使用以下java代码随机选择15%的顶点：

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class RandomSample {

 public static class Map extends Mapper<LongWritable, Text, Text, Text> {
    private Text word = new Text();

    public void map(LongWritable key, Text value, Context context)
    throws IOException, InterruptedException {
        if (Math.random()<0.15)
            context.write(value,null);
        else
            context.write(null,null);
    context.write(value,null);
    } 
 }

 public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "randomsample");
    job.setJarByClass(RandomSample.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.waitForCompletion(true);
 }

}

并使用这个bash脚本来运行它

echo "Running Job"
hadoop jar RandomSample.jar RandomSample $1 tmp
echo "copying result to local path (RandomSample)"
hadoop fs -getmerge tmp RandomSample
echo "Clean up"
hadoop fs -rmr tmp

例如，如果我们将脚本命名为random\u sample.sh，要从folder/example/中选择15%，只需运行

./random_sample.sh /example/

然后，你可以用简单的 grep 对第二个文件执行的操作，以仅选择包含随机选择的顶点的边