2018年安徽省大数据比赛MapReduce题目解答第二题

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/qq_41479464/article/details/101922670

num.txt在此博客中：https://blog.csdn.net/qq_41479464/article/details/101922339

使用MR的处理方式,去除num.txt中以2开头的数字,并且统计每个数字出现的次数将结果保存为num2.txt（10分）

 主函数：

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;



public class MapReduceNum {
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf,MapReduceNum.class.getSimpleName());
		job.setJarByClass(MapReduceNum.class);
		FileInputFormat.addInputPath(job, new Path(args[0]));
		job.setMapperClass(MyMap.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setReducerClass(MyRed.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		job.waitForCompletion(true);
		
	}
	

}

Map函数：

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class MyMap extends Mapper<LongWritable, Text, Text, IntWritable>{
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
			throws IOException, InterruptedException {
		String line[] = value.toString().split(",");
		for (String string : line) {
			if(!string.startsWith("2"));
			context.write(new Text(string),new IntWritable(1));
		}		
		
	}

}

Reduce函数：

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class MyRed extends Reducer<Text, IntWritable, Text, LongWritable> {
	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Reducer<Text, IntWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
		long count = 0l;
		for (IntWritable val : values) {
			count = count +val.get();
		}
		//将结果输出，输出到hdfs上
		context.write(new Text(key), new LongWritable(count));
	}

}