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

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

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

Introduction

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

Prototype

public void setJobName(String name) throws IllegalStateException

Source Link

Document

Set the user-specified job name.

Usage

From source file:edu.umd.JBizz.BuildInvertedIndexCompressed.java

License:Apache License

/**
 * Runs this tool.// w  w w.j a v  a  2 s  .c om
 */
@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);
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

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

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

    job.setNumReduceTasks(reduceTasks);

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

    //job.setMapOutputKeyClass(Text.class);
    //job.setMapOutputValueClass(PairOfInts.class);
    job.setMapOutputKeyClass(PairOfStringInt.class);
    job.setMapOutputValueClass(VIntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(BytesWritable.class);
    job.setOutputFormatClass(MapFileOutputFormat.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);
    System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.JBizz.BuildPersonalizedPageRankRecords.java

License:Apache License

/**
 * Runs this tool.//from   w  w w.  j  a  v a2s.  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 nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("sources").hasArg().withDescription("Personalization Nodes")
            .create(SOURCES));

    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(SOURCES)) {
        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));
    String sources = cmdline.getOptionValue(SOURCES);

    String[] sourceList = sources.trim().split(",");
    int numSources = sourceList.length;

    int source = Integer.parseInt(sourceList[0]);

    int[] sourceNodes = new int[numSources];
    for (int i = 0; i < numSources; i++) {
        sourceNodes[i] = Integer.parseInt(sourceList[i]);
    }

    LOG.info("Tool name: " + BuildPersonalizedPageRankRecords.class.getSimpleName());
    LOG.info(" - inputDir: " + inputPath);
    LOG.info(" - outputDir: " + outputPath);
    LOG.info(" - numNodes: " + n);
    LOG.info("source list: " + sourceList);
    LOG.info("first source: " + source);

    Configuration conf = getConf();
    conf.setInt(NODE_CNT_FIELD, n);
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt(SOURCE, source);
    conf.setInt(NUM_SOURCES, numSources);
    conf.set(SOURCE_NODES, sources);

    Job job = Job.getInstance(conf);
    job.setJobName(BuildPersonalizedPageRankRecords.class.getSimpleName() + ":" + inputPath);
    job.setJarByClass(BuildPersonalizedPageRankRecords.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:edu.umd.JBizz.ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool.// w w  w.  j  a  va2s .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("top n").create(TOP));

    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(TOP)) {
        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(TOP));

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

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

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

    job.setNumReduceTasks(1);

    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(FloatWritable.class);

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

    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.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:edu.umd.JBizz.RunPersonalizedPageRankBasic.java

License:Apache License

private float phase1(int i, int j, String basePath, int numNodes) throws Exception {
    Job job = Job.getInstance(getConf());
    job.setJobName("PageRank:Basic:iteration" + j + ":Phase1");
    job.setJarByClass(RunPersonalizedPageRankBasic.class);

    String in = basePath + "/iter" + formatter.format(i);
    String out = basePath + "/iter" + formatter.format(j) + "t";
    String outm = out + "-mass";

    // We need to actually count the number of part files to get the number of partitions (because
    // the directory might contain _log).
    int numPartitions = 0;
    for (FileStatus s : FileSystem.get(getConf()).listStatus(new Path(in))) {
        if (s.getPath().getName().contains("part-"))
            numPartitions++;/*from w w  w  .  j  a  v  a  2s  . c  o  m*/
    }

    LOG.info("PageRank: iteration " + j + ": Phase1");
    LOG.info(" - input: " + in);
    LOG.info(" - output: " + out);
    LOG.info(" - nodeCnt: " + numNodes);
    //LOG.info(" - useCombiner: " + useCombiner);
    //LOG.info(" - useInmapCombiner: " + useInMapperCombiner);
    LOG.info("computed number of partitions: " + numPartitions);

    int numReduceTasks = numPartitions;

    job.getConfiguration().setInt("NodeCount", numNodes);
    job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false);
    job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false);
    //job.getConfiguration().set("mapred.child.java.opts", "-Xmx2048m");
    job.getConfiguration().set("PageRankMassPath", outm);

    job.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(job, new Path(in));
    FileOutputFormat.setOutputPath(job, new Path(out));

