MapReduce项目案例3——温度统计

2020-01-02 10:22:22	1c
2020-01-03 10:22:22	2c
2020-01-04 10:22:22	4c
2020-02-01 10:22:22	7c
2020-02-02 10:22:22	9c
2020-02-03 10:22:22	11c
2020-02-04 10:22:22	1c
2019-01-02 10:22:22	1c
2019-01-03 10:22:22	2c
2019-01-04 10:22:22	4c
2019-02-01 10:22:22	7c
2019-02-02 10:22:22	9c
2018-02-03 10:22:22	11c
2018-02-04 10:22:22	1c

• 按年月分组
• 再按温度排序取前两个

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;


public class Weather implements WritableComparable {
    private int year;
    private int month;
    private int day;
    private int degree;//温度

    @Override//按顺序读取
    public void readFields(DataInput dataInput) throws IOException {
        this.year = dataInput.readInt();
        this.month = dataInput.readInt();
        this.day = dataInput.readInt();
        this.degree = dataInput.readInt();
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeInt(year);
        dataOutput.writeInt(month);
        dataOutput.writeInt(day);
        dataOutput.writeInt(degree);
        //java.lang.RuntimeException: java.io.EOFException ---序列化与反序列化不一致的问题
    }

    @Override
    public int compareTo(Weather o) {
        int t1 = Integer.compare(this.year, o.getYear());
        if (t1 == 0) {
            int t2 = Integer.compare(this.month, o.getMonth());
            if (t2 == 0) {
                return -Integer.compare(this.degree, o.getDegree());
            }
            return t2;
        }
        return t1;
    }

    public void setYear(int year) {
        this.year = year;
    }

    public void setMonth(int month) {
        this.month = month;
    }

    public void setDay(int day) {
        this.day = day;
    }

    public void setDegree(int degree) {
        this.degree = degree;
    }

    public int getYear() {
        return year;
    }

    public int getMonth() {
        return month;
    }

    public int getDay() {
        return day;
    }

    public int getDegree() {
        return degree;
    }

    @Override
    public String toString() {
        return "Weather{" +
                "year=" + year +
                ", month=" + month +
                ", day=" + day +
                ", degree=" + degree +
                '}';
    }
}

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;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;


public class WeatherMapper extends Mapper {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //根据分割符分割
        String[] split = value.toString().trim().split("t");
        if (split != null && split.length >= 2) {
            SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
            Calendar calendar = Calendar.getInstance();
            try {
                Date date = format.parse(split[0]);
                calendar.setTime(date);

                Weather weather = new Weather();
                weather.setYear(calendar.get(Calendar.YEAR));
                weather.setMonth(calendar.get(Calendar.MONTH) + 1);//注意：月份从0开始计数的
                weather.setDay(calendar.get(Calendar.DAY_OF_MONTH));

                int degree = Integer.parseInt(split[1].substring(0, split[1].lastIndexOf("c")));
                weather.setDegree(degree);

                context.write(weather, new IntWritable(degree));
            } catch (ParseException e) {
                e.printStackTrace();
            }
        }
    }
}

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Partitioner;


public class WeatherPartition extends Partitioner {
    @Override
    public int getPartition(Weather weather, IntWritable intWritable, int numPartitions) {//numPartitions由job.setNumReduceTasks(3)决定
        //写一个算法计算hash,这个算法要满足业务需求，每一个键值都会调用此方法，所以该方法需要简洁
        System.out.println((weather.getYear() - 1929) % numPartitions);
        return (weather.getYear() - 1929) % numPartitions;
    }
}

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;


public class WeatherGroup extends WritableComparator {
    public WeatherGroup() {
        super(Weather.class, true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        Weather weather1 = (Weather) a;
        Weather weather2 = (Weather) b;
        int c1 = Integer.compare(weather1.getYear(), weather2.getYear());
        if (c1 == 0) {
            int c2 = Integer.compare(weather1.getMonth(), weather2.getMonth());
            return c2;
        }
        return c1;
    }
}

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

import java.io.IOException;


public class WeatherReduce extends Reducer {
    @Override
    protected void reduce(Weather key, Iterable values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable i : values) {
            count++;
            if (count >= 3) {
                break;
            }
            String res = key.getYear() + "-" + key.getMonth() + "-" + key.getDay() + "t" + i.get();
            context.write(new Text(res), NullWritable.get());
        }
    }
}

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.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 WeatherMain {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance();//创建job实例
        job.setJarByClass(WeatherMain.class);

        //1.map
        job.setMapperClass(WeatherMapper.class);
        //输出类型除了Text最好都设置一下，否则没有输出的
        job.setMapOutputKeyClass(Weather.class);
        job.setMapOutputValueClass(IntWritable.class);

        //2.分区
        job.setPartitionerClass(WeatherPartition.class);
        //设置reduce数目
        job.setNumReduceTasks(3);//output输出三个文件夹

        //3.排序
        //job.setSortComparatorClass(WeatherSort.class);

        //4.reduce内部分组
        job.setGroupingComparatorClass(WeatherGroup.class);

        //5.reduce
        job.setReducerClass(WeatherReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.addInputPath(job, new Path("E:\HadoopMRData\input"));//输入目录
        Path outPath = new Path("E:\HadoopMRData\output");
        
        FileOutputFormat.setOutputPath(job, outPath);
        
        

        System.exit(job.waitForCompletion(true) ? 0 : 1);//启动，0表示正常退出
    }
}