List of usage examples for org.apache.commons.cli2 CommandLine hasOption
boolean hasOption(final Option option);
From source file:egat.cli.strategyregret.StrategyRegretCommandHandler.java
@Override protected void handleAdditionalChildOptions(CommandLine commandLine) throws CommandProcessingException { if (commandLine.hasOption(playerOption)) { playerId = (String) commandLine.getValue(playerOption); }/*from w w w .j ava 2s . c o m*/ profilePath = (String) commandLine.getValue(profilePathOption); uniform = commandLine.hasOption(uniformOption); }
From source file:egat.cli.eminform.EpsilonMinFormCommandHandler.java
@Override protected void handleAdditionalChildOptions(CommandLine commandLine) throws CommandProcessingException { maxSize = Integer.parseInt(commandLine.getValue(maxSizeOption).toString()); if (commandLine.hasOption(toleranceOption)) { tolerance = Double.parseDouble(commandLine.getValue(toleranceOption).toString()); } else {//from w w w . j a va 2 s.co m tolerance = 1e-8; } if (commandLine.hasOption(maxQueueOption)) { maxQueue = Integer.parseInt(commandLine.getValue(maxQueueOption).toString()); } else { maxQueue = Integer.MAX_VALUE; } breadth = commandLine.hasOption(breadthOption); epsilonGreedy = commandLine.hasOption(epsilonGreedyOption); tauGreedy = commandLine.hasOption(tauGreedyOption); }
From source file:imageClassify.BuildForest.java
@Override public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option dataOpt = obuilder.withLongName("data").withShortName("d").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Data path").create(); Option datasetOpt = obuilder.withLongName("dataset").withShortName("ds").withRequired(true) .withArgument(abuilder.withName("dataset").withMinimum(1).withMaximum(1).create()) .withDescription("Dataset path").create(); Option selectionOpt = obuilder.withLongName("selection").withShortName("sl").withRequired(false) .withArgument(abuilder.withName("m").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, Number of variables to select randomly at each tree-node.\n" + "For classification problem, the default is square root of the number of explanatory variables.\n" + "For regression problem, the default is 1/3 of the number of explanatory variables.") .create();/*from w w w. j a v a 2 s. c om*/ Option noCompleteOpt = obuilder.withLongName("no-complete").withShortName("nc").withRequired(false) .withDescription("Optional, The tree is not complemented").create(); Option minSplitOpt = obuilder.withLongName("minsplit").withShortName("ms").withRequired(false) .withArgument(abuilder.withName("minsplit").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, The tree-node is not divided, if the branching data size is " + "smaller than this value.\nThe default is 2.") .create(); Option minPropOpt = obuilder.withLongName("minprop").withShortName("mp").withRequired(false) .withArgument(abuilder.withName("minprop").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, The tree-node is not divided, if the proportion of the " + "variance of branching data is smaller than this value.\n" + "In the case of a regression problem, this value is used. " + "The default is 1/1000(0.001).") .create(); Option seedOpt = obuilder.withLongName("seed").withShortName("sd").withRequired(false) .withArgument(abuilder.withName("seed").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, seed value used to initialise the Random number generator").create(); Option partialOpt = obuilder.withLongName("partial").withShortName("p").withRequired(false) .withDescription("Optional, use the Partial Data implementation").create(); Option nbtreesOpt = obuilder.withLongName("nbtrees").withShortName("t").withRequired(true) .withArgument(abuilder.withName("nbtrees").withMinimum(1).withMaximum(1).create()) .withDescription("Number of trees to grow").create(); Option outputOpt = obuilder.withLongName("output").withShortName("o").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Output path, will contain the Decision Forest").create(); Option helpOpt = obuilder.withLongName("help").withShortName("h").withDescription("Print out help") .create(); Group group = gbuilder.withName("Options").withOption(dataOpt).withOption(datasetOpt) .withOption(selectionOpt).withOption(noCompleteOpt).withOption(minSplitOpt).withOption(minPropOpt) .withOption(seedOpt).withOption(partialOpt).withOption(nbtreesOpt).withOption(outputOpt) .withOption(helpOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption("help")) { CommandLineUtil.printHelp(group); return -1; } isPartial = cmdLine.hasOption(partialOpt); String dataName = cmdLine.getValue(dataOpt).toString(); String datasetName = cmdLine.getValue(datasetOpt).toString(); String outputName = cmdLine.getValue(outputOpt).toString(); nbTrees = Integer.parseInt(cmdLine.getValue(nbtreesOpt).toString()); if (cmdLine.hasOption(selectionOpt)) { m = Integer.parseInt(cmdLine.getValue(selectionOpt).toString()); } complemented = !cmdLine.hasOption(noCompleteOpt); if (cmdLine.hasOption(minSplitOpt)) { minSplitNum = Integer.parseInt(cmdLine.getValue(minSplitOpt).toString()); } if (cmdLine.hasOption(minPropOpt)) { minVarianceProportion = Double.parseDouble(cmdLine.getValue(minPropOpt).toString()); } if (cmdLine.hasOption(seedOpt)) { seed = Long.valueOf(cmdLine.getValue(seedOpt).toString()); } if (log.isDebugEnabled()) { log.debug("data : {}", dataName); log.debug("dataset : {}", datasetName); log.debug("output : {}", outputName); log.debug("m : {}", m); log.debug("complemented : {}", complemented); log.debug("minSplitNum : {}", minSplitNum); log.debug("minVarianceProportion : {}", minVarianceProportion); log.debug("seed : {}", seed); log.debug("nbtrees : {}", nbTrees); log.debug("isPartial : {}", isPartial); } dataPath = new Path(dataName); datasetPath = new Path(datasetName); outputPath = new Path(outputName); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); return -1; } buildForest(); return 0; }
From source file:bigimp.BuildForest.java
