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:IndexWords.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length < 2) {
        return -1;
    }/*  ww w  .ja  va2s. c o m*/

    checkWords = new String[args.length - 2];

    int numIter = 5;

    Path input = new Path(args[0]);

    for (int i = 0; i < numIter; i++) {
        JobConf conf = new JobConf(getConf(), IndexWords.class);
        conf.setJobName("indexwords");

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

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

        conf.setMapperClass(MapClass.class);
        conf.setReducerClass(Reduce.class);

        FileInputFormat.setInputPaths(conf, input);
        FileOutputFormat.setOutputPath(conf, new Path(args[1] + Integer.toString(i)));

        RunningJob rj = JobClient.runJob(conf);
        input = new Path(args[1] + Integer.toString(i));
        double resVal = rj.getCounters().getCounter(RecordCounters.RESIDUAL_COUNTER) * 1.0 / 10000;
        System.out.println(N + " " + (resVal / (1.0 * N)));
        if (resVal / (1.0 * N) < 0.001)
            break;
    }

    return 0;
}

From source file:ClimateData.java

License:Open Source License

public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(ClimateData.class);
    conf.setJobName("climatedata");

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

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

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

    JobClient.runJob(conf);//from w  w w .  jav a2 s  .c om
}

From source file:FriendsJob.java

License:Apache License

/**
 * @param args//from  ww w.  j a  v  a2 s.  c o  m
 */
public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(FriendsJob.class);
    conf.setJobName("anagramcount");

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

    conf.setMapperClass(FriendsMapper.class);
    // conf.setCombinerClass(AnagramReducer.class);
    conf.setReducerClass(FriendsReducer.class);

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

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

    JobClient.runJob(conf);

}

From source file:SleepJobWithArray.java

License:Apache License

public JobConf setupJobConf(int numMapper, int numReducer, long mapSleepTime, int mapSleepCount,
        long reduceSleepTime, int reduceSleepCount) {
    JobConf job = new JobConf(getConf(), SleepJobWithArray.class);
    job.setNumMapTasks(numMapper);//w  w  w . j  a va2s  .  c  om
    job.setNumReduceTasks(numReducer);
    job.setMapperClass(SleepJobWithArray.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(NullWritable.class);
    job.setReducerClass(SleepJobWithArray.class);
    job.setOutputFormat(NullOutputFormat.class);
    job.setInputFormat(SleepInputFormat.class);
    job.setPartitionerClass(SleepJobWithArray.class);
    job.setSpeculativeExecution(false);
    FileInputFormat.addInputPath(job, new Path("ignored"));
    job.setLong("sleep.job.map.sleep.time", mapSleepTime);
    job.setLong("sleep.job.reduce.sleep.time", reduceSleepTime);
    job.setInt("sleep.job.map.sleep.count", mapSleepCount);
    job.setInt("sleep.job.reduce.sleep.count", reduceSleepCount);
    return job;
}

From source file:AnagramJob.java

License:Apache License

/**
 * @param args//w  w  w  .j  a v a 2  s .  c om
 */
public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(AnagramJob.class);
    conf.setJobName("anagramcount");

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

    conf.setMapperClass(AnagramMapper.class);
    // conf.setCombinerClass(AnagramReducer.class);
    conf.setReducerClass(AnagramReducer.class);

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

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

    JobClient.runJob(conf);

}

From source file:CountHistogram.java

License:Open Source License

@Override
public int run(String[] args) throws Exception {
    try {/*from w ww .jav  a  2 s. c om*/
        JobClient client = new JobClient();
        JobConf job = new JobConf(getConf(), CountHistogram.class);
        job.setJobName("CountHistogram");

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

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

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

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

        client.setConf(job);
        JobClient.runJob(job);
    } catch (Exception e) {
        e.printStackTrace();
        throw e;
    }
    return 0;
}

From source file:adept.mapreduce.MapReduce.java

License:Apache License

public JobConf getConfiguration(String inputPath, String outputPath, String mapClass) throws Exception {
    //Configuration conf = getConf();
    Class thisclass = getClass();
    JobConf job = new JobConf(new Configuration(), thisclass);

    try {//from   w ww .ja  va  2s .  co  m
        Path in = new Path(inputPath);

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

        job.setJobName("Algorithm Map-Reduce");
        job.setMapperClass((Class<? extends Mapper>) Class.forName(mapClass));

    } catch (Exception e) {
        throw new RuntimeException("Exception occurred: " + e.getMessage());
    }

    job.setReducerClass(AdeptReducer.class);
    job.setInputFormat(KeyValueTextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.set("key.value.separator.in.input.line", "\t");

    return job;
}

From source file:adept.mapreduce.MapReduceExample.java

License:Apache License

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

    Configuration conf = getConf();
    //Configuration conf = new Configuration();

    JobConf job = new JobConf(conf, MapReduceExample.class);

    Path in = new Path(args[0]);

    Path out = new Path(args[1]);

    FileInputFormat.setInputPaths(job, in);

    FileOutputFormat.setOutputPath(job, out);

    job.setJobName("MapReduecExample");

    job.setMapperClass(MapClass.class);

    job.setReducerClass(Reduce.class);

    job.setInputFormat(KeyValueTextInputFormat.class);

    job.setOutputFormat(TextOutputFormat.class);

    job.setOutputKeyClass(Text.class);

    job.setOutputValueClass(Text.class);

    job.set("key.value.separator.in.input.line", ",");

    JobClient.runJob(job);/*w ww. j a  v a2  s .  c  o  m*/

    return 0;

}

From source file:arrestsbyyear.ArrestsByYear.java

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

    JobConf job = new JobConf(conf, ArrestsByYear.class);

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

    job.setJobName("ArrestsByYear");
    job.setMapperClass(MapClass.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormat(KeyValueTextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    //   job.set("key.value.separator.in.input.line", "");

    JobClient.runJob(job);//from  ww  w  .j av a  2 s  . c o  m

    return 0;
}

From source file:at.illecker.hadoop.rootbeer.examples.matrixmultiplication.cpu.MatrixMultiplicationCpu.java

License:Apache License

public static Configuration createMatrixMultiplicationCpuConf(Configuration initialConf, Path aPath, Path bPath,
        Path outPath, int outCardinality, boolean isDebugging) {

    JobConf conf = new JobConf(initialConf, MatrixMultiplicationCpu.class);
    conf.setJobName("MatrixMultiplicationCPU: " + aPath + " x " + bPath + " = " + outPath);

    conf.setInt(CONF_OUT_CARD, outCardinality);
    conf.setBoolean(CONF_DEBUG, isDebugging);

    conf.setInputFormat(CompositeInputFormat.class);
    conf.set("mapred.join.expr",
            CompositeInputFormat.compose("inner", SequenceFileInputFormat.class, aPath, bPath));

    conf.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(conf, outPath);

    conf.setMapperClass(MatrixMultiplyCpuMapper.class);
    conf.setCombinerClass(MatrixMultiplicationCpuReducer.class);
    conf.setReducerClass(MatrixMultiplicationCpuReducer.class);

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

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

    // Increase client heap size
    conf.set("mapred.child.java.opts", "-Xms8G -Xmx8G");

    return conf;//from   w w  w.j av a  2s  . c om
}