18-hadoop-weather案例

package com.wenbronk.weather;

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

import org.apache.hadoop.io.WritableComparable;

/**
 * 自定义key, 对key进行分组
 * 实现writableComparble方法, 可序列化并比较是否同一个对象
 * @author root
 *
 */
public class MyKey implements WritableComparable<MyKey> {

    private int year;
    private int month;
    private double hot;
    
    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 double getHot() {
        return hot;
    }
    public void setHot(double hot) {
        this.hot = hot;
    }
    
    /**
     * 反序列化
     */
    @Override
    public void readFields(DataInput arg0) throws IOException {
        this.year = arg0.readInt();
        this.month = arg0.readInt();
        this.hot = arg0.readDouble();
    }
    
    /**
     * 序列化
     */
    @Override
    public void write(DataOutput arg0) throws IOException {
        arg0.writeInt(year);
        arg0.writeInt(month);
        arg0.writeDouble(hot);
    }
    
    /**
     * 比较, 判断是否同一个对象, 当对象作为key时
     */
    @Override
    public int compareTo(MyKey o) {
        int c1 = Integer.compare(this.year, o.getYear());
        if (c1 == 0) {
            int c2 = Integer.compare(this.month, o.getMonth());
            if (c2 == 0) {
                return Double.compare(this.hot, o.getHot());
            }
        }
        return 1;
    }
    
    
}

package com.wenbronk.weather;

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

/**
 * 自定义排序
 * @author root
 */
public class MySort extends WritableComparator {
    
    /**
     * 在构造方法中, 通过调用父类构造创建MyKey
     * MyKey.class : 比较的对象
     * true : 创建这个对象
     */
    public MySort() {
        super(MyKey.class, true);
    }
    
    /**
     * 自定义排序方法
     * 传入的比较对象为 map 输出的key
     * 
     * 年相同比较月, 月相同, 温度降序
     */
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        MyKey key1 = (MyKey) a;
        MyKey key2 = (MyKey) b;
        
        int r1 = Integer.compare(key1.getYear(), key2.getYear());
        if (r1 == 0) {
            int r2 = Integer.compare(key1.getMonth(), key2.getMonth());
            
            if (r2 == 0) {
                // 温度降序
                return - Double.compare(key1.getHot(), key2.getHot());
            }else {
                return r2;
            }
        }
        return r1;
    }
    
}

package com.wenbronk.weather;

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

/**
 * 自定义分组
 * @author root
 *
 */
public class MyGroup extends WritableComparator {

    public MyGroup() {
        super(MyKey.class, true);
    }
    
    /**
     * 年, 月相同, 则为一组
     */
    @Override
    public int compare(WritableComparable a, WritableComparable b) {
        MyKey key1 = (MyKey) a;
        MyKey key2 = (MyKey) b;
        
        int r1 = Integer.compare(key1.getYear(), key2.getYear());
        if (r1 == 0) {
            return Integer.compare(key1.getMonth(), key2.getMonth());
        }
        return r1;
    }
    
}

package com.wenbronk.weather;

import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

/**
 * 自定义partition, 保证一年一个reducer进行处理
 * 从map接收值
 * @author root
 *
 */
public class MyPartition extends HashPartitioner<MyKey, DoubleWritable> {

    /**
     * maptask每输出一个数据, 调用一次此方法
     * 执行时间越短越好
     * 年的数量是确定的, 可以传递reduceTask数量, 在配置文件可设置, 在程序执行时也可设置
     * 
     */
    @Override
    public int getPartition(MyKey key, DoubleWritable value, int numReduceTasks) {
        // 减去最小的, 更精确
        return (key.getYear() - 1949) % numReduceTasks;
    }
    
}

package com.wenbronk.weather;

import java.io.IOException;
import java.text.DateFormat;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * 执行mapreduce 统计每年温度的前三个
 * 
 * @author wenbronk
 *
 */
public class RunMapReduce {

    public static void main(String[] args) throws Exception {
        // 初始化时加载src或classpath下所有的配置文件
        Configuration configuration = new Configuration();

        // 本地执行
         configuration.set("fs.default", "hdfs://wenbronk.hdfs.com:8020 ");
         configuration.set("yarn.resourcemanager", "hdfs://192.168.208.106");

        // 服务器执行
//        configuration.set("mapred.jar", "?C:/Users/wenbr/Desktop/weather.jar");
//        configuration.set("mapred.jar", "E:\\sxt\\target\\weather.jar");
//        configuration.set("mapreduce.app-submission.cross-platform", "true");
//        
//        configuration.set("mapreduce.framework.name", "yarn"); 
//        configuration.set("yarn.resourcemanager.address", "192.168.208.106:"+8030);
//        configuration.set("yarn.resourcemanager.scheduler.address", "192.168.208.106:"+8032);

