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

List of usage examples for org.apache.hadoop.mapred JobConf 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:de.tudarmstadt.lt.nlkg.ConvertInvertSVO.java

License:Apache License

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

    conf.setMapperClass(ConversionMapper.class);
    conf.setCombinerClass(IdentityReducer.class);
    conf.setReducerClass(IdentityReducer.class);

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

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

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

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

From source file:de.tudarmstadt.lt.nlkg.ConvertSVO.java

License:Apache License

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

    conf.setMapperClass(ConversionMapper.class);
    conf.setCombinerClass(IdentityReducer.class);
    conf.setReducerClass(IdentityReducer.class);

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

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

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

    JobClient.runJob(conf);/*from  w  w  w .  j av  a2s.  co m*/
    return 0;
}

From source file:dinocode.SpeciesGraphBuilder.java

public static void main(String[] args) throws Exception {
    JobClient client = new JobClient();
    JobConf conf = new JobConf(SpeciesDriver.class);
    conf.setJobName("Page-rank Species Graph Builder");
    final File f = new File(SpeciesDriver.class.getProtectionDomain().getCodeSource().getLocation().getPath());
    String inFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/InputFiles/species_medium.txt";
    String outFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outputFiles/Result";
    FileInputFormat.setInputPaths(conf, new Path(inFiles));
    FileOutputFormat.setOutputPath(conf, new Path(outFiles));

    //conf.setOutputKeyClass(Text.class); 
    //conf.setOutputValueClass(Text.class); 
    conf.setMapperClass(SpeciesGraphBuilderMapperd.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(Text.class);

    //conf.setInputFormat(org.apache.hadoop.mapred.TextInputFormat.class); 
    //conf.setOutputFormat(org.apache.hadoop.mapred.SequenceFileOutputFormat.class); 
    conf.setReducerClass(SpeciesGraphBuilderReducerd.class);
    //conf.setCombinerClass(SpeciesGraphBuilderReducer.class); 

    //conf.setInputPath(new Path("graph1")); 
    //conf.setOutputPath(new Path("graph2")); 
    // take the input and output from the command line
    FileInputFormat.setInputPaths(conf, new Path(inFiles));
    FileOutputFormat.setOutputPath(conf, new Path(outFiles));

    client.setConf(conf);/*from w  w  w.ja v  a 2s  . co  m*/
    try {
        JobClient.runJob(conf);
    } catch (Exception e) {
        e.printStackTrace();
    }

    inFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outputFiles/Result/part-00000";
    for (int i = 0; i < 500; i++) {
        client = new JobClient();
        conf = new JobConf(SpeciesDriver.class);
        conf.setJobName("Species Iter");

        int count = i + 1;
        outFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outputFiles/Result" + count;
        conf.setNumReduceTasks(5);

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

        FileInputFormat.setInputPaths(conf, new Path(inFiles));
        FileOutputFormat.setOutputPath(conf, new Path(outFiles));

        conf.setMapperClass(SpeciesIterMapper2d.class);
        conf.setReducerClass(SpeciesIterReducer2d.class);
        conf.setCombinerClass(SpeciesIterReducer2d.class);

        client.setConf(conf);
        try {
            JobClient.runJob(conf);
        } catch (Exception e) {
            e.printStackTrace();
        }
        inFiles = outFiles;

    }

    //Viewer
    client = new JobClient();
    conf = new JobConf(SpeciesDriver.class);
    conf.setJobName("Species Viewer");

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

    inFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outputFiles/Result500/part-00000";
    outFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outputFiles/ResultFinal";

    FileInputFormat.setInputPaths(conf, new Path(inFiles));
    FileOutputFormat.setOutputPath(conf, new Path(outFiles));

    conf.setMapperClass(SpeciesViewerMapperd.class);
    conf.setReducerClass(org.apache.hadoop.mapred.lib.IdentityReducer.class);

    client.setConf(conf);
    try {
        JobClient.runJob(conf);
    } catch (Exception e) {
        e.printStackTrace();
    }

}

From source file:drivers.CalculatePageRank.java

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    JobConf job = new JobConf(conf, this.getClass());
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);
    job.setJobName("Fiqie|Calculate");
    job.setMapperClass(CalculatePageRank1Mapper.class);
    job.setReducerClass(CalculatePageRank1Reducer.class);
    job.setInputFormat(KeyValueTextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    JobClient.runJob(job);//from w  w w.  ja  v a 2s  .c  om
    return 0;
}

