Example usage for org.apache.hadoop.mapred JobConf setOutputValueClass

List of usage examples for org.apache.hadoop.mapred JobConf setOutputValueClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapred.*
  5. JobConf
  6. setOutputValueClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setOutputValueClass.

Prototype

public void setOutputValueClass(Class<?> theClass)

Source Link

Document

Set the value class for job outputs.

Usage

From source file:crunch.MaxTemperature.java

License:Apache License

/**
     * Creates a JobConf for a Job that will sum up the TrackStatistics per track.
     * //from  w ww  . j a va2  s .c o  m
     * @param inputDir The path to the folder containing the raw input data files.
     * @return The sum JobConf.
     */
    private JobConf getSumJobConf(Path inputDir) {
        log.info("Creating configuration for sum job");
        // output results to a temporary intermediate folder, this will get deleted by start() method
        Path playsOutput = new Path("sum");

        JobConf conf = new JobConf(TrackStatisticsProgram.class);
        conf.setOutputKeyClass(IntWritable.class); // track id
        conf.setOutputValueClass(TrackStats.class); // statistics for a track
        conf.setInputFormat(TextInputFormat.class); // raw listening data
        conf.setOutputFormat(SequenceFileOutputFormat.class);
        conf.setMapperClass(SumMapper.class);
        conf.setCombinerClass(SumReducer.class);
        conf.setReducerClass(SumReducer.class);

        FileInputFormat.addInputPath(conf, inputDir);
        FileOutputFormat.setOutputPath(conf, playsOutput);
        conf.setJobName("sum");
        return conf;
    }

From source file:crunch.MaxTemperature.java

License:Apache License

/**
     * Creates a JobConf for a Job that will merge the unique listeners and track statistics.
     * /* w w  w  .  j  a va2 s . c o m*/
     * @param outputPath The path for the results to be output to.
     * @param sumInputDir The path containing the data from the sum Job.
     * @param listenersInputDir The path containing the data from the unique listeners job.
     * @return The merge JobConf.
     */
    private JobConf getMergeConf(Path outputPath, Path sumInputDir, Path listenersInputDir) {
        log.info("Creating configuration for merge job");
        JobConf conf = new JobConf(TrackStatisticsProgram.class);
        conf.setOutputKeyClass(IntWritable.class); // track id
        conf.setOutputValueClass(TrackStats.class); // overall track statistics
        conf.setCombinerClass(SumReducer.class); // safe to re-use reducer as a combiner here
        conf.setReducerClass(SumReducer.class);
        conf.setOutputFormat(TextOutputFormat.class);

        FileOutputFormat.setOutputPath(conf, outputPath);

        MultipleInputs.addInputPath(conf, sumInputDir, SequenceFileInputFormat.class, IdentityMapper.class);
        MultipleInputs.addInputPath(conf, listenersInputDir, SequenceFileInputFormat.class,
                MergeListenersMapper.class);
        conf.setJobName("merge");
        return conf;
    }

From source file:de.tudarmstadt.lt.n2n.hadoop.FilterByCountJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), FilterByCountJob.class);
    conf.setJobName(FilterByCountJob.class.getSimpleName());

    conf.setMapperClass(FilterByCountMapper.class);
    conf.setReducerClass(IdentityReducer.class);

    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

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

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    // delete output path for testing purposes
    // FileSystem.get(conf).delete(new Path(args[1]), true);

    JobClient.runJob(conf);/*from  w w  w. ja  v a  2 s.com*/
    return 0;
}

From source file:de.tudarmstadt.lt.n2n.hadoop.FilterByVocabularyJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), FilterByVocabularyJob.class);
    conf.setJobName(FilterByVocabularyJob.class.getSimpleName());

    conf.setMapperClass(FilterByVocabularyMapper.class);
    conf.setReducerClass(IdentityReducer.class);

    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

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

    String word_list_file = conf.get(SHARED_CONSTANTS.PARAM_WORD_LIST);
    if (word_list_file == null)
        throw new MissingArgumentException(
                "Please specify word list with '-Dnlkg.filterbywordsfile=<path-to-file-in-hdfs>'.");

    DistributedCache.addFileToClassPath(new Path(word_list_file), conf);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);/*from  w w w.j a  v a2 s. c  o  m*/
    return 0;
}

From source file:de.tudarmstadt.lt.n2n.hadoop.FlipJoBims.java

License:Apache License

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

    JobConf conf = new JobConf(FlipJoBims.class);

    /* begin necessary for UKP cluster */
    conf.setMemoryForMapTask(1000L); // 1 GB /* necessary for UKP cdh3 */
    conf.setMemoryForReduceTask(1000L); // 1 GB /* necessary for UKP cdh3 */
    FileOutputFormat.setCompressOutput(conf, true); // compress output
    FileOutputFormat.setOutputCompressorClass(conf,
            org.apache.hadoop.io.compress.BZip2Codec.class); /* use the bzip2 codec for compression */
    conf.setCompressMapOutput(true); // compress mapper output
    /* end necessary for UKP cluster */

    conf.setJobName(FlipJoBims.class.getSimpleName());
    args = new GenericOptionsParser(conf, args).getRemainingArgs();

    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapperClass(FlipJoBims.Map.class);
    conf.setNumReduceTasks(0);/*from w w w .ja  va2s. c  o m*/
    // conf.setReducerClass(IdentityReducer.class);

    conf.setMapOutputKeyClass(Text.class);
    conf.setOutputKeyClass(Text.class);

    conf.setMapOutputValueClass(Text.class);
    conf.setOutputValueClass(Text.class);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);

