List of usage examples for org.apache.hadoop.mapred JobConf setJobName
public void setJobName(String name)
From source file:edu.yale.cs.hadoopdb.benchmark.SelectionTaskHDFS.java
License:Apache License
@Override protected JobConf configureJob(String... args) throws IOException { JobConf conf = new JobConf(getConf(), this.getClass()); conf.setJobName("selection_hdfs"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(Map.class); conf.setNumReduceTasks(0);// ww w .ja v a 2s .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(PAGE_RANK_VALUE_PARAM, args[0]); FileInputFormat.setInputPaths(conf, new Path(args[1])); // OUTPUT properties Path outputPath = new Path(args[2]); HDFSUtil.deletePath(outputPath); FileOutputFormat.setOutputPath(conf, outputPath); return conf; }
From source file:edu.yale.cs.hadoopdb.benchmark.UDFAggTaskDB.java
License:Apache License
@Override protected JobConf configureJob(String... args) throws IOException { JobConf conf = new JobConf(this.getClass()); conf.setJobName("udf_agg_db"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(LongWritable.class); conf.setMapperClass(Query4Map.class); conf.setCombinerClass(LongSumReducer.class); conf.setReducerClass(LongSumReducer.class); conf.setOutputFormat(TextOutputFormat.class); if (args.length < 1) { throw new RuntimeException("Incorrect arguments provided for " + this.getClass()); }//from w w w .j ava 2 s . co m // OUTPUT properties Path outputPath = new Path(args[0]); HDFSUtil.deletePath(outputPath); FileOutputFormat.setOutputPath(conf, outputPath); conf.set(DBConst.DB_RELATION_ID, "Documents"); conf.set(DBConst.DB_RECORD_READER, DocumentRecord.class.getName()); conf.set(DBConst.DB_SQL_QUERY, "SELECT url, contents FROM Documents;"); return conf; }
From source file:edu.yale.cs.hadoopdb.benchmark.UDFAggTaskHDFS.java
License:Apache License
@Override protected JobConf configureJob(String... args) throws IOException { JobConf conf = new JobConf(this.getClass()); conf.setJobName("udf_agg_hdfs"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(LongWritable.class); conf.setMapperClass(Map.class); conf.setCombinerClass(LongSumReducer.class); conf.setReducerClass(LongSumReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); if (args.length < 2) { throw new RuntimeException("Incorrect arguments provided for " + this.getClass()); }/* w ww . jav 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.dataloader.GlobalHasher.java
License:Apache License
@Override protected JobConf configureJob(String... args) throws Exception { JobConf conf = new JobConf(getConf(), this.getClass()); conf.setJobName("GlobalHasher"); conf.setMapOutputKeyClass(UnsortableInt.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(NullWritable.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(GlobalHasher.Map.class); conf.setReducerClass(GlobalHasher.Reduce.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); if (args.length < 5) { throw new RuntimeException("Incorrect arguments provided for " + this.getClass()); }//from w w w . j av a2 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); int partNo = Integer.parseInt(args[2]); conf.setNumReduceTasks(partNo); conf.set(DELIMITER_PARAM, args[3]); int hashFieldPos = Integer.parseInt(args[4]); conf.setInt(HASH_FIELD_POS_PARAM, hashFieldPos); return conf; }
From source file:eu.scape_project.tb.chutney.ChutneyDriver.java
License:Apache License
/** * This method sets up and runs the job on Hadoop * @param args The passed through command line arguments *//*w w w .j av a 2 s. c o m*/ public int run(String[] args) { CommandLineParser parser = new PosixParser(); Options options = new Options(); options.addOption("n", "jobname", true, "name to assign to the hadoop job"); options.addOption("i", "inputlist", true, "text file containing list of input files (ensure no trailing carriage returns)"); options.addOption("t", "jobtype", true, "type of job; CLJ (command line job), TSJ (Taverna Server job), TCL (Taverna command line job), XML (XML defined command line job), XWR (XML workflow report)"); options.addOption("x", "xmlcode", true, "xml definition of job to run for XML jobs"); options.addOption("h", "help", false, "help text"); JobConf conf = new JobConf(ChutneyDriver.class); String input = null; String xmlcode = null; CommandLine com; try { com = parser.parse(options, args); if (com.hasOption("help")) { throw (new ParseException("")); } String jobName = Settings.JOB_NAME + "default"; if (com.hasOption("jobname")) { //set