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

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

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

Introduction

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

Prototype

public void setOutputFormat(Class<? extends OutputFormat> theClass)

Source Link

Document

Set the OutputFormat implementation for the map-reduce job.

Usage

From source file:edu.umd.cloud9.collection.wikipedia.BuildWikipediaLinkGraph.java

License:Apache License

private void task2(String inputPath, String outputPath, int partitions) throws IOException {
    LOG.info("Building adjacency lists...");
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    JobConf conf = new JobConf(getConf(), BuildWikipediaLinkGraph.class);
    conf.setJobName(//  w w  w .j a v a 2  s. co m
            String.format("BuildWikipediaLinkGraph:AdjacencyList[input: %s, output: %s, num_partitions: %d]",
                    inputPath, outputPath, partitions));

    conf.setNumReduceTasks(partitions);

    TextInputFormat.addInputPath(conf, new Path(inputPath));
    TextOutputFormat.setOutputPath(conf, new Path(outputPath));

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

    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(IntWritable.class);

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

    conf.setMapperClass(MyMapper2.class);
    conf.setReducerClass(MyReducer2.class);

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

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.collection.wikipedia.DemoCountWikipediaPages.java

License:Apache License

@SuppressWarnings("static-access")
@Override/* w w w  . j  a va 2  s  .  c o m*/
public int run(String[] args) throws Exception {
    Options options = new Options();
    options.addOption(
            OptionBuilder.withArgName("path").hasArg().withDescription("XML dump file").create(INPUT_OPTION));

    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_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String inputPath = cmdline.getOptionValue(INPUT_OPTION);

    LOG.info("Tool name: " + this.getClass().getName());
    LOG.info(" - XML dump file: " + inputPath);

    JobConf conf = new JobConf(getConf(), DemoCountWikipediaPages.class);
    conf.setJobName(String.format("DemoCountWikipediaPages[%s: %s]", INPUT_OPTION, inputPath));

    conf.setNumMapTasks(10);
    conf.setNumReduceTasks(0);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));

    conf.setInputFormat(WikipediaPageInputFormat.class);
    conf.setOutputFormat(NullOutputFormat.class);

    conf.setMapperClass(MyMapper.class);

    JobClient.runJob(conf);

    return 0;
}

From source file:edu.umd.cloud9.collection.wikipedia.graph.ExtractWikipediaAnchorText.java

License:Apache License

private void task1(String inputPath, String outputPath) throws IOException {
    LOG.info("Exracting anchor text (phase 1)...");
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    JobConf conf = new JobConf(getConf(), ExtractWikipediaAnchorText.class);
    conf.setJobName(/*  w  w w.  j ava2s . c  o m*/
            String.format("ExtractWikipediaAnchorText:phase1[input: %s, output: %s]", inputPath, outputPath));

    // 10 reducers is reasonable.
    conf.setNumReduceTasks(10);

    SequenceFileInputFormat.addInputPath(conf, new Path(inputPath));
    TextOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

    conf.setMapOutputKeyClass(PairOfStringInt.class);
    conf.setMapOutputValueClass(PairOfStrings.class);

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

    conf.setMapperClass(MyMapper1.class);
    conf.setReducerClass(MyReducer1.class);
    conf.setPartitionerClass(MyPartitioner1.class);

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

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.collection.wikipedia.graph.ExtractWikipediaAnchorText.java

License:Apache License

private void task2(String inputPath, String outputPath) throws IOException {
    LOG.info("Exracting anchor text (phase 2)...");
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    JobConf conf = new JobConf(getConf(), ExtractWikipediaAnchorText.class);
    conf.setJobName(/*from  w w w  .j a va 2s  . c  o  m*/
            String.format("ExtractWikipediaAnchorText:phase2[input: %s, output: %s]", inputPath, outputPath));

    // Gathers everything together for convenience; feasible for Wikipedia.
    conf.setNumReduceTasks(1);

    TextInputFormat.addInputPath(conf, new Path(inputPath));
    TextOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(MapFileOutputFormat.class);

    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(Text.class);

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

    conf.setMapperClass(MyMapper2.class);
    conf.setReducerClass(MyReducer2.class);

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

    JobClient.runJob(conf);
    // Clean up intermediate data.
    FileSystem.get(conf).delete(new Path(inputPath), true);
}

From source file:edu.umd.cloud9.collection.wikipedia.graph.ExtractWikipediaLinkGraph.java