@Override public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException, InstantiationException, IllegalAccessException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option dataOpt = obuilder.withLongName("data").withShortName("d").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Data path").create(); Option datasetOpt = obuilder.withLongName("dataset").withShortName("ds").withRequired(true) .withArgument(abuilder.withName("dataset").withMinimum(1).withMaximum(1).create()) .withDescription("Dataset path").create(); Option selectionOpt = obuilder.withLongName("selection").withShortName("sl").withRequired(false) .withArgument(abuilder.withName("m").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, Number of variables to select randomly at each tree-node.\n" + "For classification problem, the default is square root of the number of explanatory variables.\n" + "For regression problem, the default is 1/3 of the number of explanatory variables.") .create();/*from ww w. j a v a 2s . c o m*/ Option noCompleteOpt = obuilder.withLongName("no-complete").withShortName("nc").withRequired(false) .withDescription("Optional, The tree is not complemented").create(); Option minSplitOpt = obuilder.withLongName("minsplit").withShortName("ms").withRequired(false) .withArgument(abuilder.withName("minsplit").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, The tree-node is not divided, if the branching data size is " + "smaller than this value.\nThe default is 2.") .create(); Option minPropOpt = obuilder.withLongName("minprop").withShortName("mp").withRequired(false) .withArgument(abuilder.withName("minprop").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, The tree-node is not divided, if the proportion of the " + "variance of branching data is smaller than this value.\n" + "In the case of a regression problem, this value is used. " + "The default is 1/1000(0.001).") .create(); Option seedOpt = obuilder.withLongName("seed").withShortName("sd").withRequired(false) .withArgument(abuilder.withName("seed").withMinimum(1).withMaximum(1).create()) .withDescription("Optional, seed value used to initialise the Random number generator").create(); Option partialOpt = obuilder.withLongName("partial").withShortName("p").withRequired(false) .withDescription("Optional, use the Partial Data implementation").create(); Option nbtreesOpt = obuilder.withLongName("nbtrees").withShortName("t").withRequired(true) .withArgument(abuilder.withName("nbtrees").withMinimum(1).withMaximum(1).create()) .withDescription("Number of trees to grow").create(); Option outputOpt = obuilder.withLongName("output").withShortName("o").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Output path, will contain the Decision Forest").create(); Option helpOpt = obuilder.withLongName("help").withShortName("h").withDescription("Print out help") .create(); Group group = gbuilder.withName("Options").withOption(dataOpt).withOption(datasetOpt) .withOption(selectionOpt).withOption(noCompleteOpt).withOption(minSplitOpt).withOption(minPropOpt) .withOption(seedOpt).withOption(partialOpt).withOption(nbtreesOpt).withOption(outputOpt) .withOption(helpOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption("help")) { CommandLineUtil.printHelp(group); return -1; } isPartial = cmdLine.hasOption(partialOpt); String dataName = cmdLine.getValue(dataOpt).toString(); String datasetName = cmdLine.getValue(datasetOpt).toString(); String outputName = cmdLine.getValue(outputOpt).toString(); nbTrees = Integer.parseInt(cmdLine.getValue(nbtreesOpt).toString()); if (cmdLine.hasOption(selectionOpt)) { m = Integer.parseInt(cmdLine.getValue(selectionOpt).toString()); } complemented = !cmdLine.hasOption(noCompleteOpt); if (cmdLine.hasOption(minSplitOpt)) { minSplitNum = Integer.parseInt(cmdLine.getValue(minSplitOpt).toString()); } if (cmdLine.hasOption(minPropOpt)) { minVarianceProportion = Double.parseDouble(cmdLine.getValue(minPropOpt).toString()); } if (cmdLine.hasOption(seedOpt)) { seed = Long.valueOf(cmdLine.getValue(seedOpt).toString()); } if (log.isDebugEnabled()) { log.debug("data : {}", dataName); log.debug("dataset : {}", datasetName); log.debug("output : {}", outputName); log.debug("m : {}", m); log.debug("complemented : {}", complemented); log.debug("minSplitNum : {}", minSplitNum); log.debug("minVarianceProportion : {}", minVarianceProportion); log.debug("seed : {}", seed); log.debug("nbtrees : {}", nbTrees); log.debug("isPartial : {}", isPartial); } dataPath = new Path(dataName); datasetPath = new Path(datasetName); outputPath = new Path(outputName); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); return -1; } buildForest(); return 0; }
From source file:imageClassify.TestForest.java
@Override public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = DefaultOptionCreator.inputOption().create(); Option datasetOpt = obuilder.withLongName("dataset").withShortName("ds").withRequired(true) .withArgument(abuilder.withName("dataset").withMinimum(1).withMaximum(1).create()) .withDescription("Dataset path").create(); Option modelOpt = obuilder.withLongName("model").withShortName("m").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Path to the Decision Forest").create(); Option outputOpt = DefaultOptionCreator.outputOption().create(); Option analyzeOpt = obuilder.withLongName("analyze").withShortName("a").withRequired(false).create(); Option mrOpt = obuilder.withLongName("mapreduce").withShortName("mr").withRequired(false).create(); Option helpOpt = DefaultOptionCreator.helpOption(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(datasetOpt).withOption(modelOpt) .withOption(outputOpt).withOption(analyzeOpt).withOption(mrOpt).withOption(helpOpt).create(); try {/*from w ww. j a v a2s . c om*/ Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption("help")) { CommandLineUtil.printHelp(group); return -1; } String dataName = cmdLine.getValue(inputOpt).toString(); String datasetName = cmdLine.getValue(datasetOpt).toString(); String modelName = cmdLine.getValue(modelOpt).toString(); String outputName = cmdLine.hasOption(outputOpt) ? cmdLine.getValue(outputOpt).toString() : null; analyze = cmdLine.hasOption(analyzeOpt); useMapreduce = cmdLine.hasOption(mrOpt); if (log.isDebugEnabled()) { log.debug("inout : {}", dataName); log.debug("dataset : {}", datasetName); log.debug("model : {}", modelName); log.debug("output : {}", outputName); log.debug("analyze : {}", analyze); log.debug("mapreduce : {}", useMapreduce); } dataPath = new Path(dataName); datasetPath = new Path(datasetName); modelPath = new Path(modelName); if (outputName != null) { outputPath = new Path(outputName); } } catch (OptionException e) { log.warn(e.toString(), e); CommandLineUtil.printHelp(group); return -1; } testForest(); return 0; }
