hadoop 最大值最小值

                                                            hadoop 最大值最小值

1、数据准备
[root@x00 hd]# cat eightteen_a.txt 
102
10
39
109
200
11
3
90
28
[root@x00 hd]# cat eightteen_b.txt 
5
2
30
838
10005


结果预测
Max 10005
Min 2


public class MaxMinMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
    private Text textkey = new Text();
@Override
protected void map(LongWritable key, Text value,
Context context)throws IOException, InterruptedException {
String line = value.toString();
if(line.trim().length()>0){
context.write(new Text("textkey"), new LongWritable(Integer.valueOf(line.trim())));
}
}


}


public class MaxMinReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
      Long max = Long.MIN_VALUE;//设置最大值
      Long min = Long.MAX_VALUE;//设置最小值
@Override
protected void reduce(Text key, Iterable<LongWritable> values,
Context context)
throws IOException, InterruptedException {
for (LongWritable val : values) {
if(val.get()>max){
max = val.get();
}
if(val.get()<min){
min = val.get();
}

}
context.write(new Text("max"), new LongWritable(max));
context.write(new Text("min"), new LongWritable(min));
}



}


package com.hadoop.five;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 JobMain {
public static void main(String[] args)throws Exception {
Configuration configuration = new Configuration();
Job job = new Job(configuration,"max_min_job");
job.setJarByClass(JobMain.class);

job.setMapperClass(MaxMinMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

job.setReducerClass(MaxMinReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

FileInputFormat.addInputPath(job, new Path(args[0]));
Path path = new Path(args[1]);
FileSystem fs = FileSystem.get(configuration);
if(fs.exists(path)){
fs.delete(path, true);
}
FileOutputFormat.setOutputPath(job, path);

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


}


}


  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
好的,可以使用 MapReduce 框架来实现。 首先,需要编写 Mapper 类来读取大文件中的数据,将其输出为键值对。键为 NullWritable,值为 IntWritable,表示每一个数值。 ```java import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.mapreduce.Mapper; public class MaxMinMapper extends Mapper<Object, Text, NullWritable, IntWritable> { private IntWritable num = new IntWritable(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); num.set(Integer.parseInt(line)); context.write(NullWritable.get(), num); } } ``` 然后,需要编写 Reducer 类来计算最大值最小值。在 Reducer 类的 reduce() 方法中,将所有数值进行比较,并输出最大值最小值。 ```java import java.io.IOException; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.mapreduce.Reducer; public class MaxMinReducer extends Reducer<NullWritable, IntWritable, NullWritable, IntWritable> { private IntWritable max = new IntWritable(Integer.MIN_VALUE); private IntWritable min = new IntWritable(Integer.MAX_VALUE); public void reduce(NullWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { for (IntWritable val : values) { if (val.get() > max.get()) { max.set(val.get()); } if (val.get() < min.get()) { min.set(val.get()); } } context.write(NullWritable.get(), max); context.write(NullWritable.get(), min); } } ``` 最后,需要编写 Driver 类来设置 MapReduce 作业的输入、输出路径和使用的 Mapper、Reducer 类等信息。 ```java import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class MaxMinDriver { public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "MaxMin"); job.setJarByClass(MaxMinDriver.class); job.setMapperClass(MaxMinMapper.class); job.setReducerClass(MaxMinReducer.class); job.setOutputKeyClass(NullWritable.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); } } ``` 在命令行中运行程序: ```bash hadoop jar MaxMin.jar MaxMinDriver input output ``` 其中,MaxMin.jar 是打包后的程序包,input 是输入文件的路径,output 是输出结果的路径。 程序运行后,可以在输出路径下找到结果文件,其中记录了所有数值的最大值最小值
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值