学生总成绩报表
【hadoop|MapReduce实验——学生总成绩报表,学生平均成绩】
文章图片
Map类
package StudentScore_06;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import java.util.StringTokenizer;
public class MyMap extends
Mapper {
@Override
protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
//读取一行数据
String val = value.toString();
//把读取的数据以换行作为分隔符
StringTokenizer stringTokenizer = new StringTokenizer(val,"\n");
while (stringTokenizer.hasMoreElements()){
StringTokenizer tmp = new StringTokenizer(stringTokenizer.nextToken());
//对读取的一行的名称和成绩进行切分并写入到context对象中
String username = tmp.nextToken();
String score = tmp.nextToken();
context.write(new Text(username),new IntWritable(Integer.valueOf(score)));
}
}
}
Reduce 类
package StudentScore_06;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
public class MyReduce extends Reducer {
protected void reduce(Text key,Iterable values,Context context) throws IOException, InterruptedException {
//获取键值对集合 遍历对象
Iterator iterator = values.iterator();
int sum = 0;
//循环获取相同键的所有值并进行计算和
while(iterator.hasNext()){
int v = iterator.next().get();
sum+=v;
}
context.write(key,new IntWritable(sum));
}
}
Reduce类(求学生平均成绩)
package StudentAvgScore_07;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
public class MyReduce extends Reducer {
protected void reduce(Text key,Iterable values,Context context) throws IOException, InterruptedException {
//获取键值对集合 遍历对象
Iterator iterator = values.iterator();
int count = 0;
int sum = 0;
//循环获取相同键的所有值并进行计算和
while(iterator.hasNext()){
int v = iterator.next().get();
sum+=v;
count++;
}
int avg = sum/count;
context.write(key,new IntWritable(avg));
}
}
Job类
package StudentScore_06;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.io.Text;
import java.io.IOException;
public class TestJob {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
//1、获取作业对象
Job job = Job.getInstance(conf);
//2、设置主类
job.setJarByClass(TestJob.class);
//3、设置job参数
job.setMapperClass(MyMap.class);
job.setReducerClass(MyReduce.class);
//4 set map reduce output type
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//5、设置job输入输出
FileInputFormat.setInputPaths(job,new Path("file:///simple/source.txt"));
FileOutputFormat.setOutputPath(job,new Path("file:///simple/output"));
//6 commit job
System.out.println(job.waitForCompletion(true) ? 0 : 1);
;
}
}
推荐阅读
- hadoop|MapReduce实验——计算整数的最大值最小值
- 离线数仓|Hive 3.1.2 数仓基本概念 大致分层
- hadoop|13、Hive数据仓库——结合shell脚本企业实战用法,定时调度
- 电商数仓|电商数据仓库系统
- hadoop|5、Hive数据仓库——Hive分区及动态分区
- hive|面试官(hive表有数据,但为什么impala查询不到数据())
- Hive|Hive-sql连续登陆问题
- 大数据|大数据计算框架与平台--深入浅出分析
- #|用户行为采集平台搭建