List of usage examples for org.apache.commons.cli2.commandline Parser Parser
Parser
From source file:org.apache.mahout.text.WikipediaToSequenceFile.java
/** * Takes in two arguments:/*w w w. ja v a 2s .c o m*/ * <ol> * <li>The input {@link org.apache.hadoop.fs.Path} where the input documents live</li> * <li>The output {@link org.apache.hadoop.fs.Path} where to write the classifier as a * {@link org.apache.hadoop.io.SequenceFile}</li> * </ol> */ public static void main(String[] args) throws IOException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option dirInputPathOpt = DefaultOptionCreator.inputOption().create(); Option dirOutputPathOpt = DefaultOptionCreator.outputOption().create(); Option categoriesOpt = obuilder.withLongName("categories") .withArgument(abuilder.withName("categories").withMinimum(1).withMaximum(1).create()) .withDescription("Location of the categories file. One entry per line. " + "Will be used to make a string match in Wikipedia Category field") .withShortName("c").create(); Option exactMatchOpt = obuilder.withLongName("exactMatch") .withDescription("If set, then the category name must exactly match the " + "entry in the categories file. Default is false") .withShortName("e").create(); Option allOpt = obuilder.withLongName("all").withDescription("If set, Select all files. Default is false") .withShortName("all").create(); Option removeLabelOpt = obuilder.withLongName("removeLabels") .withDescription("If set, remove [[Category:labels]] from document text after extracting label." + "Default is false") .withShortName("rl").create(); Option helpOpt = DefaultOptionCreator.helpOption(); Group group = gbuilder.withName("Options").withOption(categoriesOpt).withOption(dirInputPathOpt) .withOption(dirOutputPathOpt).withOption(exactMatchOpt).withOption(allOpt).withOption(helpOpt) .withOption(removeLabelOpt).create(); Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); try { CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } String inputPath = (String) cmdLine.getValue(dirInputPathOpt); String outputPath = (String) cmdLine.getValue(dirOutputPathOpt); String catFile = ""; if (cmdLine.hasOption(categoriesOpt)) { catFile = (String) cmdLine.getValue(categoriesOpt); } boolean all = false; if (cmdLine.hasOption(allOpt)) { all = true; } boolean removeLabels = false; if (cmdLine.hasOption(removeLabelOpt)) { removeLabels = true; } runJob(inputPath, outputPath, catFile, cmdLine.hasOption(exactMatchOpt), all, removeLabels); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } catch (InterruptedException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } catch (ClassNotFoundException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:org.apache.mahout.utils.nlp.collocations.llr.CollocDriver.java
@Override public int run(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription("The Path for input files.").withShortName("i").create(); Option outputOpt = obuilder.withLongName("output").withRequired(true) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The Path write output to").withShortName("o").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:2") .withShortName("ng").create(); Option minSupportOpt = obuilder.withLongName("minSupport").withRequired(false) .withArgument(abuilder.withName("minSupport").withMinimum(1).withMaximum(1).create()) .withDescription("(Optional) Minimum Support. Default Value: " + CollocReducer.DEFAULT_MIN_SUPPORT) .withShortName("s").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").withRequired(false) .withArgument(abuilder.withName("numReducers").withMinimum(1).withMaximum(1).create()) .withDescription(/* w w w. j a v a 2 s . c om*/ "(Optional) Number of reduce tasks. Default Value: " + DEFAULT_PASS1_NUM_REDUCE_TASKS) .withShortName("nr").create(); Option preprocessOpt = obuilder.withLongName("preprocess").withRequired(false) .withDescription("If set, input is SequenceFile<Text,Text> where the value is the document, " + " which will be tokenized using the specified analyzer.") .withShortName("p").create(); Option unigramOpt = obuilder.withLongName("unigram").withRequired(false) .withDescription("If set, unigrams will be emitted in the final output alongside collocations") .withShortName("u").create(); Option overwriteOutput = obuilder.withLongName("overwrite").withRequired(false) .withDescription("If set, overwrite the output directory").withShortName("w").