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

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

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

Introduction

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

Prototype

@Deprecated
public static Job getInstance(Cluster ignored) throws IOException

Source Link

Document

Creates a new Job with no particular Cluster .

Usage

From source file:ComputeCooccurrenceMatrixStripes.java

License:Apache License

/**
 * Runs this tool.//from   w w  w.j  a  v a  2 s  .c  o  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));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("window size").create(WINDOW));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers")
            .create(NUM_REDUCERS));

    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);
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;
    int window = cmdline.hasOption(WINDOW) ? Integer.parseInt(cmdline.getOptionValue(WINDOW)) : 2;

    LOG.info("Tool: " + ComputeCooccurrenceMatrixStripes.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - window: " + window);
    LOG.info(" - number of reducers: " + reduceTasks);

    Job job = Job.getInstance(getConf());
    job.setJobName(ComputeCooccurrenceMatrixStripes.class.getSimpleName());
    job.setJarByClass(ComputeCooccurrenceMatrixStripes.class);

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

    job.getConfiguration().setInt("window", window);

    job.setNumReduceTasks(reduceTasks);

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

    job.setMapOutputKeyClass(Text.class);
    job.setOutputValueClass(String2IntOpenHashMapWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(String2IntOpenHashMapWritable.class);

    job.setMapperClass(MyMapper.class);
    job.setCombinerClass(MyReducer.class);
    job.setReducerClass(MyReducer.class);

    long startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:BuildPageRankRecords.java

License:Apache License

/**
 * Runs this tool.//from  ww w  .j a v a 2  s  .  c o 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));
    options.addOption(
            OptionBuilder.withArgName("num").hasArg().withDescription("number of nodes").create(NUM_NODES));

    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) || !cmdline.hasOption(NUM_NODES)) {
        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);
    int n = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));

    LOG.info("Tool name: " + BuildPageRankRecords.class.getSimpleName());
    LOG.info(" - inputDir: " + inputPath);
    LOG.info(" - outputDir: " + outputPath);
    LOG.info(" - numNodes: " + n);

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

    Job job = Job.getInstance(conf);
    job.setJobName(BuildPageRankRecords.class.getSimpleName() + ":" + inputPath);
    job.setJarByClass(BuildPageRankRecords.class);

    job.setNumReduceTasks(0);

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

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

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

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

    job.setMapperClass(MyMapper.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:BigramRelativeFrequencyTuple.java

License:Apache License

/**
 * Runs this tool./*from w  w w .  jav  a  2s. com*/
 */
public int run(String[] args) throws Exception {
    if (args.length != 3) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];
    int reduceTasks = Integer.parseInt(args[2]);

    LOG.info("Tool name: " + BigramRelativeFrequencyTuple.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - num reducers: " + reduceTasks);

    Job job = Job.getInstance(getConf());
    job.setJobName(BigramRelativeFrequencyTuple.class.getSimpleName());
    job.setJarByClass(BigramRelativeFrequencyTuple.class);

    job.setNumReduceTasks(reduceTasks);

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

    job.setMapOutputKeyClass(BinSedesTuple.class);
    job.setMapOutputValueClass(FloatWritable.class);
    job.setOutputKeyClass(BinSedesTuple.class);
    job.setOutputValueClass(FloatWritable.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapperClass(MyMapper.class);
    job.setCombinerClass(MyCombiner.class);
    job.setReducerClass(MyReducer.class);
    job.setPartitionerClass(MyPartitioner.class);

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

    long startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:avro.mr.MapReduceAvroWordCount.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: AvroWordCount <input path> <output path>");
        return -1;
    }/*from  w  w w  . jav  a2s . c o m*/

    Job job = Job.getInstance(getConf());
    job.setJarByClass(MapReduceAvroWordCount.class);
    job.setJobName("wordcount");

    // We call setOutputSchema first so we can override the configuration
    // parameters it sets
    AvroJob.setOutputKeySchema(job, Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT)));
    job.setOutputValueClass(NullWritable.class);

