美文网首页
hadoop实战-3.windows上远程运行mapreduce

hadoop实战-3.windows上远程运行mapreduce

作者: 笨鸡 | 来源:发表于2019-03-14 15:22 被阅读0次

    1.WordMapper.java

    package WordCount;
    
    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 WordMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            final IntWritable ONE = new IntWritable(1);
    
            String s = value.toString();
            String[] words = s.split(" ");
            for (String word : words) {
                context.write(new Text(word), ONE);
            }
        }
    }
    

    2.WordReducer.java

    package WordCount;
    
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Reducer;
    
    import java.io.IOException;
    
    public class WordReducer extends Reducer<Text, IntWritable, Text, LongWritable> {
            @Override
        protected void reduce(Text key, Iterable<IntWritable> values,
                              Reducer<Text, IntWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
            long count = 0;
            for (IntWritable value : values) {
                count += value.get();
            }
            context.write(key, new LongWritable(count));
        }
    }
    

    3.Test.java

    package WordCount;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    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;
    
    public class Test {
    
        public static void main(String[] args) throws Exception{
            Configuration conf = new Configuration();
    
            conf.set("fs.defaultFS","hdfs://master:9000/");
            conf.set("mapreduce.job.jar", "out/artifacts/HelloMapReduce.jar");
            conf.set("mapreduce.framework.name","yarn");
            conf.set("mapreduce.jobhistory.address","192.168.56.100:10020");
            conf.set("yarn.resourcemanager.hostname","master");
            conf.set("mapreduce.app-submission.cross-platform", "true");
    
            Job job = Job.getInstance(conf);
    
    //        job.setJarByClass(Test.class);
    
            job.setMapperClass(WordMapper.class);
            job.setReducerClass(WordReducer.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(LongWritable.class);
    
            FileInputFormat.setInputPaths(job, "/hello.txt");
            FileOutputFormat.setOutputPath(job, new Path("/output/"));
    
            job.waitForCompletion(true);
        }
    }
    

    4.生成jar包

    参考 https://www.cnblogs.com/airnew/p/9540982.html

    5.运行结果

    mapreduce1.png
    map.png
    reduce.png
    mapreduce2.png
    mapreduce生成output.png
    mapreduce-result.png

    喜欢的话,希望您动动小手点个赞支持下哦

    相关文章

      网友评论

          本文标题:hadoop实战-3.windows上远程运行mapreduce

          本文链接:https://www.haomeiwen.com/subject/pczqmqtx.html