List of usage examples for org.apache.hadoop.mapred FileOutputFormat setCompressOutput
public static void setCompressOutput(JobConf conf, boolean compress)
From source file:edu.umd.cloud9.demo.DemoWordCountTuple2.java
License:Apache License
/** * Runs this tool.//ww w . java 2 s .com */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int numMapTasks = Integer.parseInt(args[2]); int numReduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: DemoWordCountTuple2"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + numMapTasks); sLogger.info(" - number of reducers: " + numReduceTasks); JobConf conf = new JobConf(DemoWordCountTuple2.class); conf.setJobName("DemoWordCountTuple2"); conf.setNumMapTasks(numMapTasks); conf.setNumReduceTasks(numReduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); conf.setInputFormat(SequenceFileInputFormat.class); conf.setOutputKeyClass(Tuple.class); conf.setOutputValueClass(IntWritable.class); conf.setOutputFormat(SequenceFileOutputFormat.class); conf.setMapperClass(MapClass.class); conf.setCombinerClass(ReduceClass.class); conf.setReducerClass(ReduceClass.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.examples.BigramCount.java
License:Apache License
/** * Runs this tool.//w w w . ja va2 s . co m */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int mapTasks = Integer.parseInt(args[2]); int reduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: BigramCount"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + mapTasks); sLogger.info(" - number of reducers: " + reduceTasks); JobConf conf = new JobConf(BigramCount.class); conf.setJobName("BigramCount"); conf.setNumMapTasks(mapTasks); conf.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); /** * Note that these must match the Class arguments given in the mapper */ conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(MyMapper.class); conf.setCombinerClass(MyReducer.class); conf.setReducerClass(MyReducer.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(outputDir.toUri(), conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.examples.BigramRelativeFrequency.java
License:Apache License
/** * Runs this tool.// w w w . j a va2 s . c o m */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int mapTasks = Integer.parseInt(args[2]); int reduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: BigramRelativeFrequency"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + mapTasks); sLogger.info(" - number of reducers: " + reduceTasks); JobConf conf = new JobConf(BigramRelativeFrequency.class); conf.setJobName("BigramRelativeFrequency"); conf.setNumMapTasks(mapTasks); conf.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); /** * Note that these must match the Class arguments given in the mapper */ conf.setOutputKeyClass(PairOfStrings.class); conf.setOutputValueClass(FloatWritable.class); conf.setMapperClass(MyMapper.class); conf.setCombinerClass(MyCombiner.class); conf.setReducerClass(MyReducer.class); conf.setPartitionerClass(MyPartitioner.class); //Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(outputDir.toUri(), conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.examples.BuildInvertedIndex.java
License:Apache License
/** * Runs this tool./*from w w w . ja v a2 s . c o m*/ */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int mapTasks = Integer.parseInt(args[2]); int reduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: BuildInvertedIndex"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + mapTasks); sLogger.info(" - number of reducers: " + reduceTasks); JobConf conf = new JobConf(BuildInvertedIndex.class); conf.setJobName("BuildInvertedIndex"); conf.setNumMapTasks(mapTasks); conf.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); /** * Note that these must match the Class arguments given in the mapper */ conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(PairOfInts.class); conf.setMapperClass(MyMapper.class); conf.setReducerClass(MyReducer.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(outputDir.toUri(), conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.examples.DemoWordCount.java
License:Apache License
/** * Runs this tool./* ww w . j a v a 2s . co m*/ */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int mapTasks = Integer.parseInt(args[2]); int reduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: DemoWordCount"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + mapTasks); sLogger.info(" - number of reducers: " + reduceTasks); JobConf conf = new JobConf(DemoWordCount.class); conf.setJobName("DemoWordCount"); conf.setNumMapTasks(mapTasks); conf.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); /** * Note that these must match the Class arguments given in the mapper */ conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(MyMapper.class); conf.setCombinerClass(MyReducer.class); conf.setReducerClass(MyReducer.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(outputDir.toUri(), conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.examples.JingBigramRelativeFrequency.java
