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

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

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

Introduction

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

Prototype

public void setMapperClass(Class<? extends Mapper> cls) throws IllegalStateException

Source Link

Document

Set the Mapper for the job.

Usage

From source file:com.javiertordable.mrif.MapReduceQuadraticSieve.java

License:Apache License

/**
 * Setup the MapReduce parameters and run it.
 *
 * Tool parses the command line arguments for us.
 *///from  w  w w .  ja  va2  s  .  c  o  m
public int run(String[] args) throws Exception {
    Configuration conf = getConf();

    // Check the arguments. we need the integer to attempt to factor.
    if (args.length < 1) {
        System.out.println("Please indicate the integer to factor");
        LOGGER.severe("No integer to factor. Exit.");
        System.exit(1);
    }

    // Parse N and add it to the job configuration, so that the workers can
    // access it as well.
    BigInteger N = new BigInteger(args[0]);
    LOGGER.info("Attempting factorization of: " + N.toString());
    conf.set(INTEGER_TO_FACTOR_NAME, N.toString());

    // Obtain the factor base for the integer N.
    FactorBaseArray factorBase = SieveInput.factorBase(N);
    LOGGER.info("Factor base of size: " + factorBase.size());
    conf.set(FACTOR_BASE_NAME, factorBase.toString());

    // Prepare the input of the mapreduce.
    LOGGER.info("Sieve of size: " + SieveInput.fullSieveIntervalSize(N));
    try {
        // Write the full sieve interval to disk.
        SieveInput.writeFullSieveInterval(N, "input/" + INPUT_FILE_NAME);
    } catch (FileNotFoundException e) {
        System.out.println("Unable to open the file for writing.");
    } catch (IOException e) {
        System.out.println("Unable to write to the output file.");
    }

    // Configure the classes of the mapreducer
    Job job = new Job(conf, "QuadraticSieve");
    job.setJarByClass(MapReduceQuadraticSieve.class);
    job.setMapperClass(SieveMapper.class);
    job.setReducerClass(FindSquaresReducer.class);

    // Output will be two pairs of strings:
    // <"Factor1", "59">
    // <"Factor2", "101">
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    FileInputFormat.addInputPath(job, new Path("input/"));
    FileOutputFormat.setOutputPath(job, new Path("output/"));

    // Submit the job.
    job.waitForCompletion(true);

    return 0;
}

From source file:com.jbw.mutioutputformat.PatitionByStation.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path input = new Path(conf.get("input"));
    Path output = new Path(conf.get("output"));
    Job job = Job.getInstance();
    job.setJarByClass(PatitionByStation.class);
    job.setJobName("papapa");
    job.setMapperClass(StationMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setReducerClass(StationReducer.class);
    job.setOutputKeyClass(NullWritable.class);
    FileInputFormat.addInputPath(job, input);
    FileOutputFormat.setOutputPath(job, output);
    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jbw.recommendsystem.add.AddMRD.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path in = new Path(conf.get("input"));
    Path out = new Path(conf.get("output"));

    Job job = Job.getInstance(conf);
    job.setJobName("5");
    job.setJarByClass(AddMRD.class);

    job.setMapperClass(AddMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

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

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

    TextInputFormat.addInputPath(job, in);
    TextOutputFormat.setOutputPath(job, out);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jbw.recommendsystem.cooc.CoocMRD.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path in = new Path(conf.get("input"));
    Path out = new Path(conf.get("output"));

    Job surJob = Job.getInstance(conf);
    surJob.setJarByClass(CoocMRD.class);
    surJob.setJobName("Coor");

    surJob.setMapperClass(CoocMapper.class);
    surJob.setReducerClass(IntSumReducer.class);

    surJob.setMapOutputKeyClass(Text.class);
    surJob.setMapOutputValueClass(IntWritable.class);

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

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

    TextInputFormat.addInputPath(surJob, in);
    TextOutputFormat.setOutputPath(surJob, out);

    return surJob.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jbw.recommendsystem.iteamlist.ItemMRD.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path in = new Path(conf.get("input"));
    Path out = new Path(conf.get("output"));

    Job surJob = Job.getInstance(conf);
    surJob.setJarByClass(ItemMRD.class);
    surJob.setJobName("item");

    surJob.setMapperClass(ItemMapper.class);
    surJob.setReducerClass(ItemReducer.class);

    surJob.setMapOutputKeyClass(Text.class);
    surJob.setMapOutputValueClass(Text.class);

