【大数据系列】MapReduce示例一年之内的最高气温

一、项目采用maven构建，如下为pom.xml中引入的jar包

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>com.slp</groupId>
  <artifactId>HadoopDevelop</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>HadoopDevelop</name>
  <url>http://maven.apache.org</url>
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <hadoopVersion>2.8.0</hadoopVersion>
  </properties>

  <dependencies>
  <!-- Hadoop start -->
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>${hadoopVersion}</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs</artifactId>
    <version>${hadoopVersion}</version>
</dependency>

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-core</artifactId>
    <version>${hadoopVersion}</version>
</dependency>
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-client</artifactId>
    <version>${hadoopVersion}</version>
</dependency>
<!-- Hadoop -->
<dependency>
    <groupId>jdk.tools</groupId>
    <artifactId>jdk.tools</artifactId>
    <version>1.8</version>
    <scope>system</scope>
    <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
  </dependencies>
</project>

二、输入文件

2014010114
2014010216
2014010317
2014010410
2014010506
2012010609
2012010732
2012010812
2012010919
2012011023
2001010116
2001010212
2001010310
2001010411
2001010529
2013010619
2013010722
2013010812
2013010929
2013011023
2008010105
2008010216
2008010337
2008010414
2008010516
2007010619
2007010712
2007010812
2007010999
2007011023
2010010114
2010010216
2010010317
2010010410
2010010506
2015010649
2015010722
2015010812
2015010999
2015011023

三、代码实现

package com.slp.temperature;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.output.FileOutputFormat;

import com.slp.temperature.Temperature.TempMapper.TempReducer;

public class Temperature {

    static class TempMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
        /**
         * 四个泛型类型分别代表
         * KeyIn  Mapper的输入数据Key ,这里是每行文字的起始位置（0,12,...）
         * ValueIn Mapper的输入数据的Value,这里是每行文字
         * KeyOut  Mapper的输出数据的Key,这里是每行文字中的年份
         * ValueOut Mapper的输出数据的value,这里是每行文字中的气温
         */
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            // TODO Auto-generated method stub
            //super.map(key, value, context);
            //打印样本
            System.out.println("Before Mapper : "+ key+","+value);
            String line = value.toString();
            String year = line.substring(0, 4);
            int temperature = Integer.parseInt(line.substring(8));
            context.write(new Text(year), new IntWritable(temperature));
            //map之后打印样本
            System.out.println("After Mapper:" + new Text(year)+","+new IntWritable(temperature));
        }
        /**
         * 四个泛型类型分别代表
         * KeyIn  Mapper的输入数据Key ,这里是每行文字的年份
         * ValueIn Mapper的输入数据的Value,这里是每行文字中的气温
         * KeyOut  Mapper的输出数据的Key,这里是不重复的年份
         * ValueOut Mapper的输出数据的value,这里是这一年中的最高气温
         */
        static class TempReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

            @Override
            protected void reduce(Text key, Iterable<IntWritable> values,
                    Reducer<Text, IntWritable, Text, IntWritable>.Context context)
                    throws IOException, InterruptedException {
                // TODO Auto-generated method stub
                //super.reduce(arg0, arg1, arg2);
                int maxValue = Integer.MIN_VALUE;
                StringBuffer sb = new StringBuffer();
                //取value中的最大值
                for(IntWritable value : values){
                    maxValue = Math.max(maxValue, value.get());
                    sb.append(value).append(",");
                }
                //打印样本
                System.out.println("Before Reduce:"+key+","+sb.toString());
                context.write(key, new IntWritable(maxValue));
                //打印样本
                System.out.println("After Reduce : "+key+","+maxValue);
                
            }
            
        }
    }
    public static void main(String[] args) throws Exception {
        //输入路径
        String dst = "D:\hadoopnode\input\temp.txt";
        //输出路径
        String desout = "D:\hadoopnode\outtemp";
        Configuration conf = new Configuration();
        conf.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
        conf.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
          Job job = new Job(conf);
          //如果需要打成jar运行，需要配置如下
          job.setJarByClass(Temperature.class);
          
