowBean() {
};
public void set(String phoneNbr, long up_flow, long d_flow) {
this.phoneNbr = phoneNbr;
this.up_flow = up_flow;
this.d_flow = d_flow;
this.sum_flow = up_flow + d_flow;
}
public String getPhoneNbr() {
return phoneNbr;
}
public void setPhoneNbr(String phoneNbr) {
this.phoneNbr = phoneNbr;
}
public long getUp_flow() {
return up_flow;
}
public void setUp_flow(long up_flow) {
this.up_flow = up_flow;
}
public long getD_flow() {
return d_flow;
}
public void setD_flow(long d_flow) {
this.d_flow = d_flow;
}
public long getSum_flow() {
return sum_flow;
}
public void setSum_flow(long sum_flow) {
this.sum_flow = sum_flow;
}
/**
* 序列化,将数据字段以字节流写出去
*/
@Override
public void write(DataOutput output) throws IOException {
output.writeUTF(phoneNbr);
output.writeLong(up_flow);
output.writeLong(d_flow);
output.writeLong(sum_flow);
}
/**
* 反序列化,从字节流中读出各个数据字段 读出的顺序应该跟序列化时写入的的顺序保持一致
*/
@Override
public void readFields(DataInput input) throws IOException {
phoneNbr = input.readUTF();
up_flow = input.readLong();
d_flow = input.readLong();
sum_flow = input.readLong();
}
@Override
public String toString() {
return up_flow + "\t" + d_flow + "\t" + sum_flow;
}
@Override
public int compareTo(FlowBean o) {
return sum_flow > o.getSum_flow() ? -1 : 1;
}
}
package com.test.hadoop.mr.flowcount;
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
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;
public class FlowCount {
public static class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
private FlowBean flowBean = new FlowBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
try {
// 拿到一行数据
String line = value.toString();
// 切分字段
String[] fields = StringUtils.split(line, "\t");
// 拿到我需要的若干个字段
String phoneNbr = fields[0];
long up_flow = Long.parseLong(fields[fields.length - 3]);
long d_flow = Long.parseLong(fields[fields.length - 2]);
// 将数据封装到一个flowbean中
flowBean.set(phoneNbr, up_flow, d_flow);
// 以手机号为key,将流量数据输出去
context.write(new Text(phoneNbr), flowBean);
} catch (Exception e) {
e.printStackTrace();
}
}
}
public static class FlowCouontReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
private FlowBean flowBean = new FlowBean();
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context)
throws IOException, InterruptedException {
long up_flow_sum = 0;
long d_flow_sum = 0;
for (FlowBean flowBean : values) {
up_flow_sum += flowBean.getUp_flow();
d_flow_sum += flowBean.getD_flow();
}
flowBean.set(key.toString(), up_flow_sum, d_flow_sum);
context.write(key, flowBean);
}
}
public static void main(String[] args) throws Exception, IOException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(FlowCount.class);
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCouontReducer.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);
FileInputFormat.setInputPaths(job, new Path("D:/BaiduYunDownload/flow/srcData"));
FileOutputFormat.setOutputPath(job, new Path("D:/BaiduYunDownload/flow/out"));
job.waitForCompletion(true);
}
}
自定义排序
hadoop的排序是在shuffle中完成的
排序的依据是map输出的key
要想实现自定义的排序,就要将需要排序的数据封装到key中传输,并且要将数据实现WritableComparable接口
总流量排序
以流量统计的输出结果作为流量排序的输入
FlowBean 实现compareTo方法
FlowCountSort.java
package com.test.hadoop.mr.flowcount;
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
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;
public class FlowCountSort {
public static class FlowCountSortMapper extends Mapper<LongWritable, Text, FlowBean, NullWritable> {
FlowBean flowBean = new FlowBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
try {
String line = value.toString();
String[] fields = StringUtils.split(line, "\t");
String phoneNbr = fields[0];
long up_flow = Long.parseLong(fields[1]);
long d_flow = Long.parseLong(fields[2]);