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 helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt) .withOption(maxNGramSizeOpt).withOption(overwriteOutput).withOption(minSupportOpt) .withOption(minLLROpt).withOption(numReduceTasksOpt).withOption(analyzerNameOpt) .withOption(preprocessOpt).withOption(unigramOpt).withOption(helpOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return 1; } Path input = new Path(cmdLine.getValue(inputOpt).toString()); Path output = new Path(cmdLine.getValue(outputOpt).toString()); int maxNGramSize = DEFAULT_MAX_NGRAM_SIZE; 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.overwriteOutput(output); } int minSupport = CollocReducer.DEFAULT_MIN_SUPPORT; if (cmdLine.hasOption(minSupportOpt)) { minSupport = Integer.parseInt(cmdLine.getValue(minSupportOpt).toString()); } log.info("Minimum Support value: {}", minSupport); 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 = DEFAULT_PASS1_NUM_REDUCE_TASKS; if (cmdLine.hasOption(numReduceTasksOpt)) { reduceTasks = Integer.parseInt(cmdLine.getValue(numReduceTasksOpt).toString()); } log.info("Number of pass1 reduce tasks: {}", reduceTasks); boolean emitUnigrams = cmdLine.hasOption(unigramOpt); if (cmdLine.hasOption(preprocessOpt)) { log.info("Input will be preprocessed"); 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 analyzerClass.newInstance(); } Path tokenizedPath = new Path(output, DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); DocumentProcessor.tokenizeDocuments(input, analyzerClass, tokenizedPath); input = tokenizedPath; } else { log.info("Input will NOT be preprocessed"); } // parse input and extract collocations long ngramCount = generateCollocations(input, output, emitUnigrams, maxNGramSize, reduceTasks, minSupport); // tally collocations and perform LLR calculation computeNGramsPruneByLLR(ngramCount, output, emitUnigrams, minLLRValue, reduceTasks); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); return 1; } return 0; }
From source file:org.apache.mahout.utils.vectors.arff.Driver.java
public static void main(String[] args) throws IOException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription(/* www.ja va2 s . co m*/ "The file or directory containing the ARFF files. If it is a directory, all .arff files will be converted") .withShortName("d").create(); Option outputOpt = obuilder.withLongName("output").withRequired(true) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription( "The output directory. Files will have the same name as the input, but with the extension .mvc") .withShortName("o").create(); Option maxOpt = obuilder.withLongName("max").withRequired(false) .withArgument(abuilder.withName("max").withMinimum(1).withMaximum(1).create()) .withDescription( "The maximum number of vectors to output. If not specified, then it will loop over all docs") .withShortName("m").create(); Option dictOutOpt = obuilder.withLongName("dictOut").withRequired(true) .withArgument(abuilder.withName("dictOut").withMinimum(1).withMaximum(1).create()) .withDescription("The file to output the label bindings").withShortName("t").create(); Option jsonDictonaryOpt = obuilder.withLongName("json-dictonary").withRequired(false) .withDescription("Write dictonary in JSON format").withShortName("j").create(); Option delimiterOpt = obuilder.withLongName("delimiter").withRequired(false) .withArgument(abuilder.withName("delimiter").withMinimum(1).withMaximum(1).create()) .withDescription("The delimiter for outputing the dictionary").withShortName("l").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(maxOpt) .withOption(helpOpt).withOption(dictOutOpt).withOption(jsonDictonaryOpt).withOption(delimiterOpt) .create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } if (cmdLine.hasOption(inputOpt)) { // Lucene case File input = new File(cmdLine.getValue(inputOpt).toString()); long maxDocs = Long.MAX_VALUE; if (cmdLine.hasOption(maxOpt)) { maxDocs = Long.parseLong(cmdLine.getValue(maxOpt).toString()); } if (maxDocs < 0) { throw new IllegalArgumentException("maxDocs must be >= 0"); } String outDir = cmdLine.getValue(outputOpt).toString(); log.info("Output Dir: {}", outDir); String delimiter = cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString() : "\t"; File dictOut = new File(cmdLine.getValue(dictOutOpt).toString()); boolean jsonDictonary = cmdLine.hasOption(jsonDictonaryOpt); ARFFModel model = new MapBackedARFFModel(); if (input.exists() && input.isDirectory()) { File[] files = input.listFiles(new FilenameFilter() { @Override public boolean accept(File file, String name) { return name.endsWith(".arff"); } }); for (File file : files) { writeFile(outDir, file, maxDocs, model, dictOut, delimiter, jsonDictonary); } } else { writeFile(outDir, input, maxDocs, model, dictOut, delimiter, jsonDictonary); } } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:org.apache.mahout.utils.vectors.libsvm.Driver.java
