hadoop 天气案例

对下面一组气温数据进行处理，得到每个月份最高的两个气温值

2018-12-12 14:30 25c
2018-12-12 15:30 26c
2017-12-12 12:30 36c
2019-01-01 14:30 22c
2018-05-05 15:30 26c
2018-05-26 15:30 37c
2018-05-06 15:30 36c
2018-07-05 15:30 36c
2018-07-05 12:30 40c
2017-12-15 12:30 16c

输出格式如下：

2019-1 22
2018-12 26
2018-12 25
2018-7 40
2018-7 36
2018-5 37
2018-5 36
2017-12 36
2017-12 16

public class App {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration(true);
        conf.set("fs.defaultFS","hdfs://hadoop01:9000");
　　　　　//windows下面运行添加一下两个配置
        conf.set("mapreduce.app-submission.cross-platform","true");
        conf.set("mapreduce.framework.name","local");

        Job job = Job.getInstance(conf);

        //设置jobName
        job.setJobName("myJob");
        job.setJarByClass(App.class);
        //配置map
        //mapper类
        job.setMapperClass(MyMapperClass.class);
        //输出的key类型
        job.setMapOutputKeyClass(TQ.class);
        //输出的value类型
        job.setMapOutputValueClass(IntWritable.class);

        //将输出的(K,V)=>(K,V,P)
        //job.setPartitionerClass(MyPartitioner.class);
        //数据在内存spill（溢写）之前先排序，注：继承WritableComparator
        job.setSortComparatorClass(MySortComparator.class);

        //配置reduce
        //根据需求确定分组的维度,继承自WritableComparator
        job.setGroupingComparatorClass(MyGrouping.class);
        //如map阶段根据年、月、温度三个维度排序，而reduce只根据年、月两个维度
        job.setReducerClass(MyReduce.class);

        Path input=new Path("/input/weather.txt");
        Path out=new Path("/output/weather");
        if(out.getFileSystem(conf).exists(out)){
            out.getFileSystem(conf).delete(out,true);
        }

        //数据来源 HDFS路径
        FileInputFormat.addInputPath(job,input);
        //计算结果的输出目录
        FileOutputFormat.setOutputPath(job,out);
        //job.setNumReduceTasks(2);

        job.waitForCompletion(true);
    }
}

public class TQ implements WritableComparable<TQ> {

    private int year;

    public int getYear() {
        return year;
    }

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

    public int getMonth() {
        return month;
    }

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

    public int getDay() {
        return day;
    }

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

    public int getTemp() {
        return temp;
    }

    public void setTemp(int temp) {
        this.temp = temp;
    }

    private int month;
    private int day;
    /**
        温度
     */
    private int temp;

    @Override
    public int compareTo(TQ other) {

        int c1= Integer.compare(this.getYear(),other.getYear());
        if(c1==){
           return Integer.compare(this.getMonth(),other.getMonth());
        }
        return c1;
    }

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(this.year);
        out.writeInt(this.month);
        out.writeInt(this.day);
        out.writeInt(this.temp);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.year=in.readInt();
        this.month=in.readInt();
        this.day=in.readInt();
        this.temp=in.readInt();
    }
}

/**
 * 根据年-月对map输出进行分组
 */
public class MyGrouping extends WritableComparator {
    public MyGrouping(){
        super(TQ.class,true);
    }
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        TQ tq1 = (TQ) a;
        TQ tq2 = (TQ) b;
        if (tq1.getYear() == tq2.getYear() && tq1.getMonth() == tq2.getMonth()) {
            return ;
        }
        return ;
    }
}

public class MyMapperClass extends Mapper<LongWritable,Text,TQ, IntWritable> {
    TQ tq=new TQ();
    IntWritable outVal=new IntWritable();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[]splits= value.toString().split(" ");
        String[]date=splits[].split("-");
        tq.setYear(Integer.parseInt(date[]));
        tq.setMonth(Integer.parseInt(date[]));
        tq.setDay(Integer.parseInt(date[]));

        tq.setTemp(Integer.parseInt(splits[].replace("c","")));
        outVal.set(tq.getTemp());
        context.write(tq,outVal);

    }
}

public class MyReduce extends Reducer<TQ, IntWritable, Text,IntWritable> {
    Text txtKey=new Text();

    @Override
    protected void reduce(TQ key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        Iterator<IntWritable> iterator = values.iterator();
        int flag=;
        while (iterator.hasNext()) {
            if (flag == ) {
                break;
            }
            txtKey.set(String.format("%s-%s",key.getYear(),key.getMonth()));

            IntWritable next = iterator.next();
            context.write(txtKey,next);
            flag++;
        }
    }
}

/**
    数据在内存spill（溢写）之前先排序,根据年月温度
 */
public class MySortComparator extends WritableComparator {
    public MySortComparator(){
        super(TQ.class,true);
    }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        TQ tq1=(TQ)a;
        TQ tq2=(TQ)b;

        int c1= Integer.compare(tq1.getYear(),tq2.getYear());
            if(c1==){
                int c2=Integer.compare(tq1.getMonth(),tq2.getMonth());
                if (c2 == ) {
                    return -Integer.compare(tq1.getTemp(),tq2.getTemp());
                }
                return -c2;
            }
        return -c1;
    }
}