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

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

    TextInputFormat.addInputPath(surJob, in);
    TextOutputFormat.setOutputPath(surJob, out);

    return surJob.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jbw.recommendsystem.martrixlist.MartrixListMRD.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path in = new Path(conf.get("input"));
    Path out = new Path(conf.get("output"));

    Job surJob = Job.getInstance(conf);
    surJob.setJarByClass(MartrixListMRD.class);
    surJob.setJobName("user");

    surJob.setMapperClass(MListMapper.class);
    surJob.setReducerClass(MListReducer.class);

    surJob.setMapOutputKeyClass(Text.class);
    surJob.setMapOutputValueClass(Text.class);

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

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

    TextInputFormat.addInputPath(surJob, in);
    TextOutputFormat.setOutputPath(surJob, out);

    return surJob.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jbw.tar.sf.TarDriver.java

@Override
public int run(String[] strings) throws Exception {
    Configuration conf = getConf();
    Path in = new Path(conf.get("input"));
    Path out = new Path(conf.get("output"));

    Job job = Job.getInstance(conf);
    job.setJarByClass(TarDriver.class);
    job.setJobName("test");

    job.setMapperClass(SmallFileMapper.class);

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

    job.setInputFormatClass(TextInputFormat.class);
    TextInputFormat.addInputPath(job, in);

    job.setOutputFormatClass(TarOutputFormat.class);
    TarOutputFormat.setOutputPath(job, out);

    // job.setNumReduceTasks(0);

    /*//ww  w .  j  a va 2s .  c  om
        job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TarOutputFormat.class);
    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(Text.class);
     */
    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.jeffy.mr.WordCount.java

License:Apache License

/**
 * @param args//  ww w  .j a  va  2 s  . co  m
 */
public static void main(String[] args) {

    String input = "hdfs://master:8020/tmp/jeffy/input/wordcount.txt";
    String output = "hdfs://master:8020/tmp/jeffy/output";
    Configuration config = new Configuration();
    /**
     * Windows???no jobCtrol
     * http://stackoverflow.com/questions/24075669/mapreduce-job-fail-when-submitted-from-windows-machine
     */
    config.set("mapreduce.app-submission.cross-platform", "true");
    config.set("mapred.remote.os", "Linux");
    try {
        Job job = Job.getInstance(config);
        //Windows???
        job.setJarByClass(WordCount.class);
        //?????
        job.setJar("D:\\bigdata\\mapreduce-demo\\src\\main\\java\\WordCount.jar");
        job.setJobName("Wordcount job");
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

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

        TextInputFormat.setInputPaths(job, new Path(input));
        TextOutputFormat.setOutputPath(job, new Path(output));
        // Submit the job, then poll for progress until the job is complete
        try {
            job.waitForCompletion(true);
        } catch (ClassNotFoundException | InterruptedException e) {
            e.printStackTrace();
        }
    } catch (IOException e) {
        e.printStackTrace();
    }

}

From source file:com.jet.hadoop.wordcount.WordCount.java

License:Apache License

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

    long timeBegin = System.currentTimeMillis();
    System.out.println("hadoop wordcount begins at" + timeBegin);

    if (args == null || args.length == 0) {
        args = new String[2];
        args[0] = "E:\\Work\\input\\hello.txt";
        args[1] = "E:\\Work\\output";
    }//from w  w w. ja v  a2 s.  c  om

    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
        System.err.println("Usage: wordcount <in> [<in>...] <out>");
        System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    //      job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    //      job.setNumReduceTasks(2);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
        FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
    boolean result = job.waitForCompletion(true);

    long timeEnd = System.currentTimeMillis();
    System.out.println("hadoop wordcount ended at" + timeEnd);
    System.out.println("hadoop wordcount cost time" + (timeEnd - timeBegin) / 1000 + " seconds.");

    System.exit(result ? 0 : 1);
}

From source file:com.jhkt.playgroundArena.hadoop.tasks.jobs.AverageJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {

    Configuration conf = getConf();
    Job job = new Job(conf, AverageJob.class.getSimpleName());
    job.setJarByClass(AverageJob.class);

    Path in = new Path(args[0]);
    Path out = new Path(args[1]);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);

    job.setJobName("Sample Average Job");
    job.setMapperClass(AverageMapper.class);
    job.setCombinerClass(AverageCombiner.class);
    job.setReducerClass(AverageReducer.class);

    job.setInputFormatClass(TextInputFormat.class);
    //job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

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

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

    return 0;/*w ww .jav a2s  .  c o m*/
}