예제 #1
0
  public static void main(String[] args) throws Exception {

    final String NAME_NODE = "hdfs://sandbox.hortonworks.com:8020";
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf);
    job.setJarByClass(WordCount.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(NullWritable.class);
    if (args.length > 2) {
      job.setNumReduceTasks(Integer.parseInt(args[2]));
    }

    job.setMapperClass(CountMapper.class);
    job.setReducerClass(CountReducer.class);
    job.setJarByClass(WordCount.class);
    job.setNumReduceTasks(1);

    FileInputFormat.addInputPath(job, new Path(args[0] + "data/plot_summaries.txt"));
    FileSystem fs = FileSystem.get(conf);
    // handle (e.g. delete) existing output path
    Path outputDestination = new Path(args[0] + args[1]);
    if (fs.exists(outputDestination)) {
      fs.delete(outputDestination, true);
    }

    // set output path & start job1
    FileOutputFormat.setOutputPath(job, outputDestination);
    int jobCompletionStatus = job.waitForCompletion(true) ? 0 : 1;
  }
예제 #2
0
  @Override
  public int run(String[] args) throws Exception {

    String locatorHost = args[0];
    int locatorPort = Integer.parseInt(args[1]);
    String hdfsHomeDir = args[2];

    System.out.println(
        "KnownKeysMRv2 invoked with args (locatorHost = "
            + locatorHost
            + " locatorPort = "
            + locatorPort
            + " hdfsHomeDir = "
            + hdfsHomeDir);

    Configuration conf = getConf();
    conf.set(GFInputFormat.INPUT_REGION, "partitionedRegion");
    conf.set(GFInputFormat.HOME_DIR, hdfsHomeDir);
    conf.setBoolean(GFInputFormat.CHECKPOINT, false);
    conf.set(GFOutputFormat.REGION, "validationRegion");
    conf.set(GFOutputFormat.LOCATOR_HOST, locatorHost);
    conf.setInt(GFOutputFormat.LOCATOR_PORT, locatorPort);

    Job job = Job.getInstance(conf, "knownKeysMRv2");
    job.setInputFormatClass(GFInputFormat.class);
    job.setOutputFormatClass(GFOutputFormat.class);

    job.setMapperClass(KnownKeysMRv2Mapper.class);
    job.setMapOutputKeyClass(GFKey.class);
    job.setMapOutputValueClass(PEIWritable.class);

    job.setReducerClass(KnownKeysMRv2Reducer.class);
    // job.setOutputKeyClass(String.class);
    // job.setOutputValueClass(ValueHolder.class);

    return job.waitForCompletion(false) ? 0 : 1;
  }
  public int run(String args[]) throws Exception {
    Configuration conf = getConf();

    /* creates a new job with given job name */
    Job job = Job.getInstance(conf, "Mat_vect_mul");
    job.setJarByClass(Mat_vect_mul.class);

    /* adds input-vector file to the cache */
    DistributedCache.addCacheFile(new Path(args[1]).toUri(), job.getConfiguration());

    /* set the key class and value class for the job output */
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    /* set mapper and reducer for the job */
    job.setMapperClass(Map1.class);
    job.setReducerClass(Reduce1.class);

    /* set the input foramt and output format for the job */
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    /* add path to the list of inputs for the map-reduce job */
    FileInputFormat.addInputPath(job, new Path(args[0]));

    /* set path of the output diretcory for the map-reduce job*/
    FileOutputFormat.setOutputPath(job, new Path(args[2]));

    /* Submit the job, then poll for progress until the job is complete */
    boolean succ = job.waitForCompletion(true);
    if (!succ) {
      System.out.println("Job failed, exiting");
      return -1;
    }

    return 0;
  }