Mapreduce实例——求平均值———代码

MyAverage.java:

package com.ya.mapreduce;

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.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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class MyAverage {
    static {
        try {
            System.load("D:\\install\\winutils-master\\winutils-master\\hadoop-3.0.0\\bin\\hadoop.dll");//建议采用绝对地址，bin目录下的hadoop.dll文件路径
        } catch (UnsatisfiedLinkError e) {
            System.err.println("Native code library failed to load.\n"+ e);
            System.exit(1);
        }
    }

    public static class Map extends Mapper<Object, Text, Text, IntWritable> {
        private static Text newKey = new Text();
        //实现map函数
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            // 将输入的纯文本文件的数据转化成String
            String line = value.toString();
            System.out.println(line);
            String arr[] = line.split("\t");
            newKey.set(arr[0]);
            int click = Integer.parseInt(arr[1]);
            context.write(newKey, new IntWritable(click));
        }
    }

    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        //实现reduce函数
        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int num = 0;
            int count = 0;
            for (IntWritable val : values) {
                num += val.get();//每个元素求和num
                count++;//统计元素的次数count
            }
            int avg = num / count;//计算平均数
            context.write(key, new IntWritable(avg));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        System.out.println("start");
        Job job = new Job(conf, "MyAverage");
        job.setJarByClass(MyAverage.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        Path in = new Path("hdfs://node01:8020/kkb/data/mapreduce4/in/goods_click.txt");
        Path out = new Path("hdfs://node01:8020/kkb/data/mapreduce4/out");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

结果：