Mapreduce实验一：WordCountTest

1.确定Hadoop处于启动状态

[root@neusoft-master ~]# jps

23763 Jps
3220 SecondaryNameNode
3374 ResourceManager
2935 NameNode
3471 NodeManager
3030 DataNode

2. 在/usr/local/filecotent下新建hellodemo文件，并写入以下内容，以\t（tab键隔开）

[root@neusoft-master filecontent]# vi hellodemo
hello you
hello me

3.在linux中执行以下步骤：

3.1hdfs中创建data目录

[root@neusoft-master filecontent]# hadoop dfs -mkdir /data

3.2 将/usr/local/filecontent/hellodemo 上传到hdfs的data目录中

[root@neusoft-master filecontent]# hadoop dfs -put hellodemo /data

3.3查看data目录下的内容

[root@neusoft-master filecontent]# hadoop dfs -ls /data
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

17/02/01 00:39:44 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Found 1 items
-rw-r--r-- 3 root supergroup 19 2017-02-01 00:39 /data/hellodemo

3.4查看hellodemo的文件内容

[root@neusoft-master filecontent]# hadoop dfs -text /data/hellodemo

4. 编写WordCountTest.java并打包成jar文件

 package Mapreduce;

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 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.input.TextInputFormat;
 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

 /**
  * 假设有个目录结构
  * /目录1
  * /目录1/hello.txt
  * /目录1/目录2/hello.txt
  *
  * 问：统计/目录1下面所有的文件中的单词技术
  *
  */
 public class WordCountTest {
     public static void main(String[] args) throws Exception {
         //2将自定义的MyMapper和MyReducer组装在一起
         Configuration conf=new Configuration();
         String jobName=WordCountTest.class.getSimpleName();
         //1首先寫job，知道需要conf和jobname在去創建即可
         Job job = Job.getInstance(conf, jobName);

         //*13最后，如果要打包运行改程序，则需要调用如下行
         job.setJarByClass(WordCountTest.class);

         //3读取HDFS內容：FileInputFormat在mapreduce.lib包下
         FileInputFormat.setInputPaths(job, new Path("hdfs://neusoft-master:9000/data/hellodemo"));
         //4指定解析<k1,v1>的类（谁来解析键值对）
         job.setInputFormatClass(TextInputFormat.class);
         //5指定自定义mapper类
         job.setMapperClass(MyMapper.class);
         //6指定map输出的key2的类型和value2的类型  <k2,v2>
         job.setMapOutputKeyClass(Text.class);
         job.setMapOutputValueClass(LongWritable.class);
         //7分区(默认1个)，排序，分组，规约 采用 默认

         //接下来采用reduce步骤
         //8指定自定义的reduce类
         job.setReducerClass(MyReducer.class);
         //9指定输出的<k3,v3>类型
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(LongWritable.class);
         //10指定输出<K3,V3>的类
         job.setOutputFormatClass(TextOutputFormat.class);
         //11指定输出路径
         FileOutputFormat.setOutputPath(job, new Path("hdfs://neusoft-master:9000/out1"));

         //12写的mapreduce程序要交给resource manager运行
         job.waitForCompletion(true);
     }
     private static class MyMapper extends Mapper<LongWritable, Text, Text,LongWritable>{
         Text k2 = new Text();
         LongWritable v2 = new LongWritable();
         @Override
         protected void map(LongWritable key, Text value,//三个参数
                 Mapper<LongWritable, Text, Text, LongWritable>.Context context)
                 throws IOException, InterruptedException {
             String line = value.toString();
             String[] splited = line.split("\t");//因为split方法属于string字符的方法，首先应该转化为string类型在使用
             for (String word : splited) {
                 //word表示每一行中每个单词
                 //对K2和V2赋值
                 k2.set(word);
                 v2.set(1L);
                 context.write(k2, v2);
             }
         }
     }
     private static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
         LongWritable v3 = new LongWritable();
         @Override //k2表示单词，v2s表示不同单词出现的次数，需要对v2s进行迭代
         protected void reduce(Text k2, Iterable<LongWritable> v2s,  //三个参数
                 Reducer<Text, LongWritable, Text, LongWritable>.Context context)
                 throws IOException, InterruptedException {
             long sum =0;
             for (LongWritable v2 : v2s) {
                 //LongWritable本身是hadoop类型，sum是java类型
                 //首先将LongWritable转化为字符串，利用get方法
                 sum+=v2.get();
             }
             v3.set(sum);
             //将k2,v3写出去
             context.write(k2, v3);
         }
     }
 }

