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

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

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

Introduction

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

Prototype

public void setOutputFormatClass(Class<? extends OutputFormat> cls) throws IllegalStateException

Source Link

Document

Set the OutputFormat for the job.

Usage

From source file:WordCount.java

License:Apache License

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

    ///start/*from  w w w .  j  a va2s .  co m*/
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }
    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";
        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);

        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);

            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);

            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }

        job.setInputFormatClass(ColumnFamilyInputFormat.class);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);

        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row
        //Son degisiklik
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);
        //System.out.println("tessssssaaat");

        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");

        job.waitForCompletion(true);
    }
    //print
    final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:WordCount.java

License:Apache License

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

    ///start//from  w  ww.  j ava  2  s  . c o m
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }

    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";

        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);

        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);
            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);
            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }
        job.setInputFormatClass(ColumnFamilyInputFormat.class);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);

        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row          
        //Son degisiklik
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);
        //System.out.println("tessssssaaat");

        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");

        job.waitForCompletion(true);
    }

    //print
    final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:TopFiveAverageMoviesRatedByFemales.java

public static void main(String[] args) throws Exception {
    JobConf conf1 = new JobConf();
    Job job1 = new Job(conf1, "TopFiveAverageMoviesRatedByFemales");
    org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job1, new Path(args[0]),
            TextInputFormat.class, TopFiveAverageMoviesRatedByFemales.MapRatings.class);
    org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job1, new Path(args[1]),
            TextInputFormat.class, TopFiveAverageMoviesRatedByFemales.MapGender.class);

    job1.setReducerClass(TopFiveAverageMoviesRatedByFemales.ReduceToMovieIdAndRatings.class);
    job1.setMapOutputKeyClass(Text.class);
    job1.setMapOutputValueClass(Text.class);
    job1.setOutputKeyClass(Text.class);
    job1.setOutputValueClass(Text.class);
    job1.setJarByClass(TopFiveAverageMoviesRatedByFemales.class);

    job1.setOutputFormatClass(TextOutputFormat.class);
    FileOutputFormat.setOutputPath(job1, new Path(args[3]));

    boolean flag = job1.waitForCompletion(true);
    boolean flag1 = false;
    boolean flag2 = false;

    if (flag) {/*w w w.j  av  a 2 s. c o m*/
        JobConf conf2 = new JobConf();
        Job job2 = new Job(conf2, "AverageCalculation");

        //org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job2, new Path(args[2]), TextInputFormat.class, Map2_1.class);
        //org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job2, new Path(args[3]), TextInputFormat.class, Map2_2.class);

        job2.setMapperClass(MapAverage.class);
        job2.setReducerClass(ReduceAverage.class);
        job2.setMapOutputKeyClass(Text.class);
        job2.setMapOutputValueClass(Text.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);
        job2.setJarByClass(TopFiveAverageMoviesRatedByFemales.class);

        job2.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job2, new Path(args[3]));
        FileOutputFormat.setOutputPath(job2, new Path(args[4]));

        flag1 = job2.waitForCompletion(true);
    }

    if (flag1) {
        JobConf conf3 = new JobConf();
        Job job3 = new Job(conf3, "AverageCalculation");

        org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job3, new Path(args[4]),
                TextInputFormat.class, MapAverageTop5.class);
        org.apache.hadoop.mapreduce.lib.input.MultipleInputs.addInputPath(job3, new Path(args[2]),
                TextInputFormat.class, MapMovieName.class);

        //job3.setMapperClass(MapAverageTop5.class);
        job3.setReducerClass(ReduceAverageTop5.class);
        job3.setMapOutputKeyClass(Text.class);
        job3.setMapOutputValueClass(Text.class);
        job3.setOutputKeyClass(Text.class);
        job3.setOutputValueClass(Text.class);
        job3.setJarByClass(TopFiveAverageMoviesRatedByFemales.class);

        job3.setOutputFormatClass(TextOutputFormat.class);
        //FileInputFormat.addInputPath(job3, new Path(args[4]));
        FileOutputFormat.setOutputPath(job3, new Path(args[5]));

        flag2 = job3.waitForCompletion(true);

    }
}

From source file:ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool.//w  ww.  j  a va  2 s  . com
 */
@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));
    options.addOption(OptionBuilder.withArgName("src").hasArg().withDescription("source node").create(SRC));

    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(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 = "abc";//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(TOP_PG, 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(PairOfIntFloat.class);
    job.setMapOutputValueClass(IntWritable.class);

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

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

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

    job.waitForCompletion(true);

    FileSystem fileSystem = FileSystem.get(conf);
    Path path = new Path(outputPath + "/part-r-00000");
    ;
    //MapFile.Reader reader = new MapFile.Reader(new Path(outputPath+ "/part-r-00000"),conf);

    // InputStream fis=new FileInputStream(outputPath+"/part-r-00000");
    BufferedReader br = new BufferedReader(new InputStreamReader(fileSystem.open(path)));
    String s;
    float key;//=new FloatWritable();
    int value;//=new IntWritable();
    while ((s = br.readLine()) != null) {
        String[] sources = s.split("\\s+");
        key = Float.parseFloat(sources[0]);
        value = Integer.parseInt(sources[1]);
        if (key == 0.0f) {
            System.out.print("\n" + "Source: " + value + "\n");
        } else {
            System.out.print(String.format("%.5f %d", key, value) + "\n");
        }
    }
    //reader.close();
    br.close();