From source file:com.digitalpebble.behemoth.tika.TikaDriver.java
public int run(String[] args) throws Exception { final FileSystem fs = FileSystem.get(getConf()); GroupBuilder gBuilder = new GroupBuilder().withName("Options:"); List<Option> options = new ArrayList<Option>(); Option inputOpt = buildOption("input", "i", "The input path", true, true, null); options.add(inputOpt);// w w w. j a va2 s .c o m Option outOpt = buildOption("output", "o", "The output path", true, true, null); options.add(outOpt); Option tikaOpt = buildOption("tikaProcessor", "t", "The fully qualified name of a TikaProcessor class that handles the extraction (optional)", true, false, null); options.add(tikaOpt); Option mimeTypeOpt = buildOption("mimeType", "m", "The mime type to use (optional)", true, false, ""); options.add(mimeTypeOpt); for (Option opt : options) { gBuilder = gBuilder.withOption(opt); } Group group = gBuilder.create(); try { Parser parser = new Parser(); parser.setGroup(group); // TODO catch exceptions with parsing of opts CommandLine cmdLine = parser.parse(args); Path inputPath = new Path(cmdLine.getValue(inputOpt).toString()); Path outputPath = new Path(cmdLine.getValue(outOpt).toString()); String handlerName = null; if (cmdLine.hasOption(tikaOpt)) { handlerName = cmdLine.getValue(tikaOpt).toString(); } JobConf job = new JobConf(getConf()); job.setJarByClass(this.getClass()); if (cmdLine.hasOption(mimeTypeOpt)) { String mimeType = cmdLine.getValue(mimeTypeOpt).toString(); job.set(TikaConstants.TIKA_MIME_TYPE_KEY, mimeType); } if (handlerName != null && handlerName.equals("") == false) { job.set(TIKA_PROCESSOR_KEY, handlerName); } job.setJobName("Tika : " + inputPath.toString()); job.setInputFormat(SequenceFileInputFormat.class); job.setOutputFormat(SequenceFileOutputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(BehemothDocument.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(BehemothDocument.class); job.setMapperClass(TikaMapper.class); boolean isFilterRequired = BehemothReducer.isRequired(job); if (isFilterRequired) job.setReducerClass(BehemothReducer.class); else { job.setNumReduceTasks(0); } FileInputFormat.addInputPath(job, inputPath); FileOutputFormat.setOutputPath(job, outputPath); try { long start = System.currentTimeMillis(); JobClient.runJob(job); long finish = System.currentTimeMillis(); if (log.isInfoEnabled()) { log.info("TikaDriver completed. Timing: " + (finish - start) + " ms"); } } catch (Exception e) { log.error("Exception", e); return -1; // don't delete the output as some of it could be used // fs.delete(outputPath, true); } finally { } } catch (OptionException e) { log.error("OptionException", e.getMessage()); HelpFormatter formatter = new HelpFormatter(); formatter.setGroup(group); formatter.print(); return -1; } return 0; }
From source file:com.gsinnovations.howdah.AbstractJob.java
/** Obtain input and output directories from command-line options or hadoop * properties. If <code>addInputOption</code> or <code>addOutputOption</code> * has been called, this method will throw an <code>OptionException</code> if * no source (command-line or property) for that value is present. * Otherwise, <code>inputPath</code> or <code>outputPath<code> will be * non-null only if specified as a hadoop property. Command-line options * take precedence over hadoop properties. * * @param cmdLine/*from ww w. j av a 2 s. co m*/ * @throws IllegalArgumentException if either inputOption is present, * and neither <code>--input</code> nor <code>-Dmapred.input dir</code> are * specified or outputOption is present and neither <code>--output</code> * nor <code>-Dmapred.output.dir</code> are specified. */ protected void parseDirectories(CommandLine cmdLine) { Configuration conf = getConf(); if (inputOption != null && cmdLine.hasOption(inputOption)) { this.inputPath = new Path(cmdLine.getValue(inputOption).toString()); } if (inputPath == null && conf.get("mapred.input.dir") != null) { this.inputPath = new Path(conf.get("mapred.input.dir")); } if (outputOption != null && cmdLine.hasOption(outputOption)) { this.outputPath = new Path(cmdLine.getValue(outputOption).toString()); } if (outputPath == null && conf.get("mapred.output.dir") != null) { this.outputPath = new Path(conf.get("mapred.output.dir")); } if (inputOption != null && inputPath == null) { throw new IllegalArgumentException("No input specified: " + inputOption.getPreferredName() + " or -Dmapred.input.dir must be provided to specify input directory"); } if (outputOption != null && outputPath == null) { throw new IllegalArgumentException("No output specified: " + outputOption.getPreferredName() + " or -Dmapred.output.dir must be provided to specify output directory"); } }
From source file:com.elex.dmp.vectorizer.SparseVectorsFromSequenceFiles.java