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setSortComparatorClass(Text.Comparator.class);

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

    job.waitForCompletion(true);

    return 0;
}

From source file:avro.mr.MapReduceColorCount.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: MapReduceColorCount <input path> <output path>");
        return -1;
    }//from   www.ja  va 2s. c om

    Job job = Job.getInstance(getConf());
    job.setJarByClass(MapReduceColorCount.class);
    job.setJobName("Color Count");

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

    job.setInputFormatClass(AvroKeyInputFormat.class);
    job.setMapperClass(ColorCountMapper.class);
    AvroJob.setInputKeySchema(job, User.getClassSchema());
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(ColorCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

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

From source file:avro.mr.MapReduceColorCountSeqFile.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: MapReduceColorCount <input path> <output path>");
        return -1;
    }/*ww  w. j  av  a 2s .co m*/

    Job job = Job.getInstance(getConf());
    job.setJarByClass(MapReduceColorCountSeqFile.class);
    job.setJobName("Color Count 2");

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

    job.setInputFormatClass(AvroSequenceFileInputFormat.class);
    AvroJob.setInputKeySchema(job, Schema.create(Schema.Type.LONG));
    AvroJob.setInputValueSchema(job, User.getClassSchema());

    job.setMapperClass(ColorCountMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputFormatClass(AvroSequenceFileOutputFormat.class);
    job.setReducerClass(ColorCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

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

From source file:basic.PartitionGraph.java

License:Apache License

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

    options.addOption(new Option(RANGE, "use range partitioner"));

    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));
    options.addOption(
            OptionBuilder.withArgName("num").hasArg().withDescription("number of nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of partitions")
            .create(NUM_PARTITIONS));

    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) || !cmdline.hasOption(NUM_NODES)
            || !cmdline.hasOption(NUM_PARTITIONS)) {
        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 inPath = cmdline.getOptionValue(INPUT);
    String outPath = cmdline.getOptionValue(OUTPUT);
    int nodeCount = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    int numParts = Integer.parseInt(cmdline.getOptionValue(NUM_PARTITIONS));
    boolean useRange = cmdline.hasOption(RANGE);

    LOG.info("Tool name: " + PartitionGraph.class.getSimpleName());
    LOG.info(" - input dir: " + inPath);
    LOG.info(" - output dir: " + outPath);
    LOG.info(" - num partitions: " + numParts);
    LOG.info(" - node cnt: " + nodeCount);
    LOG.info(" - use range partitioner: " + useRange);

    Configuration conf = getConf();
    conf.setInt("NodeCount", nodeCount);

    Job job = Job.getInstance(conf);
    job.setJobName(PartitionGraph.class.getSimpleName() + ":" + inPath);
    job.setJarByClass(PartitionGraph.class);

    job.setNumReduceTasks(numParts);

    FileInputFormat.setInputPaths(job, new Path(inPath));
    FileOutputFormat.setOutputPath(job, new Path(outPath));

    job.setInputFormatClass(NonSplitableSequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

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

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

    if (useRange) {
        job.setPartitionerClass(RangePartitioner.class);
    }

    FileSystem.get(conf).delete(new Path(outPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:biglayer.AutoCoder.java

License:Apache License

/**
 * Runs this tool.//from   w  ww .  java2 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));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers")
            .create(NUM_REDUCERS));

    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);

    String inputPath = "qiwang321/MNIST-mingled-key/part*";
    String outputPath = "shangfu/layeroutput";

    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

    LOG.info("Tool: " + AutoCoder.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - number of reducers: " + reduceTasks);
    Configuration conf = getConf();

    conf.setInt("num_reduce_task", reduceTasks);
    conf.set("sidepath", outputPath + "_side/");