    //while(!SysOut.isEmpty())
    //{
    //   System.out.print(SysOut.poll());
    //}

    return 0;
}

From source file:WordCount.java

License:Apache License

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

    ///start/*from ww w.j a  v  a  2s .c  om*/
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }
    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";
        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        //System.out.println("test");

        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);
            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);
            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }

        job.setInputFormatClass(ColumnFamilyInputFormat.class);

        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);
        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row

        //Son degisiklik
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);
        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");
        job.waitForCompletion(true);
    }
    //print
    final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:BigramRelativeFrequencyJson.java

License:Apache License

/**
 * Runs this tool./*from  www.j  a va2s  . c  o  m*/
 */
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: " + BigramRelativeFrequencyJson.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - num reducers: " + reduceTasks);

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

    job.setNumReduceTasks(reduceTasks);

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

    job.setMapOutputKeyClass(MyTuple.class);
    job.setMapOutputValueClass(FloatWritable.class);
    job.setOutputKeyClass(MyTuple.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:TestBAM.java

License:Open Source License

public int run(String[] args) throws Exception {
    final Configuration conf = getConf();

    conf.set(MyOutputFormat.HEADER_FROM_FILE, args[0]);
    DistributedCache.addFileToClassPath(new Path("hdfs:///libjars/hadoop-bam-7.0.0-jar-with-dependencies.jar"),
            conf);/*  w w w  . j a v a  2  s.c o m*/

    final Job job = new Job(conf);

    job.setJarByClass(TestBAM.class);
    job.setMapperClass(TestBAMMapper.class);
    job.setReducerClass(TestBAMReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(SAMRecordWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(SAMRecordWritable.class);

    job.setInputFormatClass(AnySAMInputFormat.class);
    job.setOutputFormatClass(TestBAM.MyOutputFormat.class);

    org.apache.hadoop.mapreduce.lib.input.FileInputFormat.addInputPath(job, new Path(args[0]));

    org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.submit();

    if (!job.waitForCompletion(true)) {
        System.err.println("sort :: Job failed.");
        return 1;
    }

    return 0;
}

From source file:PairsPMI_M.java

License:Apache License

/**
 * Runs this tool.//from  w ww.j ava 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;
    }

    // First MapReduce Job

    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: " + PairsPMI_M.class.getSimpleName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - tmp path: " + outputPath + "/tmp");
    LOG.info(" - num reducers: " + reduceTasks);

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

    // Delete the tmp directory if it exists already
    Path tmpDir = new Path("tmp_wj");
    FileSystem.get(getConf()).delete(tmpDir, true);

    job.setNumReduceTasks(reduceTasks);

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

    job.setMapOutputKeyClass(PairOfStrings.class);
    job.setMapOutputValueClass(FloatWritable.class);
    job.setOutputKeyClass(PairOfStrings.class);
    job.setOutputValueClass(FloatWritable.class);

    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    //    job.setOutputFormatClass(TextOutputFormat.class);

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

    long startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    double time1 = (System.currentTimeMillis() - startTime) / 1000.0;
    System.out.println("Job Finished in " + time1 + " seconds");
    numRecords = job.getCounters().findCounter("org.apache.hadoop.mapred.Task$Counter", "MAP_INPUT_RECORDS")
            .getValue();

    /*
     *  Second MapReduce Job
     */

    LOG.info("Tool name: " + PairsPMI_M.class.getSimpleName());
    LOG.info("second stage of MapReduce");
    LOG.info(" - input from tmp path: " + outputPath + "/tmp_wj");
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - num reducers: " + reduceTasks);

    // set the global variable
    Configuration conf = getConf();
    conf.setLong("numRec", numRecords);

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

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

    job.setNumReduceTasks(reduceTasks);
    FileInputFormat.setInputPaths(job, new Path("tmp_wj/part*"));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setMapOutputKeyClass(PairOfStrings.class);
    job.setMapOutputValueClass(FloatWritable.class);
    // job.setOutputKeyClass(PairOfStrings.class);
    job.setOutputKeyClass(Text.class);

    job.setOutputValueClass(FloatWritable.class);
    job.setInputFormatClass(SequenceFileInputFormat.class);
    //   job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.setMapperClass(MyMapperSecond.class);
    //    job.setCombinerClass(MyCombiner.class);
    job.setReducerClass(MyReducerSecond.class);
    job.setPartitionerClass(MyPartitioner.class);

    startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    double time2 = (System.currentTimeMillis() - startTime) / 1000.0;
    System.out.println("Second job finished in " + time2 + " seconds");
    System.out.println("Total time: " + (time1 + time2) + " seconds");

    return 0;
}

From source file:PopularURLs.java

License:Open Source License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = new Job(conf, "popularurls");
    job.setJarByClass(PopularURLs.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.waitForCompletion(true);/*from w  w w.  java 2  s.c om*/
}

From source file:BuildPageRankRecords.java

License:Apache License

/**
 * Runs this tool.// w w 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 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;
}