Hadoop图形输入-链接作业

Question

我有一个如下格式的输入文件。

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

上面的输入文件有一个键，它是行号和作为无向图的图边的值。例如，对于第一条记录，行号是1，边在1和2之间。在映射逻辑中，我必须找到哪个垂直线的阶数较低。我该怎么办？请帮助我，因为我是Hadoop地图减少的新手。

Answer 1

为了识别图中阶数最低的顶点，我们有两个实现两个作业。这被称为Hadoop MapReduce编程中的链接作业

作业1

作业一将计算每个顶点的度数。Reducer会将输出保存到HDFS文件夹中。

作业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。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样本输入文件。示例输入文件1 21 32 31 4

arg[1]是输出文件的位置。

请在运行作业时提供arg[0]和arg[1]。

/opt是用于存储临时数据的临时位置。