List of usage examples for java.io BufferedWriter close
@SuppressWarnings("try") public void close() throws IOException
From source file:edu.cmu.lti.oaqa.knn4qa.apps.FilterVocabulary.java
public static void main(String[] args) { String optKeys[] = { IN_VOC_FILE_PARAM, OUT_VOC_FILE_PARAM, CommonParams.MEM_FWD_INDEX_PARAM, CommonParams.MAX_WORD_QTY_PARAM }; String optDescs[] = { IN_VOC_FILE_DESC, OUT_VOC_FILE_DESC, CommonParams.MEM_FWD_INDEX_DESC, CommonParams.MAX_WORD_QTY_DESC }; boolean hasArg[] = { true, true, true, true }; ParamHelper mParamHelper = null;/*from w ww . j av a 2 s . c o m*/ try { mParamHelper = new ParamHelper(args, optKeys, optDescs, hasArg); CommandLine cmd = mParamHelper.getCommandLine(); String outputFile = cmd.getOptionValue(OUT_VOC_FILE_PARAM); if (null == outputFile) { UsageSpecify(OUT_VOC_FILE_DESC, mParamHelper.getOptions()); } String inputFile = cmd.getOptionValue(IN_VOC_FILE_PARAM); if (null == inputFile) { UsageSpecify(IN_VOC_FILE_DESC, mParamHelper.getOptions()); } int maxWordQty = Integer.MAX_VALUE; String tmpi = cmd.getOptionValue(CommonParams.MAX_WORD_QTY_PARAM); if (null != tmpi) { maxWordQty = Integer.parseInt(tmpi); } String memFwdIndxName = cmd.getOptionValue(CommonParams.MEM_FWD_INDEX_PARAM); if (null == memFwdIndxName) { UsageSpecify(CommonParams.MEM_FWD_INDEX_DESC, mParamHelper.getOptions()); } VocabularyFilterAndRecoder filter = new FrequentIndexWordFilterAndRecoder(memFwdIndxName, maxWordQty); BufferedReader finp = new BufferedReader( new InputStreamReader(CompressUtils.createInputStream(inputFile))); BufferedWriter fout = new BufferedWriter( new OutputStreamWriter(CompressUtils.createOutputStream(outputFile))); try { String line; int wordQty = 0; long addedQty = 0; long totalQty = 0; for (totalQty = 0; (line = finp.readLine()) != null;) { ++totalQty; // Skip empty lines line = line.trim(); if (line.isEmpty()) continue; GizaVocRec rec = new GizaVocRec(line); if (filter.checkWord(rec.mWord)) { rec.save(fout); addedQty++; } if (totalQty % REPORT_INTERVAL_QTY == 0) System.out.println(String.format( "Processed %d lines (%d source word entries) from '%s', added %d lines", totalQty, wordQty, inputFile, addedQty)); } } finally { finp.close(); fout.close(); } } catch (ParseException e) { Usage("Cannot parse arguments", mParamHelper != null ? mParamHelper.getOptions() : null); e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); System.err.println("Terminating due to an exception: " + e); System.exit(1); } }
From source file:fr.eo.util.dumper.Dumper.java
/** * @param args//from www .j av a 2 s. co m */ public static void main(String[] args) { String appName = args[0]; System.out.println("Starting dumper ..."); Statement stmt = null; try { System.out.println("Getting database connection ..."); Connection conn = getJtdsConnection(); List<RequestDefinitionBean> requests = RequestDefinitionParser.getRequests(appName); assetFolder = RequestDefinitionParser.getAppBaseDir(appName) + "assets/"; for (RequestDefinitionBean request : requests) { int currentFileSize = 0, cpt = 1; stmt = conn.createStatement(); System.out.println("Dumping " + request.name + "..."); ResultSet rs = stmt.executeQuery(request.sql); BufferedWriter bw = getWriter(request.name, cpt); bw.append(COPYRIGHTS); currentFileSize += COPYRIGHTS.length(); bw.append("--" + request.name + "\n"); while (rs.next()) { StringBuilder sb = new StringBuilder(); sb.append("INSERT INTO "); sb.append(request.table).append(" VALUES ("); int pos = 0; for (String fieldName : request.fields) { String str = getFieldValue(request, pos, rs, fieldName); sb.append(str); pos++; if (pos < request.fields.size()) { sb.append(","); } } sb.append(");\n"); currentFileSize += sb.length(); bw.append(sb.toString()); bw.flush(); if (currentFileSize > MAX_FILE_SIZE) { bw.close(); bw = getWriter(request.name, ++cpt); bw.append(COPYRIGHTS); bw.append("--" + request.name + "\n"); currentFileSize = COPYRIGHTS.length(); } } bw.flush(); bw.close(); } System.out.println("done."); } catch (SQLException e) { e.printStackTrace(); } catch (ClassNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { if (stmt != null) { try { stmt.close(); } catch (SQLException e) { e.printStackTrace(); } } } DumpFilesDescriptor descriptor = new DumpFilesDescriptor(); descriptor.lineNumbers = getDumpLinesNumber(); descriptor.dumpFileNames = dumpFileNames; writeDescriptorFile(descriptor); System.out.println("nb :" + descriptor.lineNumbers); }
