zoukankan      html  css  js  c++  java
  • Mapreduce实验

    import java.io.IOException;
    import java.util.StringTokenizer;
    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 void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    Job job = Job.getInstance();
    job.setJobName("WordCount");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(doMapper.class);
    job.setReducerClass(doReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    Path in = new Path("hdfs://localhost:9000/mymapreduce1/in/123");
    Path out = new Path("hdfs://localhost:9000/mymapreduce1/out4");
    FileInputFormat.addInputPath(job, in);
    FileOutputFormat.setOutputPath(job, out);
    System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
    public static class doMapper extends Mapper<Object, Text, Text, IntWritable>{
    public static final IntWritable one = new IntWritable(1);
    public static Text word = new Text();
    @Override
    protected void map(Object key, Text value, Context context)
    throws IOException, InterruptedException {
    StringTokenizer tokenizer = new StringTokenizer(value.toString(), "	");
    word.set(tokenizer.nextToken());
    context.write(word, one);
    }
    }
    public static class doReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
    private IntWritable result = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context)
    throws IOException, InterruptedException {
    int sum = 0;
    for (IntWritable value : values) {
    sum += value.get();
    }
    result.set(sum);
    context.write(key, result);
    }
    }
    }
    

      

  • 相关阅读:
    资料工作手册
    这么点破玩艺,昨天我为了学会它,花了六小时
    压力太大,使人过早衰老
    这是真的么。
    我可怜的好友。。。
    操了,上个网怎么就这么憋屈呢
    编程习惯,代码风格,其实很重要
    其实,我并不喜欢脚本语言
    咱也起一卦,看看北京是否还会继续下雨
    我一点不偏激,只是,我从不抱有侥幸思想
  • 原文地址:https://www.cnblogs.com/cuijunfeng/p/11768725.html
Copyright © 2011-2022 走看看