          //job执行作业时输入和输出文件的路径
          FileInputFormat.addInputPath(job, new Path(dst));
          FileOutputFormat.setOutputPath(job, new Path(desout));
          
          //指定自定义的Mapper和Reducer作为两个阶段的任务处理类
          job.setMapperClass(TempMapper.class);
          job.setReducerClass(TempReducer.class);
          
          //设置最后输出结果的key和value的类型
          job.setOutputKeyClass(Text.class);
          job.setOutputValueClass(IntWritable.class);
          
          //执行job直到完成
          job.waitForCompletion(true);
          System.out.println("Finished");
    }
}

四、输出结果

Before Mapper : 0,2014010114
After Mapper:2014,14
Before Mapper : 12,2014010216
After Mapper:2014,16
Before Mapper : 24,2014010317
After Mapper:2014,17
Before Mapper : 36,2014010410
After Mapper:2014,10
Before Mapper : 48,2014010506
After Mapper:2014,6
Before Mapper : 60,2012010609
After Mapper:2012,9
Before Mapper : 72,2012010732
After Mapper:2012,32
Before Mapper : 84,2012010812
After Mapper:2012,12
Before Mapper : 96,2012010919
After Mapper:2012,19
Before Mapper : 108,2012011023
After Mapper:2012,23
Before Mapper : 120,2001010116
After Mapper:2001,16
Before Mapper : 132,2001010212
After Mapper:2001,12
Before Mapper : 144,2001010310
After Mapper:2001,10
Before Mapper : 156,2001010411
After Mapper:2001,11
Before Mapper : 168,2001010529
After Mapper:2001,29
Before Mapper : 180,2013010619
After Mapper:2013,19
Before Mapper : 192,2013010722
After Mapper:2013,22
Before Mapper : 204,2013010812
After Mapper:2013,12
Before Mapper : 216,2013010929
After Mapper:2013,29
Before Mapper : 228,2013011023
After Mapper:2013,23
Before Mapper : 240,2008010105
After Mapper:2008,5
Before Mapper : 252,2008010216
After Mapper:2008,16
Before Mapper : 264,2008010337
After Mapper:2008,37
Before Mapper : 276,2008010414
After Mapper:2008,14
Before Mapper : 288,2008010516
After Mapper:2008,16
Before Mapper : 300,2007010619
After Mapper:2007,19
Before Mapper : 312,2007010712
After Mapper:2007,12
Before Mapper : 324,2007010812
After Mapper:2007,12
Before Mapper : 336,2007010999
After Mapper:2007,99
Before Mapper : 348,2007011023
After Mapper:2007,23
Before Mapper : 360,2010010114
After Mapper:2010,14
Before Mapper : 372,2010010216
After Mapper:2010,16
Before Mapper : 384,2010010317
After Mapper:2010,17
Before Mapper : 396,2010010410
After Mapper:2010,10
Before Mapper : 408,2010010506
After Mapper:2010,6
Before Mapper : 420,2015010649
After Mapper:2015,49
Before Mapper : 432,2015010722
After Mapper:2015,22
Before Mapper : 444,2015010812
After Mapper:2015,12
Before Mapper : 456,2015010999
After Mapper:2015,99
Before Mapper : 468,2015011023
After Mapper:2015,23
Before Reduce:2001,12,10,11,29,16,
After Reduce : 2001,29
Before Reduce:2007,23,19,12,12,99,
After Reduce : 2007,99
Before Reduce:2008,16,14,37,16,5,
After Reduce : 2008,37
Before Reduce:2010,10,6,14,16,17,
After Reduce : 2010,17
Before Reduce:2012,19,12,32,9,23,
After Reduce : 2012,32
Before Reduce:2013,23,29,12,22,19,
After Reduce : 2013,29
Before Reduce:2014,14,6,10,17,16,
After Reduce : 2014,17
Before Reduce:2015,23,49,22,12,99,
After Reduce : 2015,99
Finished

五、reduce输出内容