WordCountTest.java

//1首先寫job，知道需要conf和jobname在去創建即可
Job job = Job.getInstance(conf, jobName);

//2将自定义的MyMapper和MyReducer组装在一起
Configuration conf=new Configuration();
String jobName=WordCountTest.class.getSimpleName();

FileInputFormat.setInputPaths(job, new Path("hdfs://neusoft-master:9000/data/hellodemo"));
//4指定解析<k1,v1>的类（谁来解析键值对）
job.setInputFormatClass(TextInputFormat.class);
//5指定自定义mapper类
job.setMapperClass(MyMapper.class);
//6指定map输出的key2的类型和value2的类型 <k2,v2>
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//7分区(默认1个)，排序，分组，规约 采用 默认

//接下来采用reduce步骤
//8指定自定义的reduce类
job.setReducerClass(MyReducer.class);
//9指定输出的<k3,v3>类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
//10指定输出<K3,V3>的类
job.setOutputFormatClass(TextOutputFormat.class);
//11指定输出路径
FileOutputFormat.setOutputPath(job, new Path("hdfs://neusoft-master:9000/out1"));

//12写的mapreduce程序要交给resource manager运行
job.waitForCompletion(true);

//*13最后，如果要打包运行改程序，则需要调用如下行
job.setJarByClass(WordCountTest.class);

mapper任务

private static class MyMapper extends Mapper<LongWritable, Text, Text,LongWritable>{
Text k2 = new Text();
LongWritable v2 = new LongWritable();
@Override
protected void map(LongWritable key, Text value,//三个参数
Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] splited = line.split("\t");//因为split方法属于string字符的方法，首先应该转化为string类型在使用
for (String word : splited) {
//word表示每一行中每个单词
//对K2和V2赋值
k2.set(word);
v2.set(1L);
context.write(k2, v2);
}
}
}

Reducer任务

private static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
LongWritable v3 = new LongWritable();
@Override //k2表示单词，v2s表示不同单词出现的次数，需要对v2s进行迭代
protected void reduce(Text k2, Iterable<LongWritable> v2s, //三个参数
Reducer<Text, LongWritable, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
long sum =0;
for (LongWritable v2 : v2s) {
//LongWritable本身是hadoop类型，sum是java类型
//首先将LongWritable转化为字符串，利用get方法
sum+=v2.get();
}
v3.set(sum);
//将k2,v3写出去
context.write(k2, v3);
}
}
}

