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

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

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

Introduction

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

Prototype

public void setOutputKeyClass(Class<?> theClass)

Source Link

Document

Set the key class for the job output data.

Usage

From source file:edu.umn.cs.spatialHadoop.operations.ConvexHull.java

License:Open Source License

public static void convexHullMapReduce(Path inFile, Path userOutPath, OperationsParams params)
        throws IOException {
    JobConf job = new JobConf(params, ConvexHull.class);
    Path outPath = userOutPath;/*from   w ww  . j  a v a 2 s.  c  o  m*/
    FileSystem outFs = (userOutPath == null ? inFile : userOutPath).getFileSystem(job);
    Shape shape = params.getShape("shape");

    if (outPath == null) {
        do {
            outPath = new Path(inFile.toUri().getPath() + ".convex_hull_" + (int) (Math.random() * 1000000));
        } while (outFs.exists(outPath));
    } else {
        if (outFs.exists(outPath)) {
            if (params.getBoolean("overwrite", false)) {
                outFs.delete(outPath, true);
            } else {
                throw new RuntimeException("Output path already exists and -overwrite flag is not set");
            }
        }
    }

    job.setJobName("ConvexHull");
    job.setClass(SpatialSite.FilterClass, ConvexHullFilter.class, BlockFilter.class);
    job.setMapperClass(IdentityMapper.class);
    job.setCombinerClass(ConvexHullReducer.class);
    job.setReducerClass(ConvexHullReducer.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(shape.getClass());
    job.setInputFormat(ShapeInputFormat.class);
    ShapeInputFormat.addInputPath(job, inFile);
    job.setOutputFormat(GridOutputFormat2.class);
    GridOutputFormat2.setOutputPath(job, outPath);

    JobClient.runJob(job);

    // If outputPath not set by user, automatically delete it
    if (userOutPath == null)
        outFs.delete(outPath, true);
}

From source file:edu.umn.cs.spatialHadoop.operations.Skyline.java

License:Open Source License

private static void skylineMapReduce(Path inFile, Path userOutPath, OperationsParams params)
        throws IOException {
    JobConf job = new JobConf(params, Skyline.class);
    Path outPath = userOutPath;//from www  . j  a  va  2  s.  com
    FileSystem outFs = (userOutPath == null ? inFile : userOutPath).getFileSystem(job);
    Shape shape = params.getShape("shape");

    if (outPath == null) {
        do {
            outPath = new Path(inFile.toUri().getPath() + ".skyline_" + (int) (Math.random() * 1000000));
        } while (outFs.exists(outPath));
    }

    job.setJobName("Skyline");
    job.setClass(SpatialSite.FilterClass, SkylineFilter.class, BlockFilter.class);
    job.setMapperClass(IdentityMapper.class);
    job.setCombinerClass(SkylineReducer.class);
    job.setReducerClass(SkylineReducer.class);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(shape.getClass());
    job.setInputFormat(ShapeIterInputFormat.class);
    ShapeInputFormat.addInputPath(job, inFile);
    job.setOutputFormat(TextOutputFormat.class);
    TextOutputFormat.setOutputPath(job, outPath);

    JobClient.runJob(job);

    // If outputPath not set by user, automatically delete it
    if (userOutPath == null)
        outFs.delete(outPath, true);
}

From source file:edu.umn.cs.sthadoop.operations.STJoin.java

License:Open Source License

/**
 * /*from w w  w.  j av  a  2s.  com*/
 * @param inputPath
 * @param outputPath
 * @param params
 * @return
 * @throws IOException
 * @throws Exception
 * @throws InterruptedException
 */
private static long stJoin(Path inputPath, Path outputPath, OperationsParams params)
        throws IOException, Exception, InterruptedException {

    JobConf conf = new JobConf(new Configuration(), STJoin.class);
    FileSystem outfs = outputPath.getFileSystem(conf);
    outfs.delete(outputPath, true);
    conf.setJobName("STJoin");
    // pass params to the join map-reduce 
    conf.set("timedistance", params.get("timedistance"));
    conf.set("spacedistance", params.get("spacedistance"));
    //      conf.setMapOutputKeyClass(LongWritable.class);
    //      conf.setMapOutputValueClass(Text.class);
    conf.setOutputKeyClass(LongWritable.class);
    conf.setOutputValueClass(Text.class);
    // Mapper settings
    conf.setMapperClass(STJoinMap.class);
    //      conf.setReducerClass(STJoinReduce.class);
    //      conf.setCombinerClass(STJoinReduce.class);
    conf.setBoolean("mapreduce.input.fileinputformat.input.dir.recursive", true);
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    FileInputFormat.setInputPaths(conf, inputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);
    conf.setNumReduceTasks(0);
    JobClient.runJob(conf).waitForCompletion();
    outfs = inputPath.getFileSystem(conf);
    outfs.delete(inputPath);
    return 0;
}

From source file:edu.yale.cs.hadoopdb.benchmark.AggTaskLargeDB.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws Exception {

    JobConf conf = new JobConf(this.getClass());
    conf.setJobName("aggregation_db_large");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(DoubleWritable.class);
    conf.setOutputFormat(TextOutputFormat.class);

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

    if (args.length < 1) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }// ww  w . j  a v  a 2 s  .c o  m