flowBean.set(phoneNbr, up_flow, d_flow);
context.write(flowBean, NullWritable.get());
} catch (Exception e) {
e.printStackTrace();
}
}
}
public static class FlowCountSortReducer extends Reducer<FlowBean, NullWritable, Text, FlowBean> {
@Override
protected void reduce(FlowBean bean, Iterable<NullWritable> values, Context context)
throws IOException, InterruptedException {
context.write(new Text(bean.getPhoneNbr()), bean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(FlowCountSort.class);
job.setMapperClass(FlowCountSortMapper.class);
job.setReducerClass(FlowCountSortReducer.class);
job.setMapOutputKeyClass(FlowBean.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path("D:/BaiduYunDownload/flow/out"));
FileOutputFormat.setOutputPath(job, new Path("D:/BaiduYunDownload/flow/out2"));
job.waitForCompletion(true);
}
}
实现自定义分区的步骤:
1.1先分析一下具体的业务逻辑,确定大概有多少个分区
1.2首先书写一个类,它要继承org.apache.hadoop.mapreduce.Partitioner这个类
1.3重写public int getPartition这个方法,根据具体逻辑,读数据库或者配置返回相同的数字
1.4在main方法中设置Partioner的类,job.setPartitionerClass(DataPartitioner.class);
1.5设置Reducer的数量,job.setNumReduceTasks(6);
AreaPartitioner
import java.util.HashMap;
import org.apache.hadoop.mapreduce.Partitioner;
public class AreaPartitioner<KEY, VALUE> extends Partitioner<KEY, VALUE>{
private static HashMap<String, Integer> areaMap = new HashMap<>();
static {
areaMap.put("136", 0);
areaMap.put("137", 1);
areaMap.put("138", 2);
areaMap.put("139", 3);
}
@Override
public int getPartition(KEY key, VALUE value, int numPartitions) {
Integer provinceCode = areaMap.get(key.toString().substring(0,3));
return provinceCode==null?4:provinceCode;
}
}
public class FlowCountPartition {
public static class FlowCountPartitionMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
private FlowBean flowBean = new FlowBean();
@Override
protected void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {
// 拿到一行数据
String line = value.toString();
// 切分字段
String[] fields = StringUtils.split(line, "\t");
// 拿到我们需要的若干个字段
String phoneNbr = fields[0];
long up_flow = Long.parseLong(fields[fields.length - 3]);
long d_flow = Long.parseLong(fields[fields.length - 2]);
// 将数据封装到一个flowbean中
flowBean.set(phoneNbr, up_flow, d_flow);
// 以手机号为key,将流量数据输出去
context.write(new Text(phoneNbr), flowBean);
}
}
public static class FlowCountPartitionReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
private FlowBean flowBean = new FlowBean();
@Override
protected void reduce(Text key, Iterable<FlowBean> values,Context context)
throws IOException, InterruptedException {
long up_flow_sum = 0;
long d_flow_sum = 0;
for(FlowBean bean:values){
up_flow_sum += bean.getUp_flow();
d_flow_sum += bean.getD_flow();
}
flowBean.set(key.toString(), up_flow_sum, d_flow_sum);
context.write(key, flowBean);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf,"flowpartjob");
job.setJarByClass(FlowCountPartition.class);
job.setMapperClass(FlowCountPartitionMapper.class);
job.setReducerClass(FlowCountPartitionReducer.class);
/**
* 加入自定义分区定义 : AreaPartitioner
*/
job.setPartitionerClass(AreaPartitioner.class);
/**
* 设置reduce task的数量,要跟AreaPartitioner返回的partition个数匹配
* 如果reduce task的数量比partitioner中分组数多,就会产生多余的几个空文件
* 如果reduce task的数量比partitioner中分组数少,就会发生异常,因为有一些key没有对应reducetask接收
* (如果reduce task的数量为1,也能正常运行,所有的key都会分给这一个reduce task)
* reduce task 或 map task 指的是,reuder和mapper在集群中运行的实例
*/
job.setNumReduceTasks(1);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
设置reduce task的数量,要跟AreaPartitioner返回的partition个数匹配
如果reduce task的数量比partitioner中分组数多,就会产生多余的几个空文件
如果reduce task的数量比partitioner中分组数少,就会发生异常,因为有一些key没有对应reducetask接收
(如果reduce task的数量为1,也能正常运行,所有的key都会分给这一个reduce task)
reduce task 或 map task 指的是,reuder和mapper在集群中运行的实例