From source file:io.druid.query.aggregation.datasketches.quantiles.GenerateTestData.java
public static void main(String[] args) throws Exception { Path buildPath = FileSystems.getDefault().getPath("doubles_build_data.tsv"); Path sketchPath = FileSystems.getDefault().getPath("doubles_sketch_data.tsv"); BufferedWriter buildData = Files.newBufferedWriter(buildPath, StandardCharsets.UTF_8); BufferedWriter sketchData = Files.newBufferedWriter(sketchPath, StandardCharsets.UTF_8); Random rand = new Random(); int sequenceNumber = 0; for (int i = 0; i < 20; i++) { int product = rand.nextInt(10); UpdateDoublesSketch sketch = UpdateDoublesSketch.builder().build(); for (int j = 0; j < 20; j++) { double value = rand.nextDouble(); buildData.write("2016010101"); buildData.write('\t'); buildData.write(Integer.toString(sequenceNumber)); // dimension with unique numbers for ingesting raw data buildData.write('\t'); buildData.write(Integer.toString(product)); // product dimension buildData.write('\t'); buildData.write(Double.toString(value)); buildData.newLine();//from ww w .jav a 2s. c om sketch.update(value); sequenceNumber++; } sketchData.write("2016010101"); sketchData.write('\t'); sketchData.write(Integer.toString(product)); // product dimension sketchData.write('\t'); sketchData.write(Base64.encodeBase64String(sketch.toByteArray(true))); sketchData.newLine(); } buildData.close(); sketchData.close(); }
From source file:PCC.java
/** * @param args the command line arguments * @throws java.io.IOException//from w ww .j ava 2 s. co m */ public static void main(String[] args) throws IOException { // TODO code application logic here PearsonsCorrelation corel = new PearsonsCorrelation(); PCC method = new PCC(); ArrayList<String> name = new ArrayList<>(); Multimap<String, String> genes = ArrayListMultimap.create(); BufferedWriter bw = new BufferedWriter(new FileWriter(args[1])); BufferedReader br = new BufferedReader(new FileReader(args[0])); String str; while ((str = br.readLine()) != null) { String[] a = str.split("\t"); name.add(a[0]); for (int i = 1; i < a.length; i++) { genes.put(a[0], a[i]); } } for (String key : genes.keySet()) { double[] first = new double[genes.get(key).size()]; int element1 = 0; for (String value : genes.get(key)) { double d = Double.parseDouble(value); first[element1] = d; element1++; } for (String key1 : genes.keySet()) { if (!key.equals(key1)) { double[] second = new double[genes.get(key1).size()]; int element2 = 0; for (String value : genes.get(key1)) { double d = Double.parseDouble(value); second[element2] = d; element2++; } double corrlation = corel.correlation(first, second); if (corrlation > 0.5) { bw.write(key + "\t" + key1 + "\t" + corrlation + "\t" + method.pvalue(corrlation, second.length) + "\n"); } } } } br.close(); bw.close(); }
From source file:di.uniba.it.tee2.wiki.Wikidump2Text.java
/** * @param args the command line arguments */// w w w .jav a 2 s.c om public static void main(String[] args) { try { CommandLine cmd = cmdParser.parse(options, args); if (cmd.hasOption("l") && cmd.hasOption("d") && cmd.hasOption("o")) { encoding = cmd.getOptionValue("e", "UTF-8"); int counter = 0; try { BufferedWriter writer = new BufferedWriter(new OutputStreamWriter( new GZIPOutputStream(new FileOutputStream(cmd.getOptionValue("o"))), "UTF-8")); WikipediaDumpIterator it = new WikipediaDumpIterator(new File(cmd.getOptionValue("d")), encoding); PageCleaner cleaner = PageCleanerWrapper.getInstance(cmd.getOptionValue("l")); while (it.hasNext()) { WikiPage wikiPage = it.next(); ParsedPage parsedPage = wikiPage.getParsedPage(); if (parsedPage != null) { String