List of usage examples for org.apache.hadoop.mapreduce Job setOutputFormatClass
public void setOutputFormatClass(Class<? extends OutputFormat> cls) throws IllegalStateException
From source file:com.kasabi.labs.freebase.mr.Freebase2RDFDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (log.isDebugEnabled()) { log.debug("run({})", Utils.toString(args)); }//from w w w . ja va2 s .c o m if (args.length != 2) { System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName()); ToolRunner.printGenericCommandUsage(System.err); return -1; } Configuration configuration = getConf(); boolean useCompression = configuration.getBoolean(Constants.OPTION_USE_COMPRESSION, Constants.OPTION_USE_COMPRESSION_DEFAULT); if (useCompression) { configuration.setBoolean("mapred.compress.map.output", true); configuration.set("mapred.output.compression.type", "BLOCK"); configuration.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec"); } boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERRIDE_OUTPUT, Constants.OPTION_OVERRIDE_OUTPUT_DEFAULT); FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration); if (overrideOutput) { fs.delete(new Path(args[1]), true); } Job job = new Job(configuration); job.setJobName("Freebase2RDFDriver"); job.setJarByClass(getClass()); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(Freebase2RDFMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setReducerClass(Freebase2RDFReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); Utils.setReducers(job, configuration, log); job.setOutputFormatClass(TextOutputFormat.class); if (log.isDebugEnabled()) Utils.log(job, log); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.knewton.mapreduce.example.SSTableMRExample.java
License:Apache License
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException, URISyntaxException, ParseException { long startTime = System.currentTimeMillis(); Options options = buildOptions();/*from ww w .ja va 2s . c om*/ CommandLineParser cliParser = new BasicParser(); CommandLine cli = cliParser.parse(options, args); if (cli.getArgs().length < 2 || cli.hasOption('h')) { printUsage(options); } Job job = getJobConf(cli); job.setJarByClass(SSTableMRExample.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(StudentEventWritable.class); job.setMapperClass(StudentEventMapper.class); job.setReducerClass(StudentEventReducer.class); job.setInputFormatClass(SSTableColumnInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); // input arg String inputPaths = cli.getArgs()[0]; LOG.info("Setting initial input paths to {}", inputPaths); SSTableInputFormat.addInputPaths(job, inputPaths); // output arg FileOutputFormat.setOutputPath(job, new Path(cli.getArgs()[1])); if (cli.hasOption('c')) { LOG.info("Using compression for output."); FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class); FileOutputFormat.setCompressOutput(job, true); } job.waitForCompletion(true); LOG.info("Total runtime: {}s", (System.currentTimeMillis() - startTime) / 1000); }
From source file:com.kse.bigdata.main.Driver.java
License:Apache License
public static void main(String[] args) throws Exception { /********************************************************************************** ** Merge the source files into one. ** /** Should change the directories of each file before executing the program ** ***********************************************************************************/ // String inputFileDirectory = "/media/bk/??/BigData_Term_Project/Debug"; // String resultFileDirectory = "/media/bk/??/BigData_Term_Project/debug.csv"; // File resultFile = new File(resultFileDirectory); // if(!resultFile.exists()) // new SourceFileMerger(inputFileDirectory, resultFileDirectory).mergeFiles(); /********************************************************************************** * Hadoop Operation.//from w w w .j av a2 s . c o m * Befort Start, Check the Length of Sequence We Want to Predict. **********************************************************************************/ Configuration conf = new Configuration(); //Enable MapReduce intermediate compression as Snappy conf.setBoolean("mapred.compress.map.output", true); conf.