北京 2019 年空气质量等级数据分析与可视化

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 Air16Mapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //super.map(key, value, context);
        String line=value.toString();   //[2019-01-01    良    53    128    35    52]
        String[] arr=line.split("\\t");
        if (arr.length>1){
            String quality=arr[1];
//            System.out.println(quality);
            context.write(new Text(quality),new IntWritable(1));
        }
    }
}

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

import java.io.IOException;


public class Air16Reducer extends Reducer<Text, IntWritable,Text,IntWritable> {

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

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.FileOutputStream;
import java.io.IOException;

public class Air16Runner {
    public static  void  main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf=new Configuration();
        //创建job
        Job job= Job.getInstance(conf,"air");
        //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(Air16Runner.class);
        job.setMapperClass(Air16Mapper.class);
        job.setReducerClass(Air16Reducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        System.exit(job.waitForCompletion(true)?0:1);

    }
}