这篇文章主要讲解了“怎么用MapReduce列出工资比上司高的员工姓名及工资”，文中的讲解内容简单清晰，易于学习与理解，下面请大家跟着小编的思路慢慢深入，一起来研究和学习“怎么用MapReduce列出工资比上司高的员工姓名及工资”吧！
数据
EMPNO ENAME JOB MGR HIREDATE SAL COMM DEPTNO
7369 SMITH CLERK 7902 17-12月-80 800 20
7499 ALLEN SALESMAN 7698 20-2月 -81 1600 300 30
7521 WARD SALESMAN 7698 22-2月 -81 1250 500 30
7566 JONES MANAGER 7839 02-4月 -81 2975 20
7654 MARTIN SALESMAN 7698 28-9月 -81 1250 1400 30
7698 BLAKE MANAGER 7839 01-5月 -81 2850 30
7782 CLARK MANAGER 7839 09-6月 -81 2450 10
7839 KING PRESIDENT 17-11月-81 5000 10
7844 TURNER SALESMAN 7698 08-9月 -81 1500 0 30
7900 JAMES CLERK 7698 03-12月-81 950 30
7902 FORD ANALYST 7566 03-12月-81 3000 20
7934 MILLER CLERK 7782 23-1月 -82 1300 10
代码
package cn.kissoft.hadoop.week07;
import java.io.IOException;
import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import cn.kissoft.hadoop.util.HdfsUtil;
/**
* Homework-05:列出工资比上司高的员工姓名及其工资
*
* @author wukong(jinsong.sun@139.com)
*/
public class MorePayThanHigherups extends Configured implements Tool {
public static class M extends Mapper<LongWritable, Text, Text, Text> {
@Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String id = line.substring(1, 11).trim();
String name = line.substring(11, 21).trim();
String sal = line.substring(57, 68).trim();
String pid = line.substring(32, 43).trim();
context.write(new Text(pid), new Text("EMP," + pid + "," + name
+ "," + sal + "," + id));
context.write(new Text(id), new Text("BOSS," + id + "," + name
+ "," + sal + "," + pid));
}
}
public static class R extends Reducer<Text, Text, NullWritable, Text> {
@Override
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
String bossName = null;
int bossSal = 0;
List<Emp> emps = new ArrayList<Emp>();
for (Text value : values) {
System.out.println(value);
String[] ss = value.toString().split(",");
if (ss[0].equals("EMP")) {// 可能有多个
emps.add(new Emp(ss[2], Integer.parseInt(ss[3])));
} else if (ss[0].equals("BOSS")) {// 只有一个
bossName = ss[2];
bossSal = Integer.parseInt(ss[3]);
}
}
for (Emp e : emps) {
if (bossSal > 0 && e.getSal() > bossSal) {
context.write(null, new Text(e.getName() + "," + e.getSal()
+ "," + bossName + "," + bossSal));
}
}
}
}
@Override
public int run(String[] args) throws Exception {
Configuration conf = getConf();
Job job = new Job(conf, "Job-TotalSalaryByDeptMR");
job.setJarByClass(this.getClass());
job.setMapperClass(M.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setReducerClass(R.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(NullWritable.class); // 指定输出的KEY的格式
job.setOutputValueClass(Text.class); // 指定输出的VALUE的格式
FileInputFormat.addInputPath(job, new Path(args[0])); // 输入路径
FileOutputFormat.setOutputPath(job, new Path(args[1])); // 输出路径
return job.waitForCompletion(true) ? 0 : 1;
// job.waitForCompletion(true);
// return job.isSuccessful() ? 0 : 1;
}
/**
*
* @param args hdfs://bd11:9000/user/wukong/w07/emp.txt hdfs://bd11:9000/user/wukong/w07/out05/
* @throws Exception
*/