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

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

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

    job.setMapperClass(MapWithInMapperCombiningClass.class);

    job.setReducerClass(ReduceClass.class);

    FileSystem.get(getConf()).delete(new Path(out), true);
    FileSystem.get(getConf()).delete(new Path(outm), true);

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

    float mass = 0;
    FileSystem fs = FileSystem.get(getConf());
    for (FileStatus f : fs.listStatus(new Path(outm))) {
        FSDataInputStream fin = fs.open(f.getPath());
        mass = mass + fin.readFloat();
        fin.close();
    }

    return mass;
}

From source file:edu.umd.JBizz.RunPersonalizedPageRankBasic.java

License:Apache License

private void phase2(int i, int j, float missing, String basePath, int numNodes, String sources)
        throws Exception {
    Job job = Job.getInstance(getConf());
    job.setJobName("PageRank:Basic:iteration" + j + ":Phase2");
    job.setJarByClass(RunPersonalizedPageRankBasic.class);

    LOG.info("missing PageRank mass: " + missing);
    LOG.info("number of nodes: " + numNodes);

    String in = basePath + "/iter" + formatter.format(j) + "t";
    String out = basePath + "/iter" + formatter.format(j);

    LOG.info("PageRank: iteration " + j + ": Phase2");
    LOG.info(" - input: " + in);
    LOG.info(" - output: " + out);

    String[] sourceList = sources.trim().split(",");
    int numSources = sourceList.length;

    int source = Integer.parseInt(sourceList[0]);

    job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false);
    job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false);
    job.getConfiguration().setFloat("MissingMass", (float) missing);
    job.getConfiguration().setInt("NodeCount", numNodes);
    job.getConfiguration().setInt("sourcesList", source);

    job.setNumReduceTasks(0);// w ww.jav a  2 s. c  o  m

    FileInputFormat.setInputPaths(job, new Path(in));
    FileOutputFormat.setOutputPath(job, new Path(out));

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

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

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

    job.setMapperClass(MapPageRankMassDistributionClass.class);

    FileSystem.get(getConf()).delete(new Path(out), true);

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

From source file:edu.umd.shrawanraina.BuildInvertedIndexCompressed.java

License:Apache License

/**
 * Runs this tool.//from   w  w w .j  a va  2  s  .  c om
 */
@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);
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

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

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

    job.setNumReduceTasks(reduceTasks);

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

    job.setMapOutputKeyClass(PairOfStringInt.class);
    job.setMapOutputValueClass(VIntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(BytesWritable.class);
    job.setOutputFormatClass(MapFileOutputFormat.class);

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

    // Delete the output directory if it exists already.
    Path outputDir = new Path(outputPath);
    FileSystem.get(getConf()).delete(outputDir, true);
    /*
    // Delete side data directory if it exists already.
    Path sdDir = new Path("sidedata");
    FileSystem.get(getConf()).delete(sdDir, 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:edu.umd.shrawanraina.BuildInvertedIndexHBase.java

License:Apache License

/**
 * Runs this tool./*from  w w w  .  j  a v  a2s  . c om*/
 */
@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 outputTable = cmdline.getOptionValue(OUTPUT);
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

    // If the table doesn't already exist, create it.
    Configuration conf = getConf();
    conf.addResource(new Path("/etc/hbase/conf/hbase-site.xml"));

    Configuration hbaseConfig = HBaseConfiguration.create(conf);
    HBaseAdmin admin = new HBaseAdmin(hbaseConfig);

    if (admin.tableExists(outputTable)) {
        LOG.info(String.format("Table '%s' exists: dropping table and recreating.", outputTable));
        LOG.info(String.format("Disabling table '%s'", outputTable));
        admin.disableTable(outputTable);
        LOG.info(String.format("Droppping table '%s'", outputTable));
        admin.deleteTable(outputTable);
    }

    HTableDescriptor tableDesc = new HTableDescriptor(TableName.valueOf(outputTable));
    for (int i = 0; i < FAMILIES.length; i++) {
        HColumnDescriptor hColumnDesc = new HColumnDescriptor(FAMILIES[i]);
        tableDesc.addFamily(hColumnDesc);
    }

    admin.createTable(tableDesc);
    LOG.info(String.format("Successfully created table '%s'", outputTable));

    admin.close();