title = wikiPage.getTitle(); if (!title.matches(notValidTitle)) { if (parsedPage.getText() != null) { writer.append(cleaner.clean(parsedPage.getText())); writer.newLine(); writer.newLine(); counter++; if (counter % 10000 == 0) { System.out.println(counter); writer.flush(); } } } } } writer.flush(); writer.close(); } catch (Exception ex) { Logger.getLogger(Wikidump2Text.class.getName()).log(Level.SEVERE, null, ex); } System.out.println("Indexed pages: " + counter); } else { HelpFormatter helpFormatter = new HelpFormatter(); helpFormatter.printHelp("Wikipedia dump to text", options, true); } } catch (ParseException ex) { Logger.getLogger(Wikidump2Text.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:de.ipbhalle.metfrag.main.CommandLineTool.java
/** * @param args/* w ww .ja v a 2 s. c om*/ * @throws Exception */ public static void main(String[] args) { CommandLineParser parser = new PosixParser(); // create the Options Options options = new Options(); options.addOption("d", "database", true, "database: " + Databases.getString() + " (default: kegg)"); options.addOption("l", "localdb", true, "use a local database together with a settings file for candidate search (default: not used) note: only usable if pubchem database is selected (-d)"); options.addOption("a", "mzabs", true, "allowed absolute (Da) mass deviation of fragment and peak masses (default: 0.01)"); options.addOption("p", "mzppm", true, "allowed relative (ppm) mass deviation of fragment and peak masses (default: 10)"); options.addOption("s", "searchppm", true, "relative (ppm) mass deviation used for candidate search in given compound database (-d) (default: 10; not used by default if sdf database is selected (-d))\n"); options.addOption("n", "exactmass", true, "neutral mass of measured compound used for candidate search in database (-d) (mandatory)"); options.addOption("b", "biological", false, "only consider compounds including CHNOPS atoms (not used by default)"); options.addOption("i", "databaseids", true, "database ids of compounds used for in silico fragmentation (separated by ,) (not used by default; not used if sdf database is selected (-d)) note: given ids must be valid ids of given database (-d)"); options.addOption("t", "treedepth", true, "treedepth used for in silico fragmentation (default: 2) note: high values result in high computation time"); options.addOption("M", "mode", true, "mode used for measured ms/ms spectrum:\n" + Modes.getString() + "(default: 3)"); options.addOption("f", "formula", true, "molecular formula of measured compound used for candidate search in database (-d) (not used by default; not used if sdf database is selected (-d))"); options.addOption("B", "breakrings", false, "allow splitting of aromatic rings of candidate structures during in silico fragmentation (not used by default)"); options.addOption("F", "storefragments", false, "store in silico generated fragments of candidate molecules (not used by default)"); options.addOption("R", "resultspath", true, "directory where result files are stored (default: /tmp)"); options.addOption("L", "sdffile", true, "location of the local sdf file (mandatory if sdf database (-d) is selected)"); options.addOption("h", "help", false, "print help"); options.addOption("D", "spectrumfile", true, "file containing peak data (mandatory) note: commandline options overwrite parameters given in the spectrum data file"); options.addOption("T", "threads", true, "number of threads used for fragment calculation (default: number of available cpu cores)"); options.addOption("c", "chemspidertoken", true, "Token for ChemSpider database search (not used by default; only necessary (mandatory) if ChemSpider database (-d) is selected)"); options.addOption("v", "verbose", false, "get more output information during the processing (not used by default)"); options.addOption("S", "samplename", true, "name of the sample measured (mandatory) note: result files are stored with given value"); options.addOption("P", "saveparameters", false, "save used parameters (not