首页 > 代码库 > 【大数据系列】windows下连接Linux环境开发

【大数据系列】windows下连接Linux环境开发

一、配置文件

1.core-site.xml

<configuration>
   <property>
     <name>fs.defaultFS</name>
     <value>hdfs://www.node1.com:9000</value>
   </property>
</configuration>

2、hdfs-site.xml

<configuration>
  <property>
    <name>dfs.replication</name>
    <value>2</value>
  </property>
</configuration>

3、yarn-site.xml

<property>
<name>yarn.resourcemanager.hostname</name>
<value>www.node1.com</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>

4、slaves

www.node2.com
www.node3.com

二、建立本地连接

三、创建MapReduceProject

1、File  -- new - Other  --MapReduceProject 

2、建立测试文件

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 WordCount {
    public static class TokenizerMapper 
    extends Mapper<Object, Text, Text, IntWritable>{

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context
    ) throws IOException, InterruptedException {
    StringTokenizer itr = new StringTokenizer(value.toString());
    while (itr.hasMoreTokens()) {
    word.set(itr.nextToken());
    context.write(word, one);
    }
    }
    }

    public static class IntSumReducer 
    extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, 
    Context context
    ) throws IOException, InterruptedException {
    int sum = 0;
    for (IntWritable val : values) {
    sum += val.get();
    }
    result.set(sum);
    context.write(key, result);
    }
    }

    public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
    System.err.println(otherArgs.length);
    System.err.println("Usage: wordcount <in> <out>");
    System.exit(2);
    }
    System.out.println(otherArgs[0]);
    System.out.println(otherArgs[1]);
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

3、run configuration

hdfs://www.node1.com:9000/usr/wc
hdfs://www.node1.com:9000/usr/wc/output

4、run

技术分享

5、part-r-00000

apple    2
banana    1
cat    1
dog    1
hadoop    1
hadpp    1
hello    1
mapreduce    1
name    1
world    1
yarn    2

6、wc.txt

hadoop hello
hadpp world
apple dog
banana cat
mapreduce name
yarn
apple
yarn

 

【大数据系列】windows下连接Linux环境开发