/** * The main method.// ww w. j a v a 2 s. c o m * * @param args the arguments * @throws IOException Signals that an I/O exception has occurred. */ public static void main(String[] args) throws IOException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription( "The file or directory containing the ARFF files. If it is a directory, all .arff files will be converted") .withShortName("d").create(); Option outputOpt = obuilder.withLongName("output").withRequired(true) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription( "The output directory. Files will have the same name as the input, but with the extension .mvc") .withShortName("o").create(); Option maxOpt = obuilder.withLongName("max").withRequired(false) .withArgument(abuilder.withName("max").withMinimum(1).withMaximum(1).create()) .withDescription( "The maximum number of vectors to output. If not specified, then it will loop over all docs") .withShortName("m").create(); Option dictOutOpt = obuilder.withLongName("dictOut").withRequired(true) .withArgument(abuilder.withName("dictOut").withMinimum(1).withMaximum(1).create()) .withDescription("The file to output the label bindings").withShortName("t").create(); Option outWriterOpt = obuilder.withLongName("outputWriter").withRequired(false) .withArgument(abuilder.withName("outputWriter").withMinimum(1).withMaximum(1).create()) .withDescription( "The VectorWriter to use, either seq (SequenceFileVectorWriter - default) or file (Writes to a File using JSON format)") .withShortName("e").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(maxOpt) .withOption(helpOpt).withOption(dictOutOpt).withOption(outWriterOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } if (cmdLine.hasOption(inputOpt)) {// Lucene case File input = new File(cmdLine.getValue(inputOpt).toString()); long maxDocs = Long.MAX_VALUE; if (cmdLine.hasOption(maxOpt)) { maxDocs = Long.parseLong(cmdLine.getValue(maxOpt).toString()); } if (maxDocs < 0) { throw new IllegalArgumentException("maxDocs must be >= 0"); } String outDir = cmdLine.getValue(outputOpt).toString(); Driver.log.info("Output Dir: {}", outDir); String outWriter = null; if (cmdLine.hasOption(outWriterOpt)) { outWriter = cmdLine.getValue(outWriterOpt).toString(); } File dictOut = new File(cmdLine.getValue(dictOutOpt).toString()); List<Double> labels = new ArrayList<Double>(); if (input.exists() && input.isDirectory()) { File[] files = input.listFiles(); for (File file : files) { // Driver.writeFile(outWriter, outDir, file, maxDocs, labels); } } else { // Driver.writeFile(outWriter, outDir, input, maxDocs, labels); } Driver.log.info("Dictionary Output file: {}", dictOut); BufferedWriter writer = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(dictOut), Charset.forName("UTF8"))); for (Double label : labels) { writer.append(label.toString()).append('\n'); } writer.close(); } } catch (OptionException e) { Driver.log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:org.apache.mahout.utils.vectors.lucene.ClusterLabels.java
public static void main(String[] args) { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option indexOpt = obuilder.withLongName("dir").withRequired(true) .withArgument(abuilder.withName("dir").withMinimum(1).withMaximum(1).create()) .withDescription("The Lucene index directory").withShortName("d").create(); Option outputOpt = obuilder.withLongName("output").withRequired(false) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output file. If not specified, the result is printed on console.") .withShortName("o").create(); Option fieldOpt = obuilder.withLongName("field").withRequired(true) .withArgument(abuilder.withName("field").withMinimum(1).withMaximum(1).create()) .withDescription("The content field in the index").withShortName("f").create(); Option