License:Apache License

private void task1(String inputPath, String outputPath, int partitions) throws IOException {
    LOG.info("Exracting edges...");
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    JobConf conf = new JobConf(getConf(), ExtractWikipediaLinkGraph.class);
    conf.setJobName(String.format("ExtractWikipediaLinkGraph:Edges[input: %s, output: %s, num_partitions: %d]",
            inputPath, outputPath, partitions));

    conf.setNumReduceTasks(partitions);//from w  w  w. j  ava 2 s .  c  o  m

    SequenceFileInputFormat.addInputPath(conf, new Path(inputPath));
    TextOutputFormat.setOutputPath(conf, new Path(outputPath));

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

    conf.setMapOutputKeyClass(PairOfStringInt.class);
    conf.setMapOutputValueClass(Text.class);

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

    conf.setMapperClass(MyMapper1.class);
    conf.setReducerClass(MyReducer1.class);
    conf.setPartitionerClass(MyPartitioner1.class);

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

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.collection.wikipedia.graph.ExtractWikipediaLinkGraph.java

License:Apache License

private void task2(String inputPath, String outputPath, int partitions) throws IOException {
    LOG.info("Building adjacency lists...");
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    JobConf conf = new JobConf(getConf(), ExtractWikipediaLinkGraph.class);
    conf.setJobName(//from   w  w  w.  ja  va  2  s.  c  o m
            String.format("ExtractWikipediaLinkGraph:AdjacencyList[input: %s, output: %s, num_partitions: %d]",
                    inputPath, outputPath, partitions));

    conf.setNumReduceTasks(partitions);

    TextInputFormat.addInputPath(conf, new Path(inputPath));
    TextOutputFormat.setOutputPath(conf, new Path(outputPath));

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

    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(IntWritable.class);

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

    conf.setMapperClass(MyMapper2.class);
    conf.setReducerClass(MyReducer2.class);

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

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.demo.DemoWordCondProbJSON.java

License:Apache License

/**
 * Runs this tool.//from w  w  w  .j  a  v  a2  s.c o  m
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int mapTasks = Integer.parseInt(args[2]);
    int reduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCondProbJSON");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + mapTasks);
    sLogger.info(" - number of reducers: " + reduceTasks);

    JobConf conf = new JobConf(DemoWordCondProbJSON.class);
    conf.setJobName("DemoWordCondProbJSON");

    conf.setNumMapTasks(mapTasks);
    conf.setNumReduceTasks(reduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setOutputKeyClass(MyTuple.class);
    conf.setOutputValueClass(FloatWritable.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapperClass(MyMapper.class);
    // this is a potential gotcha! can't use ReduceClass for combine because
    // we have not collected all the counts yet, so we can't divide through
    // to compute the conditional probabilities
    conf.setCombinerClass(IdentityReducer.class);
    conf.setReducerClass(MyReducer.class);
    conf.setPartitionerClass(MyPartitioner.class);

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCondProbTuple.java

License:Apache License

/**
 * Runs this tool.//ww  w.jav  a 2s . c  o m
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int mapTasks = Integer.parseInt(args[2]);
    int reduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCondProbTuple");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + mapTasks);
    sLogger.info(" - number of reducers: " + reduceTasks);

    JobConf conf = new JobConf(DemoWordCondProbTuple.class);
    conf.setJobName("DemoWordCondProbTuple");

    conf.setNumMapTasks(mapTasks);
    conf.setNumReduceTasks(reduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setOutputKeyClass(Tuple.class);
    conf.setOutputValueClass(FloatWritable.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapperClass(MyMapper.class);
    // this is a potential gotcha! can't use ReduceClass for combine because
    // we have not collected all the counts yet, so we can't divide through
    // to compute the conditional probabilities
    conf.setCombinerClass(IdentityReducer.class);
    conf.setReducerClass(MyReducer.class);
    conf.setPartitionerClass(MyPartitioner.class);

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCountJSON.java

License:Apache License

/**
 * Runs this tool./*from   w w  w .ja va  2s  .  c  om*/
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int numMapTasks = Integer.parseInt(args[2]);
    int numReduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCountJSON");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + numMapTasks);
    sLogger.info(" - number of reducers: " + numReduceTasks);

    JobConf conf = new JobConf(DemoWordCountTuple1.class);
    conf.setJobName("DemoWordCountJSON");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(MyKey.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

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

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCountTuple1.java

License:Apache License

/**
 * Runs this tool./*ww w . j  a  v a2s .com*/
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int numMapTasks = Integer.parseInt(args[2]);
    int numReduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCountTuple1");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + numMapTasks);
    sLogger.info(" - number of reducers: " + numReduceTasks);

    JobConf conf = new JobConf(DemoWordCountTuple1.class);
    conf.setJobName("DemoWordCountTuple1");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(Tuple.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

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

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}