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

Introduction

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

Prototype

public void setMapperClass(Class<? extends Mapper> theClass) 

Source Link

Document

Set the Mapper class for the job.

Usage

From source file:Brush.RedundantRemoval.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: RedundantRemoval");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(RedundantRemoval.class);
    conf.setJobName("RedundantRemoval " + inputPath);

    BrushConfig.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

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

    //conf.setBoolean("mapred.output.compress", true);

    conf.setMapperClass(RedundantRemovalMapper.class);
    conf.setReducerClass(RedundantRemovalReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:Brush.RemoveLowCoverage.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: RemoveLowCoverage");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(RemoveLowCoverage.class);
    conf.setJobName("RemoveLowCoverage " + inputPath + " " + BrushConfig.K);

    BrushConfig.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

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

    conf.setMapperClass(RemoveLowCoverageMapper.class);
    conf.setReducerClass(RemoveLowCoverageReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:Brush.Stats.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: Stats");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(Stats.class);
    conf.setJobName("Stats " + inputPath);

    BrushConfig.initializeConfiguration(conf);
    conf.setNumReduceTasks(1);//from  ww  w . j a va2 s  . co  m

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

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

    conf.setMapperClass(StatsMapper.class);
    conf.setReducerClass(StatsReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:Brush.TipsRemoval.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: TipsRemoval");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    JobConf conf = new JobConf(TipsRemoval.class);
    conf.setJobName("RemoveTips " + inputPath + " " + BrushConfig.K);
    BrushConfig.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    //conf.setBoolean("mapred.output.compress", true);

    conf.setMapperClass(TipsRemovalMapper.class);
    conf.setReducerClass(TipsRemovalReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:Brush.TransitiveReduction.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: TransitiveReduction");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    //JobConf conf = new JobConf(Stats.class);
    JobConf conf = new JobConf(TransitiveReduction.class);
    conf.setJobName("TransitiveReduction " + inputPath);

    BrushConfig.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    //conf.setBoolean("mapred.output.compress", true);

    conf.setMapperClass(TransitiveReductionMapper.class);
    conf.setReducerClass(TransitiveReductionReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:Brush.VerifyOverlap.java

License:Apache License

public RunningJob run(String inputPath, String outputPath) throws Exception {
    sLogger.info("Tool name: VerifyOverlap");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);

    //JobConf conf = new JobConf(Stats.class);
    JobConf conf = new JobConf(VerifyOverlap.class);
    conf.setJobName("VerifyOverlap " + inputPath);

    BrushConfig.initializeConfiguration(conf);

    FileInputFormat.addInputPath(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));

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

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

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

    //conf.setBoolean("mapred.output.compress", true);
    //conf.setClass("mapred.output.compression.codec", GzipCodec.class,CompressionCodec.class);

    conf.setMapperClass(VerifyOverlapMapper.class);
    conf.setReducerClass(VerifyOverlapReducer.class);

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

    return JobClient.runJob(conf);
}

---

From source file:BU.MET.CS755.SpeciesIterDriver2.java

static boolean MRSpeciesView(String input, String args[]) {
    Job theJob = null;// www .j  av  a  2  s.c o  m

    JobConf conf = new JobConf(SpeciesIterDriver2.class);
    conf.setJobName("Species Viewer");

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

    inputpath = input;
    outputpath = args[1] + "FinalRanks";

    FileInputFormat.setInputPaths(conf, new Path(inputpath));
    FileOutputFormat.setOutputPath(conf, new Path(outputpath));

    conf.setMapperClass(SpeciesViewerMapper.class);
    conf.setReducerClass(org.apache.hadoop.mapred.lib.IdentityReducer.class);

    try {
        theJob = new Job(conf, "SpeciesIter");
        theJob.waitForCompletion(true);
    } catch (Exception e) {
        e.printStackTrace();
    }

    return true;
}

---

From source file:buildtestproject.MyFirstMapReduce.java

public static void main(String[] args) throws Exception {
    //Configuration conf = new Configuration();
    JobConf conf = new JobConf(MyFirstMapReduce.class);
    //Job job = Job.getInstance(conf, "word-count-one");
    conf.setJobName("word-count-one");

    conf.setMapperClass(TokenizerMapper.class);
    conf.setCombinerClass(IntSumReducer.class);
    conf.setReducerClass(IntSumReducer.class);

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

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

    //        job.setJarByClass(MyFirstMapReduce.class);
    //        job.setMapperClass(TokenizerMapper.class);
    //        job.setCombinerClass(IntSumReducer.class);
    //        job.setReducerClass(IntSumReducer.class);
    //        //from w w w  .  ja  v  a  2s.c  o  m
    //        job.setOutputKeyClass(Text.class);
    //        job.setOutputValueClass(IntWritable.class);

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

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

    JobClient.runJob(conf);

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

---

From source file:Business.DataJoin.java

@Override
public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    JobConf job = new JobConf(conf, DataJoin.class);

    final File f = new File(MapReduceOne.class.getProtectionDomain().getCodeSource().getLocation().getPath());
    String inFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/inFiles/";
    String outFiles = f.getAbsolutePath().replace("/build/classes", "") + "/src/outFiles/OutputOne";
    //use the arguments instead if provided.
    if (args.length > 1) {
        inFiles = args[1];//from  ww w  .  ja v  a  2  s . c o m
        outFiles = args[2];
    }
    Path in = new Path(inFiles);
    Path out = new Path(outFiles);
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);

    job.setJobName("Data Join");
    job.setMapperClass(MapClass.class);
    job.setReducerClass(ReduceClass.class);

    job.setInputFormat(TextInputFormat.class);
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(TaggedWritable.class);
    job.set("mapred.textoutputformat.separator", ",");

    JobClient.runJob(job);
    return 0;
}

---

From source file:ca.etsmtl.lasi.hbasewikipedialoader.HBaseWikipediaLoader.java

License:Apache License

/**
 * Sets up the actual job.//ww w .j  ava  2  s  .c  o  m
 * 
 * @param conf
 *          The current configuration.
 * @param args
 *          The command line parameters.
 * @return The newly created job.
 * @throws IOException
 *           When setting up the job fails.
 */
public static JobConf createSubmittableJob(HBaseConfiguration conf, String[] args) throws IOException {
    JobConf jobConf = new JobConf(conf, HBaseWikipediaLoader.class);
    jobConf.setJobName(NAME);

    // Stream stuff
    jobConf.set("stream.recordreader.class", "org.apache.hadoop.streaming.StreamXmlRecordReader");
    jobConf.set("stream.recordreader.begin", "<page>");
    jobConf.set("stream.recordreader.end", "</page>");

    jobConf.setSpeculativeExecution(false);

    jobConf.setMapOutputKeyClass(ImmutableBytesWritable.class);
    jobConf.setMapOutputValueClass(BatchUpdate.class);

    jobConf.setMapperClass(Map.class);

    jobConf.setNumReduceTasks(0);

    jobConf.setInputFormat(StreamInputFormat.class);
    jobConf.setOutputFormat(TableOutputFormat.class);
    jobConf.set(TableOutputFormat.OUTPUT_TABLE, TABLE);
    jobConf.setOutputKeyClass(ImmutableBytesWritable.class);
    jobConf.setOutputValueClass(BatchUpdate.class);

    StreamInputFormat.setInputPaths(jobConf, new Path(args[0]));
    FileOutputFormat.setOutputPath(jobConf, new Path("/tmp/" + NAME + "-" + System.currentTimeMillis()));

    return jobConf;

}

---

• «
• 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
• »