used by default)"); options.addOption("e", "printexamplespecfile", false, "print an example spectrum data file (not used by default)"); options.addOption("C", "charge", true, "charge used in combination with mode (-M):\n" + Charges.getString() + " (default: 1)"); options.addOption("r", "range", true, "range of candidates that will be processed: N (first N), M-N (from M to N), M- (from M), -N (till N); if N is greater than the number of candidates it will be set accordingly"); // parse the command line arguments CommandLine line = null; try { line = parser.parse(options, args); } catch (ParseException e1) { System.out.println(e1.getMessage()); System.out.println("Error: Could not parse option parameters."); System.out.println("Use help -h (--help) for information."); System.exit(1); } if (line == null) { System.out.println("Error: Could not parse option parameters."); System.out.println("Use help -h (--help) for information."); System.exit(1); } if (checkInitialParamsPresent(line, options)) System.exit(0); if (!checkSpectrumFile(line)) { System.out.println("Error: Option parameters are not set correctly."); System.out.println("Use help -h (--help) for information."); System.exit(1); } if (!parseSpectrumFile(spectrumfile)) { System.out.println("Error: Could not correctly parse the spectrum data file."); System.out.println("Use help -h (--help) for information."); System.exit(1); } int successfulSet = setParameters(line, options); if (successfulSet == 2) System.exit(0); if (successfulSet != 0) { System.out.println("Error: Option parameters are not set correctly."); System.out.println("Use help -h (--help) for information."); System.exit(1); } boolean successfulChecked = true; if (successfulSet == 0) successfulChecked = checkParameters(); if (saveParametersIsSet) { try { BufferedWriter bwriter = new BufferedWriter(new FileWriter(new File( resultspath + System.getProperty("file.separator") + "parameters_" + sampleName + ".txt"))); bwriter.write(getParameters()); bwriter.close(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } } try { boolean isPositive = true; if (charge.getValue() == 2) isPositive = false; spec = new WrapperSpectrum(peaksString, mode.getValueWithOffset(), exactMass.getValue(), isPositive); } catch (Exception e) { System.out.println("Error: Could not parse spectrum correctly. Check the given peak list."); System.exit(1); } if (!successfulChecked) { System.out.println("Error: Option parameters are not set correctly."); System.out.println("Use help -h (--help) for information."); System.exit(1); } List<MetFragResult> results = null; String pathToStoreFrags = ""; if (storeFragments) pathToStoreFrags = resultspath; //run metfrag when all checks were successful if (usesdf) { try { if (verbose) { System.out.println("start fragmenter with local database"); System.out.println("using database " + database); } results = MetFrag.startConvenienceSDF(spec, mzabs.getValue(), mzppm.getValue(), searchppm.getValue(), true, breakRings, treeDepth.getValue(), true, true, true, false, Integer.MAX_VALUE, true, sdfFile, "", null, searchppmIsSet, pathToStoreFrags, numberThreads.getValue(), verbose, sampleName, onlyBiologicalCompounds); } catch (Exception e) { System.out.println("Error: " + e.getMessage()); System.out.println("Error: Could not perform in silico fragmentation step."); System.exit(1); } } else { try { if (verbose) { if (!localdbIsSet) System.out.println("start fragmenter with web database"); else System.out.println("start fragmenter with local database"); System.out.println("using database " + database); } results = MetFrag.startConvenience(database, databaseIDs, formula, exactMass.getValue(), spec, useProxy, mzabs.getValue(), mzppm.getValue(), searchppm.getValue(), true, breakRings, treeDepth.getValue(), true, false, true, false, startindex.getValue(), endindex.getValue(), true, pathToStoreFrags, numberThreads.getValue(), chemSpiderToken, verbose, sampleName, localdb, onlyBiologicalCompounds, dblink, dbuser, dbpass, uniquebyinchi); } catch (Exception e) { e.printStackTrace(); System.out.println("Error: " + e.getMessage()); System.out.println("Error: Could not perform in silico fragmentation step."); System.exit(1); } } saveResults(results); }
