List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException
From source file:DateExample_Year.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2);//from w w w . java 2 s. c o m } Job job = new Job(conf, "word count fs"); job.setJarByClass(DateExample_Year.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(IsValidKeyFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:RecordExtracting.java
License:Apache License
/** * Runs this tool.//from ww w. ja va2s . co m */ @SuppressWarnings({ "static-access" }) public int run(String[] args) throws Exception { Options options = new Options(); /* options.addOption(OptionBuilder.withArgName("path").hasArg() .withDescription("input path").create(INPUT)); options.addOption(OptionBuilder.withArgName("path").hasArg() .withDescription("output path").create(OUTPUT)); options.addOption(OptionBuilder.withArgName("num").hasArg() .withDescription("number of nodes").create(NUM_NODES)); //parsing more than 1 integer later;*/ options.addOption( OptionBuilder.withArgName("src").hasArg().withDescription("spamming users").create(SOURCES)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers") .create(NUM_REDUCERS)); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } /* if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT) || !cmdline.hasOption(NUM_NODES)||!cmdline.hasOption(SOURCES)) { System.out.println("args: " + Arrays.toString(args)); HelpFormatter formatter = new HelpFormatter(); formatter.setWidth(120); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; }*/ String inputPath = "xzzqskfinal/reviewsNew.txt";//cmdline.getOptionValue(INPUT); String outputPath = "xzzqskfinal/SpammingRecord";//cmdline.getOptionValue(OUTPUT); //int n = Integer.parseInt(cmdline.getOptionValue(NUM_NODES)); //Change to array later String src = cmdline.getOptionValue(SOURCES); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; LOG.info("Tool name: " + RecordExtracting.class.getSimpleName()); LOG.info(" - inputDir: " + inputPath); LOG.info(" - outputDir: " + outputPath); //LOG.info(" - numNodes: " + n); Configuration conf = getConf(); conf.set("mapreduce.map.memory.mb", "2048"); conf.set("mapreduce.map.java.opts", "-Xmx2048m"); conf.set("mapreduce.reduce.memory.mb", "2048"); conf.set("mapreduce.reduce.java.opts", "-Xmx2048m"); //conf.setInt(NODE_CNT_FIELD, n); //more to be set later; conf.set(NODE_SRC, src); conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024); Job job = Job.getInstance(conf); job.setJobName(RatingSpamming.class.getSimpleName()); job.setJarByClass(RecordExtracting.class); job.setNumReduceTasks(reduceTasks); FileInputFormat.addInputPath(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setInputFormatClass(TextInputFormat.class); //job.setOutputFormatClass(TextOutputFormat.class); //job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapOutputKeyClass(PairOfStrings.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(PairOfStrings.class); job.setOutputValueClass(Text.class); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // Delete the output directory if it exists already. FileSystem.get(conf).delete(new Path(outputPath), true); job.waitForCompletion(true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:RunPageRankBasic.java
License:Apache License
private float phase1(int i, int j, String basePath, int numNodes, boolean useCombiner, boolean useInMapperCombiner) throws Exception { Job job = Job.getInstance(getConf()); job.setJobName("PageRank:Basic:iteration" + j + ":Phase1"); job.setJarByClass(RunPageRankBasic.class); String in = basePath + "/iter" + formatter.format(i); String out = basePath + "/iter" + formatter.format(j) + "t"; String outm = out + "-mass"; // We need to actually count the number of part files to get the number of partitions (because // the directory might contain _log). int numPartitions = 0; for (FileStatus s : FileSystem.get(getConf()).listStatus(new Path(in))) { if (s.getPath().getName().contains("part-")) numPartitions++;/*from w w w. jav a 2 s . c om*/ } LOG.info("PageRank: iteration " + j + ": Phase1"); LOG.info(" - input: " + in); LOG.info(" - output: " + out); LOG.info(" - nodeCnt: " + numNodes); LOG.info(" - useCombiner: " + useCombiner); LOG.info(" - useInmapCombiner: " + useInMapperCombiner); LOG.info("computed number of partitions: " + numPartitions); int numReduceTasks = numPartitions; job.getConfiguration().setInt("NodeCount", numNodes); job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false); job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false); //job.getConfiguration().set("mapred.child.java.opts", "-Xmx2048m"); job.getConfiguration().set("PageRankMassPath", outm); job.setNumReduceTasks(numReduceTasks); FileInputFormat.setInputPaths(job, new Path(in)); FileOutputFormat.setOutputPath(job, new Path(out)); job.setInputFormatClass(NonSplitableSequenceFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(PageRankNode.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(PageRankNode.class); job.setMapperClass(useInMapperCombiner ? MapWithInMapperCombiningClass.class : MapClass.class); if (useCombiner) { job.setCombinerClass(CombineClass.class); } job.setReducerClass(ReduceClass.class); FileSystem.get(getConf()).delete(new Path(out), true); FileSystem.get(getConf()).delete(new Path(outm), true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); float mass = Float.NEGATIVE_INFINITY; FileSystem fs = FileSystem.get(getConf()); for (FileStatus f : fs.listStatus(new Path(outm))) { FSDataInputStream fin = fs.open(f.getPath()); mass = sumLogProbs(mass, fin.readFloat()); fin.close(); } return mass; }
