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

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

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

Introduction

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

Prototype

public void setReducerClass(Class<? extends Reducer> theClass)

Source Link

Document

Set the Reducer class for the job.

Usage

From source file:SleepJob.java

License:Apache License

public JobConf setupJobConf(int numMapper, int numReducer, long mapSleepTime, int mapSleepCount,
        long reduceSleepTime, int reduceSleepCount) {
    JobConf job = new JobConf(getConf(), SleepJob.class);
    job.setNumMapTasks(numMapper);/*w  ww .j  a va2s  . co m*/
    job.setNumReduceTasks(numReducer);
    job.setMapperClass(SleepJob.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(NullWritable.class);
    job.setReducerClass(SleepJob.class);
    job.setOutputFormat(NullOutputFormat.class);
    job.setInputFormat(SleepInputFormat.class);
    job.setPartitionerClass(SleepJob.class);
    job.setSpeculativeExecution(false);
    FileInputFormat.addInputPath(job, new Path("ignored"));
    job.setLong("sleep.job.map.sleep.time", mapSleepTime);
    job.setLong("sleep.job.reduce.sleep.time", reduceSleepTime);
    job.setInt("sleep.job.map.sleep.count", mapSleepCount);
    job.setInt("sleep.job.reduce.sleep.count", reduceSleepCount);
    return job;
}

From source file:update_sentiment.java

License:LGPL

public static void runjob(String input, String output) throws Exception {
    JobConf conf = new JobConf(update_sentiment.class);
    conf.setJobName("Update_Sentiment_Train");

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

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

    FileInputFormat.setInputPaths(conf, new Path(input));
    FileOutputFormat.setOutputPath(conf, new Path(output));

    JobClient.runJob(conf);/*from  w  ww.  j  a  v  a2s  . co m*/
}

From source file:BMTKeyValueLoader.java

License:Apache License

public int run(String[] args) {
    JobConf conf = new JobConf(getConf(), CassandraTableLoader.class);
    GenericOptionsParser parser = new GenericOptionsParser(conf, args);

    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.setJobName("BMTKeyValueLoader");
    conf.setMapperClass(Map.class);
    conf.setReducerClass(Reduce.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    List<String> other_args = new ArrayList<String>();
    for (int i = 0; i < args.length; ++i) {
        other_args.add(args[i]);/*  w  w  w .  j  av  a2s . c o  m*/
    }

    FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
    try {
        JobClient.runJob(conf);
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    return 0;
}

From source file:HoopRemoteTask.java

License:Open Source License

/**
*
*///from ww w. j a  v a 2 s  . co  m
public static void main(String args[]) throws Exception {
    // run the HoopLink constructor; We need this to have a global settings registry       
    @SuppressWarnings("unused")
    HoopLink link = new HoopLink();

    dbg("main ()");

    showTimeStamp();

    /**
     * I've taken out the statistics portion since it relies on code that isn't distributed
     * The next version will have this solved. I might try the solution in:
     * http://stackoverflow.com/questions/7443074/initialize-public-static-variable-in-hadoop-through-arguments
     * Although chances are I will switch to using Hoop to collect much better performance and distribution 
     * statistics. See Hoop.java for more information
     */

    HoopPerformanceMeasure metrics = new HoopPerformanceMeasure();
    metrics.setMarker("main");
    HoopLink.metrics.getDataSet().add(metrics);

    if (parseArgs(args) == false) {
        usage();
        return;
    }

    if (HoopLink.postonly == true) {
        postOnly();
        return;
    }

    if (HoopLink.task.equals("none") == true) {
        dbg("No task defined, please use the commandline option -task <task>");
        return;
    }

    dbg("Starting system ...");

    HoopRemoteTask driver = new HoopRemoteTask();

    if (HoopLink.useHadoop == false) {
        dbg("Starting built-in mapper ...");

        driver.indexDocuments();
    } else {
        dbg("Starting hadoop job ...");

        Configuration conf = new Configuration();

        // TRANSFER SETTHoopGS FROM HoopLink to Configuration!!!

        transferConf(conf);

        // Now we're feeling much better

        HoopRemoteTask.hdfs = FileSystem.get(conf);

        if (HoopLink.dbglocal == true) {
            dbg("Enabling local debugging ...");
            conf.set("mapred.job.tracker", "local");
        } else
            dbg("Disabling local debugging");

        JobConf job = new JobConf(conf, HoopRemoteTask.class);

        job.setJobName(driver.getClassName());

        driver.setJob(job);

