Example usage for org.apache.hadoop.mapreduce Job 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:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

public static Job prepareJob(String inputPath, String outputPath, Class<? extends InputFormat> inputFormat,
        Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey,
        Class<? extends Writable> mapperValue, Class<? extends Reducer> reducer,
        Class<? extends Writable> reducerKey, Class<? extends Writable> reducerValue,
        Class<? extends OutputFormat> outputFormat, Configuration conf) throws IOException {

    //    Job job = new Job(new Configuration(conf));
    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();

    if (reducer.equals(Reducer.class)) {
        if (mapper.equals(Mapper.class)) {
            throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
        }// w  w w  . j  a  va  2  s  . com
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

    job.setInputFormatClass(inputFormat);
    jobConf.set("mapred.input.dir", inputPath);

    job.setMapperClass(mapper);
    if (mapperKey != null) {
        job.setMapOutputKeyClass(mapperKey);
    }
    if (mapperValue != null) {
        job.setMapOutputValueClass(mapperValue);
    }

    jobConf.setBoolean("mapred.compress.map.output", true);

    job.setReducerClass(reducer);
    job.setOutputKeyClass(reducerKey);
    job.setOutputValueClass(reducerValue);

    job.setOutputFormatClass(outputFormat);
    jobConf.set("mapred.output.dir", outputPath);

    return job;
}

---

From source file:com.github.sakserv.minicluster.mapreduce.Driver.java

License:Apache License

public static void main(String[] args) throws Exception {

    if (args.length != 2) {
        System.out.println("usage: [input] [output]");
        System.exit(-1);//from   www  .ja v  a2s .co m
    }

    if (null == configuration) {
        configuration = new Configuration();
    }

    Job job = Job.getInstance(configuration);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(WordMapper.class);
    job.setReducerClass(SumReducer.class);

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

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

    job.setJarByClass(Driver.class);

    job.waitForCompletion(true);

}

---

From source file:com.github.ygf.pagerank.InLinks.java

License:Apache License

private void computeInLinks(Configuration conf, Path linksFile, Path outputDir) throws Exception {

    // This job computes the number of in-links for every page. The
    // implementation is very similar to the classic word count example.

    Job job = Job.getInstance(conf, "InLinks:Computation");

    job.setJarByClass(InLinks.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setMapperClass(InLinksMapper.class);
    job.setCombinerClass(InLinksReducer.class);
    job.setReducerClass(InLinksReducer.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, linksFile);
    FileOutputFormat.setOutputPath(job, new Path(outputDir, "inlinks"));

    job.waitForCompletion(true);// w  ww. jav  a2s  .  c om
}

---

From source file:com.github.ygf.pagerank.InLinks.java

License:Apache License

private void summarizeResults(Configuration conf, Path outputDir) throws Exception {

    int topResults = Integer.parseInt(conf.get("inlinks.top_results"));

    Job job = Job.getInstance(conf, "InLinks:TopN");

    job.setJarByClass(InLinks.class);

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setMapperClass(InLinksTopNMapper.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setReducerClass(InLinksTopNReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(outputDir, "inlinks"));
    FileOutputFormat.setOutputPath(job, new Path(outputDir, "inlinks-top" + topResults));

    job.setNumReduceTasks(1);//  www .j  a v a2 s. co  m
    job.waitForCompletion(true);
}

---

From source file:com.github.ygf.pagerank.PageRank.java

License:Apache License

private void createTransitionMatrix(Configuration conf, Path linksFile, Path outputDir) throws Exception {

    // This job reads the links-simple-sorted.txt input file and generates
    // the corresponding transition matrix. The matrix is divided into
    // square blocks and each block is represented by the nonzero entries.
    // See Section 5.2 (and 5.2.3 in particular) of Mining of Massive Datasets
    // (http://infolab.stanford.edu/~ullman/mmds.html) for details.
    // The output is written to the "M" subdir in the output dir.

    Job job = Job.getInstance(conf, "PageRank:Matrix");

    job.setJarByClass(PageRank.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setMapperClass(PageRankMatrixMapper.class);
    job.getConfiguration().setBoolean("mapreduce.map.output.compress", true);
    job.getConfiguration().setClass("mapreduce.map.output.compress.codec", DefaultCodec.class,
            CompressionCodec.class);
    job.setMapOutputKeyClass(ShortArrayWritable.class);
    job.setMapOutputValueClass(ShortArrayWritable.class);
    job.setReducerClass(PageRankMatrixReducer.class);
    SequenceFileOutputFormat.setCompressOutput(job, true);
    SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);
    SequenceFileOutputFormat.setOutputCompressorClass(job, DefaultCodec.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(ShortArrayWritable.class);
    job.setOutputValueClass(MatrixBlockWritable.class);
    FileInputFormat.addInputPath(job, linksFile);
    FileOutputFormat.setOutputPath(job, new Path(outputDir, "M"));

    job.waitForCompletion(true);/* w ww .j a  v  a 2  s .  c  o m*/
}

---

From source file:com.github.ygf.pagerank.PageRank.java

License:Apache License

private void pageRankIteration(int iter, Configuration conf, Path outputDir) throws Exception {

    // This job performs an iteration of the power iteration method to
    // compute PageRank. The map task processes each block M_{i,j}, loads 
    // the corresponding stripe j of the vector v_{k-1} and produces the
    // partial result of the stripe i of the vector v_k. The reduce task
    // sums all the partial results of v_k and adds the teleportation factor
    // (the combiner only sums all the partial results). See Section 5.2
    // (and 5.2.3 in particular) of Mining of Massive Datasets
    // (http://infolab.stanford.edu/~ullman/mmds.html) for details. The
    // output is written in a "vk" subdir of the output dir, where k is the
    // iteration number. MapFileOutputFormat is used to keep an array of the
    // stripes of v.

