zoukankan      html  css  js  c++  java
  • Hadoop版Helloworld之wordcount运行示例

    1.编写一个统计单词数量的java程序,并命名为wordcount.java,代码如下:

    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;
    
    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();
        Job job = Job.getInstance(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(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
      }
    }

    2.声明java环境变量:

    export JAVA_HOME=/usr/java/default
    export PATH=${JAVA_HOME}/bin:${PATH}
    export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar

    其中JAVA_HOME根据自己安装java的实际路径进行配置。

    注意:如果不声明以上环境变量,那么在以后运行时,将会收到错误提示:

    3.编译并创建jar包。

    bin/hadoop com.sun.tools.javac.Main WordCount.java
    jar cf wc.jar WordCount*.class

    4.运行第三步骤生成的wc.jar包。此时要注意,output文件夹不要手工创建,系统运行后会自动创建。

    bin/hadoop jar wc.jar WordCount /user/root/wordcount/input /user/root/wordcount/output

    正常运行结束后,会在outPut文件夹下生成part-r-00000及__SUCCESS两个文件,其中part-r-00000存储分析结果。运行命令:

    bin/hadoop fs -cat /user/root/wordcount/output/part-r-00000

    即可查看分析结果,如下图所示:

    至此,本示例完成。

  • 相关阅读:
    git-for-windows 安装无图标的问题
    开源协议
    根据iframe获取window
    JS的checkbox状态切换dom无变化
    SQL条件!=null查不出数据
    jquery获取select选中项的文本
    泛型擦除
    树形菜单数据结构
    jqgrid动态填充select
    巨坑:jqgrid竟然取不到编辑模式下input的值
  • 原文地址:https://www.cnblogs.com/jizhong/p/6265072.html
Copyright © 2011-2022 走看看