@Override public int run(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputDirOpt = DefaultOptionCreator.inputOption().create(); Option outputDirOpt = DefaultOptionCreator.outputOption().create(); Option minSupportOpt = obuilder.withLongName("minSupport") .withArgument(abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Minimum Support. Default Value: 2").withShortName("s").create(); Option analyzerNameOpt = obuilder.withLongName("analyzerName") .withArgument(abuilder.withName("analyzerName").withMinimum(1).withMaximum(1).create()) .withDescription("The class name of the analyzer").withShortName("a").create(); Option chunkSizeOpt = obuilder.withLongName("chunkSize") .withArgument(abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()) .withDescription("The chunkSize in MegaBytes. 100-10000 MB").withShortName("chunk").create(); Option weightOpt = obuilder.withLongName("weight").withRequired(false) .withArgument(abuilder.withName("weight").withMinimum(1).withMaximum(1).create()) .withDescription("The kind of weight to use. Currently TF or TFIDF").withShortName("wt").create(); Option minDFOpt = obuilder.withLongName("minDF").withRequired(false) .withArgument(abuilder.withName("minDF").withMinimum(1).withMaximum(1).create()) .withDescription("The minimum document frequency. Default is 1").withShortName("md").create(); Option maxDFPercentOpt = obuilder.withLongName("maxDFPercent").withRequired(false) .withArgument(abuilder.withName("maxDFPercent").withMinimum(1).withMaximum(1).create()) .withDescription(/* ww w . j a v a2 s. co m*/ "The max percentage of docs for the DF. Can be used to remove really high frequency terms." + " Expressed as an integer between 0 and 100. Default is 99. If maxDFSigma is also set, it will override this value.") .withShortName("x").create(); Option maxDFSigmaOpt = obuilder.withLongName("maxDFSigma").withRequired(false) .withArgument(abuilder.withName("maxDFSigma").withMinimum(1).withMaximum(1).create()) .withDescription( "What portion of the tf (tf-idf) vectors to be used, expressed in times the standard deviation (sigma) of the document frequencies of these vectors." + " Can be used to remove really high frequency terms." + " Expressed as a double value. Good value to be specified is 3.0. In case the value is less then 0 no vectors " + "will be filtered out. Default is -1.0. Overrides maxDFPercent") .withShortName("xs").create(); Option minLLROpt = obuilder.withLongName("minLLR").withRequired(false) .withArgument(abuilder.withName("minLLR").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional)The minimum Log Likelihood Ratio(Float) Default is " + LLRReducer.DEFAULT_MIN_LLR) .withShortName("ml").create(); Option numReduceTasksOpt = obuilder.withLongName("numReducers") .withArgument(abuilder.withName("numReducers").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Number of reduce tasks. Default Value: 1").withShortName("nr") .create(); Option powerOpt = obuilder.withLongName("norm").withRequired(false) .withArgument(abuilder.withName("norm").withMinimum(1).withMaximum(1).create()) .withDescription( "The norm to use, expressed as either a float or \"INF\" if you want to use the Infinite norm. " + "Must be greater or equal to 0. The default is not to normalize") .withShortName("n").create(); Option logNormalizeOpt = obuilder.withLongName("logNormalize").withRequired(false) .withDescription("(Optional) Whether output vectors should be logNormalize. If set true else false") .withShortName("lnorm").create(); Option maxNGramSizeOpt = obuilder.withLongName("maxNGramSize").withRequired(false) .withArgument(abuilder.withName("ngramSize").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) The maximum size of ngrams to create" + " (2 = bigrams, 3 = trigrams, etc) Default Value:1") .withShortName("ng").create(); Option sequentialAccessVectorOpt = obuilder.withLongName("sequentialAccessVector").withRequired(false) .withDescription( "(Optional) Whether output vectors should be SequentialAccessVectors. If set true else false") .withShortName("seq").create(); Option namedVectorOpt = obuilder.withLongName("namedVector").withRequired(false) .withDescription("(Optional) Whether output vectors should be NamedVectors. If set true else false") .withShortName("nv").create(); Option overwriteOutput = obuilder.withLongName("overwrite").withRequired(false) .withDescription("If set, overwrite the output directory").withShortName("ow").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(minSupportOpt).withOption(analyzerNameOpt) .withOption(chunkSizeOpt).withOption(outputDirOpt).withOption(inputDirOpt).withOption(minDFOpt) .withOption(maxDFSigmaOpt).withOption(maxDFPercentOpt).withOption(weightOpt).withOption(powerOpt) .withOption(minLLROpt).withOption(numReduceTasksOpt).withOption(maxNGramSizeOpt) .withOption(overwriteOutput).withOption(helpOpt).withOption(sequentialAccessVectorOpt) .withOption(namedVectorOpt).withOption(logNormalizeOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return -1; } Path inputDir = new Path((String) cmdLine.getValue(inputDirOpt)); Path outputDir = new Path((String) cmdLine.getValue(outputDirOpt)); int chunkSize = 100; if (cmdLine.hasOption(chunkSizeOpt)) { chunkSize = Integer.parseInt((String) cmdLine.getValue(chunkSizeOpt)); } int minSupport = 2; if (cmdLine.hasOption(minSupportOpt)) { String minSupportString = (String) cmdLine.getValue(minSupportOpt); minSupport = Integer.parseInt(minSupportString); } int maxNGramSize = 1; if (cmdLine.hasOption(maxNGramSizeOpt)) { try { maxNGramSize = Integer.parseInt(cmdLine.getValue(maxNGramSizeOpt).toString()); } catch (NumberFormatException ex) { log.warn("Could not parse ngram size option"); } } log.info("Maximum n-gram size is: {}", maxNGramSize); if (cmdLine.hasOption(overwriteOutput)) { HadoopUtil.delete(getConf(), outputDir); } float minLLRValue = LLRReducer.DEFAULT_MIN_LLR; if (cmdLine.hasOption(minLLROpt)) { minLLRValue = Float.parseFloat(cmdLine.getValue(minLLROpt).toString()); } log.info("Minimum LLR value: {}", minLLRValue); int reduceTasks = 1; if (cmdLine.hasOption(numReduceTasksOpt)) { reduceTasks = Integer.parseInt(cmdLine.getValue(numReduceTasksOpt).toString()); } log.info("Number of reduce tasks: {}", reduceTasks); Class<? extends Analyzer> analyzerClass = DefaultAnalyzer.class; if (cmdLine.hasOption(analyzerNameOpt)) { String className = cmdLine.getValue(analyzerNameOpt).toString(); analyzerClass = Class.forName(className).asSubclass(Analyzer.class); // try instantiating it, b/c there isn't any point in setting it if // you can't instantiate it ClassUtils.instantiateAs(analyzerClass, Analyzer.class); } boolean processIdf; if (cmdLine.hasOption(weightOpt)) { String wString = cmdLine.getValue(weightOpt).toString(); if ("tf".equalsIgnoreCase(wString)) { processIdf = false; } else if ("tfidf".equalsIgnoreCase(wString)) { processIdf = true; } else { throw new OptionException(weightOpt); } } else { processIdf = true; } int minDf = 1; if (cmdLine.hasOption(minDFOpt)) { minDf = Integer.parseInt(cmdLine.getValue(minDFOpt).toString()); } int maxDFPercent = 99; if (cmdLine.hasOption(maxDFPercentOpt)) { maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString()); } double maxDFSigma = -1.0; if (cmdLine.hasOption(maxDFSigmaOpt)) { maxDFSigma = Double.parseDouble(cmdLine.getValue(maxDFSigmaOpt).toString()); } float norm = PartialVectorMerger.NO_NORMALIZING; if (cmdLine.hasOption(powerOpt)) { String power = cmdLine.getValue(powerOpt).toString(); if ("INF".equals(power)) { norm = Float.POSITIVE_INFINITY; } else { norm = Float.parseFloat(power); } } boolean logNormalize = false; if (cmdLine.hasOption(logNormalizeOpt)) { logNormalize = true; } Configuration conf = getConf(); Path tokenizedPath = new Path(outputDir, DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); //TODO: move this into DictionaryVectorizer , and then fold SparseVectorsFrom with EncodedVectorsFrom to have one framework for all of this. DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, tokenizedPath, conf); boolean sequentialAccessOutput = false; if (cmdLine.hasOption(sequentialAccessVectorOpt)) { sequentialAccessOutput = true; } boolean namedVectors = false; if (cmdLine.hasOption(namedVectorOpt)) { namedVectors = true; } boolean shouldPrune = maxDFSigma >= 0.0; String tfDirName = shouldPrune ? DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-toprune" : DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER; if (!processIdf) { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, norm, logNormalize, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } else { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, -1.0f, false, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } Pair<Long[], List<Path>> docFrequenciesFeatures = null; // Should document frequency features be processed if (shouldPrune || processIdf) { docFrequenciesFeatures = TFIDFConverter.calculateDF(new Path(outputDir, tfDirName), outputDir, conf, chunkSize); } long maxDF = maxDFPercent; //if we are pruning by std dev, then this will get changed if (shouldPrune) { Path dfDir = new Path(outputDir, TFIDFConverter.WORDCOUNT_OUTPUT_FOLDER); Path stdCalcDir = new Path(outputDir, HighDFWordsPruner.STD_CALC_DIR); // Calculate the standard deviation double stdDev = BasicStats.stdDevForGivenMean(dfDir, stdCalcDir, 0.0, conf); long vectorCount = docFrequenciesFeatures.getFirst()[1]; maxDF = (int) (100.0 * maxDFSigma * stdDev / vectorCount); // Prune the term frequency vectors Path tfDir = new Path(outputDir, tfDirName); Path prunedTFDir = new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER); Path prunedPartialTFDir = new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-partial"); if (processIdf) { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, -1.0f, false, reduceTasks); } else { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, norm, logNormalize, reduceTasks); } HadoopUtil.delete(new Configuration(conf), tfDir); } if (processIdf) { TFIDFConverter.processTfIdf(new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER), outputDir, conf, docFrequenciesFeatures, minDf, maxDF, norm, logNormalize, sequentialAccessOutput, namedVectors, reduceTasks); } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } return 0; }
From source file:com.elex.dmp.vectorizer.TFVectorsUseFixedDictionary.java
@Override public int run(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputDirOpt = DefaultOptionCreator.inputOption().create(); Option outputDirOpt = DefaultOptionCreator.outputOption().create(); Option minSupportOpt = obuilder.withLongName("minSupport") .withArgument(abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Minimum Support. Default Value: 2").withShortName("s").create(); Option analyzerNameOpt = obuilder.withLongName("analyzerName") .withArgument(abuilder.withName("analyzerName").withMinimum(1).withMaximum(1).create()) .withDescription("The class name of the analyzer").withShortName("a").create(); Option chunkSizeOpt = obuilder.withLongName("chunkSize") .withArgument(abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()) .withDescription("The chunkSize in MegaBytes. 100-10000 MB").withShortName("chunk").create(); Option weightOpt = obuilder.withLongName("weight").withRequired(false) .withArgument(abuilder.withName("weight").withMinimum(1).withMaximum(1).create()) .withDescription("The kind of weight to use. Currently TF or TFIDF").withShortName("wt").create(); Option minDFOpt = obuilder.withLongName("minDF").withRequired(false) .withArgument(abuilder.withName("minDF").withMinimum(1).withMaximum(1).create()) .withDescription("The minimum document frequency. Default is 1").withShortName("md").create(); Option maxDFPercentOpt = obuilder.withLongName("maxDFPercent").withRequired(false) .withArgument(abuilder.withName("maxDFPercent").withMinimum(1).withMaximum(1).create()) .withDescription(/*from w w w . jav a2 s . c o m*/ "The max percentage of docs for the DF. Can be used to remove really high frequency terms." + " Expressed as an integer between 0 and 100. Default is 99. If maxDFSigma is also set, it will override this value.") .withShortName("x").create(); Option maxDFSigmaOpt = obuilder.withLongName("maxDFSigma").withRequired(false) .withArgument(abuilder.withName("maxDFSigma").withMinimum(1).withMaximum(1).create()) .withDescription( "What portion of the tf (tf-idf) vectors to be used, expressed in times the standard deviation (sigma) of the document frequencies of these vectors." + " Can be used to remove really high frequency terms." + " Expressed as a double value. Good value to be specified is 3.0. In case the value is less then 0 no vectors " + "will be filtered out. Default is -1.0. Overrides maxDFPercent") .withShortName("xs").create(); Option minLLROpt = obuilder.withLongName("minLLR").withRequired(false) .withArgument(abuilder.withName("minLLR").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional)The minimum Log Likelihood Ratio(Float) Default is " + LLRReducer.DEFAULT_MIN_LLR) .withShortName("ml").create(); Option numReduceTasksOpt = obuilder.withLongName("numReducers") .withArgument(abuilder.withName("numReducers").