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:WordCount_NoCombiner.java

License:Apache License

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

    GenericOptionsParser parser = new GenericOptionsParser(conf, args);
    String[] otherArgs = parser.getRemainingArgs();

    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);//ww  w .  j  a v a 2 s  .  c om
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount_NoCombiner.class);
    job.setMapperClass(TokenizerMapper.class);

    // delete this line to disable combining
    // job.setCombinerClass(IntSumReducer.class);

    job.setPartitionerClass(WordPartitioner.class);
    job.setNumReduceTasks(5);

    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:Outlinks.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
        System.err.println("Usage: inlinks <in> [<in>...] <out>");
        System.exit(2);//from w  ww . ja  v  a  2 s.  c  om
    }
    Job job = new Job(conf, "inlinks");
    job.setJarByClass(Outlinks.class);
    job.setMapperClass(TokenizerMapper.class);
    //job.setCombinerClass(IdentityReducer.class);
    job.setReducerClass(IdentityReducer.class);
    job.setNumReduceTasks(10);
    job.setOutputKeyClass(IntWritable.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]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:Edge.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);/*from  w w w. j a  v a2 s  .  c o m*/
    }

    Path tempDir = new Path("/temp/edge");

    Job job = new Job(conf, "word count");
    job.setJarByClass(Edge.class);

    job.setMapperClass(SplitMapper.class);
    job.setCombinerClass(DuplicateCombiner.class);

    //job.setSortComparatorClass(DecentComparator.class);

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

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, tempDir);

    if (job.waitForCompletion(true)) {

        Job job2 = new Job(conf, "edge");
        job2.setJarByClass(Edge.class);
        job2.setMapperClass(SwitchMapper.class);
        job2.setSortComparatorClass(DecentComparator.class);
        job2.setReducerClass(SwitchReducer.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job2, tempDir);
        FileOutputFormat.setOutputPath(job2, new Path(otherArgs[1]));

        System.exit(job2.waitForCompletion(true) ? 0 : 1);
    }

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

From source file:LinkedGraph.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);/*www.  j a  va 2 s  . c  o  m*/
    }
    Job job = new Job(conf, "Graph");
    job.setJarByClass(LinkedGraph.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:MarkovStateTransitionModel.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = new Job(getConf());
    String jobName = "Markov tate transition model";
    job.setJobName(jobName);/*from w  ww  .  j ava 2s. c o  m*/

    job.setJarByClass(MarkovStateTransitionModel.class);

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

    Utility.setConfiguration(job.getConfiguration(), "avenir");
    job.setMapperClass(MarkovStateTransitionModel.StateTransitionMapper.class);
    job.setReducerClass(MarkovStateTransitionModel.StateTransitionReducer.class);
    job.setCombinerClass(MarkovStateTransitionModel.StateTransitionCombiner.class);

    job.setMapOutputKeyClass(Tuple.class);
    job.setMapOutputValueClass(IntWritable.class);

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

    job.setNumReduceTasks(job.getConfiguration().getInt("num.reducer", 1));

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

From source file:DescSorter.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
        System.err.println("Usage: flights <in> <in> <out>");
        System.exit(2);//from   w w  w. ja v  a  2 s  .  c  o  m
    }
    Job job = new Job(conf, "AvgDelays");
    job.setJarByClass(DescSorter.class);
    job.setMapperClass(FlightMapper.class);

    job.setMapOutputKeyClass(CompositeKey.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setPartitionerClass(CompositeKeyPartitioner.class);
    job.setSortComparatorClass(SortComparator.class);
    job.setGroupingComparatorClass(GroupingComparator.class);

    job.setReducerClass(AvgDelayReducer.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.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]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:CalculateHistogram.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);/*from   w w w  . j a  v a2  s. c o  m*/
    }

    Job job = new Job(conf, "MRDT - Generate Histogram");
    job.setJarByClass(CalculateHistogram.class);
    job.setMapperClass(HistogramMap.class);
    job.setReducerClass(HistogramReduce.class);

    //job.setOutputValueClass(HistogramBucket.class);

    //job.setMapOutputKeyClass(LongWritable.class);
    //job.setMapOutputValueClass(Text.class);

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

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

From source file:DumpPageRankRecordsToPlainText.java

License:Apache License

/**
 * Runs this tool.//from w  w  w  . j  a v a 2  s  .  co m
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));

    CommandLine cmdline;
    CommandLineParser parser = new GnuParser();

    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        return -1;
    }

    if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) {
        System.out.println("args: " + Arrays.toString(args));
        HelpFormatter formatter = new HelpFormatter();
        formatter.setWidth(120);
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String inputPath = cmdline.getOptionValue(INPUT);
    String outputPath = cmdline.getOptionValue(OUTPUT);

    LOG.info("Tool name: " + DumpPageRankRecordsToPlainText.class.getSimpleName());
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    Configuration conf = new Configuration();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);

    Job job = Job.getInstance(conf);
    job.setJobName(DumpPageRankRecordsToPlainText.class.getSimpleName());
    job.setJarByClass(DumpPageRankRecordsToPlainText.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

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

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:MaleUsersBelow7Years.java

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

    Job job = new Job(configuration, "CountMaleUsersLessThan7");
    job.setJarByClass(MaleUsersBelow7Years.class);
    job.setMapperClass(Map.class);
    job.setReducerClass(Reducer.class);
    job.setCombinerClass(Reducer.class);

    //set output and input formats;mapper-input reducer-output
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    FileInputFormat.addInputPath(job, new Path(args[0])); //path for input file
    FileOutputFormat.setOutputPath(job, new Path(args[1])); // Path for output file
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:PrimeDivisor.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);/*from w w  w  .ja v a2s .  c  o  m*/
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(PrimeDivisor.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}