MapReduce实验——分析年气象数据平均温度

分析年气象数据平均温度

Map类

package AvgTemperature_04;

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 MyMap extends
        Mapper<LongWritable,Text, Text, IntWritable> {
    private static final int MISSING = 9999;
    @Override
    protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
        //读取一条数据
        String line = value.toString();
        //获取年份
        String year = line.substring(15,19);
        int airTem;
        if(line.charAt(45) == '+'){
            //判断温度正负
            airTem = Integer.parseInt(line.substring(46,50));
        }else{
            airTem = Integer.parseInt(line.substring(45,50));
        }
        String quality = line.substring(50,51);
        System.out.println("quality:"+quality);
        //判断温度是否异常
        if(airTem != MISSING && quality.matches("[01459]]")){
            context.write(new Text(year),new IntWritable(airTem));
        }
    }
}

Reduce类

package AvgTemperature_04;

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

import java.io.IOException;

public class MyReduce extends Reducer<Text, IntWritable,Text,IntWritable> {
    protected void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
        //声明变量sumValue作为年温度和
        int sumValue = 0;
        //声明count作为统计同一年温度记录的次数
        int count = 0;
        //循环求同一年所有温度的和 以及 记录温度次数
        for (IntWritable value:values) {
            sumValue += value.get();
            count++;
        }
        int avgValue = sumValue/count;
        context.write(key,new IntWritable(avgValue));
    }
}

Job类

package AvgTemperature_04;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.io.Text;
import java.io.IOException;

public class TestJob {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        //1、获取作业对象
        Job job = Job.getInstance(conf);
        //2、设置主类
        job.setJarByClass(TestJob.class);
        //3、设置job参数
        job.setMapperClass(MyMap.class);
        job.setReducerClass(MyReduce.class);
        //4 set map reduce output type
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //5、设置job输入输出
        FileInputFormat.setInputPaths(job,new Path("file:///simple/source.txt"));
        FileOutputFormat.setOutputPath(job,new Path("file:///simple/output"));
        //6 commit job
        System.out.println(job.waitForCompletion(true) ? 0 : 1);;
    }
}