From source file:com.nextdoor.bender.S3SnsNotifier.java
public static void main(String[] args) throws ParseException, InterruptedException, IOException { formatter = DateTimeFormat.forPattern("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'").withZoneUTC(); /*//from w w w . ja v a2s. com * Parse cli arguments */ Options options = new Options(); options.addOption(Option.builder().longOpt("bucket").hasArg().required() .desc("Name of S3 bucket to list s3 objects from").build()); options.addOption(Option.builder().longOpt("key-file").hasArg().required() .desc("Local file of S3 keys to process").build()); options.addOption( Option.builder().longOpt("sns-arn").hasArg().required().desc("SNS arn to publish to").build()); options.addOption(Option.builder().longOpt("throttle-ms").hasArg() .desc("Amount of ms to wait between publishing to SNS").build()); options.addOption(Option.builder().longOpt("processed-file").hasArg() .desc("Local file to use to store procssed S3 object names").build()); options.addOption(Option.builder().longOpt("skip-processed").hasArg(false) .desc("Whether to skip S3 objects that have been processed").build()); options.addOption( Option.builder().longOpt("dry-run").hasArg(false).desc("If set do not publish to SNS").build()); CommandLineParser parser = new DefaultParser(); CommandLine cmd = parser.parse(options, args); String bucket = cmd.getOptionValue("bucket"); String keyFile = cmd.getOptionValue("key-file"); String snsArn = cmd.getOptionValue("sns-arn"); String processedFile = cmd.getOptionValue("processed-file", null); boolean skipProcessed = cmd.hasOption("skip-processed"); dryRun = cmd.hasOption("dry-run"); long throttle = Long.parseLong(cmd.getOptionValue("throttle-ms", "-1")); if (processedFile != null) { File file = new File(processedFile); if (!file.exists()) { logger.debug("creating local file to store processed s3 object names: " + processedFile); file.createNewFile(); } } /* * Import S3 keys that have been processed */ if (skipProcessed && processedFile != null) { try (BufferedReader br = new BufferedReader(new FileReader(processedFile))) { String line; while ((line = br.readLine()) != null) { alreadyPublished.add(line.trim()); } } } /* * Setup writer for file containing processed S3 keys */ FileWriter fw = null; BufferedWriter bw = null; if (processedFile != null) { fw = new FileWriter(processedFile, true); bw = new BufferedWriter(fw); } /* * Create clients */ AmazonS3Client s3Client = new AmazonS3Client(); AmazonSNSClient snsClient = new AmazonSNSClient(); /* * Get S3 object list */ try (BufferedReader br = new BufferedReader(new FileReader(keyFile))) { String line; while ((line = br.readLine()) != null) { String key = line.trim(); if (alreadyPublished.contains(key)) { logger.info("skipping " + key); } ObjectMetadata om = s3Client.getObjectMetadata(bucket, key); S3EventNotification s3Notification = getS3Notification(key, bucket, om.getContentLength()); String json = s3Notification.toJson(); /* * Publish to SNS */ if (publish(snsArn, json, snsClient, key) && processedFile != null) { bw.write(key + "\n"); bw.flush(); } if (throttle != -1) { Thread.sleep(throttle); } } } if (processedFile != null) { bw.close(); fw.close(); } }
From source file:main.java.RMDupper.java
