标签：数据分析 hadoop job 可视化 2018 io org apache import

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class Weather13Mapper extends Mapper<LongWritable, Text,Text, DoubleWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //super.map(key, value, context);
        String line=value.toString();   //[2018年01月01日  阴/小雨  11℃/8℃  东南风<3级/北风<3级]
        String[] arr=line.split("  ");
        FileSplit inputSplit = (FileSplit) context.getInputSplit();
        String name = inputSplit.getPath().getName ();
//        String t1=name.substring(0,4);
        String t2=name.substring(5,7);
//        String time=t1+"/"+t2;
//        System.out.println(t1+"/"+t2);
        if (arr.length>2){
//            String weather=arr[2];
//            System.out.println(weather);
            String w=arr[2].replace("℃","");
//            System.out.println(w);
            String[] w1=w.split("/");
            double weather=(Double.parseDouble(w1[0])+Double.parseDouble(w1[w1.length-1]))/2;
            context.write(new Text(t2),new DoubleWritable(weather));
        }
    }
}

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

import java.io.IOException;

public class Weather13Reducer extends Reducer<Text, DoubleWritable,Text,DoubleWritable> {
    @Override
    protected void reduce(Text key, Iterable<DoubleWritable> values, Context context) throws IOException, InterruptedException {
        //super.reduce(key, values, context);
        double sum=0;
        double sc=0;
//        double avg_weather=0;
        for (DoubleWritable i:values){
            sum+=i.get();
            sc++;
        }
//        avg_weather=sum/sc;
        context.write(key,new DoubleWritable(Double.parseDouble(String.format("%.1f",sum/sc))));
    }
}

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

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
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.FileOutputStream;
import java.io.IOException;

public class Weather13Runner {
    public static  void  main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf=new Configuration();
        //创建job
        Job job= Job.getInstance(conf,"weather");
        //设置输入输出路径
        FileInputFormat.addInputPath(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //设置运行类
        job.setJarByClass(Weather13Runner.class);
        job.setMapperClass(Weather13Mapper.class);
        job.setReducerClass(Weather13Reducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);
        System.exit(job.waitForCompletion(true)?0:1);

    }
}

标签：数据分析,hadoop,job,可视化,2018,io,org,apache,import
来源： https://www.cnblogs.com/modikasi/p/16665556.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。