Example usage for org.apache.hadoop.mapreduce Job setJarByClass

List of usage examples for org.apache.hadoop.mapreduce Job setJarByClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setJarByClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setJarByClass.

Prototype

public void setJarByClass(Class<?> cls)

Source Link

Document

Set the Jar by finding where a given class came from.

Usage

From source file:adts.ContainingArticle.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "ContainingArticle");
    job.setJarByClass(ContainingArticle.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.class);

    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    Path queriesInputPath = new Path(args[0]);
    Path articlesInputPath = new Path(args[1]);
    MultipleInputs.addInputPath(job, queriesInputPath, TextInputFormat.class, QueriesMap.class);
    MultipleInputs.addInputPath(job, articlesInputPath, TextInputFormat.class, ArticlesMap.class);

    FileOutputFormat.setOutputPath(job, new Path("/root/temporary"));
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    job.waitForCompletion(true);/*www . jav  a2s. c o  m*/

    Job collectingJob = new Job(conf, "ContainingArticle");
    collectingJob.setJarByClass(ContainingArticle.class);

    collectingJob.setOutputKeyClass(IntWritable.class);
    collectingJob.setOutputValueClass(Text.class);

    collectingJob.setMapperClass(CollectMap.class);
    collectingJob.setReducerClass(CollectReduce.class);

    collectingJob.setInputFormatClass(TextInputFormat.class);
    collectingJob.setOutputFormatClass(TextOutputFormat.class);
    collectingJob.setMapOutputKeyClass(Text.class);
    collectingJob.setMapOutputValueClass(IntWritable.class);

    FileInputFormat.addInputPath(collectingJob, new Path("/root/temporary"));
    FileOutputFormat.setOutputPath(collectingJob, new Path("/root/temporary2"));

    collectingJob.waitForCompletion(true);

    Job countingJob = new Job(conf, "ContainingArticle");
    countingJob.setJarByClass(ContainingArticle.class);

    countingJob.setOutputKeyClass(Text.class);
    countingJob.setOutputValueClass(IntWritable.class);

    countingJob.setMapperClass(CountMap.class);
    countingJob.setReducerClass(CountReduce.class);

    countingJob.setInputFormatClass(TextInputFormat.class);
    countingJob.setOutputFormatClass(TextOutputFormat.class);
    countingJob.setMapOutputKeyClass(IntWritable.class);
    countingJob.setMapOutputValueClass(Text.class);

    FileInputFormat.addInputPath(countingJob, new Path("/root/temporary2"));
    FileOutputFormat.setOutputPath(countingJob, new Path(args[2]));

    countingJob.waitForCompletion(true);
}

From source file:adts.CreateCorrespondences.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration config = HBaseConfiguration.create();
    Job job = new Job(config, "CreateCorrespondences");
    job.setJarByClass(CreateCorrespondences.class);

    Scan scan = new Scan();
    scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
    scan.setCacheBlocks(false); // don't set to true for MR jobs

    TableMapReduceUtil.initTableMapperJob("content", // input HBase table name
            scan, // Scan instance to control CF and attribute selection
            Map.class, // mapper
            Text.class, // mapper output key
            Text.class, // mapper output value
            job);//from  w  w w  .java 2  s .  c om
    job.setReducerClass(Reduce.class);
    job.setNumReduceTasks(1);
    FileOutputFormat.setOutputPath(job, new Path(args[0]));

    boolean b = job.waitForCompletion(true);
    if (!b) {
        throw new IOException("error with job!");
    }
}

From source file:adts.PopularKeywords.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "PopularKeywords");
    job.setJarByClass(PopularKeywords.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    Path queriesInputPath = new Path(args[0]);
    Path StopWordsInputPath = new Path(args[1]);
    MultipleInputs.addInputPath(job, queriesInputPath, TextInputFormat.class, Map.class);
    MultipleInputs.addInputPath(job, StopWordsInputPath, TextInputFormat.class, StopwordsMap.class);