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.SnappyCodec"); //Enable Profiling //conf.setBoolean("mapred.task.profile", true); String testPath = null; String inputPath = null; String outputPath = null; int sampleSize = 1; ArrayList<String> results = new ArrayList<String>(); for (int index = 0; index < args.length; index++) { /* * Mandatory command */ //Extract input path string from command line. if (args[index].equals("-in")) inputPath = args[index + 1]; //Extract output path string from command line. if (args[index].equals("-out")) outputPath = args[index + 1]; //Extract test data path string from command line. if (args[index].equals("-test")) testPath = args[index + 1]; /* * Optional command */ //Extract a number of neighbors. if (args[index].equals("-nn")) conf.setInt(Reduce.NUMBER_OF_NEAREAST_NEIGHBOR, Integer.parseInt(args[index + 1])); //Whether job uses normalization or not. if (args[index].equals("-norm")) conf.setBoolean(Map.NORMALIZATION, true); //Extract the number of sample size to test. if (args[index].equals("-s")) sampleSize = Integer.valueOf(args[index + 1]); //Whether job uses mean or median //[Default : mean] if (args[index].equals("-med")) conf.setBoolean(Reduce.MEDIAN, true); } String outputFileName = "part-r-00000"; SequenceSampler sampler = new SequenceSampler(testPath, sampleSize); LinkedList<Sequence> testSequences = sampler.getRandomSample(); // Test Sequence // String testSeqString = "13.591-13.674-13.778-13.892-13.958-14.049-14.153-14.185-14.169-14.092-13.905-13.702-13.438-13.187-13.0-12.914-12.868-12.766-12.62-12.433-12.279-12.142-12.063-12.025-100"; // Sequence testSeq = new Sequence(testSeqString); // LinkedList<Sequence> testSequences = new LinkedList<>(); // testSequences.add(testSeq); for (Sequence seq : testSequences) { /* ******************** Hadoop Launch *********************** */ System.out.println(seq.getTailString()); conf.set(Map.INPUT_SEQUENCE, seq.toString()); Job job = new Job(conf); job.setJarByClass(Driver.class); job.setJobName("term-project-driver"); job.setMapperClass(Map.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(Text.class); // Should think another way to implement the combiner class // Current Implementation is not helpful to Job. // job.setCombinerClass(Combiner.class); //Set 1 for number of reduce task for keeping 100 most neighbors in sorted set. job.setNumReduceTasks(1); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.waitForCompletion(true); /* * if job finishes, get result of the job and store it in results(list). */ try { FileSystem hdfs = FileSystem.get(new Configuration()); BufferedReader fileReader = new BufferedReader( new InputStreamReader(hdfs.open(new Path(outputPath + "/" + outputFileName)))); String line; while ((line = fileReader.readLine()) != null) { results.add(seq.getSeqString() + " " + line); } fileReader.close(); hdfs.delete(new Path(outputPath), true); hdfs.close(); } catch (IOException e) { e.printStackTrace(); System.exit(1); } } /* * if all jobs finish, store results of jobs to output/result.txt file. */ String finalOutputPath = "output/result.csv"; try { FileSystem hdfs = FileSystem.get(new Configuration()); Path file = new Path(finalOutputPath); if (hdfs.exists(file)) { hdfs.delete(file, true); } OutputStream os = hdfs.create(file); PrintWriter printWriter = new PrintWriter(new OutputStreamWriter(os, "UTF-8")); //CSV File Header printWriter.println("Actual,Predicted,MER,MAE"); printWriter.flush(); for (String result : results) { String[] tokens = result.split("\\s+"); printWriter.println(tokens[0] + "," + tokens[1] + "," + tokens[2] + "," + tokens[3]); printWriter.flush(); } printWriter.close(); hdfs.close(); } catch (IOException e) { e.printStackTrace(); System.exit(1); } }
From source file:com.lakala.hbase.IndexBuilder2.java
License:Apache License
/** * Job configuration./*from ww w .j a v a 2 s .c om*/ */ public static Job configureJob(Configuration conf, String[] args) throws IOException { String tableName = args[0]; String columnFamily = args[1]; System.out.println("****" + tableName); conf.set(TableInputFormat.SCAN, convertScanToString(new Scan())); conf.set(TableInputFormat.INPUT_TABLE, tableName); conf.set("index.tablename", tableName); conf.set("index.familyname", columnFamily); String[] fields = new String[args.length - 2]; for (int i = 0; i < fields.length; i++) { fields[i] = args[i + 2]; } conf.setStrings("index.fields", fields); conf.set("index.familyname", "attributes"); Job job = new Job(conf, tableName); job.setJarByClass(IndexBuilder.class); job.setMapperClass(Map.class); job.setNumReduceTasks(0); job.setInputFormatClass(TableInputFormat.class); job.setOutputFormatClass(MultiTableOutputFormat.class); return job; }
From source file:com.lakhani.anchorgraph.anchorgraph.java