    // OUTPUT properties
    Path outputPath = new Path(args[0]);
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    conf.set(DBConst.DB_RELATION_ID, "UserVisits");
    conf.set(DBConst.DB_RECORD_READER, AggUserVisitsRecord.class.getName());
    conf.set(DBConst.DB_SQL_QUERY,
            "SELECT sourceIP, SUM(adRevenue) AS sumAdRevenue " + "FROM UserVisits GROUP BY sourceIP;");

    return conf;
}

From source file:edu.yale.cs.hadoopdb.benchmark.AggTaskLargeHDFS.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws IOException {

    JobConf conf = new JobConf(getConf(), this.getClass());
    conf.setJobName("aggregation_hdfs_large");

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

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

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

    if (args.length < 2) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }/*from  ww w  . j a  v a 2 s . com*/

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

    // OUTPUT properties
    Path outputPath = new Path(args[1]);
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    return conf;

}

From source file:edu.yale.cs.hadoopdb.benchmark.AggTaskSmallDB.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws Exception {

    JobConf conf = new JobConf(this.getClass());
    conf.setJobName("aggregation_db_small");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(DoubleWritable.class);
    conf.setOutputFormat(TextOutputFormat.class);

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

    if (args.length < 1) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }/*  w  w w  . j  av  a 2  s.  c om*/

    // OUTPUT properties
    Path outputPath = new Path(args[0]);
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    conf.set(DBConst.DB_RELATION_ID, "UserVisits");
    conf.set(DBConst.DB_RECORD_READER, AggUserVisitsRecord.class.getName());
    conf.set(DBConst.DB_SQL_QUERY,
            "SELECT SUBSTRING(sourceIP, 1, 7) AS subSourceIP, SUM(adRevenue) AS sumAdRevenue FROM UserVisits GROUP BY subSourceIP;");

    return conf;
}

From source file:edu.yale.cs.hadoopdb.benchmark.AggTaskSmallHDFS.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws IOException {

    JobConf conf = new JobConf(this.getClass());
    conf.setJobName("aggregation_hdfs_small");

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

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

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

    if (args.length < 2) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }//from   ww  w.  j  a  v a 2s. c  om

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

    // OUTPUT properties
    Path outputPath = new Path(args[1]);
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    return conf;

}

From source file:edu.yale.cs.hadoopdb.benchmark.GrepTaskDB.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws IOException {

    JobConf conf = new JobConf(GrepTaskDB.class);
    conf.setJobName("grep_db_job");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(Map.class);
    conf.setNumReduceTasks(0);/*www  .  j  a v  a2  s  .c  o  m*/

    // GREP arguments
    conf.setOutputFormat(TextOutputFormat.class);
    for (int i = 0; i < args.length; ++i) {
        if ("-pattern".equals(args[i]))
            conf.set("pattern", args[++i]);
        else if ("-output".equals(args[i]))
            conf.set("output", args[++i]);
    }

    // OUTPUT properties

    Path outputPath = new Path(conf.get("output"));
    System.out.println(conf.get("output"));
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    // DB properties
    conf.set(DBConst.DB_RELATION_ID, "grep");
    conf.set(DBConst.DB_RECORD_READER, DocumentsRecord.class.getName());
    conf.set(DBConst.DB_SQL_QUERY,
            "SELECT key1, field FROM grep WHERE field LIKE '%" + conf.get("pattern") + "%';");

    return conf;

}

From source file:edu.yale.cs.hadoopdb.benchmark.GrepTaskHDFS.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws IOException {

    JobConf conf = new JobConf(getConf(), this.getClass());
    conf.setJobName("grep_hdfs");

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

    conf.setMapperClass(Map.class);
    conf.setNumReduceTasks(0);/*  w ww .  java  2 s. com*/

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

    if (args.length < 3) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }

    conf.set(GREP_PATTERN_PARAM, args[0]);

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

    Path outputPath = new Path(args[2]);
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    return conf;

}

From source file:edu.yale.cs.hadoopdb.benchmark.JoinTaskDB.java

License:Apache License

@Override
protected JobConf configureJob(String... args) throws Exception {
    JobConf conf = new JobConf(JoinTaskDB.class);
    conf.setJobName("join_db");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(Map.class);
    conf.setReducerClass(Reduce.class);
    conf.setNumReduceTasks(1); // Because we look for 1 TOP value

    // join arguments
    conf.setOutputFormat(TextOutputFormat.class);
    for (int i = 0; i < args.length; ++i) {
        if ("-date_l".equals(args[i]))
            conf.set("date_l", args[++i]);
        else if ("-date_u".equals(args[i]))
            conf.set("date_u", args[++i]);
        else if ("-output".equals(args[i]))
            conf.set("output", args[++i]);
    }//w  ww  .ja va  2s. c o  m

    // OUTPUT properties
    Path outputPath = new Path(conf.get("output"));
    HDFSUtil.deletePath(outputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    conf.set(DBConst.DB_RELATION_ID, "UserVisits");
    conf.set(DBConst.DB_RECORD_READER, JoinRecord.class.getName());

    String TABLE_R = "Rankings";
    String TABLE_UV = "UserVisits";

    conf.set(DBConst.DB_SQL_QUERY,
            "SELECT sourceIP, SUM(pageRank) as sumPageRank, COUNT(pageRank) as countPageRank, SUM(adRevenue) as totalRevenue "
                    + "FROM " + TABLE_R + " AS R, " + TABLE_UV + " AS UV " + "WHERE R.pageURL = UV.destURL "
                    + "AND UV.visitDate BETWEEN '" + conf.get("date_l") + "' AND '" + conf.get("date_u") + "' "
                    + "GROUP BY UV.sourceIP;");

    return conf;
}