hadoop - Hadoop Graph输入-链接作业

Question

我有以下格式的输入文件。

input.txt
1, 1   2
2, 1   3
3, 2   3
4, 1   4 

上面的输入文件具有一个键，该键是行号和该值作为无向图的图边。例如，对于第一个记录，行号为1，边线为1到2。在映射逻辑中，我必须找到具有低阶度的顶点。我该怎么办。请帮助我，作为Hadoop-map reduce的新手。

Answer 1

为了识别图中最低度的顶点，我们有两个实现两个任务。这在Hadoop MapReduce编程中称为链接作业

工作1

作业一将为每个顶点计算度数。 Reducer会将输出保存到HDFS文件夹。

工作2

作业2将读取作业1的输出作为输入，并找到度数最低的顶点。

请在下面找到用JAVA编写的详细代码。该程序的参数是输入文本文件和输出文件

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 LowestDegreeOfGraph {

    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);  

        @Override
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            Text word = new Text();
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                context.write(word, one);
            }                       
        }   
    }


    public static class MapForFindingLowDegree extends Mapper<LongWritable, Text, Text, Text> {


        @Override
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            Text word = new Text();
            String[] line = value.toString().split("\t");

            context.write(new Text("vertexWithLowestDegree"), new Text(line[0]+","+line[1]));                   
        }   
    }


    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {


        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();             
            }

            context.write(key, new IntWritable(sum));           

        }       

    }

public static class ReduceForFindingLowDegree extends Reducer<Text, Text, Text, Text> {


        @Override
        public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            int flag = 0;
            int vertex=0;
            int degree=0;
            for (Text value : values) {
                String[]    line=value.toString().split(",");
                if(flag==0){
                    vertex=Integer.parseInt(line[0]);
                    degree=Integer.parseInt(line[1]);
                    flag=1;
                }else if(degree>Integer.parseInt(line[1])){
                    vertex=Integer.parseInt(line[0]);
                    degree=Integer.parseInt(line[1]);
                }
            }

            context.write(new Text("Vertex with the lowest degree "+vertex),new Text("Degree "+degree));            

        }       

    }



    public static void main(String[] args) throws Exception {


        Configuration conf=new Configuration();
        conf.set("fs.default.name", "hdfs://localhost:8020");
        Job job = new Job(conf);
        job.setJarByClass(LowestDegreeOfGraph.class);
        job.setJobName("For calculating the degree for every vertex");
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path("/opt/"));
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.waitForCompletion(true);    

        Job job2 = new Job(conf);
        job2.setJarByClass(LowestDegreeOfGraph.class);
        job2.setJobName("Identifying the Vertex with lowest degree");
        FileInputFormat.addInputPath(job2, new Path("/opt/"));
        FileOutputFormat.setOutputPath(job2, new Path((args[1])));
        job2.setMapperClass(MapForFindingLowDegree.class);
        job2.setReducerClass(ReduceForFindingLowDegree.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);
        job2.waitForCompletion(true);   

    }




}

arg [0]是输入文件。 PFB示例输入文件。
样本输入文件
1 2
1 3
2 3
1 4

arg [1]是输出文件的位置。

请在运行JOB时提供arg [0]和arg [1]。

/ opt是用于存储临时数据的临时位置。