    FileOutputFormat.setOutputPath(job, new Path("/root/temporary"));

    job.waitForCompletion(true);/*from   w  ww.ja va  2  s  .  c o m*/

    Job sortingJob = new Job(conf, "PopularKeywords");
    sortingJob.setJarByClass(PopularKeywords.class);

    sortingJob.setOutputKeyClass(Text.class);
    sortingJob.setOutputValueClass(LongWritable.class);

    sortingJob.setMapperClass(ReverseMap.class);
    sortingJob.setReducerClass(ReverseReduce.class);

    sortingJob.setInputFormatClass(TextInputFormat.class);
    sortingJob.setOutputFormatClass(TextOutputFormat.class);
    sortingJob.setSortComparatorClass(LongWritable.DecreasingComparator.class);
    sortingJob.setMapOutputKeyClass(LongWritable.class);
    sortingJob.setMapOutputValueClass(Text.class);

    FileInputFormat.addInputPath(sortingJob, new Path("/root/temporary"));
    FileOutputFormat.setOutputPath(sortingJob, new Path(args[2]));

    sortingJob.setNumReduceTasks(1);
    sortingJob.waitForCompletion(true);
}

From source file:adts.PrepareInput.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "PrepareInput");
    job.setJarByClass(PrepareInput.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setNumReduceTasks(1);// w  w w .  ja  v a 2  s  .  c o m
    job.waitForCompletion(true);
}

From source file:adts.SuccessfullQueries.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "SuccessfullQueries");
    job.setJarByClass(SuccessfullQueries.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.waitForCompletion(true);//  w ww . j  av  a  2  s  .c o  m
}

From source file:AllLab_Skeleton.Lab1.Lab1_Wordcount.java

/**
 * @param args the command line arguments
 *///from w  w w .  j av  a2s  .  c o  m
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(Lab1_Wordcount.class);
    job.setMapperClass(WordCount_Mapper.class);
    job.setCombinerClass(WordCount_Reducer.class);
    job.setReducerClass(WordCount_Reducer.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);
}

From source file:AllLab_Skeleton.Lab2.Lab2SecondarySort.java

/**
 * @param args the command line arguments
 *//*  w ww  .ja v a2 s .  c o m*/
public static void main(String[] args) {

    try {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "SecondarySort");
        job.setJarByClass(Lab2SecondarySort.class);

        job.setMapperClass(Lab2Mapper.class);
        job.setMapOutputKeyClass(CompositeKeyWritable.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setPartitionerClass(Lab2Partitioner.class);
        job.setGroupingComparatorClass(Lab2GroupComparator.class);

        job.setReducerClass(Lab2Reducer.class);
        job.setOutputKeyClass(CompositeKeyWritable.class);
        job.setOutputValueClass(NullWritable.class);

        job.setNumReduceTasks(8);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);

    } catch (IOException | InterruptedException | ClassNotFoundException ex) {
        System.out.println("Erorr Message" + ex.getMessage());
    }
}

From source file:AllLab_Skeleton.Lab4.Lab4_Std_dev.java

public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "medianstd");
    job.setJarByClass(Lab4_Std_dev.class);
    job.setMapperClass(Map.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(DoubleWritable.class);

    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(MedianSDCustomWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    System.exit(job.waitForCompletion(true) ? 0 : 1);

}

From source file:AllLab_Skeleton.Lab6.BloomFilterBhavesh.java

public static void main(String[] args) throws Exception {

    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Bloom Filter");
    job.setJarByClass(BloomFilterBhavesh.class);
    job.setMapperClass(BloomFilterMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(NullWritable.class);
    job.setNumReduceTasks(0);//from  ww w . java2s.com
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    boolean success = job.waitForCompletion(true);
    System.out.println(success);

}

From source file:AllLab_Skeleton.Lab6.BloomFilterUsingDistributedCache.java

public static void main(String[] args) throws Exception {

    Configuration conf = new Configuration();

    Job job = Job.getInstance(conf, "Bloom Filter");
    job.setJarByClass(BloomFilterUsingDistributedCache.class);
    job.setMapperClass(BloomFilterMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(NullWritable.class);

    //adding the file in the cache having the Person class records
    //job.addCacheFile(new Path("localhost:9000/bhavesh/LabAssignment/CacheInput/cache.txt").toUri());
    DistributedCache.addCacheFile(new URI(args[2]), job.getConfiguration());
    job.setNumReduceTasks(0);/*from  www  .  jav  a2  s  . c o  m*/

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.waitForCompletion(true);

}