大数据实战（下）_MapReduce实战

大纲

• 演示实例讲解
• 演示编写MapReduce实例

MapReduce代码

创建 linecount Java 项目
代码如下：

package com.trendwise.java;
import java.io.IOException;
import java.util.Iterator;
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
public class Linecount {
    //This is the Mapper Module, i.e. Map.java
    public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable obj = new IntWritable(1);
        private Text words = new Text("Total Lines are");

        public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            output.collect(words, obj);
        }
    }
    // This is the Reducer Module, i.e. Reduce.java
    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
        public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
                Reporter reporter) throws IOException {
            int sum1 = 0;
            while (values.hasNext()) {
                sum1 += values.next().get();
            }
            output.collect(key, new IntWritable(sum1));
        }
    }
    //This is the Driver Module
    public static void main(String[] args) throws Exception {
        JobConf config = new JobConf(Linecount.class);
        config.setJobName("Linecount");
        config.setOutputKeyClass(Text.class);
        config.setOutputValueClass(IntWritable.class);
        config.setMapperClass(Map.class);
        config.setCombinerClass(Reduce.class);
        config.setReducerClass(Reduce.class);
        config.setInputFormat(TextInputFormat.class);
        config.setOutputFormat(TextOutputFormat.class);
        FileInputFormat.setInputPaths(config, new Path(args[0]));
        FileOutputFormat.setOutputPath(config, new Path(args[1]));
        JobClient.runJob(config);
    }
}

创建Java类，在一个类里面创建MapReduce程序，有利于直观查看代码，不利于java代码的管理，功能多就会混乱，对于简单测试环境可以使用。
eclipse，可以安装MapReduce插件便于本地化来开发测试

http://www.cnblogs.com/baixl/p/4154429.html 来自白大虾博客园hadoop2x版本
http://www.cnblogs.com/edisonchou/p/4297521.html 来自博客园另一位大神 hadoop1x版本
来自网易云课堂