idFieldOpt = obuilder.withLongName("idField").withRequired(false) .withArgument(abuilder.withName("idField").withMinimum(1).withMaximum(1).create()) .withDescription(//from www.ja v a2s . co m "The field for the document ID in the index. If null, then the Lucene internal doc " + "id is used which is prone to error if the underlying index changes") .withShortName("i").create(); Option seqOpt = obuilder.withLongName("seqFileDir").withRequired(true) .withArgument(abuilder.withName("seqFileDir").withMinimum(1).withMaximum(1).create()) .withDescription("The directory containing Sequence Files for the Clusters").withShortName("s") .create(); Option pointsOpt = obuilder.withLongName("pointsDir").withRequired(true) .withArgument(abuilder.withName("pointsDir").withMinimum(1).withMaximum(1).create()) .withDescription( "The directory containing points sequence files mapping input vectors to their cluster. ") .withShortName("p").create(); Option minClusterSizeOpt = obuilder.withLongName("minClusterSize").withRequired(false) .withArgument(abuilder.withName("minClusterSize").withMinimum(1).withMaximum(1).create()) .withDescription("The minimum number of points required in a cluster to print the labels for") .withShortName("m").create(); Option maxLabelsOpt = obuilder.withLongName("maxLabels").withRequired(false) .withArgument(abuilder.withName("maxLabels").withMinimum(1).withMaximum(1).create()) .withDescription("The maximum number of labels to print per cluster").withShortName("x").create(); Option helpOpt = DefaultOptionCreator.helpOption(); Group group = gbuilder.withName("Options").withOption(indexOpt).withOption(idFieldOpt).withOption(outputOpt) .withOption(fieldOpt).withOption(seqOpt).withOption(pointsOpt).withOption(helpOpt) .withOption(maxLabelsOpt).withOption(minClusterSizeOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } Path seqFileDir = new Path(cmdLine.getValue(seqOpt).toString()); Path pointsDir = new Path(cmdLine.getValue(pointsOpt).toString()); String indexDir = cmdLine.getValue(indexOpt).toString(); String contentField = cmdLine.getValue(fieldOpt).toString(); String idField = null; if (cmdLine.hasOption(idFieldOpt)) { idField = cmdLine.getValue(idFieldOpt).toString(); } String output = null; if (cmdLine.hasOption(outputOpt)) { output = cmdLine.getValue(outputOpt).toString(); } int maxLabels = DEFAULT_MAX_LABELS; if (cmdLine.hasOption(maxLabelsOpt)) { maxLabels = Integer.parseInt(cmdLine.getValue(maxLabelsOpt).toString()); } int minSize = DEFAULT_MIN_IDS; if (cmdLine.hasOption(minClusterSizeOpt)) { minSize = Integer.parseInt(cmdLine.getValue(minClusterSizeOpt).toString()); } ClusterLabels clusterLabel = new ClusterLabels(seqFileDir, pointsDir, indexDir, contentField, minSize, maxLabels); if (idField != null) { clusterLabel.setIdField(idField); } if (output != null) { clusterLabel.setOutput(output); } clusterLabel.getLabels(); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } catch (IOException e) { log.error("Exception", e); } }
From source file:org.apache.mahout.utils.vectors.lucene.Driver.java
public static void main(String[] args) throws IOException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("dir").withRequired(true) .withArgument(abuilder.withName("dir").withMinimum(1).withMaximum(1).create()) .withDescription("The Lucene directory").withShortName("d").create(); Option outputOpt = obuilder.withLongName("output").withRequired(true) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output file").withShortName("o").create(); Option fieldOpt = obuilder.withLongName("field").withRequired(true) .withArgument(abuilder.withName("field").withMinimum(1).withMaximum(1).create()) .withDescription("The field in the index").withShortName("f").create(); Option idFieldOpt = obuilder.withLongName("idField").withRequired(false) .withArgument(abuilder.withName("idField").withMinimum(1).withMaximum(1).create()) .withDescription(/* www . ja va2 s. co m*/ "The field in the index containing the index. If null, then the Lucene internal doc " + "id is used which is prone to error if the underlying index changes") .create(); Option dictOutOpt = obuilder.withLongName("dictOut").withRequired(true) .withArgument(abuilder.withName("dictOut").withMinimum(1).withMaximum(1).create()) .withDescription("The output of the dictionary").withShortName("t").create(); Option seqDictOutOpt = obuilder.withLongName("seqDictOut").withRequired(false) .withArgument(abuilder.withName("seqDictOut").withMinimum(1).withMaximum(1).create()) .withDescription("The output of the dictionary as sequence file").withShortName("st").