问题描述:
在输入文件中,有多个,其中每个输入文件代表一个学生的各科成绩,其中每行的数据形式为<科目,成绩>,你需要将每个文件中的每科目的成绩进行统计,然后求平均值。
输入文件格式:
这里有三个学生:
输出文件格式:
实例代码:
package com.test;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class StudentAverage {
public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
@SuppressWarnings("deprecation")
Job job = new Job(new Configuration(), "StudentAverage");
job.setJarByClass(StudentAverage.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path("hdfs://localhost:9000/Student/input"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/Student/output"));
job.waitForCompletion(true);
System.out.println("运行结束!");
}
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable>{
protected void map(LongWritable key, Text value,
org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws java.io.IOException, InterruptedException {
String[] data = value.toString().split(" ");
context.write(new Text(data[0]), new IntWritable(Integer.parseInt(data[1])));
};
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
protected void reduce(Text key, java.lang.Iterable<IntWritable> values, Context context)
throws java.io.IOException, InterruptedException {
int average = 0;
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
average = sum / 3;
context.write(new Text(key), new IntWritable(average));
};
}
}