List of usage examples for org.apache.mahout.vectorizer HighDFWordsPruner STD_CALC_DIR
String STD_CALC_DIR
To view the source code for org.apache.mahout.vectorizer HighDFWordsPruner STD_CALC_DIR.
Click Source Link
From source file:com.caseystella.ingest.SparseVectorsFromSequenceFiles.java
License:Apache License
@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 ww . j a v a 2s . 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; }
From source file:com.digitalpebble.behemoth.mahout.SparseVectorsFromBehemoth.java
License:Apache License
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 typeNameOpt = obuilder.withLongName("typeToken").withRequired(false) .withArgument(abuilder.withName("typeToken").withMinimum(1).withMaximum(1).create()) .withDescription("The annotation type for Tokens").withShortName("t").create(); Option featureNameOpt = obuilder.withLongName("featureName").withRequired(false) .withArgument(abuilder.withName("featureName").withMinimum(1).withMaximum(1).create()) .withDescription(//from www . java 2 s . co m "The name of the feature containing the token values, uses the text if unspecified") .withShortName("f").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( "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 labelMDOpt = obuilder.withLongName("labelMDKey").withRequired(false) .withArgument(abuilder.withName("label_md_key").create()) .withDescription("Document metadata holding the label").withShortName("label").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(minSupportOpt).withOption(typeNameOpt) .withOption(featureNameOpt).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).withOption(labelMDOpt).create(); CommandLine cmdLine = null; try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return -1; } if (!cmdLine.hasOption(inputDirOpt)) { CommandLineUtil.printHelp(group); return -1; } if (!cmdLine.hasOption(outputDirOpt)) { CommandLineUtil.printHelp(group); return -1; } } catch (OptionException e) { log.error("Exception", e); 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); } String type = null; String featureName = ""; if (cmdLine.hasOption(typeNameOpt)) { type = cmdLine.getValue(typeNameOpt).toString(); Object tempFN = cmdLine.getValue(featureNameOpt); if (tempFN != null) { featureName = tempFN.toString(); log.info("Getting tokens from " + type + "." + featureName.toString()); } else log.info("Getting tokens from " + type); } 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; } String labelMDKey = null; if (cmdLine.hasOption(labelMDOpt)) { labelMDKey = cmdLine.getValue(labelMDOpt).toString(); } Configuration conf = getConf(); Path tokenizedPath = new Path(outputDir, DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); // no annotation type degfin if (type != null) { BehemothDocumentProcessor.tokenizeDocuments(inputDir, type, featureName, tokenizedPath); } // no annotation type defined : rely on Lucene's analysers else { BehemothDocumentProcessor.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; try { 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); } // dump labels? if (labelMDKey != null) { conf.set(BehemothDocumentProcessor.MD_LABEL, labelMDKey); BehemothDocumentProcessor.dumpLabels(inputDir, new Path(outputDir, "labels"), conf); } } catch (RuntimeException e) { log.error("Exception caught", e); return -1; } return 0; }
From source file:com.elex.dmp.vectorizer.SparseVectorsFromSequenceFiles.java
License:Apache License
@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(/* w ww. j a v a 2 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
License:Apache License
@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 ww 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(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.ml.hadoop.nlp.SparseVectorsFromSequenceFiles.java
License:Apache License
@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 dictionaryPathOpt = obuilder.withLongName("dictionaryPath") .withArgument(abuilder.withName("dictionaryPath").withMinimum(1).withMaximum(1).create()) .withDescription("Dictionary path for update TFIDF").withShortName("dp").create(); Option docFrequencyPathOpt = obuilder.withLongName("docFrequencyPath") .withArgument(abuilder.withName("docFrequencyPath").withMinimum(1).withMaximum(1).create()) .withDescription("Doc frequency path for update TFIDF").withShortName("dfp").create(); Option tfVectorsPathOpt = obuilder.withLongName("tfVectorsPath") .withArgument(abuilder.withName("tfVectorsPath").withMinimum(1).withMaximum(1).create()) .withDescription("TF Vectors path").withShortName("tfvp").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 , TFIDF or TFIDF_UPDATE") .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(// www .j a v a2 s. c om "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(dictionaryPathOpt).withOption(docFrequencyPathOpt).withOption(tfVectorsPathOpt) .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("Changed... 