MapReduce簡單一實例：wordcount--大資料紀錄片第五記

標籤：http   result   common   查詢   log   技術   alt   count   inf   

不知道為啥不是很想學習MapReduce方面的知識，不過現在這麼想可能過段時間還是免不了去學，這邊先記錄下一個MapReduce的執行個體wordcount代碼。

1、

pom.xml：

<dependencies>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>RELEASE</version>
    </dependency>
    <dependency>
        <groupId>org.apache.logging.log4j</groupId>
        <artifactId>log4j-core</artifactId>
        <version>2.8.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.8.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.8.3</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.8.3</version>
    </dependency>
</dependencies>


2、
WordCountMapper：
　　

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;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
   Text k = new Text();
   IntWritable v = new IntWritable(1);

   @Override
   protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      //擷取一行文本
      String line = value.toString();
      //根據分隔字元切分
      String[] words = line.split(" ");
      //輸出
      for (String word : words) {
         k.set(word);
         context.write(k, v);
      }
   }
}


3、
WordCountReducer：
　　

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
   int sum;
   IntWritable v = new IntWritable();

   @Override
   protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
      //累加求和
      sum = 0;
      for (IntWritable count : values) {
         sum += count.get();
      }
      //輸出
      v.set(sum);
      context.write(key, v);
   }
}


4、
WordCountDriver：

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCountDriver {
   public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

      //擷取配置資訊及封裝任務
      Configuration configuration = new Configuration();
      Job job = Job.getInstance(configuration);

      //設定jar載入路徑
      job.setJarByClass(WordCountDriver.class);

      //設定map和reduce類
      job.setMapperClass(WordCountMapper.class);
      job.setReducerClass(WordCountReducer.class);

      //設定map輸出
      job.setMapOutputKeyClass(Text.class);
      job.setOutputValueClass(IntWritable.class);

      //設定reduce輸出
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(IntWritable.class);

      //設定輸入和輸出路徑
      FileInputFormat.setInputPaths(job, new Path(args[0]));
      FileOutputFormat.setOutputPath(job, new Path(args[1]));

      //提交
      boolean result = job.waitForCompletion(true);
      System.exit(result ? 0 : 1);

   }
}


5、參數設定：

 

 

6、結果查詢：

 

MapReduce簡單一實例：wordcount--大資料紀錄片第五記