    Job job = Job.getInstance(conf, "PageRank:Iteration");

    job.setJarByClass(PageRank.class);
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setMapperClass(PageRankIterationMapper.class);
    job.setMapOutputKeyClass(ShortWritable.class);
    job.setMapOutputValueClass(FloatArrayWritable.class);
    job.setCombinerClass(PageRankIterationCombiner.class);
    job.setReducerClass(PageRankIterationReducer.class);
    job.setOutputFormatClass(MapFileOutputFormat.class);
    job.setOutputKeyClass(ShortWritable.class);
    job.setOutputValueClass(FloatArrayWritable.class);
    FileInputFormat.addInputPath(job, new Path(outputDir, "M"));
    FileOutputFormat.setOutputPath(job, new Path(outputDir, "v" + iter));

    job.waitForCompletion(true);//from  w  w w . j  a v  a2  s. c  o  m
}

---

From source file:com.github.ygf.pagerank.PageRank.java

License:Apache License

private void summarizeResults(int iter, Configuration conf, Path outputDir) throws Exception {

    // This job creates a plain text file with the top N PageRanks and the
    // titles of the pages. Each map task emits the top N PageRanks it
    // receives, and the reduce task merges the partial results into the
    // global top N PageRanks. A single reducer is used in the job in order
    // to have access to all the individual top N PageRanks from the
    // mappers. The reducer looks up the titles in the index built by
    // TitleIndex. This job was designed considering that N is small.

    int topResults = Integer.parseInt(conf.get("pagerank.top_results"));

    Job job = Job.getInstance(conf, "PageRank:TopN");

    job.setJarByClass(PageRank.class);
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setMapperClass(PageRankTopNMapper.class);
    job.setMapOutputKeyClass(FloatWritable.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setReducerClass(PageRankTopNReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(FloatWritable.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(outputDir, "v" + iter));
    FileOutputFormat.setOutputPath(job, new Path(outputDir, "v" + iter + "-top" + topResults));

    job.setNumReduceTasks(1);/*from   w w w. j a v  a  2 s . c  o  m*/
    job.waitForCompletion(true);
}

---

From source file:com.github.ygf.pagerank.TitleIndex.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.out.println("Usage: TitleIndex <titles-sorted.txt> <output-dir>");
        ToolRunner.printGenericCommandUsage(System.out);
        return 2;
    }/*from   w w w  .ja v a  2 s .  com*/

    Path titlesFile = new Path(args[0]);
    Path outputDir = new Path(args[1]);

    Configuration conf = getConf();

    // Do not create _SUCCESS files. MapFileOutputFormat.getReaders calls
    // try to read the _SUCCESS as another MapFile dir.
    conf.set("mapreduce.fileoutputcommitter.marksuccessfuljobs", "false");

    // This job creates a MapFile of the titles indexed by the page id.
    // UnsplittableTextInputFormat is used to ensure that the same map task
    // gets all the lines in the titlesFile and it can count the line
    // numbers. The number of reduce tasks is set to 0.

    Job job = Job.getInstance(conf, "TitleIndex");

    job.setJarByClass(InLinks.class);
    job.setInputFormatClass(UnsplittableTextInputFormat.class);
    job.setMapperClass(TitleIndexMapper.class);
    job.setOutputFormatClass(MapFileOutputFormat.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, titlesFile);
    FileOutputFormat.setOutputPath(job, outputDir);

    job.setNumReduceTasks(0);
    job.waitForCompletion(true);

    return 0;
}

---

From source file:com.goldsaxfoundation.bigdata.Module5.SimpleMapReduce.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    Job job = new Job(conf, "wordcount");
    job.setJarByClass(SimpleMapReduce.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.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);//w  w w.  j a v  a 2s  .  c o  m
}

---

From source file:com.google.cloud.bigtable.mapreduce.Export.java

License:Apache License

/**
 * Sets up the actual job./*from   w  w w  .  java 2 s  . c  o  m*/
 *
 * @param conf  The current configuration.
 * @param args  The command line parameters.
 * @return The newly created job.
 * @throws java.io.IOException When setting up the job fails.
 */
public static Job createSubmittableJob(Configuration conf, String[] args) throws IOException {
    conf.setIfUnset("hbase.client.connection.impl", BigtableConfiguration.getConnectionClass().getName());
    conf.setIfUnset(BigtableOptionsFactory.BIGTABLE_RPC_TIMEOUT_MS_KEY, "60000");
    conf.setBoolean(TableInputFormat.SHUFFLE_MAPS, true);

    String tableName = args[0];
    Path outputDir = new Path(args[1]);
    Job job = Job.getInstance(conf, NAME + "_" + tableName);
    job.setJobName(NAME + "_" + tableName);
    job.setJarByClass(Export.class);
    // Set optional scan parameters
    Scan s = getConfiguredScanForJob(conf, args);
    TableMapReduceUtil.initTableMapperJob(tableName, s, IdentityTableMapper.class, ImmutableBytesWritable.class,
            Result.class, job, false);
    // No reducers.  Just write straight to output files.
    job.setNumReduceTasks(0);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(ImmutableBytesWritable.class);
    job.setOutputValueClass(Result.class);
    FileOutputFormat.setOutputPath(job, outputDir); // job conf doesn't contain the conf so doesn't have a default fs.
    return job;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »