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

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

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

Introduction

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

Prototype

public void setOutputValueClass(Class<?> theClass) throws IllegalStateException

Source Link

Document

Set the value class for job outputs.

Usage

From source file:accesslog4.Accesslog4.java

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Path inputPath = new Path(args[0]);
    Path outputPath = new Path(args[1]);
    Job job = Job.getInstance(conf, "Accesslog4");
    job.setJarByClass(Accesslog4.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, inputPath);
    FileOutputFormat.setOutputPath(job, outputPath);
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

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);/*from   w ww  . ja v  a  2 s . co  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.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 ww w.j a  v a2 s  .c om

    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);//from  w  ww.j  a va  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);//from www  .j a  v  a2 s  .  c om
}

From source file:AllLab_Skeleton.Lab1.Lab1_Wordcount.java

/**
 * @param args the command line arguments
 *///from w w  w  .j  a va 2 s  .co  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
 *///from w w w .  j av a 2 s . c om
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.ReduceSideJoin.java

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

    Configuration conf = new Configuration();

    Job job = Job.getInstance(conf, "ReduceSideJoin");
    job.setJarByClass(ReduceSideJoin.class);

    // Use MultipleInputs to set which input uses what mapper
    // This will keep parsing of each data set separate from a logical
    // standpoint
    // The first two elements of the args array are the two inputs
    MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, UserJoinMapper.class);
    MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, CommentJoinMapper.class);
    job.getConfiguration().set("join.type", "leftouter");
    //job.setNumReduceTasks(0);
    job.setReducerClass(UserJoinReducer.class);

    job.setOutputFormatClass(TextOutputFormat.class);
    TextOutputFormat.setOutputPath(job, new Path(args[2]));

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

    job.waitForCompletion(true);/*w w w. j a v  a 2 s  .com*/
}

From source file:alluxio.checker.MapReduceIntegrationChecker.java

License:Apache License

/**
 * Implements MapReduce with Alluxio integration checker.
 *
 * @return 0 for success, 2 for unable to find Alluxio classes, 1 otherwise
 *///from  w w  w . j a  v  a  2  s.  co  m
private int run(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String numMaps = new GenericOptionsParser(conf, args).getRemainingArgs()[0];
    conf.set(MRJobConfig.NUM_MAPS, numMaps);
    createHdfsFilesystem(conf);

    Job job = Job.getInstance(conf, "MapReduceIntegrationChecker");
    job.setJarByClass(MapReduceIntegrationChecker.class);
    job.setMapperClass(CheckerMapper.class);
    job.setCombinerClass(CheckerReducer.class);
    job.setReducerClass(CheckerReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setInputFormatClass(EmptyInputFormat.class);
    FileOutputFormat.setOutputPath(job, mOutputFilePath);

    try {
        if (!job.waitForCompletion(true)) {
            return 1;
        }
        Status resultStatus = generateReport();
        return resultStatus.equals(Status.SUCCESS) ? 0
                : (resultStatus.equals(Status.FAIL_TO_FIND_CLASS) ? 2 : 1);
    } finally {
        if (mFileSystem.exists(mOutputFilePath)) {
            mFileSystem.delete(mOutputFilePath, true);
        }
        mFileSystem.close();
    }
}