MapReduce学习笔记（7）—— 寻找共同好友
1 数据
冒号前是一个用户，冒号后是该用户的所有好友（数据中的好友关系是单向的）。求出哪些人两两之间有共同好友，及他俩的共同好友都有谁？
A:B,C,D,F,E,O
B:A,C,E,K
C:F,A,D,I
D:A,E,F,L
E:B,C,D,M,L
F:A,B,C,D,E,O,M
G:A,C,D,E,F
H:A,C,D,E,O
I:A,O
J:B,O
K:A,C,D
L:D,E,F
M:E,F,G
O:A,H,I,J
1.1 思路
1.1.1 map
读一行 A:B,C,D,F,E,O
输出 <C,A><D,A><E,A><O,A>
在读一行 B:A,C,E,K
输出 <C,B><E,B><K,B>
1.1.2 reduce
拿到的数据比如<C,A><C,B><C,E><C,F><C,G>......
输出：
C>
E,C>
C>
C>
E,C>
C>.....
1.1.3 第二次 map
读入一行<A-B,C>
直接输出<A-B,C>
1.1.4 第二次 reduce
读入数据 <A-B,C><A-B,F><A-B,G>.......
输出： A-B C,F,G,.....
2 第一次分类
2.1 源码
package friends;
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.output.FileOutputFormat;
import java.io.IOException;
public class SharedFriendsStepOne {
static class SharedFriendsStepOneMapper extends Mapper {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] person_friends = line.split(":");
String person = person_friends[0];
String friends = person_friends[1];
for(String friend:friends.split(",")){
//输出<好友，人>
context.write(new Text(friend),new Text(person));
}
}
}
static class SharedFriendsStepOneReducer extends Reducer{
@Override
protected void reduce(Text friend, Iterable persons, Context context) throws IOException, InterruptedException {
StringBuffer sb = new StringBuffer();
for(Text person:persons){
sb.append(person).append(",");
}
context.write(friend,new Text(sb.toString()));
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(SharedFriendsStepOne.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(SharedFriendsStepOneMapper.class);
job.setReducerClass(SharedFriendsStepOneReducer.class);
FileInputFormat.setInputPaths(job,new Path("h:/friends/input"));
FileOutputFormat.setOutputPath(job,new Path("h:/friends/output_step_one"));
job.waitForCompletion(true);
}
}
2.2 本地运行结果
3 第二次分类
3.1 源码
package friends;
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.output.FileOutputFormat;
import java.io.IOException;
import java.util.Arrays;
public class SharedFriendsStepTwo {
/*
* 拿到的数据是上一个步骤的输出结果
* A I,K,C,B,G,F,H,O,D,
* 友 人，人，人，人
*
* */
static class SharedFriendsStepTwoMapper extends Mapper {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] friend_persons = line.split("\t");
String friend = friend_persons[0];
String[] persons = friend_persons[1].split(",");
Arrays.sort(persons);
for (int i = 0; i < persons.length - 2; i++) {
for (int j = i + 1; j < persons.length - 1; j++) {
// <人-人，好友>，相同的人人对就会到同一个 reduce
context.write(new Text(persons[i] + "-" + persons[j]), new Text(friend));
}
}
}
}
static class SharedFriendsStepTwoReducer extends Reducer {
@Override
protected void reduce(Text person_person, Iterable friends, Context context) throws IOException, InterruptedException {
StringBuffer sb = new StringBuffer();
for(Text friend:friends){
sb.append(friend).append(" ");
}
context.write(person_person,new Text(sb.toString()));
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(SharedFriendsStepTwo.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(SharedFriendsStepTwoMapper.class);
job.setReducerClass(SharedFriendsStepTwoReducer.class);
FileInputFormat.setInputPaths(job,new Path("h:/friends/output_step_one"));
FileOutputFormat.setOutputPath(job,new Path("h:/friends/output_step_two"));
job.waitForCompletion(true);
}
}
3.2 本地运行结果
A-B C E
A-C F D
A-D E F
A-E B C D
A-F C D B E O
A-G D E F C
A-H E O C D
A-I O
A-K D
A-L F E
B-C A
B-D E A
B-E C
B-F E A C
B-G C E A
B-H E C A
B-I A
B-K A
B-L E
C-D F A
C-E D
C-F D A
C-G F A D
C-H A D
C-I A
C-K D A
C-L F
D-F E A
D-G A E F
D-H A E
D-I A
D-K A
D-L F E
E-F C D B
E-G D C
E-H D C
E-K D
F-G C E D A
F-H C A D E O
F-I A O
F-K D A
F-L E
G-H D E C A
G-I A
G-K A D
G-L F E
H-I A O
H-K A D
H-L E
I-K A