From source file:drivers.FinishPageRank.java

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    JobConf job = new JobConf(conf, this.getClass());
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);
    job.setJobName("Fiqie|Finish");
    job.setOutputKeyComparatorClass(DecreasingComparator.class);
    job.setMapperClass(SortingPageRankMapper.class);
    job.setReducerClass(SortingPageRankReducer.class);
    job.setInputFormat(KeyValueTextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    JobClient.runJob(job);/*from   w  w w  .j a v a  2  s .c o  m*/
    return 0;
}

From source file:drivers.InitPageRank.java

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    JobConf job = new JobConf(conf, this.getClass());
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);
    job.setJobName("Fiqie|Init");
    job.setMapperClass(InitPageRankMapper.class);
    job.setReducerClass(InitPageRankReducer.class);
    job.setInputFormat(KeyValueTextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    JobClient.runJob(job);//from   w ww . ja v a 2 s  . c o m
    return 0;
}

From source file:edu.brown.cs.mapreduce.BenchmarkBase.java

License:Open Source License

public void runCombine() throws Exception {
    if (this.last_job == null) {
        throw new NullPointerException("ERROR: Last job is Null");
    }/*from w  w  w .j a v  a2  s  .  c  o  m*/
    JobConf job = new JobConf(this.conf, this.benchmarkClass);
    job.setJobName((this.job_name != null ? this.job_name : this.benchmarkClass.getSimpleName()) + ".combine");
    job.setMapperClass(IdentityMapper.class);
    job.setNumMapTasks(0);
    job.setReducerClass(IdentityReducer.class);
    job.setNumReduceTasks(1); // this is needed to get a single output file

    // Input
    FileInputFormat.setInputPaths(job, FileOutputFormat.getOutputPath(this.last_job));
    job.setInputFormat(KeyValueTextInputFormat.class);

    // Output
    FileOutputFormat.setOutputPath(job,
            new Path(FileOutputFormat.getOutputPath(this.last_job).toString() + "/combine"));
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    JobConf real_last_job = this.last_job;
    this.runJob(job);
    this.last_job = real_last_job;
    return;
}

From source file:edu.brown.cs.mapreduce.benchmarks.Benchmark1.java

License:Open Source License

public int run(String[] args) throws Exception {
    BenchmarkBase base = new BenchmarkBase(this.getConf(), this.getClass(), args);
    JobConf job = base.getJobConf();

    job.setInputFormat(base.getSequenceFile() ? SequenceFileInputFormat.class : KeyValueTextInputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    if (base.getTupleData()) {
        job.setMapperClass(Benchmark1.TupleMap.class);
    } else {/*from w w  w  .  j  av a 2  s . c o m*/
        job.setMapperClass(Benchmark1.TextMap.class);
    }
    //job.setReducerClass(IdentityReducer.class);
    job.setNumReduceTasks(0);

    try {
        base.runJob(job);
        if (base.getCombine())
            base.runCombine();
    } catch (Exception ex) {
        ex.printStackTrace();
        System.exit(1);
    }
    return 0;
}

From source file:edu.brown.cs.mapreduce.benchmarks.Benchmark2.java

License:Open Source License

public int run(String[] args) throws Exception {
    BenchmarkBase base = new BenchmarkBase(this.getConf(), this.getClass(), args);
    JobConf job = base.getJobConf();

    job.setInputFormat(base.getSequenceFile() ? SequenceFileInputFormat.class : KeyValueTextInputFormat.class);
    //job.setInputFormat(KeyValueSetInputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(DoubleWritable.class);
    if (base.getTupleData()) {
        job.setMapperClass(Benchmark2.TupleWritableMap.class);
    } else {/*from   w w w  .  j  a  v  a 2 s  .c  o m*/
        job.setMapperClass(Benchmark2.TextMap.class);
    }
    job.setCombinerClass(Benchmark2.Reduce.class);
    job.setReducerClass(Benchmark2.Reduce.class);
    //job.setNumReduceTasks(0);

    try {
        base.runJob(job);
        if (base.getCombine())
            base.runCombine();
    } catch (Exception ex) {
        ex.printStackTrace();
        System.exit(1);
    }
    return 0;
}

From source file:edu.brown.cs.mapreduce.benchmarks.Benchmark3.java

License:Open Source License

public int run(String[] args) throws Exception {
    BenchmarkBase base = new BenchmarkBase(this.getConf(), this.getClass(), args);