License:Apache License
/** * Runs this tool.//from w w w . j a va 2 s. c om */ public int run(String[] args) throws Exception { if (args.length != 4) { printUsage(); return -1; } String inputPath = args[0]; String outputPath = args[1]; int mapTasks = Integer.parseInt(args[2]); int reduceTasks = Integer.parseInt(args[3]); sLogger.info("Tool: DemoWordCount"); sLogger.info(" - input path: " + inputPath); sLogger.info(" - output path: " + outputPath); sLogger.info(" - number of mappers: " + mapTasks); sLogger.info(" - number of reducers: " + reduceTasks); JobConf conf = new JobConf(BigramRelativeFrequency.class); conf.setJobName("DemoWordCount"); conf.setNumMapTasks(mapTasks); conf.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); /** * Note that these must match the Class arguments given in the mapper */ conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(MyMapper.class); conf.setCombinerClass(MyReducer.class); conf.setReducerClass(MyReducer.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(outputDir.toUri(), conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); JobClient.runJob(conf); sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:edu.umd.cloud9.io.benchmark.HadoopSortRandomPairsOfInts.java
License:Apache License
/** * Runs this benchmark./*from w ww.ja v a 2 s . c om*/ */ public static void main(String[] args) throws IOException { String inputPath = "random-pairs.seq"; String outputPath = "random-pairs.sorted"; int numMapTasks = 1; int numReduceTasks = 1; JobConf conf = new JobConf(HadoopSortRandomPairsOfInts.class); conf.setJobName("SortRandomPairsOfInts"); conf.setNumMapTasks(numMapTasks); conf.setNumReduceTasks(numReduceTasks); FileInputFormat.setInputPaths(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); conf.setInputFormat(SequenceFileInputFormat.class); conf.setOutputKeyClass(PairOfInts.class); conf.setOutputValueClass(IntWritable.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapperClass(IdentityMapper.class); conf.setCombinerClass(IdentityReducer.class); conf.setReducerClass(IdentityReducer.class); // Delete the output directory if it exists already Path outputDir = new Path(outputPath); FileSystem.get(conf).delete(outputDir, true); long startTime; double duration; startTime = System.currentTimeMillis(); JobClient.runJob(conf); duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Job took " + duration + " seconds"); }
From source file:edu.umd.cloud9.webgraph.driver.BuildAnchorTextForwardIndex.java
License:Apache License
/** * Runs this tool.// w ww . ja v a2 s . co m */ public int run(String[] args) throws Exception { if (args.length != 3) { printUsage(); return -1; } JobConf conf = new JobConf(getConf()); FileSystem fs = FileSystem.get(conf); String collectionPath = args[0]; String outputPath = args[1]; String indexFile = args[2]; LOG.info("Tool name: BuildAnchorTextForwardIndex"); LOG.info(" - collection path: " + collectionPath); LOG.info(" - output path: " + outputPath); LOG.info(" - index file: " + indexFile); LOG.info("Note: This tool only works on block-compressed SequenceFiles!"); conf.set("mapred.child.java.opts", "-Xmx2048m"); conf.setJobName("BuildAnchorTextForwardIndex"); conf.setNumMapTasks(100); conf.setNumReduceTasks(1); FileInputFormat.setInputPaths(conf, new Path(collectionPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); FileOutputFormat.setCompressOutput(conf, false); conf.setInputFormat(NoSplitSequenceFileInputFormat.class); conf.setOutputKeyClass(IntWritable.class); conf.setOutputValueClass(Text.class); conf.setMapRunnerClass(MyMapRunner.class); conf.setReducerClass(IdentityReducer.class); // delete the output directory if it exists already fs.delete(new Path(outputPath), true); RunningJob job = JobClient.runJob(conf); Counters counters = job.getCounters(); int blocks = (int) counters.findCounter(Blocks.Total).getCounter(); LOG.info("number of blocks: " + blocks); LOG.info("Writing index file..."); LineReader reader = new LineReader(fs.open(new Path(outputPath + "/part-00000"))); FSDataOutputStream out = fs.create(new Path(indexFile), true); out.writeUTF(IndexableAnchorTextForwardIndex.class.getName()); out.writeUTF(collectionPath); out.writeInt(blocks); int cnt = 0; Text line = new Text(); while (reader.readLine(line) > 0) { String[] arr = line.toString().split("\\s+"); int docno = Integer.parseInt(arr[0]); int offset = Integer.parseInt(arr[1]); short fileno = Short.parseShort(arr[2]); out.writeInt(docno); out.writeInt(offset); out.writeShort(fileno); cnt++; if (cnt % 1000 == 0) { LOG.info(cnt + " blocks written"); } } reader.close(); out.close(); if (cnt != blocks) { throw new RuntimeException("Error: mismatch in block count!"); } return 0; }