    Job job0 = Job.getInstance(conf);
    job0.setJobName(AutoCoder.class.getSimpleName());
    job0.setJarByClass(AutoCoder.class);
    job0.setNumReduceTasks(reduceTasks);

    job0.getConfiguration().setInt("layer_ind", 0);

    FileInputFormat.setInputPaths(job0, new Path(inputPath));
    FileOutputFormat.setOutputPath(job0, new Path(outputPath + "_0"));

    job0.setInputFormatClass(KeyValueTextInputFormat.class);
    job0.setOutputFormatClass(SequenceFileOutputFormat.class);

    job0.setMapOutputKeyClass(PairOfInts.class);
    job0.setMapOutputValueClass(ModelNode.class);
    job0.setOutputKeyClass(PairOfInts.class);
    job0.setOutputValueClass(ModelNode.class);

    job0.setMapperClass(MyMapper0.class);
    job0.setReducerClass(MyReducer0.class);
    job0.setPartitionerClass(MyPartitioner.class);
    // Delete the output directory if it exists already.
    Path outputDir = new Path(outputPath + "_0");
    FileSystem.get(getConf()).delete(outputDir, true);
    long startTime = System.currentTimeMillis();
    long codeStart = System.currentTimeMillis();
    double codeTimeSum = 0;
    job0.waitForCompletion(true);
    LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    codeTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;

    for (int iterations = 1; iterations < GlobalUtil.NUM_LAYER + 1; iterations++) {
        Job job1 = Job.getInstance(conf);
        job1.setJobName(AutoCoder.class.getSimpleName());
        job1.setJarByClass(AutoCoder.class);
        job1.setNumReduceTasks(reduceTasks);
        job1.getConfiguration().setInt("layer_ind", iterations);
        FileInputFormat.setInputPaths(job1, new Path(outputPath + "_" + (iterations - 1)));
        FileOutputFormat.setOutputPath(job1, new Path(outputPath + "_" + iterations + "_train"));

        LOG.info("Tool: " + AutoCoder.class.getSimpleName());
        LOG.info(" - input path: " + outputPath + "_" + (iterations - 1));
        LOG.info(" - output path: " + outputPath + "_" + iterations + "_train");
        LOG.info(" - number of reducers: " + reduceTasks);

        job1.setInputFormatClass(SequenceFileInputFormat.class);
        job1.setOutputFormatClass(SequenceFileOutputFormat.class);

        job1.setMapOutputKeyClass(PairOfInts.class);
        job1.setMapOutputValueClass(ModelNode.class);
        job1.setOutputKeyClass(PairOfInts.class);
        job1.setOutputValueClass(ModelNode.class);

        job1.setMapperClass(MyMapper.class);
        job1.setReducerClass(MyReducer_Train.class);
        job1.setPartitionerClass(MyPartitioner.class);
        // Delete the output directory if it exists already.
        outputDir = new Path(outputPath + "_" + iterations + "_train");
        FileSystem.get(getConf()).delete(outputDir, true);
        startTime = System.currentTimeMillis();
        job1.waitForCompletion(true);
        LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
        codeTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;

        Job job2 = Job.getInstance(conf);
        job2.setJobName(AutoCoder.class.getSimpleName());
        job2.setJarByClass(AutoCoder.class);
        job2.setNumReduceTasks(reduceTasks);
        job2.getConfiguration().setInt("layer_ind", iterations);
        FileInputFormat.setInputPaths(job2, new Path(outputPath + "_" + (iterations + "_train")));
        FileOutputFormat.setOutputPath(job2, new Path(outputPath + "_" + iterations));

