创建一个maven文件ComputeScore

修改pom文件

	<dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-client</artifactId><version>2.6.0</version><scope>test</scope></dependency>

完整pom

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"><modelVersion>4.0.0</modelVersion><groupId>com.panzi.cn</groupId><artifactId>MapReduce</artifactId><version>0.0.1-SNAPSHOT</version><packaging>jar</packaging><name>MapReduce</name><url>http://maven.apache.org</url><properties><project.build.sourceEncoding>UTF-8</project.build.sourceEncoding></properties><dependencies><dependency><groupId>junit</groupId><artifactId>junit</artifactId><version>3.8.1</version><scope>test</scope></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-client</artifactId><version>2.6.0</version><scope>test</scope></dependency></dependencies>
</project>

创建computescore的java文件

代码

package com.panzi.cn.ComputeScore;import java.io.IOException;import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.FloatWritable;
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 computescore {// 编写map类// 右键——source——map——ok// 转化String// 分片// 读取public static class myMapper extends Mapper<Object, Text, Text, FloatWritable> {@Overrideprotected void map(Object key, Text value, Mapper<Object, Text, Text, FloatWritable>.Context context)throws IOException, InterruptedException {// TODO Auto-generated method stubString val = value.toString();String[] vals = val.split(" ");float sc = Float.parseFloat(vals[2]);context.write(new Text(vals[0]), new FloatWritable(sc));}}// 编写reducer类// Text:liming {80 90}public static class myReducer extends Reducer<Text, FloatWritable, Text, FloatWritable> {// key:liming// values:{80 90}@Overrideprotected void reduce(Text key, Iterable<FloatWritable> values,Reducer<Text, FloatWritable, Text, FloatWritable>.Context context)throws IOException, InterruptedException {// TODO Auto-generated method stubfloat sum = 0;int i = 0;for (FloatWritable value : values) {sum += value.get();i++;}sum = sum / i;context.write(key, new FloatWritable(sum));}}public static void main(String[] args)throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {// TODO Auto-generated method stubif (args.length < 2) {System.out.println("the argument are adfadf");System.exit(0);}Configuration conf = new Configuration();String[] arg = new GenericOptionsParser(conf, args).getRemainingArgs();Job job = new Job(conf, "score"); // 设置环境参数job.setJarByClass(computescore.class); // 设置整个程序的类名job.setMapperClass(myMapper.class);job.setReducerClass(myReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(FloatWritable.class);FileInputFormat.addInputPath(job, new Path(arg[0]));FileOutputFormat.setOutputPath(job, new Path(arg[1]));System.exit(job.waitForCompletion(true) ? 0 : 1);}
}

封装

右键项目——export——选择java——JAR File——next——

——next——

点击Finish
上传到虚拟机上的hadoop软件目录下的share/hadoop/mapreduce中

运行

[root@master1 mapreduce]# hadoop jar wordcount.jar /data/ /out2

运行成功

查看结果

结果保存在：

[root@master1 mapreduce]# hdfs dfs -ls /out2
[root@master1 mapreduce]# hdfs dfs -cat /out2/part-r-00000

完成啦！