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

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

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

Introduction

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

Prototype

public void setJobName(String name)

Source Link

Document

Set the user-specified job name.

Usage

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

License:Open Source License

/**
 * //from  w  ww.ja va 2  s  .  co  m
 * @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());
    }//from w w  w  .j a va2  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 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  w ww  .  ja  v a 2  s.c o  m

    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 . ja  v a  2s  . co 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 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());
    }//w w w  .jav  a2s  . co  m

    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);/*ww w  .j a  v a 2s  . c  om*/

    // 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);//from w ww .j a va  2  s.  c  om

    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]);
    }/*from ww w  .j  a v  a  2 s .co 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;
}

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

License:Apache License

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

    long startTime = System.currentTimeMillis();

    if (args.length < 5) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }/*from  w  w  w .  j  a va  2  s .  c  om*/

    String dateFrom = args[0];
    String dateTo = args[1];
    String rankingsInputDir = args[2];
    String userVisitsInputDir = args[3];
    String outputDir = args[4];

    // output path (delete)
    Path outputPath = new Path(outputDir);
    HDFSUtil.deletePath(outputPath);

    // phase 1
    JobConf conf1 = new JobConf(this.getClass());
    conf1.setJobName("join_hdfs_phase1");
    Path p1Output = new Path(outputDir + "/phase1");
    FileOutputFormat.setOutputPath(conf1, p1Output);
    conf1.setInputFormat(TextInputFormat.class);
    conf1.setOutputFormat(TextOutputFormat.class);

    conf1.setOutputKeyClass(Text.class);
    conf1.setOutputValueClass(Text.class);

    FileInputFormat.setInputPaths(conf1, new Path(rankingsInputDir), new Path(userVisitsInputDir));

    conf1.set(DATE_FROM_PARAM, dateFrom);
    conf1.set(DATE_TO_PARAM, dateTo);

    conf1.setMapperClass(Phase1Map.class);
    conf1.setReducerClass(Phase1Reduce.class);
    // conf1.setPartitionerClass(theClass)

    RunningJob job1 = JobClient.runJob(conf1);

    if (job1.isSuccessful()) {

        // phase 2

        JobConf conf2 = new JobConf(this.getClass());
        conf2.setJobName("join_hdfs_phase2");
        conf2.setInputFormat(KeyValueTextInputFormat.class);
        conf2.setOutputFormat(TextOutputFormat.class);

        conf2.setOutputKeyClass(Text.class);
        conf2.setOutputValueClass(Text.class);
        conf2.setMapperClass(IdentityMapper.class);
        conf2.setReducerClass(Phase2Reduce.class);

        Path p2Output = new Path(outputDir + "/phase2");
        FileOutputFormat.setOutputPath(conf2, p2Output);
        FileInputFormat.setInputPaths(conf2, p1Output);

        RunningJob job2 = JobClient.runJob(conf2);

        if (job2.isSuccessful()) {

            // phase 3

            JobConf conf3 = new JobConf(this.getClass());
            conf3.setJobName("join_hdfs_phase3");
            conf3.setNumReduceTasks(1);
            conf3.setInputFormat(KeyValueTextInputFormat.class);
            conf3.setOutputKeyClass(Text.class);
            conf3.setOutputValueClass(Text.class);
            conf3.setMapperClass(IdentityMapper.class);
            conf3.setReducerClass(Phase3Reduce.class);

            Path p3Output = new Path(outputDir + "/phase3");
            FileOutputFormat.setOutputPath(conf3, p3Output);
            FileInputFormat.setInputPaths(conf3, p2Output);

            RunningJob job3 = JobClient.runJob(conf3);

            if (!job3.isSuccessful()) {
                System.out.println("PHASE 3 FAILED!!!");
            }

        } else {
            System.out.println("PHASE 2 FAILED!!!");
        }

    } else {
        System.out.println("PHASE 1 FAILED!!!");
    }

    long endTime = System.currentTimeMillis();
    System.out.println("\nJOB TIME : " + (endTime - startTime) + " ms.\n");

    return 0;
}

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

License:Apache License

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

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

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

    conf.setMapperClass(Map.class);
    conf.setNumReduceTasks(0);// ww  w .ja  v a 2s.c  om

    if (args.length < 2) {
        throw new RuntimeException("Incorrect arguments provided for " + this.getClass());
    }

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

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

    conf.set(DBConst.DB_RELATION_ID, "Rankings");
    conf.set(DBConst.DB_RECORD_READER, RankingsRecord.class.getName());
    conf.set(DBConst.DB_SQL_QUERY, "SELECT pageURL, pageRank FROM Rankings " + "WHERE pageRank > "
            + conf.get(PAGE_RANK_VALUE_PARAM) + ";");

    return conf;
}