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); } //default process tfidf:1, tf:2, update tfidf:3 int processIdf; if (cmdLine.hasOption(weightOpt)) { String wString = cmdLine.getValue(weightOpt).toString(); if ("tf".equalsIgnoreCase(wString)) { processIdf = 2; } else if ("tfidf".equalsIgnoreCase(wString)) { processIdf = 1; } else if ("tfidf_update".equalsIgnoreCase(wString)) { processIdf = 3; } else { throw new OptionException(weightOpt); } } else { processIdf = 1; } 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); 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, prune {}", shouldPrune); String dictionaryPath = null; if (cmdLine.hasOption(dictionaryPathOpt)) { dictionaryPath = (String) cmdLine.getValue(dictionaryPathOpt); log.info("begin dic path {}", dictionaryPath); } if (processIdf == 1) { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, -1.0f, false, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } else if (processIdf == 3) { log.info("begin update term----------------"); DictionaryVectorizer.createUpdateTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, maxNGramSize, dictionaryPath, norm, logNormalize, reduceTasks, sequentialAccessOutput, namedVectors); } else { DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath, outputDir, tfDirName, conf, minSupport, maxNGramSize, minLLRValue, norm, logNormalize, reduceTasks, chunkSize, sequentialAccessOutput, namedVectors); } String docFrequencyPaths = null; if (cmdLine.hasOption(dictionaryPathOpt)) { docFrequencyPaths = (String) cmdLine.getValue(docFrequencyPathOpt); log.info("doc frequency path {}", docFrequencyPaths); } String tfVectorsPaths = null; if (cmdLine.hasOption(tfVectorsPathOpt)) { tfVectorsPaths = (String) cmdLine.getValue(tfVectorsPathOpt); log.info("tf vectors path {}", tfVectorsPaths); } Pair<Long[], List<Path>> docFrequenciesFeatures = null; // Should document frequency features be processed if (processIdf == 1) { log.info("Calculating IDF"); docFrequenciesFeatures = TFIDFConverter.calculateDF(new Path(outputDir, tfDirName), outputDir, conf, chunkSize); log.info("...docFrequencyPathBase {}, docFrequencyFile {}", docFrequenciesFeatures.getFirst()[0], docFrequenciesFeatures.getFirst()[1]); } else if (processIdf == 3) { // load docFrequency path List<Path> docFrequencyChunks = Lists.newArrayList(); String[] paths = docFrequencyPaths.split(","); long featureCount = 0; for (String path : paths) { int splitPos = path.lastIndexOf("/"); String docFrequencyPathBase = path.substring(0, splitPos); String docFrequencyFile = path.substring(splitPos + 1, path.length()); log.info("docFrequencyPathBase {}, docFrequencyFile {}", docFrequencyPathBase, docFrequencyFile); Path docFrequencyPath = new Path(docFrequencyPathBase, docFrequencyFile); docFrequencyChunks.add(docFrequencyPath); /*for (Pair<IntWritable, LongWritable> record : new SequenceFileIterable<IntWritable, LongWritable>(docFrequencyPath, true, conf)) { featureCount = Math.max(record.getFirst().get(), featureCount); }*/ } featureCount = 107623; featureCount++; long vectorCount = Long.MAX_VALUE; /*Path tfDirPath = new Path(tfVectorsPaths + "/part-r-00000"); int i = 0; for (Pair<Text, VectorWritable> record : new SequenceFileIterable<Text, VectorWritable>(tfDirPath, true, conf)) { i++; } if (i > 0) { vectorCount = i; }*/ vectorCount = 80000; //read docFrequencyFile to get featureCount and vectorCount Long[] counts = { featureCount, vectorCount }; log.info("featureCount {}, vectorCount------------------ {}", featureCount, vectorCount); docFrequenciesFeatures = new Pair<Long[], List<Path>>(counts, docFrequencyChunks); } 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 == 1 || processIdf == 3) { 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 == 1 || processIdf == 3) { 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.netease.news.vectorizer.SparseVectorsFromSequenceFiles.java
License:Apache License
@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 www . ja v a2s . com "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 = IKAnalyzer.class; // 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:edu.indiana.d2i.htrc.io.SparseVectorsFromTokenizedDoc.java
License:Apache License
@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 www .j a v a 2s . c om*/ "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; } /* modification starts here */ Configuration conf = getConf(); // Path tokenizedPath = new Path(outputDir, // DocumentProcessor.TOKENIZED_DOCUMENT_OUTPUT_FOLDER); // DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, // tokenizedPath, conf); Path tokenizedPath = inputDir; /* end modification */ 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, 0.0D, conf); maxDF = (int) (maxDFSigma * stdDev); // 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:mahout.vectorizer.SparseVectorsFromSequenceFiles.java
License:Apache License
@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 .j av a 2 s .c om*/ "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; } 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, -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) { 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; }