the job name to something better than the default jobName = Settings.JOB_NAME + com.getOptionValue("jobname"); } conf.setJobName(jobName); JobType jobType = JobType.CommandLineJob; if (com.hasOption("jobtype")) { String value = com.getOptionValue("jobtype").toUpperCase(); if (value.equals(CommandLineJob.getShortJobType())) { jobType = CommandLineJob.getJobType(); } else if (value.equals(TavernaCommandLineJob.getShortJobType())) { jobType = TavernaCommandLineJob.getJobType(); } else if (value.equals(TavernaServerJob.getShortJobType())) { jobType = TavernaServerJob.getJobType(); } else if (value.equals(XMLCommandLineJob.getShortJobType())) { jobType = XMLCommandLineJob.getJobType(); } else if (value.equals(XMLWorkflowReport.getShortJobType())) { jobType = XMLWorkflowReport.getJobType(); } } System.out.println("JobType: " + jobType.toString()); conf.set(Settings.JOBTYPE_CONF_SETTING, jobType.toString()); if (com.hasOption("xmlcode")) { //jobType == JobType.XMLCommandLineJob xmlcode = com.getOptionValue("xmlcode"); //if it is a local file get the full path if (new File(xmlcode).exists()) xmlcode = new File(xmlcode).getAbsolutePath(); conf.set(Settings.XMLCODE_CONF_SETTING, xmlcode); } if ((jobType == JobType.XMLCommandLineJob) & (xmlcode == null)) { //i.e. no code specified System.out.println("No XML code specified on the command line"); return -1; } if (com.hasOption("inputlist")) { input = com.getOptionValue("inputlist"); } if (input.equals(null)) { System.out.println("no input given"); return -2; } } catch (ParseException e) { HelpFormatter help = new HelpFormatter(); help.printHelp("hadoop jar TavernaHadoopWrapper.jar", options); return -1; } //using matchbox it may take a while to process the jobs //set a longer timeout than the default (10 mins) //six hours should be more than enough :/ MMM*SS*MS //QAJob testing for 9 tests on ANJO files can take ~4.5hrs+ conf.set("mapred.task.timeout", Integer.toString(360 * 60 * 1000)); FileInputFormat.setInputPaths(conf, new Path(input)); FileOutputFormat.setOutputPath(conf, new Path(conf.getJobName())); //set the mapper to this class' mapper conf.setMapperClass(Chutney.class); //we don't want to reduce //conf.setReducerClass(Reducer.class); //this input format should split the input by one line per map by default. conf.setInputFormat(NLineInputFormat.class); conf.setInt("mapred.line.input.format.linespermap", 1); //sets how the output is written cf. OutputFormat //we can use nulloutputformat if we are writing our own output conf.setOutputFormat(TextOutputFormat.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); //this sets maximum jvm reuse conf.set("mapred.job.reuse.jvm.num.tasks", "-1"); //we only want one reduce task conf.setNumReduceTasks(1); try { JobClient.runJob(conf); } catch (IOException ioe) { ioe.printStackTrace(); return -1; } return 0; }
From source file:eu.stratosphere.myriad.driver.hadoop.MyriadDriverHadoopJob.java
License:Apache License
private JobConf createJobConf() { // create job JobConf conf = new JobConf(getConf()); conf.setJarByClass(MyriadDriverHadoopJob.class); conf.setJobName(String.format("%s", this.parameters.getDGenName())); conf.setOutputKeyClass(NullWritable.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(IdentityMapper.class); conf.setNumReduceTasks(0);//from ww w.j a v a 2s. c o m conf.setInputFormat(MyriadInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); // input format configuration MyriadInputFormat.setDriverJobParameters(conf, this.parameters); // output format configuration FileOutputFormat.setOutputPath(conf, new Path(this.parameters.getJobOutputPath())); return conf; }
From source file:example.ColorCount.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: ColorCount <input path> <output path>"); return -1; }/*from w w w.j av a 2 s . co m*/ JobConf conf = new JobConf(getConf(), ColorCount.class); conf.setJobName("colorcount"); FileInputFormat.setInputPaths(conf, new Path(args[0])); FileOutputFormat.setOutputPath(conf, new Path(args[1])); AvroJob.setMapperClass(conf, ColorCountMapper.class); AvroJob.setReducerClass(conf, ColorCountReducer.class); // Note that AvroJob.setInputSchema and AvroJob.setOutputSchema set // relevant config options such as input/output format, map output // classes, and output key class. AvroJob.setInputSchema(conf, User.SCHEMA$); AvroJob.setOutputSchema(conf, Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT))); JobClient.runJob(conf); return 0; }