        LOG.info("Tool: " + AutoCoder.class.getSimpleName());
        LOG.info(" - input path: " + outputPath + "_" + iterations + "_train");
        LOG.info(" - output path: " + outputPath + "_" + iterations);
        LOG.info(" - number of reducers: " + reduceTasks);

        job2.setInputFormatClass(SequenceFileInputFormat.class);
        job2.setOutputFormatClass(SequenceFileOutputFormat.class);

        job2.setMapOutputKeyClass(PairOfInts.class);
        job2.setMapOutputValueClass(ModelNode.class);
        job2.setOutputKeyClass(PairOfInts.class);
        job2.setOutputValueClass(ModelNode.class);

        job2.setMapperClass(MyMapper.class);
        job2.setReducerClass(MyReducer_GenData.class);
        job2.setPartitionerClass(MyPartitioner.class);
        // Delete the output directory if it exists already.
        outputDir = new Path(outputPath + "_" + iterations);
        FileSystem.get(getConf()).delete(outputDir, true);
        startTime = System.currentTimeMillis();
        job2.waitForCompletion(true);
        LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
        codeTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;

    }

    LOG.info(" - input path: " + outputPath + "_" + GlobalUtil.NUM_LAYER);
    LOG.info(" - output path: " + outputPath);
    reduceTasks = 1;
    LOG.info(" - number of reducers: " + reduceTasks);

    Job job_super = Job.getInstance(conf);
    job_super.setJobName(AutoCoder.class.getSimpleName());
    job_super.setJarByClass(AutoCoder.class);
    job_super.setNumReduceTasks(reduceTasks);

    FileInputFormat.setInputPaths(job_super, new Path(outputPath + "_" + GlobalUtil.NUM_LAYER));
    FileOutputFormat.setOutputPath(job_super, new Path(outputPath));

    job_super.setInputFormatClass(SequenceFileInputFormat.class);
    job_super.setOutputFormatClass(SequenceFileOutputFormat.class);

    job_super.setMapOutputKeyClass(PairOfInts.class);
    job_super.setMapOutputValueClass(ModelNode.class);
    job_super.setOutputKeyClass(NullWritable.class);
    job_super.setOutputValueClass(NullWritable.class);

    job_super.setMapperClass(MyMapper_Super.class);
    job_super.setReducerClass(MyReducer_Super.class);
    job_super.setPartitionerClass(MyPartitioner.class);

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

    startTime = System.currentTimeMillis();
    job_super.waitForCompletion(true);
    LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    codeTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;

    Log.info("Final Time: " + ((System.currentTimeMillis() - codeStart) / 1000.0) + " seconds,  " + codeTimeSum
            + " seconds.");
    //prepareNextIteration(inputPath0, outputPath,iterations,conf,reduceTasks);

    return 0;
}

From source file:bigmodel.AutoCoderLocal.java

License:Apache License

/**
 * Runs this tool.//from w ww .  ja  v  a  2s . 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));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers")
            .create(NUM_REDUCERS));

    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) + "/part-r-00000";
    String outputPath = cmdline.getOptionValue(OUTPUT);
    String dataPath = cmdline.getOptionValue(INPUT) + "/common";
    //String inputPath = "/home/qiwang321/mapreduce-data/data/in-mingled1-5/part*";
    //String outputPath = "output";
    //String dataPath = "/home/qiwang321/mapreduce-data/data/in-mingled1-5/common";
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

    LOG.info("Tool: " + AutoCoderLocal.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - number of reducers: " + reduceTasks);
    Configuration conf = getConf();
    initialParameters(conf);

    conf.set("dataPath", dataPath);

    Job job = Job.getInstance(conf);
    job.setJobName(AutoCoderLocal.class.getSimpleName());
    job.setJarByClass(AutoCoderLocal.class);
    // set the path of the information of k clusters in this iteration
    job.getConfiguration().set("sidepath", inputPath + "/side_output");
    job.setNumReduceTasks(reduceTasks);

    dataShuffle();

    FileInputFormat.setInputPaths(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    FileInputFormat.setMinInputSplitSize(job, 1000 * 1024 * 1024);
    FileInputFormat.setMaxInputSplitSize(job, 1000 * 1024 * 1024);

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

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(ModelNode.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(SuperModel.class);

    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);
    job.setPartitionerClass(MyPartitioner.class);

