MapReduce project case 3 - temperature statistics

Make statistics of each month and year , Two days before the highest temperature

1. data

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

2. Demand analysis

• Grouped by year and year
• The first two are sorted by temperature

3.Weather

import org.apache.hadoop.io.WritableComparable;

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

/** * bean */
public class Weather implements WritableComparable<Weather> {
    
    private int year;
    private int month;
    private int day;
    private int degree;// temperature 

    @Override// Read... In order 
    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 --- The problem of inconsistent serialization and deserialization 
    }

    @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 +
                '}';
    }
}

4.WeatherMapper

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;

/** * 1. mapping , Each mapped row reaches the partition  */
public class WeatherMapper extends Mapper<LongWritable, Text, Weather, IntWritable> {
    
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    
        // Divide according to the separator 
        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);// Be careful ： Month from 0 Start counting 
                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();
            }
        }
    }
}

5.WeatherPartition

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

/** * 2. Partition ： Press Weather.year Of hash Value to partition , Make each year a separate reduce, That is, a separate division for each year , Several partitions result in several output files  */
public class WeatherPartition extends Partitioner<Weather, IntWritable> {
    
    @Override
    public int getPartition(Weather weather, IntWritable intWritable, int numPartitions) {
    //numPartitions from job.setNumReduceTasks(3) decision 
        // Write an algorithm to calculate hash, This algorithm should meet the business requirements , This method is called for each key value , So this method needs to be concise 
        System.out.println((weather.getYear() - 1929) % numPartitions);
        return (weather.getYear() - 1929) % numPartitions;
    }
}

6.WeatherGroup

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

/** * 3. grouping ： Grouping in partitions ,key The same month and year in are divided into the same group , The default is the same key In the same group  * reduce The previous default is the same key In the same group , But at this time, we only need to compare the year and month , Obviously, the grouping method needs to be rewritten  * <p> *  Without grouping, data in the same partition will be transferred one by one , Can not reach the effect of screening the first two  *  Group words , According to the following grouping rules ,< years , temperature > In this way, the data of the same month and year is a group of incoming data  */
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;
    }
}

7.WeatherReduce

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;

/** * 4. Statute  */
public class WeatherReduce extends Reducer<Weather, IntWritable, Text, NullWritable> {
    
    @Override
    protected void reduce(Weather key, Iterable<IntWritable> 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());
        }
    }
}

8.WeatherMain

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;

/** * @program: Hadoop_MR * @description: * @author:  author  * @create: 2022-06-21 16:45 */
public class WeatherMain {
    
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    
        Configuration conf = new Configuration();
        Job job = Job.getInstance();// establish job example 
        job.setJarByClass(WeatherMain.class);

        //1.map
        job.setMapperClass(WeatherMapper.class);
        // Output types except Text It's best to set it all , Otherwise, there is no output 
        job.setMapOutputKeyClass(Weather.class);
        job.setMapOutputValueClass(IntWritable.class);

        //2. Partition 
        job.setPartitionerClass(WeatherPartition.class);
        // Set up reduce number 
        job.setNumReduceTasks(3);//output Output three folders 

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

        //4.reduce Internal grouping 
        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"));// Enter Directory 
        Path outPath = new Path("E:\\HadoopMRData\\output");
        /*FileSystem fs = FileSystem.get(conf); if (fs.exists(outPath)) { fs.delete(outPath, true); }*/
        FileOutputFormat.setOutputPath(job, outPath);
        
        /*FileInputFormat.addInputPath(job, new Path(args[0]));// The command line runtime passes in  FileOutputFormat.setOutputPath(job, new Path(args[1]));*/

        System.exit(job.waitForCompletion(true) ? 0 : 1);// start-up ,0 Indicates normal exit 
    }
}