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

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

Introduction

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

Prototype

public void setOutputValueClass(Class<?> theClass) throws IllegalStateException 

Source Link

Document

Set the value class for job outputs.

Usage

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);/*  ww w . java  2  s.c  o  m*/
}

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

License:Apache License

/**
 * Sets up the actual job./*w w  w. j a  v a  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;
}

From source file:com.gsinnovations.howdah.AbstractJob.java

License:Apache License

protected Job prepareJob(Path inputPath, Path 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) throws IOException {

    Job job = new Job(new Configuration(getConf()));
    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");
        }/*from www. j av  a  2 s  .c o m*/
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

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

    job.setMapperClass(mapper);
    job.setMapOutputKeyClass(mapperKey);
    job.setMapOutputValueClass(mapperValue);

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

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

    job.setJobName(getCustomJobName(job, mapper, reducer));

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

    return job;
}

From source file:com.gsinnovations.howdah.Driver.java

License:Apache License

public static void job(Path input, Path output, int numReduceTasks)
        throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = new Configuration();

    Job job = new Job(conf);

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

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setMapperClass(TikaMapper.class);
    //job.setCombinerClass(KMeansCombiner.class);
    //job.setReducerClass(KMeansReducer.class);
    job.setNumReduceTasks(numReduceTasks);

    FileInputFormat.addInputPath(job, input);
    FileOutputFormat.setOutputPath(job, output);

    job.setJarByClass(Driver.class);
    HadoopUtil.overwriteOutput(output);/*from  www.j  a va  2 s . co m*/
    job.waitForCompletion(true);

}

From source file:com.gsvic.csmr.CSMRBase.java

License:Apache License

public static void generatePairs(String in, String out)
        throws IOException, InterruptedException, ClassNotFoundException {

    Configuration conf = new Configuration();
    path = out;/*from w  w w. ja va  2 s .c om*/
    Job job;
    Path input, output;
    input = new Path(in);
    output = new Path(path + "/CSMRPairs");

    job = new Job(conf);
    job.setJobName("CSMR Pairs Job");
    job.setJarByClass(CSMRBase.class);

    FileInputFormat.addInputPath(job, input);
    FileOutputFormat.setOutputPath(job, output);

    job.setMapperClass(CSMRMapper.class);
    job.setReducerClass(CSMRReducer.class);

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

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(DocumentWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(VectorArrayWritable.class);

    job.waitForCompletion(true);
}

From source file:com.gsvic.csmr.CSMRBase.java

License:Apache License

public static void StartCSMR() throws IOException, InterruptedException, ClassNotFoundException {

    Configuration conf = new Configuration();
    Job job;
    job = new Job(conf);
    job.setJobName("CSMR Cosine Similarity Job");
    job.setJarByClass(CSMRBase.class);

    FileInputFormat.addInputPath(job, new Path(path + "/CSMRPairs/part-r-00000"));
    FileOutputFormat.setOutputPath(job, new Path(path + "/Results"));
    job.setMapperClass(Mapper.class);
    job.setReducerClass(CosineSimilarityReducer.class);

    job.setInputFormatClass(SequenceFileInputFormat.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(VectorArrayWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(DoubleWritable.class);

    System.exit(job.waitForCompletion(true) ? 1 : 0);

}

From source file:com.hadoop.examples.secondSort.SecondarySort.java

License:Apache License

public static void main(String[] args) throws Exception {
    // ?hadoop?/*w ww.  j a  va 2s  . c om*/
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: secondarysort <in> <out>");
        System.exit(2);
    }
    // ?
    Job job = new Job(conf, "secondary sort");
    job.setJarByClass(SecondarySort.class);
    // Mapper
    job.setMapperClass(MapClass.class);
    // ???CombinerCombiner<Text, IntWritable>Reduce<IntPair, IntWritable>?
    //job.setCombinerClass(Reduce.class);

    // Reducer
    job.setReducerClass(Reduce.class);

    // *
    // *group and partition by the first int in the pair
    job.setPartitionerClass(FirstPartitioner.class);
    //setSortComparatorClass()hadoopkey?(?2.Hadoopkey?)
    //IntPair?compareTo()
    //job.setSortComparatorClass(cls);
    // *
    job.setGroupingComparatorClass(FirstGroupingComparator.class);