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

    long startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    //prepareNextIteration(inputPath0, outputPath,iterations,conf,reduceTasks);

    return 0;
}

From source file:bigsidemodel.AutoCoder.java

License:Apache License

/**
 * Runs this tool./*www.  j a  va  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));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers")
            .create(NUM_REDUCERS));

    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);

    String inputPath = "qiwang321/best5-mingled-key-56x56/part*";
    String outputPath = "shangfu/bigoutput";
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

    LOG.info("Tool: " + AutoCoder.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath + "0");
    LOG.info(" - number of reducers: " + reduceTasks);
    Configuration conf = getConf();
    conf.setInt("num_reduce_task", reduceTasks);
    conf.set("sidepath", outputPath + "_side/");

    Job job0 = Job.getInstance(conf);
    job0.setJobName(AutoCoder.class.getSimpleName());
    job0.setJarByClass(AutoCoder.class);
    // set the path of the information of k clusters in this iteration
    job0.setNumReduceTasks(reduceTasks);

    FileInputFormat.setInputPaths(job0, new Path(inputPath));
    FileOutputFormat.setOutputPath(job0, new Path(outputPath + "0"));

    job0.setInputFormatClass(KeyValueTextInputFormat.class);
    job0.setOutputFormatClass(SequenceFileOutputFormat.class);

    job0.setMapOutputKeyClass(PairOfInts.class);
    job0.setMapOutputValueClass(DataNode.class);
    job0.setOutputKeyClass(PairOfInts.class);
    job0.setOutputValueClass(DataNode.class);

    job0.setMapperClass(MyMapper0.class);
    job0.setReducerClass(MyReducer0.class);
    job0.setPartitionerClass(MyPartitioner.class);

    // Delete the output directory if it exists already.
    Path outputDir = new Path(outputPath + "0");
    FileSystem.get(getConf()).delete(outputDir, true);

    long codeStart = System.currentTimeMillis();
    double jobTimeSum = 0;

    long startTime = System.currentTimeMillis();
    job0.waitForCompletion(true);
    LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    jobTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;

    //======= Job 1
    LOG.info("Tool: " + AutoCoder.class.getSimpleName());
    LOG.info(" - input path: " + outputPath + "0");
    LOG.info(" - output path: " + outputPath + "1");
    LOG.info(" - number of reducers: " + 1);
    int nModel = reduceTasks;
    reduceTasks = 1;

    Job job1 = Job.getInstance(conf);
    job1.setJobName(AutoCoder.class.getSimpleName());
    job1.setJarByClass(AutoCoder.class);
    // set the path of the information of k clusters in this iteration
    job1.setNumReduceTasks(reduceTasks);

    FileInputFormat.setInputPaths(job1, new Path(outputPath + "0"));
    FileOutputFormat.setOutputPath(job1, new Path(outputPath + "1"));

    job1.setInputFormatClass(SequenceFileInputFormat.class);
    job1.setOutputFormatClass(SequenceFileOutputFormat.class);

    job1.setMapOutputKeyClass(PairOfInts.class);
    job1.setMapOutputValueClass(DataNode.class);
    job1.setOutputKeyClass(NullWritable.class);
    job1.setOutputValueClass(NullWritable.class);

    job1.setMapperClass(MyMapper1.class);
    job1.setReducerClass(MyReducer1.class);
    job1.setPartitionerClass(MyPartitioner.class);

    // Delete the output directory if it exists already.
    outputDir = new Path(outputPath + "1");
    FileSystem.get(getConf()).delete(outputDir, true);

    startTime = System.currentTimeMillis();
    job1.waitForCompletion(true);
    LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    jobTimeSum += (System.currentTimeMillis() - startTime) / 1000.0;
    LOG.info("Final Time: " + ((System.currentTimeMillis() - codeStart) / 1000.0) + " seconds,  " + jobTimeSum
            + " seconds.");

    return 0;
}