public int run(String[] args) throws Exception { Configuration conf = new Configuration(); //DistributedCache.addCacheFile(new URI("hdfs://zphdc1n1:8020/user/clakhani/anchorgraph/centroids.txt"), conf); conf.set("numberCentroids", args[3]); conf.set("numberFeatures", args[4]); Job job = new Job(conf, "anchorgraph"); job.addCacheFile(new URI(args[2])); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(Map.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[2])); job.setJarByClass(anchorgraph.class); job.submit();//w w w.j ava 2s . c om int rc = (job.waitForCompletion(true)) ? 1 : 0; return rc; }
From source file:com.lakhani.anchorgraph.testCache.java
public int run(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "testCache"); job.addCacheFile(new URI("hdfs://zphdc1n1:8020/user/clakhani/anchorgraph/centroids.txt")); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(Map.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJarByClass(testCache.class); job.submit();/*from w w w. j ava 2 s . c o m*/ int rc = (job.waitForCompletion(true)) ? 1 : 0; return rc; }
From source file:com.lakhani.anchorgraph.wordcount.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf, "wordcount"); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setJarByClass(wordcount.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true);//w ww.j a v a 2 s. c o m }
From source file:com.lightboxtechnologies.nsrl.HashLoader.java
License:Apache License
public static void main(String[] args) throws Exception { final Configuration conf = new Configuration(); final String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 6) { System.err//from w ww .ja v a2 s. c o m .println("Usage: HashLoader <mfgfile> <osfile> <prodfile> <hashfile> <outpath> <num_reducers>"); System.exit(2); } final String mfg_filename = otherArgs[0]; final String os_filename = otherArgs[1]; final String prod_filename = otherArgs[2]; final String hash_filename = otherArgs[3]; final String output_filename = otherArgs[4]; conf.set("mfg_filename", mfg_filename); conf.set("os_filename", os_filename); conf.set("prod_filename", prod_filename); conf.setLong("timestamp", System.currentTimeMillis()); SKJobFactory.addDependencies(conf); final Job job = new Job(conf, "HashLoader"); job.setJarByClass(HashLoader.class); job.setMapperClass(HashLoaderMapper.class); job.setReducerClass(KeyValueSortReducer.class); job.setNumReduceTasks(Integer.parseInt(otherArgs[5])); job.setOutputKeyClass(ImmutableBytesWritable.class); job.setOutputValueClass(KeyValue.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(HFileOutputFormat.class); TextInputFormat.addInputPath(job, new Path(hash_filename)); HFileOutputFormat.setOutputPath(job, new Path(output_filename)); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.lightboxtechnologies.nsrl.TableDumper.java
License:Apache License
public static void main(String[] args) throws Exception { final Configuration conf = HBaseConfiguration.create(); final String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: TableDumper <table> <outpath>"); System.exit(2);/* w w w . j ava2 s . c om*/ } final String table_name = otherArgs[0]; final String output_filename = otherArgs[1]; final Job job = new Job(conf, "TableDumper"); job.setJarByClass(TableDumper.class); final Scan scan = new Scan(); TableMapReduceUtil.initTableMapperJob(table_name, scan, TableDumperMapper.class, Text.class, Text.class, job); job.setOutputFormatClass(TextOutputFormat.class); TextOutputFormat.setOutputPath(job, new Path(output_filename)); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.lightboxtechnologies.spectrum.BlockHasher.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println("Usage: BlockHasher <imageID> <image> <output>"); return 2; }//from w ww .j ava2s . c o m final String imageID = args[0]; final String image = args[1]; final String output = args[2]; Configuration conf = getConf(); final Job job = SKJobFactory.createJobFromConf(imageID, image, "BlockHasher", conf); job.setJarByClass(BlockHasher.class); job.setMapperClass(BlockHashMapper.class); // job.setReducerClass(Reducer.class); job.setNumReduceTasks(0); // job ctor copies the Configuration we pass it, get the real one conf = job.getConfiguration(); conf.setLong("timestamp", System.currentTimeMillis()); job.setInputFormatClass(RawFileInputFormat.class); RawFileInputFormat.addInputPath(job, new Path(image)); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(MD5Hash.class); FileOutputFormat.setOutputPath(job, new Path(output)); conf.setInt("mapred.job.reuse.jvm.num.tasks", -1); return job.waitForCompletion(true) ? 0 : 1; }