    // Now we're ready to start running MapReduce.
    LOG.info("Tool: " + HBaseWordCount.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output table: " + outputTable);
    LOG.info(" - number of reducers: " + reduceTasks);

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

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(PairOfInts.class);

    job.setMapperClass(MyMapper.class);
    //job.setReducerClass(MyReducer.class);
    job.setNumReduceTasks(reduceTasks);

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

    FileInputFormat.setInputPaths(job, new Path(inputPath));
    TableMapReduceUtil.initTableReducerJob(outputTable, MyTableReducer.class, job);

    // Delete the output directory if it exists already.
    Path outputDir = new Path(outputTable);
    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:edu.umd.shrawanraina.BuildInvertedIndexHBaseCompressed.java

License:Apache License

/**
 * Runs this tool./* ww  w .  j a va  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 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 outputTable = cmdline.getOptionValue(OUTPUT);
    int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS))
            : 1;

    // If the table doesn't already exist, create it.
    Configuration conf = getConf();
    conf.addResource(new Path("/etc/hbase/conf/hbase-site.xml"));

    Configuration hbaseConfig = HBaseConfiguration.create(conf);
    HBaseAdmin admin = new HBaseAdmin(hbaseConfig);

    if (admin.tableExists(outputTable)) {
        LOG.info(String.format("Table '%s' exists: dropping table and recreating.", outputTable));
        LOG.info(String.format("Disabling table '%s'", outputTable));
        admin.disableTable(outputTable);
        LOG.info(String.format("Droppping table '%s'", outputTable));
        admin.deleteTable(outputTable);
    }

    HTableDescriptor tableDesc = new HTableDescriptor(TableName.valueOf(outputTable));
    for (int i = 0; i < FAMILIES.length; i++) {
        HColumnDescriptor hColumnDesc = new HColumnDescriptor(FAMILIES[i]);
        tableDesc.addFamily(hColumnDesc);
    }

    admin.createTable(tableDesc);
    LOG.info(String.format("Successfully created table '%s'", outputTable));

    admin.close();

    // Now we're ready to start running MapReduce.
    LOG.info("Tool: " + HBaseWordCount.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output table: " + outputTable);
    LOG.info(" - number of reducers: " + reduceTasks);

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

    job.setMapOutputKeyClass(PairOfStringInt.class);
    job.setMapOutputValueClass(VIntWritable.class);

    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);
    job.setNumReduceTasks(reduceTasks);

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

    FileInputFormat.setInputPaths(job, new Path(inputPath));
    TableMapReduceUtil.initTableReducerJob(outputTable, MyTableReducer.class, job);

    // Delete the output directory if it exists already.
    Path outputDir = new Path(outputTable);
    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:edu.umd.shrawanraina.BuildPersonalizedPageRankRecords.java

License:Apache License

/**
 * Runs this tool.// w ww.ja va  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));
    options.addOption(
            OptionBuilder.withArgName("node").hasArg().withDescription("source nodes").create(SOURCES));

    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(SOURCES)) {
        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));
    String sources = cmdline.getOptionValue(SOURCES);

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

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

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

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(PageRankNodeUpd.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:edu.umd.shrawanraina.ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool.//from   w w  w  .  ja  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("top").hasArg().withDescription("top num").create(TOP));
    options.addOption(
            OptionBuilder.withArgName("node").hasArg().withDescription("source node").create(SOURCES));

    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(SOURCES) || !cmdline.hasOption(TOP)) {
        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);
    int n = Integer.parseInt(cmdline.getOptionValue(TOP));
    String source = cmdline.getOptionValue(SOURCES);
    String outputPath = cmdline.hasOption(OUTPUT) ? cmdline.getOptionValue(OUTPUT) : "final";

    LOG.info("Tool name: " + ExtractTopPersonalizedPageRankNodes.class.getSimpleName());
    LOG.info(" - input: " + inputPath);
    LOG.info(" - source: " + source);

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

    Job job = Job.getInstance(conf);
    job.setJobName(ExtractTopPersonalizedPageRankNodes.class.getSimpleName());
    job.setJarByClass(ExtractTopPersonalizedPageRankNodes.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);
    extractTop(inputPath, outputPath, source, n);
    return 0;
}