public static void main(String[] args) throws Exception {
checkArgs(args);
HdfsUtil.rm(args[1], true);
Date start = new Date();
int res = ToolRunner.run(new Configuration(),
new MorePayThanHigherups(), args);
printExcuteTime(start, new Date());
System.exit(res);
}
/**
* 判断参数个数是否正确，如果无参数运行则显示以作程序说明。
*
* @param args
*/
private static void checkArgs(String[] args) {
if (args.length != 2) {
System.err.println("");
System.err.println("Usage: Test_1 < input path > < output path > ");
System.err
.println("Example: hadoop jar ~/Test_1.jar hdfs://localhost:9000/home/james/Test_1 hdfs://localhost:9000/home/james/output");
System.err.println("Counter:");
System.err.println("\t" + "LINESKIP" + "\t"
+ "Lines which are too short");
System.exit(-1);
}
}
/**
* 打印程序运行时间
*
* @param start
* @param end
*/
private static void printExcuteTime(Date start, Date end) {
DateFormat formatter = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
float time = (float) ((end.getTime() - start.getTime()) / 60000.0);
System.out.println("任务开始：" + formatter.format(start));
System.out.println("任务结束：" + formatter.format(end));
System.out.println("任务耗时：" + String.valueOf(time) + " 分钟");
}
}
class Emp {
private String name;
private int sal;
/**
* @param name
* @param sal
*/
public Emp(String name, int sal) {
super();
this.name = name;
this.sal = sal;
}
public String getName() {
return name;
}
public int getSal() {
return sal;
}
}运行结果
FORD,3000,JONES,2975
控制台
14/08/31 23:09:06 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
14/08/31 23:09:06 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
14/08/31 23:09:07 INFO input.FileInputFormat: Total input paths to process : 1
14/08/31 23:09:07 WARN snappy.LoadSnappy: Snappy native library not loaded
14/08/31 23:09:07 INFO mapred.JobClient: Running job: job_local1925230448_0001
14/08/31 23:09:07 INFO mapred.LocalJobRunner: Waiting for map tasks
14/08/31 23:09:07 INFO mapred.LocalJobRunner: Starting task: attempt_local1925230448_0001_m_000000_0
14/08/31 23:09:07 INFO mapred.Task: Using ResourceCalculatorPlugin : null
14/08/31 23:09:07 INFO mapred.MapTask: Processing split: hdfs://bd11:9000/user/wukong/w07/emp.txt:0+1119
14/08/31 23:09:07 INFO mapred.MapTask: io.sort.mb = 100
14/08/31 23:09:07 INFO mapred.MapTask: data buffer = 79691776/99614720
14/08/31 23:09:07 INFO mapred.MapTask: record buffer = 262144/327680
14/08/31 23:09:07 INFO mapred.MapTask: Starting flush of map output
14/08/31 23:09:07 INFO mapred.MapTask: Finished spill 0
14/08/31 23:09:07 INFO mapred.Task: Task:attempt_local1925230448_0001_m_000000_0 is done. And is in the process of commiting
14/08/31 23:09:07 INFO mapred.LocalJobRunner:
14/08/31 23:09:07 INFO mapred.Task: Task 'attempt_local1925230448_0001_m_000000_0' done.
14/08/31 23:09:07 INFO mapred.LocalJobRunner: Finishing task: attempt_local1925230448_0001_m_000000_0
14/08/31 23:09:07 INFO mapred.LocalJobRunner: Map task executor complete.