From source file:RunPageRankBasic.java
License:Apache License
private void phase2(int i, int j, float missing, String basePath, int numNodes) throws Exception { Job job = Job.getInstance(getConf()); job.setJobName("PageRank:Basic:iteration" + j + ":Phase2"); job.setJarByClass(RunPageRankBasic.class); LOG.info("missing PageRank mass: " + missing); LOG.info("number of nodes: " + numNodes); String in = basePath + "/iter" + formatter.format(j) + "t"; String out = basePath + "/iter" + formatter.format(j); LOG.info("PageRank: iteration " + j + ": Phase2"); LOG.info(" - input: " + in); LOG.info(" - output: " + out); job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false); job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false); job.getConfiguration().setFloat("MissingMass", (float) missing); job.getConfiguration().setInt("NodeCount", numNodes); job.setNumReduceTasks(0);// ww w .j a va 2s. c o m FileInputFormat.setInputPaths(job, new Path(in)); FileOutputFormat.setOutputPath(job, new Path(out)); job.setInputFormatClass(NonSplitableSequenceFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(PageRankNode.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(PageRankNode.class); job.setMapperClass(MapPageRankMassDistributionClass.class); FileSystem.get(getConf()).delete(new Path(out), true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); }
From source file:WordCountSplitTest.java
License:Apache License
private final static void test(boolean use_shards, boolean use_chunks, Boolean slaveok) throws Exception { did_start = false;/*www .j av a 2 s .co m*/ final Configuration conf = new Configuration(); MongoConfigUtil.setInputURI(conf, "mongodb://localhost:30000/test.lines"); conf.setBoolean(MongoConfigUtil.SPLITS_USE_SHARDS, use_shards); conf.setBoolean(MongoConfigUtil.SPLITS_USE_CHUNKS, use_chunks); String output_table = null; if (use_chunks) { if (use_shards) output_table = "with_shards_and_chunks"; else output_table = "with_chunks"; } else { if (use_shards) output_table = "with_shards"; else output_table = "no_splits"; } if (slaveok != null) { output_table += "_" + slaveok; } MongoConfigUtil.setOutputURI(conf, "mongodb://localhost:30000/test." + output_table); System.out.println("Conf: " + conf); final Job job = new Job(conf, "word count " + output_table); job.setJarByClass(WordCountSplitTest.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(MongoInputFormat.class); job.setOutputFormatClass(MongoOutputFormat.class); final long start = System.currentTimeMillis(); System.out.println(" ----------------------- running test " + output_table + " --------------------"); try { boolean result = job.waitForCompletion(true); System.out.println("job.waitForCompletion( true ) returned " + result); } catch (Exception e) { System.out.println("job.waitForCompletion( true ) threw Exception"); e.printStackTrace(); } final long end = System.currentTimeMillis(); final float seconds = ((float) (end - start)) / 1000; java.text.NumberFormat nf = java.text.NumberFormat.getInstance(); nf.setMaximumFractionDigits(3); System.out.println("finished run in " + nf.format(seconds) + " seconds"); com.mongodb.Mongo m = new com.mongodb.Mongo( new com.mongodb.MongoURI("mongodb://localhost:30000/?slaveok=true")); com.mongodb.DB db = m.getDB("test"); com.mongodb.DBCollection coll = db.getCollection(output_table); com.mongodb.BasicDBObject query = new com.mongodb.BasicDBObject(); query.put("_id", "the"); com.mongodb.DBCursor cur = coll.find(query); if (!cur.hasNext()) System.out.println("FAILURE: could not find count of \'the\'"); else System.out.println("'the' count: " + cur.next()); // if (! result) // System.exit( 1 ); }
From source file:LoadClue.java
License:Apache License
/** * Job configuration./*from w w w . j ava2 s . c om*/ */ public static Job configureJob(Configuration conf, String[] args) throws IOException { Path inputPath = new Path(args[0]); String tableName = args[1]; Job job = new Job(conf, NAME + "_" + tableName); job.setJarByClass(Uploader.class); FileInputFormat.setInputPaths(job, inputPath); job.setInputFormatClass(ClueWebInputFormat.class); job.setMapperClass(Uploader.class); LoadClue.setTableName(tableName); // No reducers. Just write straight to table. Call initTableReducerJob // because it sets up the TableOutputFormat. TableMapReduceUtil.initTableReducerJob(tableName, null, job); TableMapReduceUtil.addDependencyJars(conf, TableOutputFormat.class); job.setNumReduceTasks(0); return job; }
From source file:ComRoughSetApproInputSampler.java
License:Apache License