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("w").create(); Option delimiterOpt = obuilder.withLongName("delimiter").withRequired(false) .withArgument(abuilder.withName("delimiter").withMinimum(1).withMaximum(1).create()) .withDescription("The delimiter for outputting the dictionary").withShortName("l").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 double 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 maxOpt = obuilder.withLongName("max").withRequired(false) .withArgument(abuilder.withName("max").withMinimum(1).withMaximum(1).create()) .withDescription( "The maximum number of vectors to output. If not specified, then it will loop over all docs") .withShortName("m").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( "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.") .withShortName("x").create(); Option maxPercentErrorDocsOpt = obuilder.withLongName("maxPercentErrorDocs").withRequired(false) .withArgument(abuilder.withName("maxPercentErrorDocs").withMinimum(1).withMaximum(1).create()) .withDescription( "The max percentage of docs that can have a null term vector. These are noise document and can occur if the " + "analyzer used strips out all terms in the target field. This percentage is expressed as a value " + "between 0 and 1. The default is 0.") .withShortName("err").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(idFieldOpt).withOption(outputOpt) .withOption(delimiterOpt).withOption(helpOpt).withOption(fieldOpt).withOption(maxOpt) .withOption(dictOutOpt).withOption(seqDictOutOpt).withOption(powerOpt).withOption(maxDFPercentOpt) .withOption(weightOpt).withOption(minDFOpt).withOption(maxPercentErrorDocsOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } if (cmdLine.hasOption(inputOpt)) { // Lucene case Driver luceneDriver = new Driver(); luceneDriver.setLuceneDir(cmdLine.getValue(inputOpt).toString()); if (cmdLine.hasOption(maxOpt)) { luceneDriver.setMaxDocs(Long.parseLong(cmdLine.getValue(maxOpt).toString())); } if (cmdLine.hasOption(weightOpt)) { luceneDriver.setWeightType(cmdLine.getValue(weightOpt).toString()); } luceneDriver.setField(cmdLine.getValue(fieldOpt).toString()); if (cmdLine.hasOption(minDFOpt)) { luceneDriver.setMinDf(Integer.parseInt(cmdLine.getValue(minDFOpt).toString())); } if (cmdLine.hasOption(maxDFPercentOpt)) { luceneDriver.setMaxDFPercent(Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString())); } if (cmdLine.hasOption(powerOpt)) { String power = cmdLine.getValue(powerOpt).toString(); if ("INF".equals(power)) { luceneDriver.setNorm(Double.POSITIVE_INFINITY); } else { luceneDriver.setNorm(Double.parseDouble(power)); } } if (cmdLine.hasOption(idFieldOpt)) { luceneDriver.setIdField(cmdLine.getValue(idFieldOpt).toString()); } if (cmdLine.hasOption(maxPercentErrorDocsOpt)) { luceneDriver.setMaxPercentErrorDocs( Double.parseDouble(cmdLine.getValue(maxPercentErrorDocsOpt).toString())); } luceneDriver.setOutFile(cmdLine.getValue(outputOpt).toString()); luceneDriver.setDelimiter( cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString() : "\t"); luceneDriver.setDictOut(cmdLine.getValue(dictOutOpt).toString()); if (cmdLine.hasOption(seqDictOutOpt)) { luceneDriver.setSeqDictOut(cmdLine.getValue(seqDictOutOpt).toString()); } luceneDriver.dumpVectors(); } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:org.apache.mahout.utils.vectors.lucene.SeqFilePrint.java
public static void main(String[] args) throws OptionException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("inputFile").withRequired(true) .withArgument(abuilder.withName("inputFile").withMinimum(1).withMaximum(1).create()) .withDescription("The output of the dictionary as sequence file").withShortName("inputFile") .create();//from www.j av a2 s .c o m Option outFileOpt = obuilder.withLongName("outFile").withRequired(true) .withArgument(abuilder.withName("outfolder").withMinimum(1).withMaximum(1).create()) .withDescription("The output of the dictionary as sequence file").withShortName("outFile").create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outFileOpt).create(); SeqFilePrint seqFilePrint = new SeqFilePrint(); Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(inputOpt)) { seqFilePrint.setInputSeqFile(cmdLine.getValue(inputOpt).toString()); } if (cmdLine.hasOption(outFileOpt)) { seqFilePrint.setOutFile(cmdLine.getValue(outFileOpt).toString()); } try { seqFilePrint.run(args); } catch (Exception ex) { Logger.getLogger(SeqFilePrint.