5.打成jar包并指定主类，在linux中运行

[root@neusoft-master filecontent]# hadoop jar hellodemo.jar
17/02/01 01:00:48 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
17/02/01 01:00:48 INFO client.RMProxy: Connecting to ResourceManager at neusoft-master/192.168.191.130:8080
17/02/01 01:00:49 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
17/02/01 01:00:49 INFO input.FileInputFormat: Total input paths to process : 1
17/02/01 01:00:49 INFO mapreduce.JobSubmitter: number of splits:1
17/02/01 01:00:49 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1485556908836_0003
17/02/01 01:00:49 INFO impl.YarnClientImpl: Submitted application application_1485556908836_0003
17/02/01 01:00:49 INFO mapreduce.Job: The url to track the job: http://neusoft-master:8088/proxy/application_1485556908836_0003/
17/02/01 01:00:49 INFO mapreduce.Job: Running job: job_1485556908836_0003
17/02/01 01:00:56 INFO mapreduce.Job: Job job_1485556908836_0003 running in uber mode : false
17/02/01 01:00:56 INFO mapreduce.Job: map 0% reduce 0%
17/02/01 01:01:00 INFO mapreduce.Job: map 100% reduce 0%
17/02/01 01:01:05 INFO mapreduce.Job: map 100% reduce 100%
17/02/01 01:01:06 INFO mapreduce.Job: Job job_1485556908836_0003 completed successfully
17/02/01 01:01:06 INFO mapreduce.Job: Counters: 49
File System Counters
FILE: Number of bytes read=65
FILE: Number of bytes written=220211
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=125
HDFS: Number of bytes written=19
HDFS: Number of read operations=6
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Job Counters
Launched map tasks=1
Launched reduce tasks=1
Data-local map tasks=1
Total time spent by all maps in occupied slots (ms)=2753
Total time spent by all reduces in occupied slots (ms)=3020
Total time spent by all map tasks (ms)=2753
Total time spent by all reduce tasks (ms)=3020
Total vcore-seconds taken by all map tasks=2753
Total vcore-seconds taken by all reduce tasks=3020
Total megabyte-seconds taken by all map tasks=2819072
Total megabyte-seconds taken by all reduce tasks=3092480
Map-Reduce Framework
Map input records=2
Map output records=4
Map output bytes=51
Map output materialized bytes=65
Input split bytes=106
Combine input records=0
Combine output records=0
Reduce input groups=3
Reduce shuffle bytes=65
Reduce input records=4
Reduce output records=3
Spilled Records=8
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=40
CPU time spent (ms)=1550
Physical memory (bytes) snapshot=448503808
Virtual memory (bytes) snapshot=3118854144
Total committed heap usage (bytes)=319291392
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=19
File Output Format Counters
Bytes Written=19

*********************

6.查看输出文件内容

[root@neusoft-master filecontent]# hadoop dfs -ls /out1
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

17/02/01 01:01:45 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Found 2 items
-rw-r--r-- 3 root supergroup 0 2017-02-01 01:01 /out1/_SUCCESS
-rw-r--r-- 3 root supergroup 19 2017-02-01 01:01 /out1/part-r-00000

[root@neusoft-master filecontent]# hadoop dfs -text /out1/part-r-00000
DEPRECATED: Use of this script to execute hdfs command is deprecated.
Instead use the hdfs command for it.

17/02/01 01:03:19 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
hello 2
me 1
you 1

7.结果分析

     根据上传到Hdfs中得文件和所得结果分析，所得结果是正确无误的。

注意：主函数中得方法有一些步骤是可省的，需要着重注意

    其中第6、8、10步均可省略

public static void main(String[] args) throws Exception {
//必须要传递的是自定的mapper和reducer的类，输入输出的路径必须指定，输出的类型<k3,v3>必须指定
//2将自定义的MyMapper和MyReducer组装在一起
Configuration conf=new Configuration();
String jobName=WordCountTest.class.getSimpleName();
//1首先寫job，知道需要conf和jobname在去創建即可
Job job = Job.getInstance(conf, jobName);

//*13最后，如果要打包运行改程序，则需要调用如下行
job.setJarByClass(WordCountTest.class);

//3读取HDFS內容：FileInputFormat在mapreduce.lib包下
FileInputFormat.setInputPaths(job, new Path("hdfs://neusoft-master:9000/data/hellodemo"));
//4指定解析<k1,v1>的类（谁来解析键值对）
//*指定解析的类可以省略不写，因为设置解析类默认的就是TextInputFormat.class
job.setInputFormatClass(TextInputFormat.class);
//5指定自定义mapper类
job.setMapperClass(MyMapper.class);
//6指定map输出的key2的类型和value2的类型 <k2,v2>
//*下面两步可以省略，当<k3,v3>和<k2,v2>类型一致的时候,<k2,v2>类型可以不指定
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//7分区(默认1个)，排序，分组，规约 采用 默认

//接下来采用reduce步骤
//8指定自定义的reduce类
job.setReducerClass(MyReducer.class);
//9指定输出的<k3,v3>类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
//10指定输出<K3,V3>的类
//*下面这一步可以省
job.setOutputFormatClass(TextOutputFormat.class);
//11指定输出路径
FileOutputFormat.setOutputPath(job, new Path("hdfs://neusoft-master:9000/out1"));

//12写的mapreduce程序要交给resource manager运行
job.waitForCompletion(true);
}

END