MapReduce的基本内容介绍（附代码）

1、WordCount程序

1.1 WordCount源程序

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
    public WordCount() {
    }
     public static void main(String[] args) throws Exception {
        Configuration cOnf= new Configuration();
        String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
        if(otherArgs.length <2) {
            System.err.println("Usage: wordcount  [...] ");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class); 
        for(int i = 0; i  {
        private IntWritable result = new IntWritable();
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable values, Reducer.Context context) throws IOException, InterruptedException {
            int sum = 0;
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
}

1.2 运行程序，Run As->Java Applicatiion

1.3 编译打包程序，产生Jar文件

Spark 2

以上就是MapReduce的基本内容介绍（附代码）的详细内容，更多请关注 第一PHP社区 其它相关文章！