Hadoop: MapReduce的最小最大值结果与原始数据集不同

在Hadoop中，可以通过自定义Mapper和Reducer来解决“MapReduce的最小最大值结果与原始数据集不同”的问题。以下是一个示例代码：

首先，创建一个Mapper类，将原始数据集中的每个数值作为键值对的键，值设置为1，并将其输出到Reducer：

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class MinMaxMapper extends Mapper<LongWritable, Text, IntWritable, IntWritable> {

    private IntWritable number = new IntWritable();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        int num = Integer.parseInt(line);

        number.set(num);
        context.write(number, number);
    }
}

接下来，创建一个Reducer类，将收到的键值对中的最小值和最大值输出为结果：

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class MinMaxReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {

    private IntWritable min = new IntWritable();
    private IntWritable max = new IntWritable();

    @Override
    protected void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int minValue = Integer.MAX_VALUE;
        int maxValue = Integer.MIN_VALUE;

        for (IntWritable value : values) {
            int num = value.get();
            minValue = Math.min(minValue, num);
            maxValue = Math.max(maxValue, num);
        }

        min.set(minValue);
        max.set(maxValue);

        context.write(min, max);
    }
}

最后，编写一个主程序来配置和运行MapReduce作业：

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MinMaxDriver {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Min Max Calculation");

        job.setJarByClass(MinMaxDriver.class);
        job.setMapperClass(MinMaxMapper.class);
        job.setReducerClass(MinMaxReducer.class);

        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);

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

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

以上代码将输入文件中的每个数值作为键值对的键，并将键值对作为Mapper的输出。Reducer将收到的键值对中的最小值和最大值输出为结果。

注意：以上代码只是一个示例，你需要根据自己的实际需求进行修改和调整。