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Number of reduce tasks. Default Value: 1").withShortName("nr") .create(); Option powerOpt = obuilder.withLongName("norm").withRequired(false) .withArgument(abuilder.withName("norm").withMinimum(1).withMaximum(1).create()) .withDescription( "The norm to use, expressed as either a float or \"INF\" if you want to use the Infinite norm. " + "Must be greater or equal to 0. The default is not to normalize") .withShortName("n").create(); Option logNormalizeOpt = obuilder.withLongName("logNormalize").withRequired(false) .withDescription("(Optional) Whether output vectors should be logNormalize. If set true else false") .withShortName("lnorm").create(); Option maxNGramSizeOpt = obuilder.withLongName("maxNGramSize").withRequired(false) .withArgument(abuilder.withName("ngramSize").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) The maximum size of ngrams to create" + " (2 = bigrams, 3 = trigrams, etc) Default Value:1") .withShortName("ng").create(); Option sequentialAccessVectorOpt = obuilder.withLongName("sequentialAccessVector").withRequired(false) .withDescription( "(Optional) Whether output vectors should be SequentialAccessVectors. If set true else false") .withShortName("seq").create(); Option namedVectorOpt = obuilder.withLongName("namedVector").withRequired(false) .withDescription("(Optional) Whether output vectors should be NamedVectors. If set true else false") .withShortName("nv").create(); Option overwriteOutput = obuilder.withLongName("overwrite").withRequired(false) .withDescription("If set, overwrite the output directory").withShortName("ow").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(minSupportOpt).withOption(analyzerNameOpt) .withOption(chunkSizeOpt).withOption(outputDirOpt).withOption(inputDirOpt).withOption(minDFOpt) .withOption(maxDFSigmaOpt).withOption(maxDFPercentOpt).withOption(weightOpt).withOption(powerOpt) .withOption(minLLROpt).withOption(numReduceTasksOpt).withOption(maxNGramSizeOpt) .withOption(overwriteOutput).withOption(helpOpt).withOption(sequentialAccessVectorOpt) .withOption(namedVectorOpt).withOption(logNormalizeOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return -1; } Path inputDir = new Path((String) cmdLine.getValue(inputDirOpt)); Path outputDir = new Path((String) cmdLine.getValue(outputDirOpt)); int chunkSize = 100; if (cmdLine.hasOption(chunkSizeOpt)) { chunkSize = Integer.parseInt((String) cmdLine.getValue(chunkSizeOpt)); } int minSupport = 2; if (cmdLine.hasOption(minSupportOpt)) { String minSupportString = (String) cmdLine.getValue(minSupportOpt); minSupport = Integer.parseInt(minSupportString); } int maxNGramSize = 1; if (cmdLine.hasOption(maxNGramSizeOpt)) { try { maxNGramSize = Integer.parseInt(cmdLine.getValue(maxNGramSizeOpt).toString()); } catch (NumberFormatException ex) { log.warn("Could not parse ngram size option"); } } log.info("Maximum n-gram size is: {}", maxNGramSize); if (cmdLine.hasOption(overwriteOutput)) { HadoopUtil.delete(getConf(), outputDir); } float minLLRValue = LLRReducer.DEFAULT_MIN_LLR; if (cmdLine.hasOption(minLLROpt)) { minLLRValue = Float.parseFloat(cmdLine.getValue(minLLROpt).toString()); } log.info("Minimum LLR value: {}", minLLRValue); int reduceTasks = 1; if (cmdLine.hasOption(numReduceTasksOpt)) { reduceTasks = Integer.parseInt(cmdLine.getValue(numReduceTasksOpt).toString()); } log.info("Number of reduce tasks: {}", reduceTasks); Class<? extends Analyzer> analyzerClass = DefaultAnalyzer.class; if (cmdLine.hasOption(analyzerNameOpt)) { String className = cmdLine.getValue(analyzerNameOpt).toString(); analyzerClass = Class.forName(className).asSubclass(Analyzer.class); // try instantiating it, b/c there isn't any point in setting it if // you can't instantiate it ClassUtils.instantiateAs(analyzerClass, Analyzer.class); } boolean processIdf; if (cmdLine.hasOption(weightOpt)) { String wString = cmdLine.getValue(weightOpt).toString(); if ("tf".equalsIgnoreCase(wString)) { processIdf = false; } else if ("tfidf".equalsIgnoreCase(wString)) { processIdf = true; } else { throw new OptionException(weightOpt); } } else { processIdf = true; } int minDf = 1; if (cmdLine.hasOption(minDFOpt)) { minDf = Integer.parseInt(cmdLine.getValue(minDFOpt).toString()); } int maxDFPercent = 99; if (cmdLine.hasOption(maxDFPercentOpt)) { maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString()); } double maxDFSigma = -1.0; if (cmdLine.hasOption(maxDFSigmaOpt)) { maxDFSigma = Double.parseDouble(cmdLine.getValue(maxDFSigmaOpt).toString()); } float norm = PartialVectorMerger.NO_NORMALIZING; if (cmdLine.hasOption(powerOpt)) { String power = cmdLine.getValue(powerOpt).toString(); if ("INF".equals(power)) { norm = Float.POSITIVE_INFINITY; } else { norm = Float.parseFloat(power); } } boolean logNormalize = false; if (cmdLine.hasOption(logNormalizeOpt)) { logNormalize = true; } Configuration conf = getConf(); Path tokenizedPath = new Path(outputDir, DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); //TODO: move this into DictionaryVectorizer , and then fold SparseVectorsFrom with EncodedVectorsFrom to have one framework for all of this. DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, tokenizedPath, conf); boolean sequentialAccessOutput = false; if (cmdLine.hasOption(sequentialAccessVectorOpt)) { sequentialAccessOutput = true; } boolean namedVectors = false; if (cmdLine.hasOption(namedVectorOpt)) { namedVectors = true; } boolean shouldPrune = maxDFSigma >= 0.0; String tfDirName = shouldPrune ? FixDictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-toprune" : FixDictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER; if (!processIdf) { FixDictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, norm, logNormalize, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } else { FixDictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, -1.0f, false, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } Pair<Long[], List<Path>> docFrequenciesFeatures = null; // Should document frequency features be processed if (shouldPrune || processIdf) { docFrequenciesFeatures = TFIDFConverter.calculateDF(new Path(outputDir, tfDirName), outputDir, conf, chunkSize); } long maxDF = maxDFPercent; //if we are pruning by std dev, then this will get changed if (shouldPrune) { Path dfDir = new Path(outputDir, TFIDFConverter.WORDCOUNT_OUTPUT_FOLDER); Path stdCalcDir = new Path(outputDir, HighDFWordsPruner.STD_CALC_DIR); // Calculate the standard deviation double stdDev = BasicStats.stdDevForGivenMean(dfDir, stdCalcDir, 0.0, conf); long vectorCount = docFrequenciesFeatures.getFirst()[1]; maxDF = (int) (100.0 * maxDFSigma * stdDev / vectorCount); // Prune the term frequency vectors Path tfDir = new Path(outputDir, tfDirName); Path prunedTFDir = new Path(outputDir, FixDictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER); Path prunedPartialTFDir = new Path(outputDir, FixDictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-partial"); if (processIdf) { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, -1.0f, false, reduceTasks); } else { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, norm, logNormalize, reduceTasks); } HadoopUtil.delete(new Configuration(conf), tfDir); } if (processIdf) { TFIDFConverter.processTfIdf( new Path(outputDir, FixDictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER), outputDir, conf, docFrequenciesFeatures, minDf, maxDF, norm, logNormalize, sequentialAccessOutput, namedVectors, reduceTasks); } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } return 0; }
From source file:com.caseystella.ingest.SparseVectorsFromSequenceFiles.java
@Override public int run(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputDirOpt = DefaultOptionCreator.inputOption().create(); Option outputDirOpt = DefaultOptionCreator.outputOption().create(); Option minSupportOpt = obuilder.withLongName("minSupport") .withArgument(abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Minimum Support. Default Value: 2").withShortName("s").create(); Option analyzerNameOpt = obuilder.withLongName("analyzerName") .withArgument(abuilder.withName("analyzerName").withMinimum(1).withMaximum(1).create()) .withDescription("The class name of the analyzer").withShortName("a").create(); Option libJarsOpt = obuilder.withLongName("libjars") .withArgument(abuilder.withName("libjars").withMinimum(1).withMaximum(1).create()) .withDescription("The default arg for libjars").withShortName("libjars").create(); Option chunkSizeOpt = obuilder.withLongName("chunkSize") .withArgument(abuilder.withName("chunkSize").withMinimum(1).withMaximum(1).create()) .withDescription("The chunkSize in MegaBytes. 100-10000 MB").withShortName("chunk").create(); Option weightOpt = obuilder.withLongName("weight").withRequired(false) .withArgument(abuilder.withName("weight").withMinimum(1).withMaximum(1).create()) .withDescription("The kind of weight to use. Currently TF or TFIDF").withShortName("wt").create(); Option minDFOpt = obuilder.withLongName("minDF").withRequired(false) .withArgument(abuilder.withName("minDF").withMinimum(1).withMaximum(1).create()) .withDescription("The minimum document frequency. Default is 1").withShortName("md").create(); Option maxDFPercentOpt = obuilder.withLongName("maxDFPercent").withRequired(false) .withArgument(abuilder.withName("maxDFPercent").withMinimum(1).withMaximum(1).create()) .withDescription(//from w w w .j av a 2 s. c o m "The max percentage of docs for the DF. Can be used to remove really high frequency terms." + " Expressed as an integer between 0 and 100. Default is 99. If maxDFSigma is also set, it will override this value.") .withShortName("x").create(); Option maxDFSigmaOpt = obuilder.withLongName("maxDFSigma").withRequired(false) .withArgument(abuilder.withName("maxDFSigma").withMinimum(1).withMaximum(1).create()) .withDescription( "What portion of the tf (tf-idf) vectors to be used, expressed in times the standard deviation (sigma) of the document frequencies of these vectors." + " Can be used to remove really high frequency terms." + " Expressed as a double value. Good value to be specified is 3.0. In case the value is less then 0 no vectors " + "will be filtered out. Default is -1.0. Overrides maxDFPercent") .withShortName("xs").create(); Option minLLROpt = obuilder.withLongName("minLLR").withRequired(false) .withArgument(abuilder.withName("minLLR").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional)The minimum Log Likelihood Ratio(Float) Default is " + LLRReducer.DEFAULT_MIN_LLR) .withShortName("ml").create(); Option numReduceTasksOpt = obuilder.withLongName("numReducers") .withArgument(abuilder.withName("numReducers").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Number of reduce tasks. Default Value: 1").withShortName("nr") .create(); Option powerOpt = obuilder.withLongName("norm").withRequired(false) .withArgument(abuilder.withName("norm").withMinimum(1).withMaximum(1).create()) .withDescription( "The norm to use, expressed as either a float or \"INF\" if you want to use the Infinite norm. " + "Must be greater or equal to 0. The default is not to normalize") .withShortName("n").create(); Option logNormalizeOpt = obuilder.withLongName("logNormalize").withRequired(false) .withDescription("(Optional) Whether output vectors should be logNormalize. If set true else false") .withShortName("lnorm").create(); Option maxNGramSizeOpt = obuilder.withLongName("maxNGramSize").withRequired(false) .withArgument(abuilder.withName("ngramSize").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) The maximum size of ngrams to create" + " (2 = bigrams, 3 = trigrams, etc) Default Value:1") .withShortName("ng").create(); Option sequentialAccessVectorOpt = obuilder.withLongName("sequentialAccessVector").withRequired(false) .withDescription( "(Optional) Whether output vectors should be SequentialAccessVectors. If set true else false") .withShortName("seq").create(); Option namedVectorOpt = obuilder.withLongName("namedVector").withRequired(false) .withDescription("(Optional) Whether output vectors should be NamedVectors. If set true else false") .withShortName("nv").create(); Option overwriteOutput = obuilder.withLongName("overwrite").withRequired(false) .withDescription("If set, overwrite the output directory").withShortName("ow").