大数据系列:hadoop 入门(hello world 版)

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 java.io.IOException;

public class DriverWordCount {
/******************************************map stage********************************************************/
    public static class WCMap extends Mapper<LongWritable, Text,Text,LongWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] words=value.toString().split(",");

            for (String vocabulary : words) {
                Text k2=new Text(vocabulary);
                LongWritable v2=new LongWritable(1L);
                context.write(k2,v2);
            }
        }
    }

    /******************************************shuffle*****************reduce  stage********************************************************/
    /******************************************分区分组  相同的key 会进入到同一个reduce中********************************************************/

    public static class WC_Reduce extends Reducer<Text,LongWritable,Text,LongWritable>{
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            long sum=0;
            for (LongWritable value : values) {
                sum+=value.get();
            }
            context.write(key,new LongWritable(sum));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // MapReduce 分为两个部分  第一部分map  第二部 reduce

        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration, DriverWordCount.class.getSimpleName());

        job.setJarByClass(DriverWordCount.class);

        FileInputFormat.addInputPath(job,new Path(args[0]));

        job.setMapperClass(WCMap.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(LongWritable.class);



        job.setReducerClass(WC_Reduce.class);
        job.setMapOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        job.waitForCompletion(true);
    }
}

运行 hadoop jar hadoop-1.0-SNAPSHOT.jar DriverWordCount /software/dianxin_data.csv /out2