        @SuppressWarnings("unused")
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        job.setJarByClass(HoopRemoteTask.class);

        if (HoopLink.task.equals("invert") == true) {
            dbg("Configuring job for invert task ...");

            job.setReducerClass(HoopInvertedListReducer.class);
            job.setMapperClass(HoopInvertedListMapper.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
        }

        if (HoopLink.task.equals("wordcount") == true) {
            dbg("Configuring job for wordcount task ...");

            job.setReducerClass(HoopWordCountReducer.class);
            job.setMapperClass(HoopWordCountMapper.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
        }

        dbg("Using input path: " + HoopLink.datapath);
        dbg("Using output path: " + HoopLink.outputpath);

        FileInputFormat.addInputPath(job, new Path(HoopLink.datapath));
        FileOutputFormat.setOutputPath(job, new Path(HoopLink.outputpath));

        job.setInputFormat(HoopWholeFileInputFormat.class);

        if ((HoopLink.shardcreate.equals("mos") == true) && (HoopLink.nrshards > 1)) {
            dbg("Setting output to sharded output streams class ...");

            job.setOutputFormat(HoopShardedOutputFormat.class);
        } else
            job.setOutputFormat(TextOutputFormat.class);

        /**
         * Temporarily commented out for testing purposes
         */

        //job.setPartitionerClass (HoopPartitioner.class);                      

        driver.register("Main");

        JobClient.runJob(job);

        postProcess(conf);
    }

    showTimeStamp();

    metrics.closeMarker();
    long timeTaken = metrics.getYValue();
    //long timeTaken=metrics.getMarkerRaw ();
    metrics.printMetrics(timeTaken);

    driver.unregister();

    /**
     * I've taken out the statistics portion since it relies on code that isn't distributed
     * The next version will have this solved. I might try the solution in:
     * http://stackoverflow.com/questions/7443074/initialize-public-static-variable-in-hadoop-through-arguments
     * Although chances are I will switch to using Hoop to collect much better performance and distribution 
     * statistics. See Hoop.java for more information
     */
    //stats.calcStatistics();
    //dbg (stats.printStatistics());
}

From source file:NaivePageRank.java

License:Apache License

public static void main(String[] args) throws Exception {
    int iteration = -1;
    String inputPath = args[0];//  w w w .  ja  v  a 2 s  .co  m
    String outputPath = args[1];
    int specIteration = 0;
    if (args.length > 2) {
        specIteration = Integer.parseInt(args[2]);
    }
    int numNodes = 100000;
    if (args.length > 3) {
        numNodes = Integer.parseInt(args[3]);
    }
    int numReducers = 32;
    if (args.length > 4) {
        numReducers = Integer.parseInt(args[4]);
    }
    System.out.println("specified iteration: " + specIteration);
    long start = System.currentTimeMillis();

    /**
     * job to count out-going links for each url
     */
    JobConf conf = new JobConf(NaivePageRank.class);
    conf.setJobName("PageRank-Count");
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(CountMapper.class);
    conf.setReducerClass(CountReducer.class);
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/count"));
    conf.setNumReduceTasks(numReducers);
    JobClient.runJob(conf);

    /******************** Initial Rank Assignment Job ***********************/
    conf = new JobConf(NaivePageRank.class);
    conf.setJobName("PageRank-Initialize");
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(InitialRankAssignmentMapper.class);
    conf.setReducerClass(InitialRankAssignmentReducer.class);
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration));
    conf.setNumReduceTasks(numReducers);
    // conf.setIterative(false);
    JobClient.runJob(conf);
    iteration++;

    do {
        /****************** Join Job ********************************/
        conf = new JobConf(NaivePageRank.class);
        conf.setJobName("PageRank-Join");
        conf.setOutputKeyClass(Text.class);
        // conf.setOutputValueClass(Text.class);
        conf.setMapperClass(ComputeRankMap.class);
        conf.setReducerClass(ComputeRankReduce.class);
        conf.setMapOutputKeyClass(TextPair.class);
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
        conf.setPartitionerClass(FirstPartitioner.class);
        conf.setOutputKeyComparatorClass(KeyComparator.class);
        conf.setOutputValueGroupingComparator(GroupComparator.class);

        // relation table
        FileInputFormat.setInputPaths(conf, new Path(inputPath));
        // rank table
        FileInputFormat.addInputPath(conf, new Path(outputPath + "/i" + (iteration - 1)));
        // count table
        FileInputFormat.addInputPath(conf, new Path(outputPath + "/count"));
        FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration));
        conf.setNumReduceTasks(numReducers);
        JobClient.runJob(conf);
        iteration++;

        /******************** Rank Aggregate Job ***********************/
        conf = new JobConf(NaivePageRank.class);
        conf.setJobName("PageRank-Aggregate");
        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(Text.class);
        conf.setMapOutputKeyClass(Text.class);
        conf.setMapperClass(RankAggregateMapper.class);
        conf.setReducerClass(RankAggregateReducer.class);
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
        FileInputFormat.setInputPaths(conf, new Path(outputPath + "/i" + (iteration - 1)));
        FileOutputFormat.setOutputPath(conf, new Path(outputPath + "/i" + iteration));
        conf.setNumReduceTasks(numReducers);
        conf.setInt("haloop.num.nodes", numNodes);
        JobClient.runJob(conf);
        iteration++;
    } while (iteration < 2 * specIteration);

    long end = System.currentTimeMillis();
    System.out.println("running time " + (end - start) / 1000 + "s");
}