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:org.apache.mahout.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. Default Value: 100MB").withShortName("chunk") .create();/* w w w.ja v a 2s .c o m*/ 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. Default: 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( "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 " + "than 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 = StandardAnalyzer.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 AnalyzerUtils.createAnalyzer(analyzerClass); } 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; } log.info("Tokenizing documents in {}", inputDir); 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 || maxDFPercent > 0.00; String tfDirName = shouldPrune ? DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER + "-toprune" : DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER; log.info("Creating Term Frequency Vectors"); if (processIdf) { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, -1.0f, false, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } else { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, norm, logNormalize, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } Pair<Long[], List<Path>> docFrequenciesFeatures = null; // Should document frequency features be processed if (shouldPrune || processIdf) { log.info("Calculating IDF"); 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) { long vectorCount = docFrequenciesFeatures.getFirst()[1]; if (maxDFSigma >= 0.0) { 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); maxDF = (int) (100.0 * maxDFSigma * stdDev / vectorCount); } long maxDFThreshold = (long) (vectorCount * (maxDF / 100.0f)); // 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"); log.info("Pruning"); if (processIdf) { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDFThreshold, minDf, conf, docFrequenciesFeatures, -1.0f, false, reduceTasks); } else { HighDFWordsPruner.pruneVectors(tfDir, prunedTFDir, prunedPartialTFDir, maxDFThreshold, minDf, 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:org.mzd.shap.spring.cli.CommandLineApplication.java
protected CommandLineApplication(Group optionGroup) { this.clParser = new Parser(); this.clParser.setHelpFormatter(new HelpFormatter()); this.clParser.setHelpTrigger("--help"); this.clParser.setGroup(optionGroup); }
From source file:org.opencloudengine.flamingo.mapreduce.core.AbstractJob.java
/** * ? ??? ./* www. j ava 2 s .c o m*/ * ? <tt>-h</tt> ? ??? <tt>null</tt>? . * * @param args ?? * @return ?? ??? ? ? {@code Map<String,String>}. * ??? key ? ? ? '--'? prefix . * ? ? {@code Map<String,String>} ? ? ? '--'? ??? . */ public Map<String, String> parseArguments(String[] args) throws Exception { Option helpOpt = addOption(DefaultOptionCreator.helpOption()); addOption("tempDir", null, " ", false); addOption("startPhase", null, " ", "0"); addOption("endPhase", null, " ", String.valueOf(Integer.MAX_VALUE)); GroupBuilder groupBuilder = new GroupBuilder().withName("Hadoop MapReduce Job :"); for (Option opt : options) { groupBuilder = groupBuilder.withOption(opt); } Group group = groupBuilder.create(); CommandLine cmdLine; try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); cmdLine = parser.parse(args); } catch (OptionException e) { log.error(e.getMessage()); CommandLineUtil.printHelpWithGenericOptions(group, e); return null; } if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelpWithGenericOptions(group); return null; } try { parseDirectories(cmdLine); } catch (IllegalArgumentException e) { log.error(e.getMessage()); CommandLineUtil.printHelpWithGenericOptions(group); return null; } argMap = new TreeMap<String, String>(); maybePut(argMap, cmdLine, this.options.toArray(new Option[this.options.size()])); log.info("Command line arguments: ", argMap); Set<String> keySet = argMap.keySet(); for (Iterator<String> iterator = keySet.iterator(); iterator.hasNext();) { String key = iterator.next(); log.info(" {} = {}", key, argMap.get(key)); } return argMap; }