尋找共同好友實現
阿新 • • 發佈：2019-02-13
import java.io.IOException; 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; public class SharedFriendsStepOne { static class SharedFriendsStepOneMapper extends Mapper<LongWritable, Text, Text, Text> { @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { // A:B,C,D,F,E,O String line = value.toString(); String[] person_friends = line.split(":"); String person = person_friends[0]; String friends = person_friends[1]; for (String friend : friends.split(",")) { // 輸出<好友，人> context.write(new Text(friend), new Text(person)); } } } static class SharedFriendsStepOneReducer extends Reducer<Text, Text, Text, Text> { @Override protected void reduce(Text friend, Iterable<Text> 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 Exception { 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("D:/srcdata/friends")); FileOutputFormat.setOutputPath(job, new Path("D:/temp/out")); job.waitForCompletion(true); } }
import java.io.IOException; import java.util.Arrays; 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; public class SharedFriendsStepTwo { static class SharedFriendsStepTwoMapper extends Mapper<LongWritable, Text, Text, Text> { // 拿到的資料是上一個步驟的輸出結果 // A I,K,C,B,G,F,H,O,D, // 友 人，人，人 @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 - 1; i++) { for (int j = i + 1; j < persons.length; j++) { // 發出 <人-人，好友> ，這樣，相同的“人-人”對的所有好友就會到同1個reduce中去 context.write(new Text(persons[i] + "-" + persons[j]), new Text(friend)); } } } } static class SharedFriendsStepTwoReducer extends Reducer<Text, Text, Text, Text> { @Override protected void reduce(Text person_person, Iterable<Text> 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 Exception { 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("D:/temp/out/part-r-00000")); FileOutputFormat.setOutputPath(job, new Path("D:/temp/out2")); job.waitForCompletion(true); } }
測試檔案：
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輸出結果：
A I,K,C,B,G,F,H,O,D, B A,F,J,E, C A,E,B,H,F,G,K, D G,C,K,A,L,F,E,H, E G,M,L,H,A,F,B,D, F L,M,D,C,G,A, G M, H O, I O,C, J O, K B, L D,E, M E,F, O A,H,I,J,F,
A-BC E
A-CF D
A-DE F
A-EB C D
A-FC D B E O
A-GD E F C
A-HE O C D
A-IO
A-KD
A-LF E
B-CA
B-DE A
B-EC
B-FE A C
B-GC E A
B-HE C A
B-IA
B-KA
B-LE
C-DF A
C-ED
C-FD A
C-GF A D
C-HA D
C-IA
C-KD A
C-LF
D-FE A
D-GA E F
D-HA E
D-IA
D-KA
D-LF E
E-FC D B
E-GD C
E-HD C
E-KD
F-GC E D A
F-HC A D E O
F-IA O
F-KD A
F-LE
G-HD E C A
G-IA
G-KA D
G-LF E
H-IA O
H-KA D
H-LE
I-KA