        // 得到执行的任务
        Job job = Job.getInstance();
        // 入口类
        job.setJarByClass(RunMapReduce.class);

        // job名字
        job.setJobName("weather");

        // job执行是map执行的类
        job.setMapperClass(WeatherMapper.class);
        job.setReducerClass(WeatherReduce.class);
        job.setMapOutputKeyClass(MyKey.class);
        job.setMapOutputValueClass(DoubleWritable.class);

        
        // 使用自定义的排序, 分组
        job.setPartitionerClass(MyPartition.class);
        job.setSortComparatorClass(MySort.class);
        job.setGroupingComparatorClass(MyGroup.class);
//        job.setJar("E:\\sxt\\target\\weather.jar");
        
        //设置 分区数量
        job.setNumReduceTasks(3);
        
        // **** 使用插件上传data.txt到hdfs/root/usr/data.txt

        //****使得左边为key, 右边为value, 此类默认为  "\t" 可以自定义
        // 或者  config.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", "\t");
        job.setInputFormatClass(KeyValueTextInputFormat.class);
        
        // 使用文件
        FileInputFormat.addInputPath(job, new Path("E:\\sxt\\1-MapReduce\\data\\weather.txt"));
//        FileInputFormat.addInputPath(job, new Path("/root/usr/weather.txt"));

        // 使用一个不存在的目录进行
        Path path = new Path("/root/usr/weather");
        // 如果存在删除
        FileSystem fs = FileSystem.get(configuration);
        if (fs.exists(path)) {
            fs.delete(path, true);
        }

        // 输出
        FileOutputFormat.setOutputPath(job, path);

        boolean forCompletion = job.waitForCompletion(true);

        if (forCompletion) {
            System.out.println("success");
        }
    }

    /**
     * key: 将 LongWritalbe 改成 Text类型的
     * 
     * 将输入更改为需要的 key, value, mapper所做的事情
     * 
     * @author wenbronk
     */
    static class WeatherMapper extends Mapper<Text, Text, MyKey, DoubleWritable> {
        /**
         * 转换字符串为日期对象
         */
        DateFormat formatter = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");

        /**
         * 将键值取出来, 封装为key 每行第一个分隔符"\t"左侧为key, 右侧有value, 传递过来的数据已经切割好了
         */
        @Override
        protected void map(Text key, Text value, Mapper<Text, Text, MyKey, DoubleWritable>.Context context)
                throws IOException, InterruptedException {
            try {
                Date date = formatter.parse(key.toString());
                Calendar calendar = Calendar.getInstance();
                calendar.setTime(date);
                int year = calendar.get(Calendar.YEAR);
                int month = calendar.get(Calendar.MONTH);

                double hot = Double.parseDouble(value.toString().substring(0, value.toString().lastIndexOf("c")));

                MyKey mykey = new MyKey();
                mykey.setYear(year);
                mykey.setMonth(month);
                mykey.setHot(hot);

                context.write(mykey, new DoubleWritable(hot));
            } catch (ParseException e) {
                e.printStackTrace();
            }
        }
    }

    /**
     * 经过partition, 分组, 排序, 传递数据给reducer 需要自定义partition, 保证一年一个reduce 自定义排序,
     * 保证按照年, 月, 温度 自定义分组, 年月相同, 一个组
     * 传进来的温度, 为已经排好序的
     * @author root
     */
    static class WeatherReduce extends Reducer<MyKey, DoubleWritable, Text, NullWritable> {
        NullWritable nullWritable = NullWritable.get();
        @Override
        protected void reduce(MyKey arg0, Iterable<DoubleWritable> arg1,
                Reducer<MyKey, DoubleWritable, Text, NullWritable>.Context arg2)
                throws IOException, InterruptedException {

            int i = 0;
            for (DoubleWritable doubleWritable : arg1) {
                i++;
                String msg = arg0.getYear() + "\t" + arg0.getMonth() + "\t" + doubleWritable.get();
                // key中已经包含需要的结果了
                arg2.write(new Text(msg), NullWritable.get());
                // 每个月的前三个
                if (i == 3) {
                    break;
                }
            }

        }
    }

}

1949-10-01 14:21:02    34c
1949-10-02 14:01:02    36c
1950-01-01 11:21:02    32c
1950-10-01 12:21:02    37c
1951-12-01 12:21:02    23c
1950-10-02 12:21:02    41c
1950-10-03 12:21:02    27c
1951-07-01 12:21:02    45c
1951-07-02 12:21:02    46c
1951-07-03 12:21:03    47c