}

From source file:de.tudarmstadt.lt.n2n.hadoop.GoogleSyntacticsJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), GoogleSyntacticsJob.class);
    conf.setJobName(GoogleSyntacticsJob.class.getSimpleName());

    conf.setMapperClass(GoogleSyntacticsJob3Mapper.class);
    conf.setReducerClass(GoogleSyntacticsJob3Reducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setOutputKeyClass(JoBimFormat.class);
    conf.setOutputValueClass(IntWritable.class);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    // delete output path for testing purposes
    // FileSystem.get(conf).delete(new Path(args[1]), true);

    String extractorConfigurationFiles = conf.get(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS);
    if (extractorConfigurationFiles == null) {
        extractorConfigurationFiles = StringUtils.join(SHARED_CONSTANTS.DEFAULT_EXTRACTOR_CONFIGURATIONS, ',');
        System.out.format("Extractorconfigurationfile parameter not set. Assuming -D%s=%s %n",
                SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
        conf.set(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
    }//from   w  w  w  . j  a v  a  2s  . co  m

    String[] extractorConfigurationFilesArr = extractorConfigurationFiles.split(",");
    for (int i = 0; i < extractorConfigurationFilesArr.length; i++)
        DistributedCache.addFileToClassPath(new Path(extractorConfigurationFilesArr[i]), conf);

    JobClient.runJob(conf);
    return 0;
}

From source file:de.tudarmstadt.lt.n2n.hadoop.pipetests.GoogleSyntacticsJob2.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), GoogleSyntacticsJob2.class);
    conf.setJobName(GoogleSyntacticsJob2.class.getSimpleName());

    conf.setMapperClass(GoogleSyntacticsJob2Mapper.class);
    conf.setReducerClass(GoogleSyntacticsJob2Reducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    // conf.setMapOutputKeyClass(Text.class);
    // conf.setMapOutputValueClass(NullWritable.class);

    conf.setOutputKeyClass(JoBimFormat.class);
    conf.setOutputValueClass(IntWritable.class);

    args = new GenericOptionsParser(conf, args).getRemainingArgs();
    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    // delete output path for testing purposes
    // FileSystem.get(conf).delete(new Path(args[1]), true);

    String extractorConfigurationFiles = conf.get(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS);
    if (extractorConfigurationFiles == null) {
        extractorConfigurationFiles = StringUtils.join(SHARED_CONSTANTS.DEFAULT_EXTRACTOR_CONFIGURATIONS, ',');
        System.out.format("Extractorconfigurationfile parameter not set. Assuming -D%s=%s %n",
                SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
        conf.set(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
    }//from  w  ww  .  j  a v  a  2  s  .  co  m

    String[] extractorConfigurationFilesArr = extractorConfigurationFiles.split(",");
    for (int i = 0; i < extractorConfigurationFilesArr.length; i++)
        DistributedCache.addFileToClassPath(new Path(extractorConfigurationFilesArr[i]), conf);

    JobClient.runJob(conf);
    return 0;
}

From source file:de.tudarmstadt.lt.n2n.hadoop.pipetests.GoogleSyntacticsJob5.java

License:Apache License

@Override
public void configure(JobConf job) {
    String extractorConfigurationFiles = job.get(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS);
    if (extractorConfigurationFiles == null) {
        extractorConfigurationFiles = StringUtils.join(SHARED_CONSTANTS.DEFAULT_EXTRACTOR_CONFIGURATIONS, ',');
        System.out.format("Extractorconfigurationfile parameter not set. Assuming -D%s=%s %n",
                SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
        job.set(SHARED_CONSTANTS.PARAM_EXTRACTORCONFIGS, extractorConfigurationFiles);
    }/*from   ww w.j  a va2s.  c  om*/
    try {
        String[] extractorConfigurationFilesArr = extractorConfigurationFiles.split(",");
        for (int i = 0; i < extractorConfigurationFilesArr.length; i++)
            DistributedCache.addFileToClassPath(new Path(extractorConfigurationFilesArr[i]), job);
    } catch (IOException e) {
        e.printStackTrace();
    }
    Text2CASInputFormat.setDocumentTextExtractorClass(job, KeyPlusValueAsDocumentExtractor.class);
    job.setMapperClass(JoBimMapper.class);
    job.setReducerClass(JoBimReducer.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);
    job.setMemoryForMapTask(4096);
    job.setMemoryForReduceTask(4096);
    job.set("mapred.child.java.opts", "-Xmx4096m");
    job.setNumReduceTasks(1); // reset to default
}

From source file:de.tudarmstadt.lt.n2n.hadoop.RelationToOneHoleTransformerJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), RelationToOneHoleTransformerJob.class);

    conf.setJobName(RelationToOneHoleTransformerJob.class.getSimpleName());
    args = new GenericOptionsParser(conf, args).getRemainingArgs();

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapperClass(RelationToOneHoleTransformerJob.Map.class);
    conf.setNumReduceTasks(0);//from  ww w.  j a v  a  2 s  .c  o  m
    // conf.setReducerClass(IdentityReducer.class); // sort or no sort? - that is here the question

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

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));
    JobClient.runJob(conf);

    return 0;
}

From source file:de.tudarmstadt.lt.n2n.hadoop.RemoveExactDuplicatesJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), RemoveExactDuplicatesJob.class);
    conf.setJobName(RemoveExactDuplicatesJob.class.getSimpleName());

    conf.setMapperClass(LineMapper.class);
    conf.setReducerClass(KeyReducer.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(NullWritable.class);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    // delete output path for testing purposes
    // FileSystem.get(conf).delete(new Path(args[1]), true);

    JobClient.runJob(conf);//from   w w w . jav a 2s.c  o  m
    return 0;
}