/** * Driver for InputSampler from the command line. * Configures a JobConf instance and calls {@link #writePartitionFile}. *//*from w w w . j ava2s .c o m*/ public int run(String[] args) throws Exception { Job job = new Job(getConf()); ArrayList<String> otherArgs = new ArrayList<String>(); Sampler<K, V> sampler = null; for (int i = 0; i < args.length; ++i) { try { if ("-r".equals(args[i])) { job.setNumReduceTasks(Integer.parseInt(args[++i])); } else if ("-inFormat".equals(args[i])) { job.setInputFormatClass(Class.forName(args[++i]).asSubclass(InputFormat.class)); } else if ("-keyClass".equals(args[i])) { job.setMapOutputKeyClass(Class.forName(args[++i]).asSubclass(WritableComparable.class)); } else if ("-splitSample".equals(args[i])) { int numSamples = Integer.parseInt(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new SplitSampler<K, V>(numSamples, maxSplits); } else if ("-splitRandom".equals(args[i])) { double pcnt = Double.parseDouble(args[++i]); int numSamples = Integer.parseInt(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new RandomSampler<K, V>(pcnt, numSamples, maxSplits); } else if ("-splitInterval".equals(args[i])) { double pcnt = Double.parseDouble(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new IntervalSampler<K, V>(pcnt, maxSplits); } else { otherArgs.add(args[i]); } } catch (NumberFormatException except) { System.out.println("ERROR: Integer expected instead of " + args[i]); return printUsage(); } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); } } if (job.getNumReduceTasks() <= 1) { System.err.println("Sampler requires more than one reducer"); return printUsage(); } if (otherArgs.size() < 2) { System.out.println("ERROR: Wrong number of parameters: "); return printUsage(); } if (null == sampler) { sampler = new RandomSampler<K, V>(0.1, 10000, 10); } Path outf = new Path(otherArgs.remove(otherArgs.size() - 1)); TotalOrderPartitioner.setPartitionFile(getConf(), outf); for (String s : otherArgs) { FileInputFormat.addInputPath(job, new Path(s)); } ComRoughSetApproInputSampler.<K, V>writePartitionFile(job, sampler); return 0; }
From source file:First.java
License:Apache License
public int run(String[] args) throws Exception { String outputReducerType = "filesystem"; if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) { String[] s = args[0].split("="); if (s != null && s.length == 2) outputReducerType = s[1];/*from www . j a v a2s.c o m*/ } logger.info("output reducer type: " + outputReducerType); for (int i = 2000; i < 2012; i++) { String columnName = Integer.toString(i); getConf().set(CONF_COLUMN_NAME, columnName); Job job = new Job(getConf(), "app"); job.setJarByClass(First.class); job.setMapperClass(TokenizerMapper.class); if (outputReducerType.equalsIgnoreCase("filesystem")) { job.setCombinerClass(ReducerToFilesystem.class); job.setReducerClass(ReducerToFilesystem.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i)); } else { job.setReducerClass(ReducerToCassandra.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(ByteBuffer.class); job.setOutputValueClass(List.class); job.setOutputFormatClass(ColumnFamilyOutputFormat.class); ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY); } job.setInputFormatClass(ColumnFamilyInputFormat.class); ConfigHelper.setRpcPort(job.getConfiguration(), "9160"); ConfigHelper.setInitialAddress(job.getConfiguration(), "localhost"); ConfigHelper.setPartitioner(job.getConfiguration(), "org.apache.cassandra.dht.RandomPartitioner"); ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY); SlicePredicate predicate = new SlicePredicate() .setColumn_names(Arrays.asList(ByteBuffer.wrap(columnName.getBytes()))); ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate); job.waitForCompletion(true); } return 0; }
From source file:TorrentWeb.java
License:Apache License
@Override public int run(String[] args) throws Exception { Configuration conf = this.getConf(); Job job = Job.getInstance(conf, "Torrent Web"); job.setJarByClass(TorrentWeb.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(TorrentWebExtracter.class); job.setReducerClass(TorrentWebReducer.class); job.setInputFormatClass(WarcInputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // Execute job and return status return job.waitForCompletion(true) ? 0 : 1; }
From source file:PerformanceEvaluation.java
License:Apache License
private void doMapReduce(final Class<? extends Test> cmd) throws IOException, InterruptedException, ClassNotFoundException { Path inputDir = writeInputFile(this.conf); this.conf.set(EvaluationMapTask.CMD_KEY, cmd.getName()); this.conf.set(EvaluationMapTask.PE_KEY, getClass().getName()); Job job = new Job(this.conf); job.setJarByClass(PerformanceEvaluation.class); job.setJobName("HBase Performance Evaluation"); job.setInputFormatClass(PeInputFormat.class); PeInputFormat.setInputPaths(job, inputDir); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(LongWritable.class); job.setMapperClass(EvaluationMapTask.class); job.setReducerClass(LongSumReducer.class); job.setNumReduceTasks(1);/* w w w . j a va2 s . co m*/ job.setOutputFormatClass(TextOutputFormat.class); TextOutputFormat.setOutputPath(job, new Path(inputDir, "outputs")); TableMapReduceUtil.addDependencyJars(job); job.waitForCompletion(true); }