From source file:hibench.HiveDataGenerator.java
License:Apache License
private void createRankingsTable() throws IOException { LOG.info("Creating table rankings..."); JobConf job = new JobConf(WebDataGen.class); String jobname = "Create " + paths.dname + " rankings"; job.setJobName(jobname);/*from ww w .j av a 2 s. c o m*/ job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job.setMapOutputKeyClass(Text.class); job.setCombinerClass(ConcatTextCombiner.class); job.setReducerClass(CountRankingAndReplaceIdReducer.class); if (options.reds > 0) { job.setNumReduceTasks(options.reds); } else { job.setNumReduceTasks(DataOptions.getMaxNumReduce()); } // job.setNumReduceTasks(options.agents/2); /*** * need to join result with LINK table so that to replace * url ids with real contents */ MultipleInputs.addInputPath(job, paths.getPath(DataPaths.T_LINK_PAGE), TextInputFormat.class, MyIdentityMapper.class); MultipleInputs.addInputPath(job, paths.getPath(DataPaths.LINKS), TextInputFormat.class, TagRecordsMapper.class); if (options.SEQUENCE_OUT) { job.setOutputFormat(SequenceFileOutputFormat.class); } else { job.setOutputFormat(TextOutputFormat.class); } if (null != options.codecClass) { job.set("mapred.output.compression.type", "BLOCK"); FileOutputFormat.setCompressOutput(job, true); FileOutputFormat.setOutputCompressorClass(job, options.codecClass); } FileOutputFormat.setOutputPath(job, paths.getResult(DataPaths.RANKINGS)); LOG.info("Running Job: " + jobname); LOG.info("Table link-page file " + paths.getPath(DataPaths.T_LINK_PAGE) + " as input"); LOG.info("Links file " + paths.getResult(DataPaths.LINKS) + " as output"); LOG.info("Ouput file " + paths.getResult(DataPaths.RANKINGS)); JobClient.runJob(job); LOG.info("Finished Running Job: " + jobname); LOG.info("Cleaning temp files..."); paths.cleanTempFiles(paths.getResult(DataPaths.RANKINGS)); }
From source file:hibench.HiveDataGenerator.java
License:Apache License
private void createUserVisitsTable() throws IOException, URISyntaxException { LOG.info("Creating user visits..."); JobConf job = new JobConf(WebDataGen.class); String jobname = "Create " + paths.dname + " uservisits"; job.setJobName(jobname);/*from w ww.j a va2 s . c om*/ /*** * Set distributed cache file for table generation, * cache files include: * 1. user agents * 2. country code and language code * 3. search keys */ DistributedCache.addCacheFile(paths.getPath(DataPaths.uagentf).toUri(), job); DistributedCache.addCacheFile(paths.getPath(DataPaths.countryf).toUri(), job); DistributedCache.addCacheFile(paths.getPath(DataPaths.searchkeyf).toUri(), job); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job.setMapOutputKeyClass(Text.class); visit.setJobConf(job); job.setInputFormat(TextInputFormat.class); MultipleInputs.addInputPath(job, paths.getPath(DataPaths.DUMMY), NLineInputFormat.class, CreateRandomAccessMapper.class); MultipleInputs.addInputPath(job, paths.getPath(DataPaths.LINKS), TextInputFormat.class, TagRecordsMapper.class); job.setCombinerClass(CreateUserVisitsCombiner.class); job.setReducerClass(CreateUserVisitsReducer.class); if (options.reds > 0) { job.setNumReduceTasks(options.reds); } else { job.setNumReduceTasks(DataOptions.getMaxNumReduce()); } // job.setNumReduceTasks(options.agents/2); if (options.SEQUENCE_OUT) { job.setOutputFormat(SequenceFileOutputFormat.class); } else { job.setOutputFormat(TextOutputFormat.class); } if (null != options.codecClass) { job.set("mapred.output.compression.type", "BLOCK"); FileOutputFormat.setCompressOutput(job, true); FileOutputFormat.setOutputCompressorClass(job, options.codecClass); } FileOutputFormat.setOutputPath(job, paths.getResult(DataPaths.USERVISITS)); LOG.info("Running Job: " + jobname); LOG.info("Dummy file " + paths.getPath(DataPaths.DUMMY) + " as input"); LOG.info("Links file " + paths.getResult(DataPaths.LINKS) + " as output"); LOG.info("Ouput file " + paths.getResult(DataPaths.USERVISITS)); JobClient.runJob(job); LOG.info("Finished Running Job: " + jobname); LOG.info("Cleaning temp files..."); paths.cleanTempFiles(paths.getResult(DataPaths.USERVISITS)); }