From source file:findstableweatherstate.FindStableWeatherState.java
public String call() throws Exception { Path firstOutputPath = new Path("input/firstOutput"); Path secondOutputPath = new Path("input/secondOutput"); long startTime, stopTime, elapsedTime; JobConf job = new JobConf(); job.setJarByClass(getClass());/* ww w . j av a 2s. co m*/ job.setJobName("invertedindex"); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setReducerClass(JoinReducer.class); MultipleInputs.addInputPath(job, new Path(getInputPathStation()), TextInputFormat.class, StationMapper.class); MultipleInputs.addInputPath(job, new Path(getInputPathReadings()), TextInputFormat.class, ReadingsMapper.class); FileOutputFormat.setOutputPath(job, firstOutputPath); JobConf job2 = new JobConf(); job2.setJarByClass(getClass()); job2.setJobName("secondJob"); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(Text.class); //job2.setInputFormat(org.apache.hadoop.mapred.TextInputFormat.class); FileInputFormat.setInputPaths(job2, firstOutputPath); job2.setMapperClass(CalculateMinMaxTemperatureMapper.class); job2.setReducerClass(CalculateMaxMinTemperatureReducer.class); if (getOutputPath() != null) { FileOutputFormat.setOutputPath(job2, secondOutputPath); } JobConf job3 = new JobConf(); job3.setJarByClass(getClass()); job3.setJobName("thirdJob"); job3.setOutputKeyClass(Text.class); job3.setOutputValueClass(Text.class); job3.setMapOutputKeyClass(DoubleWritable.class); job3.setMapOutputValueClass(Text.class); //job2.setInputFormat(org.apache.hadoop.mapred.TextInputFormat.class); FileInputFormat.setInputPaths(job3, secondOutputPath); job3.setMapperClass(SortStateMapper.class); job3.setReducerClass(SortStateReducer.class); if (getOutputPath() != null) { FileOutputFormat.setOutputPath(job3, new Path(getOutputPath())); } startTime = System.currentTimeMillis(); JobClient.runJob(job); stopTime = System.currentTimeMillis(); elapsedTime = stopTime - startTime; System.out.println("******************** First Job : " + elapsedTime / 1000); startTime = System.currentTimeMillis(); JobClient.runJob(job2); stopTime = System.currentTimeMillis(); elapsedTime = stopTime - startTime; System.out.println("******************** Second Job : " + elapsedTime / 1000); startTime = System.currentTimeMillis(); JobClient.runJob(job3); stopTime = System.currentTimeMillis(); elapsedTime = stopTime - startTime; System.out.println("******************** Third Job : " + elapsedTime / 1000); return ""; }
From source file:fire.util.fileformats.iomapred.LoadBinaryToSequence.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length < 2) { printUsage();//from w ww . java 2 s .com return 2; } JobConf conf = new JobConf(LoadBinaryToSequence.class); conf.setJobName("loadbinarytosequence"); //set the InputFormat of the job to our InputFormat conf.setInputFormat(CombineFileBinaryInputFormat.class); conf.setOutputFormat(SequenceFileOutputFormat.class); // the keys are words (strings) conf.setOutputKeyClass(Text.class); // the values are images conf.setOutputValueClass(BytesWritable.class); //use the defined mapper conf.setMapperClass(MapClass.class); FileInputFormat.addInputPaths(conf, args[0]); FileOutputFormat.setOutputPath(conf, new Path(args[1])); JobClient.runJob(conf); return 0; }
From source file:fm.last.hadoop.programs.labs.trackstats.TrackStatisticsProgram.java
License:Apache License
/** * Create a JobConf for a Job that will calculate the number of unique listeners per track. * /* w ww. j av a2 s .c om*/ * @param inputDir The path to the folder containing the raw listening data files. * @return The unique listeners JobConf. */ private JobConf getUniqueListenersJobConf(Path inputDir) { log.info("Creating configuration for unique listeners Job"); // output results to a temporary intermediate folder, this will get deleted by start() method Path uniqueListenersOutput = new Path("uniqueListeners"); JobConf conf = new JobConf(TrackStatisticsProgram.class); conf.setOutputKeyClass(IntWritable.class); // track id conf.setOutputValueClass(IntWritable.class); // number of unique listeners conf.setInputFormat(TextInputFormat.class); // raw listening data conf.setOutputFormat(SequenceFileOutputFormat.class); conf.setMapperClass(UniqueListenersMapper.class); conf.setCombinerClass(UniqueListenersCombiner.class); conf.setReducerClass(UniqueListenersReducer.class); FileInputFormat.addInputPath(conf, inputDir); FileOutputFormat.setOutputPath(conf, uniqueListenersOutput); conf.setJobName("uniqueListeners"); return conf; }