    // map Key
    // the map output is IntPair, IntWritable
    job.setMapOutputKeyClass(IntPair.class);
    // mapValue
    job.setMapOutputValueClass(IntWritable.class);

    // rduceKeyTextOutputFormatClassTextOutputFormat
    // the reduce output is Text, IntWritable
    job.setOutputKeyClass(Text.class);
    // rduceValue
    job.setOutputValueClass(IntWritable.class);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    // ??job
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.hadoop.mapreduce.examples.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    conf.set("mapreduce.app-submission.cross-platform", "true");
    String ioArgs[] = { "input", "output2" };
    String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
    if (otherArgs.length < 2) {
        System.err.println("Usage: wordcount <in> [<in>...] <out>");
        System.exit(2);// w  w w  .  j  a v  a 2 s.  com
    }
    //job
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);

    //map, combine, reduce
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);

    //
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
        FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.hadoop.mapreduce.TestLzoLazyLoading.java

License:Open Source License

private void runWordCount(Configuration cf, boolean compressIn, boolean compressOut)
        throws IOException, InterruptedException, ClassNotFoundException {
    Configuration thisConf = new Configuration(cf);
    if (compressIn) {
        thisConf.setBoolean("mapred.compression.lzo.test.codec-checked-after-map", true);
    }/*from  w  w w .  j a  va2 s .co m*/

    if (compressOut) {
        thisConf.setBoolean("mapred.compression.lzo.test.codec-checked-after-reduce", true);
    }
    Path pathIn = new Path(TEST_ROOT_DIR + "/in");
    Path pathOut = new Path(TEST_ROOT_DIR + "/out");
    localFs.delete(pathIn, true);
    localFs.delete(pathOut, true);
    writeFile(makeFileName("in/part1", compressIn), "this is a test\nof word count test\ntest\n");
    writeFile(makeFileName("in/part2", compressIn), "more test");
    Job job = new Job(thisConf, "word count");
    job.setMapperClass(MyMapper.class);
    job.setCombinerClass(MyCombiner.class);
    job.setReducerClass(MyReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    if (compressOut) {
        FileOutputFormat.setCompressOutput(job, true);
        FileOutputFormat.setOutputCompressorClass(job, LzoCodec.class);
    }
    FileInputFormat.addInputPath(job, pathIn);
    FileOutputFormat.setOutputPath(job, pathOut);
    job.submit();
    assertEquals("IsLzoChecked (client)?", compressIn, LzoCodec.isNativeLzoChecked());
    assertTrue(job.waitForCompletion(false));
    String result = readFile(makeFileName("out/part-r-00000", compressOut));
    System.out.println(result);
    assertEquals("a\t1\ncount\t1\nis\t1\nmore\t1\nof\t1\ntest\t4\nthis\t1\nword\t1\n", result);
}

From source file:com.hadoop.secondarysort.SecondarySortDESC.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    // if (otherArgs.length != 2) {
    // System.err.println("Usage: secondarysrot <in> <out>");
    // System.exit(2);
    // }//from   w  ww  .j a v a 2 s.  co m

    // JobConf jobConf = new JobConf();

    Job job = new Job(conf, "secondary sort");
    job.setJarByClass(SecondarySortDESC.class);
    job.setMapperClass(MapClass.class);
    job.setReducerClass(Reduce.class);

    // group and partition by the first int in the pair
    job.setPartitionerClass(FirstPartitioner.class);
    job.setGroupingComparatorClass(FirstGroupingComparator.class);
    // conf.setClass("mapred.output.key.comparator.class",
    // KeyComparator.class, RawComparator.class);
    // job.setSortComparatorClass(SecondGroupingComparator.class);
    // the map output is IntPair, IntWritable
    job.setMapOutputKeyClass(IntPair.class);
    job.setMapOutputValueClass(IntWritable.class);

    // the reduce output is Text, IntWritable
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    FileInputFormat.addInputPath(job, new Path(inPath));
    FileOutputFormat.setOutputPath(job, new Path(outPath));
    FileSystem fileSystem = FileSystem.get(conf);
    if (fileSystem.exists(new Path(outPath))) {
        fileSystem.delete(new Path(outPath));
    }
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}