    Date startTime = new Date();
    System.out.println("Job started: " + startTime);

    // -------------------------------------------
    // Phase #1// www.  ja  v a  2s  .c o  m
    // -------------------------------------------
    JobConf p1_job = base.getJobConf();
    p1_job.setJobName(p1_job.getJobName() + ".Phase1");
    Path p1_output = new Path(base.getOutputPath().toString() + "/phase1");
    FileOutputFormat.setOutputPath(p1_job, p1_output);

    //
    // Make sure we have our properties
    //
    String required[] = { BenchmarkBase.PROPERTY_START_DATE, BenchmarkBase.PROPERTY_STOP_DATE };
    for (String req : required) {
        if (!base.getOptions().containsKey(req)) {
            System.err.println("ERROR: The property '" + req + "' is not set");
            System.exit(1);
        }
    } // FOR

    p1_job.setInputFormat(
            base.getSequenceFile() ? SequenceFileInputFormat.class : KeyValueTextInputFormat.class);
    if (base.getSequenceFile())
        p1_job.setOutputFormat(SequenceFileOutputFormat.class);
    p1_job.setOutputKeyClass(Text.class);
    p1_job.setOutputValueClass(Text.class);
    p1_job.setMapperClass(
            base.getTupleData() ? edu.brown.cs.mapreduce.benchmarks.benchmark3.phase1.TupleWritableMap.class
                    : edu.brown.cs.mapreduce.benchmarks.benchmark3.phase1.TextMap.class);
    p1_job.setReducerClass(
            base.getTupleData() ? edu.brown.cs.mapreduce.benchmarks.benchmark3.phase1.TupleWritableReduce.class
                    : edu.brown.cs.mapreduce.benchmarks.benchmark3.phase1.TextReduce.class);
    p1_job.setCompressMapOutput(base.getCompress());

    // -------------------------------------------
    // Phase #2
    // -------------------------------------------
    JobConf p2_job = base.getJobConf();
    p2_job.setJobName(p2_job.getJobName() + ".Phase2");
    p2_job.setInputFormat(
            base.getSequenceFile() ? SequenceFileInputFormat.class : KeyValueTextInputFormat.class);
    if (base.getSequenceFile())
        p2_job.setOutputFormat(SequenceFileOutputFormat.class);
    p2_job.setOutputKeyClass(Text.class);
    p2_job.setOutputValueClass(Text.class);
    p2_job.setMapperClass(IdentityMapper.class);
    p2_job.setReducerClass(
            base.getTupleData() ? edu.brown.cs.mapreduce.benchmarks.benchmark3.phase2.TupleWritableReduce.class
                    : edu.brown.cs.mapreduce.benchmarks.benchmark3.phase2.TextReduce.class);
    p2_job.setCompressMapOutput(base.getCompress());
    p2_job.setNumMapTasks(60);

    // -------------------------------------------
    // Phase #3
    // -------------------------------------------
    JobConf p3_job = base.getJobConf();
    p3_job.setJobName(p3_job.getJobName() + ".Phase3");
    p3_job.setNumReduceTasks(1);
    p3_job.setInputFormat(
            base.getSequenceFile() ? SequenceFileInputFormat.class : KeyValueTextInputFormat.class);
    p3_job.setOutputKeyClass(Text.class);
    p3_job.setOutputValueClass(Text.class);
    //p3_job.setMapperClass(Phase3Map.class);
    p3_job.setMapperClass(IdentityMapper.class);
    p3_job.setReducerClass(
            base.getTupleData() ? edu.brown.cs.mapreduce.benchmarks.benchmark3.phase3.TupleWritableReduce.class
                    : edu.brown.cs.mapreduce.benchmarks.benchmark3.phase3.TextReduce.class);

    //
    // Execute #1
    //
    base.runJob(p1_job);

    //
    // Execute #2
    //
    Path p2_output = new Path(base.getOutputPath().toString() + "/phase2");
    FileOutputFormat.setOutputPath(p2_job, p2_output);
    FileInputFormat.setInputPaths(p2_job, p1_output);
    base.runJob(p2_job);

    //
    // Execute #3
    //
    Path p3_output = new Path(base.getOutputPath().toString() + "/phase3");
    FileOutputFormat.setOutputPath(p3_job, p3_output);
    FileInputFormat.setInputPaths(p3_job, p2_output);
    base.runJob(p3_job);

    // There does need to be a combine if (base.getCombine()) base.runCombine();

    return 0;
}