数据准备:
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
需求:
1.先求出A、B、C、….等是谁的好友
2.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?
需求解读:
1.有题目可得,该关系为单项关系可以理解为关注,即A关注的为BCDEF,B关注的为AK,所以求A B C...是谁的关注,即需要将冒号后边的作为key,前边的作为value进行map,在reduce的时候在合并即可。
2.求两两之间的共同关注,这时我们需要借助1题产生的结果文件,map是从后边的value值两两组合生成两两关系。作为新的key值输入,新的value为1题的key。
reduce的时候,将结果合并即可
源代码如下
第一题:
package Demo5; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; 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.Reducer.Context; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; /** * @author 星际毁灭 * 找出ABC等人的好友 * */ import Demo4.Log1; public class Friend1 { public static class Map extends Mapper<Object , Text , Text , Text>{ private static Text newKey=new Text(); private static final IntWritable one = new IntWritable(1); public void map(Object key,Text value,Mapper<Object, Text, Text, Text>.Context context) throws IOException, InterruptedException{ String line=value.toString(); String[] array=line.split(":"); //数据实例 A:B,C,D,F,E,O String first=array[0]; //冒号前边部分 String second=array[1]; //冒号后边部分 String[] friend=second.split(","); //冒号后边部分在切割 System.out.println(first+"\t"+second); for(int i=0;i<friend.length;i++) { context.write(new Text(friend[i]),new Text(first)); //好友关系,即源文件的反向 } } } public static class Reduce extends Reducer<Text, Text, Text, Text>{ public void reduce(Text key,Iterable<Text> values,Context context) throws IOException, InterruptedException{ String res=""; for(Text val:values) { res+=val.toString()+","; //将结果合并 } context.write(key,new Text(res)); } } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{ System.setProperty("hadoop.home.dir", "H:\\文件\\hadoop\\hadoop-2.6.4"); Configuration conf=new Configuration(); Path in=new Path("hdfs://192.168.6.132:9000/wys/in/friend1.txt"); Path out=new Path("hdfs://192.168.6.132:9000/wys/out/friend1"); Job job =new Job(conf,"OneSort"); FileInputFormat.addInputPath(job,in); FileOutputFormat.setOutputPath(job,out); job.setJarByClass(Friend1.class); job.setMapperClass(Friend1.Map.class); job.setReducerClass(Friend1.Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
第二题:
package Demo5; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; 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.Reducer.Context; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; /** * @author 王翌淞 * * 求出他们的共同好友 * */ public class Friend2 { public static class Map extends Mapper<Object , Text , Text , Text>{ private static Text newKey=new Text(); private static final IntWritable one = new IntWritable(1); public void map(Object key,Text value,Mapper<Object, Text, Text, Text>.Context context) throws IOException, InterruptedException{ String line=value.toString(); String[] array=line.split("\t"); String first=array[0]; String second=array[1]; String[] friend=second.split(","); System.out.println(first+"\t"+second); //通过两层的for循环,A的好友进行组合,有顺序 for(int i=0;i<friend.length;i++) { for(int j=i+1;j<friend.length;j++) { context.write(new Text(friend[i]+"-"+friend[j]),new Text(first)); //正序关系 context.write(new Text(friend[j]+"-"+friend[i]),new Text(first)); //倒序关系 } } //context.write(new Text(friend[i]),new Text(first)); } } public static class Reduce extends Reducer<Text, Text, Text, Text>{ public void reduce(Text key,Iterable<Text> values,Context context) throws IOException, InterruptedException{ String res=""; for(Text val:values) { res+=val.toString()+" "; } context.write(key,new Text(res)); } } public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{ System.setProperty("hadoop.home.dir", "H:\\文件\\hadoop\\hadoop-2.6.4"); Configuration conf=new Configuration(); Path in=new Path("hdfs://192.168.6.132:9000/wys/out/friend1/part-r-00000"); Path out=new Path("hdfs://192.168.6.132:9000/wys/out/friend2"); Job job =new Job(conf,"OneSort"); FileInputFormat.addInputPath(job,in); FileOutputFormat.setOutputPath(job,out); job.setJarByClass(Friend2.class); job.setMapperClass(Friend2.Map.class); job.setReducerClass(Friend2.Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.waitForCompletion(true); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
来源:https://www.cnblogs.com/wys-373/p/11455624.html