14/08/31 23:09:07 INFO mapred.Task: Using ResourceCalculatorPlugin : null
14/08/31 23:09:07 INFO mapred.LocalJobRunner:
14/08/31 23:09:07 INFO mapred.Merger: Merging 1 sorted segments
14/08/31 23:09:07 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 766 bytes
14/08/31 23:09:07 INFO mapred.LocalJobRunner:
EMP,,KING,5000,7839
BOSS,7369,SMITH,800,7902
BOSS,7499,ALLEN,1600,7698
BOSS,7521,WARD,1250,7698
EMP,7566,FORD,3000,7902
BOSS,7566,JONES,2975,7839
BOSS,7654,MARTIN,1250,7698
EMP,7698,WARD,1250,7521
EMP,7698,JAMES,950,7900
EMP,7698,MARTIN,1250,7654
EMP,7698,ALLEN,1600,7499
BOSS,7698,BLAKE,2850,7839
EMP,7698,TURNER,1500,7844
BOSS,7782,CLARK,2450,7839
EMP,7782,MILLER,1300,7934
BOSS,7839,KING,5000,
EMP,7839,CLARK,2450,7782
EMP,7839,BLAKE,2850,7698
EMP,7839,JONES,2975,7566
BOSS,7844,TURNER,1500,7698
BOSS,7900,JAMES,950,7698
EMP,7902,SMITH,800,7369
BOSS,7902,FORD,3000,7566
BOSS,7934,MILLER,1300,7782
14/08/31 23:09:07 INFO mapred.Task: Task:attempt_local1925230448_0001_r_000000_0 is done. And is in the process of commiting
14/08/31 23:09:07 INFO mapred.LocalJobRunner:
14/08/31 23:09:07 INFO mapred.Task: Task attempt_local1925230448_0001_r_000000_0 is allowed to commit now
14/08/31 23:09:07 INFO output.FileOutputCommitter: Saved output of task 'attempt_local1925230448_0001_r_000000_0' to hdfs://bd11:9000/user/wukong/w07/out05
14/08/31 23:09:07 INFO mapred.LocalJobRunner: reduce > reduce
14/08/31 23:09:07 INFO mapred.Task: Task 'attempt_local1925230448_0001_r_000000_0' done.
14/08/31 23:09:08 INFO mapred.JobClient: map 100% reduce 100%
14/08/31 23:09:08 INFO mapred.JobClient: Job complete: job_local1925230448_0001
14/08/31 23:09:08 INFO mapred.JobClient: Counters: 19
14/08/31 23:09:08 INFO mapred.JobClient: File Output Format Counters
14/08/31 23:09:08 INFO mapred.JobClient: Bytes Written=21
14/08/31 23:09:08 INFO mapred.JobClient: File Input Format Counters
14/08/31 23:09:08 INFO mapred.JobClient: Bytes Read=1119
14/08/31 23:09:08 INFO mapred.JobClient: FileSystemCounters
14/08/31 23:09:08 INFO mapred.JobClient: FILE_BYTES_READ=1082
14/08/31 23:09:08 INFO mapred.JobClient: HDFS_BYTES_READ=2238
14/08/31 23:09:08 INFO mapred.JobClient: FILE_BYTES_WRITTEN=139882
14/08/31 23:09:08 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=21
14/08/31 23:09:08 INFO mapred.JobClient: Map-Reduce Framework
14/08/31 23:09:08 INFO mapred.JobClient: Reduce input groups=13
14/08/31 23:09:08 INFO mapred.JobClient: Map output materialized bytes=770
14/08/31 23:09:08 INFO mapred.JobClient: Combine output records=0
14/08/31 23:09:08 INFO mapred.JobClient: Map input records=12
14/08/31 23:09:08 INFO mapred.JobClient: Reduce shuffle bytes=0
14/08/31 23:09:08 INFO mapred.JobClient: Reduce output records=1
14/08/31 23:09:08 INFO mapred.JobClient: Spilled Records=48
14/08/31 23:09:08 INFO mapred.JobClient: Map output bytes=716
14/08/31 23:09:08 INFO mapred.JobClient: Total committed heap usage (bytes)=326107136
14/08/31 23:09:08 INFO mapred.JobClient: SPLIT_RAW_BYTES=105
14/08/31 23:09:08 INFO mapred.JobClient: Map output records=24
14/08/31 23:09:08 INFO mapred.JobClient: Combine input records=0
14/08/31 23:09:08 INFO mapred.JobClient: Reduce input records=24
任务开始：2014-08-31 23:09:06
任务结束：2014-08-31 23:09:08
任务耗时：0.023083333 分钟
感谢各位的阅读，以上就是“怎么用MapReduce列出工资比上司高的员工姓名及工资”的内容了，经过本文的学习后，相信大家对怎么用MapReduce列出工资比上司高的员工姓名及工资这一问题有了更深刻的体会，具体使用情况还需要大家实践验证。这里是天达云，小编将为大家推送更多相关知识点的文章，欢迎关注！