Hadoop-----WorldCount代码编写、温度案例

WorldCount代码编写

WordCountMapper

package day34.com.doit.demo02;

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 WordCountMapper extends Mapper<LongWritable , Text ,Text, IntWritable> {
    /**
     *
     * @param key
     * @param value
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        String[] wordArr = value.toString().split("\\s+");
        for (String word : wordArr) {
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

WordCountReducer

package day34.com.doit.demo02;

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable i : values) {
            sum+=i.get();
        }
        context.write(key,new IntWritable(sum));
    }
}

Test

package day34.com.doit.demo02;

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;

import java.io.IOException;

public class Test {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        Configuration con = new Configuration();
        Job job = Job.getInstance(con,"wordCount");
        //设置Mapper 和Reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //Mapper的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //Reducer的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setNumReduceTasks(2);
        //设置输入 输出路径
        FileInputFormat.setInputPaths(job,new Path("d:\\work\\abc\\input"));
        FileOutputFormat.setOutputPath(job,new Path("d:\\work\\abc\\output5"));
        job.waitForCompletion(true);
    }
}

温度案例

同一时间不同地区的温度 求每天的最高温度

2022-04-03,21.2
2022-04-03,18.5
2022-04-03,24.3
2022-04-03,16.5
2022-04-03,10.0
2022-04-04,28.3
2022-04-04,18.7
2022-04-04,30.0
2022-04-04,21.1
代码实现

package day34.com.doit.demo03;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
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;

import java.io.IOException;

public class Test {
    private static class TemperatureMapper extends Mapper<LongWritable, Text,Text, DoubleWritable> {
        private Text k2 = new Text();
        private DoubleWritable v2 = new DoubleWritable();

        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, DoubleWritable>.Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] arr = line.split(",");
            k2.set(arr[0]);
            v2.set(Double.parseDouble(arr[1]));
            context.write(k2,v2);
        }
    }
    private static class TemperatureReducer extends Reducer<Text,DoubleWritable,Text,DoubleWritable> {
        private DoubleWritable d = new DoubleWritable();

        @Override
        protected void reduce(Text key, Iterable<DoubleWritable> values, Reducer<Text, DoubleWritable, Text, DoubleWritable>.Context context) throws IOException, InterruptedException {
            double max = values.iterator().next().get();
            for (DoubleWritable value : values) {
                double v = value.get();
                if (v>max) {
                    max = v;
                }
            }
            d.set(max);
            context.write(key,d);
        }
    }

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        Configuration con = new Configuration();
        Job job = Job.getInstance(con,"maxTemperature");

        //设置Mapper和Reducer
        job.setMapperClass(TemperatureMapper.class);
        job.setReducerClass(TemperatureReducer.class);
        //设置Map输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(DoubleWritable.class);
        //设置reduce的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);
        //设置输入文件位置
        FileInputFormat.setInputPaths(job,new Path("d:\\work\\abc\\temprature.txt"));
        FileOutputFormat.setOutputPath(job,new Path("d:\\work\\abc\\out_put"));
        //将任务提交 并等待完成
        job.waitForCompletion(true);

    }
}

你可能感兴趣的:(Hadoop,hadoop,mapreduce,大数据)