From source file:IndexWords.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length < 2) {
        return -1;
    }/*from  ww  w  .  java 2s . c om*/

    checkWords = new String[args.length - 2];

    int numIter = 5;

    Path input = new Path(args[0]);

    for (int i = 0; i < numIter; i++) {
        JobConf conf = new JobConf(getConf(), IndexWords.class);
        conf.setJobName("indexwords");

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

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

        conf.setMapperClass(MapClass.class);
        conf.setReducerClass(Reduce.class);

        FileInputFormat.setInputPaths(conf, input);
        FileOutputFormat.setOutputPath(conf, new Path(args[1] + Integer.toString(i)));

        RunningJob rj = JobClient.runJob(conf);
        input = new Path(args[1] + Integer.toString(i));
        double resVal = rj.getCounters().getCounter(RecordCounters.RESIDUAL_COUNTER) * 1.0 / 10000;
        System.out.println(N + " " + (resVal / (1.0 * N)));
        if (resVal / (1.0 * N) < 0.001)
            break;
    }

    return 0;
}

From source file:ClimateData.java

License:Open Source License

public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(ClimateData.class);
    conf.setJobName("climatedata");

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.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  ww  w  .j av a  2  s . co  m
}

From source file:FormatStorage2ColumnStorageMR.java

License:Open Source License

@SuppressWarnings("deprecation")
public static void main(String[] args) throws Exception {

    if (args.length != 2) {
        System.out.println("FormatStorage2ColumnStorageMR <input> <output>");
        System.exit(-1);/* ww  w  .j av a  2  s. c  o m*/
    }

    JobConf conf = new JobConf(FormatStorageMR.class);

    conf.setJobName("FormatStorage2ColumnStorageMR");

    conf.setNumMapTasks(1);
    conf.setNumReduceTasks(4);

    conf.setOutputKeyClass(LongWritable.class);
    conf.setOutputValueClass(Unit.Record.class);

    conf.setMapperClass(FormatStorageMapper.class);
    conf.setReducerClass(ColumnStorageReducer.class);

    conf.setInputFormat(FormatStorageInputFormat.class);
    conf.set("mapred.output.compress", "flase");

    Head head = new Head();
    initHead(head);

    head.toJobConf(conf);

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

    FileSystem fs = outputPath.getFileSystem(conf);
    fs.delete(outputPath, true);

    JobClient jc = new JobClient(conf);
    RunningJob rj = null;
    rj = jc.submitJob(conf);

    String lastReport = "";
    SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
    long reportTime = System.currentTimeMillis();
    long maxReportInterval = 3 * 1000;
    while (!rj.isComplete()) {
        try {
            Thread.sleep(1000);
        } catch (InterruptedException e) {
        }

        int mapProgress = Math.round(rj.mapProgress() * 100);
        int reduceProgress = Math.round(rj.reduceProgress() * 100);

        String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

        if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

            String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
            System.out.println(output);
            lastReport = report;
            reportTime = System.currentTimeMillis();
        }
    }

    System.exit(0);

}

From source file:BP.java

License:Apache License

protected JobConf configUpdateMessage() throws Exception {
    final JobConf conf = new JobConf(getConf(), BP.class);
    conf.set("nstate", "" + nstate);
    conf.set("compat_matrix_str", "" + edge_potential_str);
    conf.setJobName("BP_Update_message");

    conf.setMapperClass(MapUpdateMessage.class);
    conf.setReducerClass(RedUpdateMessage.class);

    fs.delete(message_next_path, true);//from  w  w w  . j  ava 2s.  c om

    FileInputFormat.setInputPaths(conf, message_cur_path, prior_path);
    FileOutputFormat.setOutputPath(conf, message_next_path);

    conf.setNumReduceTasks(nreducer);

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

    return conf;
}

From source file:BP.java

License:Apache License

protected JobConf configCheckErr() throws Exception {
    final JobConf conf = new JobConf(getConf(), BP.class);
    conf.set("nstate", "" + nstate);
    conf.setJobName("BP_Check Err");

    fs.delete(check_error_path, true);/*from ww  w  .j  av a 2 s.  co m*/

    conf.setMapperClass(MapCheckErr.class);
    conf.setReducerClass(RedCheckErr.class);

    FileInputFormat.setInputPaths(conf, message_cur_path, message_next_path);
    FileOutputFormat.setOutputPath(conf, check_error_path);

    conf.setNumReduceTasks(nreducer);

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

    return conf;
}