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(minSupportOpt).withOption(analyzerNameOpt) .withOption(libJarsOpt).withOption(chunkSizeOpt).withOption(outputDirOpt).withOption(inputDirOpt) .withOption(minDFOpt).withOption(maxDFSigmaOpt).withOption(maxDFPercentOpt).withOption(weightOpt) .withOption(powerOpt).withOption(minLLROpt).withOption(numReduceTasksOpt) .withOption(maxNGramSizeOpt).withOption(overwriteOutput).withOption(helpOpt) .withOption(sequentialAccessVectorOpt).withOption(namedVectorOpt).withOption(logNormalizeOpt) .create(); try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return -1; } Path inputDir = new Path((String) cmdLine.getValue(inputDirOpt)); Path outputDir = new Path((String) cmdLine.getValue(outputDirOpt)); int chunkSize = 100; if (cmdLine.hasOption(chunkSizeOpt)) { chunkSize = Integer.parseInt((String) cmdLine.getValue(chunkSizeOpt)); } int minSupport = 2; if (cmdLine.hasOption(minSupportOpt)) { String minSupportString = (String) cmdLine.getValue(minSupportOpt); minSupport = Integer.parseInt(minSupportString); } int maxNGramSize = 1; if (cmdLine.hasOption(maxNGramSizeOpt)) { try { maxNGramSize = Integer.parseInt(cmdLine.getValue(maxNGramSizeOpt).toString()); } catch (NumberFormatException ex) { log.warn("Could not parse ngram size option"); } } log.info("Maximum n-gram size is: {}", maxNGramSize); if (cmdLine.hasOption(overwriteOutput)) { HadoopUtil.delete(getConf(), outputDir); } float minLLRValue = LLRReducer.DEFAULT_MIN_LLR; if (cmdLine.hasOption(minLLROpt)) { minLLRValue = Float.parseFloat(cmdLine.getValue(minLLROpt).toString()); } log.info("Minimum LLR value: {}", minLLRValue); int reduceTasks = 1; if (cmdLine.hasOption(numReduceTasksOpt)) { reduceTasks = Integer.parseInt(cmdLine.getValue(numReduceTasksOpt).toString()); } log.info("Number of reduce tasks: {}", reduceTasks); Class<? extends Analyzer> analyzerClass = DefaultAnalyzer.class; if (cmdLine.hasOption(analyzerNameOpt)) { String className = cmdLine.getValue(analyzerNameOpt).toString(); analyzerClass = Class.forName(className).asSubclass(Analyzer.class); // try instantiating it, b/c there isn't any point in setting it if // you can't instantiate it ClassUtils.instantiateAs(analyzerClass, Analyzer.class); } boolean processIdf; if (cmdLine.hasOption(weightOpt)) { String wString = cmdLine.getValue(weightOpt).toString(); if ("tf".equalsIgnoreCase(wString)) { processIdf = false; } else if ("tfidf".equalsIgnoreCase(wString)) { processIdf = true; } else { throw new OptionException(weightOpt); } } else { processIdf = true; } int minDf = 1; if (cmdLine.hasOption(minDFOpt)) { minDf = Integer.parseInt(cmdLine.getValue(minDFOpt).toString()); } int maxDFPercent = 99; if (cmdLine.hasOption(maxDFPercentOpt)) { maxDFPercent = Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString()); } double maxDFSigma = -1.0; if (cmdLine.hasOption(maxDFSigmaOpt)) { maxDFSigma = Double.parseDouble(cmdLine.getValue(maxDFSigmaOpt).toString()); } float norm = PartialVectorMerger.NO_NORMALIZING; if (cmdLine.hasOption(powerOpt)) { String power = cmdLine.getValue(powerOpt).toString(); if ("INF".equals(power)) { norm = Float.POSITIVE_INFINITY; } else { norm = Float.parseFloat(power); } } boolean logNormalize = false; if (cmdLine.hasOption(logNormalizeOpt)) { logNormalize = true; } Configuration conf = getConf(); Path tokenizedPath = new Path(outputDir, DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); //TODO: move this into DictionaryVectorizer , and then fold SparseVectorsFrom with EncodedVectorsFrom to have one framework for all of this. DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, tokenizedPath, conf); boolean sequentialAccessOutput = false; if (cmdLine.hasOption(sequentialAccessVectorOpt)) { sequentialAccessOutput = true; } boolean namedVectors = false; if (cmdLine.hasOption(namedVectorOpt)) { namedVectors = true; } boolean shouldPrune = maxDFSigma >= 0.0; String tfDirName = shouldPrune ? DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-toprune" : DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER; if (!processIdf) { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, norm, logNormalize, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } else { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, -1.0f, false, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } Pair<Long[], List<Path>> docFrequenciesFeatures = null; // Should document frequency features be processed if (shouldPrune || processIdf) { docFrequenciesFeatures = TFIDFConverter.calculateDF(new Path(outputDir, tfDirName), outputDir, conf, chunkSize); } long maxDF = maxDFPercent; //if we are pruning by std dev, then this will get changed if (shouldPrune) { Path dfDir = new Path(outputDir, TFIDFConverter.WORDCOUNT_OUTPUT_FOLDER); Path stdCalcDir = new Path(outputDir, HighDFWordsPruner.STD_CALC_DIR); // Calculate the standard deviation double stdDev = BasicStats.stdDevForGivenMean(dfDir, stdCalcDir, 0.0, conf); long vectorCount = docFrequenciesFeatures.getFirst()[1]; maxDF = (int) (100.0 * maxDFSigma * stdDev / vectorCount); // Prune the term frequency vectors Path tfDir = new Path(outputDir, tfDirName); Path prunedTFDir = new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER); Path prunedPartialTFDir = new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-partial"); if (processIdf) { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, -1.0f, false, reduceTasks); } else { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDF, conf, docFrequenciesFeatures, norm, logNormalize, reduceTasks); } HadoopUtil.delete(new Configuration(conf), tfDir); } if (processIdf) { TFIDFConverter.processTfIdf(new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER), outputDir, conf, docFrequenciesFeatures, minDf, maxDF, norm, logNormalize, sequentialAccessOutput, namedVectors, reduceTasks); } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } return 0; }