public static void main(String[] args) throws IOException { System.err.println("DeDup v" + VERSION); // the command line parameters Options helpOptions = new Options(); helpOptions.addOption("h", "help", false, "show this help page"); Options options = new Options(); options.addOption("h", "help", false, "show this help page"); options.addOption("i", "input", true, "the input file if this option is not specified,\nthe input is expected to be piped in"); options.addOption("o", "output", true, "the output folder. Has to be specified if input is set."); options.addOption("m", "merged", false, "the input only contains merged reads.\n If this option is specified read names are not examined for prefixes.\n Both the start and end of the aligment are considered for all reads."); options.addOption("v", "version", false, "the version of DeDup."); HelpFormatter helpformatter = new HelpFormatter(); CommandLineParser parser = new BasicParser(); try {//from w w w . ja v a 2 s.c o m CommandLine cmd = parser.parse(helpOptions, args); if (cmd.hasOption('h')) { helpformatter.printHelp(CLASS_NAME, options); System.exit(0); } } catch (ParseException e1) { } String input = ""; String outputpath = ""; Boolean merged = Boolean.FALSE; try { CommandLine cmd = parser.parse(options, args); if (cmd.hasOption('i')) { input = cmd.getOptionValue('i'); piped = false; } if (cmd.hasOption('o')) { outputpath = cmd.getOptionValue('o'); } if (cmd.hasOption('m')) { merged = Boolean.TRUE; } if (cmd.hasOption('v')) { System.out.println("DeDup v" + VERSION); System.exit(0); } } catch (ParseException e) { helpformatter.printHelp(CLASS_NAME, options); System.err.println(e.getMessage()); System.exit(0); } DecimalFormat df = new DecimalFormat("##.##"); if (piped) { RMDupper rmdup = new RMDupper(System.in, System.out, merged); rmdup.readSAMFile(); System.err.println("We are in piping mode!"); System.err.println("Total reads: " + rmdup.dupStats.total + "\n"); System.err.println("Reverse removed: " + rmdup.dupStats.removed_reverse + "\n"); System.err.println("Forward removed: " + rmdup.dupStats.removed_forward + "\n"); System.err.println("Merged removed: " + rmdup.dupStats.removed_merged + "\n"); System.err.println("Total removed: " + (rmdup.dupStats.removed_forward + rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse) + "\n"); if (rmdup.dupStats.removed_merged + rmdup.dupStats.removed_forward + rmdup.dupStats.removed_reverse == 0) { System.err.println("Duplication Rate: " + df.format(0.00)); } else { System.err.println("Duplication Rate: " + df.format((double) (rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse + rmdup.dupStats.removed_forward) / (double) rmdup.dupStats.total)); } } else { if (outputpath.length() == 0) { System.err.println("The output folder has to be specified"); helpformatter.printHelp(CLASS_NAME, options); System.exit(0); } //Check whether we have a directory as output path, else produce error message and quit! File f = new File(outputpath); if (!f.isDirectory()) { System.err.println("The output folder should be a folder and not a file!"); System.exit(0); } File inputFile = new File(input); File outputFile = new File( outputpath + "/" + Files.getNameWithoutExtension(inputFile.getAbsolutePath()) + "_rmdup.bam"); File outputlog = new File( outputpath + "/" + Files.getNameWithoutExtension(inputFile.getAbsolutePath()) + ".log"); File outputhist = new File( outputpath + "/" + Files.getNameWithoutExtension(inputFile.getAbsolutePath()) + ".hist"); try { FileWriter fw = new FileWriter(outputlog); FileWriter histfw = new FileWriter(outputhist); BufferedWriter bfw = new BufferedWriter(fw); BufferedWriter histbfw = new BufferedWriter(histfw); RMDupper rmdup = new RMDupper(inputFile, outputFile, merged); rmdup.readSAMFile(); rmdup.inputSam.close(); rmdup.outputSam.close(); bfw.write("Total reads: " + rmdup.dupStats.total + "\n"); bfw.write("Reverse removed: " + rmdup.dupStats.removed_reverse + "\n"); bfw.write("Forward removed: " + rmdup.dupStats.removed_forward + "\n"); bfw.write("Merged removed: " + rmdup.dupStats.removed_merged + "\n"); bfw.write("Total removed: " + (rmdup.dupStats.removed_forward + rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse) + "\n"); bfw.write("Duplication Rate: " + df.format((double) (rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse + rmdup.dupStats.removed_forward) / (double) rmdup.dupStats.total)); bfw.flush(); bfw.close(); histbfw.write(rmdup.oc.getHistogram()); histbfw.flush(); histbfw.close(); System.out.println("Total reads: " + rmdup.dupStats.total + "\n"); System.out.println("Unmerged removed: " + (rmdup.dupStats.removed_forward + rmdup.dupStats.removed_reverse) + "\n"); System.out.println("Merged removed: " + rmdup.dupStats.removed_merged + "\n"); System.out.println("Total removed: " + (rmdup.dupStats.removed_forward + rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse) + "\n"); if (rmdup.dupStats.removed_merged + rmdup.dupStats.removed_forward + rmdup.dupStats.removed_reverse == 0) { System.out.println("Duplication Rate: " + df.format(0.00)); } else { System.out.println("Duplication Rate: " + df.format((double) (rmdup.dupStats.removed_merged + rmdup.dupStats.removed_reverse + rmdup.dupStats.removed_forward) / (double) rmdup.dupStats.total)); } } catch (IOException e) { e.printStackTrace(); } } }
From source file:apps.quantification.QuantifySVMLight.java
public static void main(String[] args) throws IOException { String cmdLineSyntax = QuantifySVMLight.class.getName() + " [OPTIONS] <path to svm_light_classify> <testIndexDirectory> <quantificationModelDirectory>"; Options options = new Options(); OptionBuilder.withArgName("d"); OptionBuilder.withDescription("Dump confidences file"); OptionBuilder.withLongOpt("d"); OptionBuilder.isRequired(false);//from w w w . java 2 s. c o m OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("t"); OptionBuilder.withDescription("Path for temporary files"); OptionBuilder.withLongOpt("t"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("v"); OptionBuilder.withDescription("Verbose output"); OptionBuilder.withLongOpt("v"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("s"); OptionBuilder.withDescription("Don't delete temporary files in svm_light format (default: delete)"); OptionBuilder.withLongOpt("s"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); SvmLightClassifierCustomizer customizer = null; GnuParser parser = new GnuParser(); String[] remainingArgs = null; try { CommandLine line = parser.parse(options, args); remainingArgs = line.getArgs(); customizer = new SvmLightClassifierCustomizer(remainingArgs[0]); if (line.hasOption("v")) customizer.printSvmLightOutput(true); if (line.hasOption("s")) { System.out.println("Keeping temporary files."); customizer.setDeleteTestFiles(false); customizer.setDeletePredictionsFiles(false); } if (line.hasOption("t")) customizer.setTempPath(line.getOptionValue("t")); } catch (Exception exp) { System.err.println("Parsing failed. Reason: " + exp.getMessage()); HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } if (remainingArgs.length != 3) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } String indexFile = remainingArgs[1]; File file = new File(indexFile); String indexName = file.getName(); String indexPath = file.getParent(); String quantifierFilename = remainingArgs[2]; FileSystemStorageManager indexFssm = new FileSystemStorageManager(indexPath, false); indexFssm.open(); IIndex test = TroveReadWriteHelper.readIndex(indexFssm, indexName, TroveContentDBType.Full, TroveClassificationDBType.Full); indexFssm.close(); FileSystemStorageManager quantifierFssm = new FileSystemStorageManager(quantifierFilename, false); quantifierFssm.open(); SvmLightDataManager classifierDataManager = new SvmLightDataManager(customizer); FileSystemStorageManager fssm = new FileSystemStorageManager(quantifierFilename, false); fssm.open(); IQuantifier[] quantifiers = QuantificationLearner.read(fssm, classifierDataManager, ClassificationMode.PER_CATEGORY); fssm.close(); quantifierFssm.close(); Quantification ccQuantification = quantifiers[0].quantify(test); Quantification paQuantification = quantifiers[1].quantify(test); Quantification accQuantification = quantifiers[2].quantify(test); Quantification maxQuantification = quantifiers[3].quantify(test); Quantification sccQuantification = quantifiers[4].quantify(test); Quantification spaQuantification = quantifiers[5].quantify(test); Quantification trueQuantification = new Quantification("True", test.getClassificationDB()); File quantifierFile = new File(quantifierFilename); String quantificationName = quantifierFile.getParent() + Os.pathSeparator() + indexName + "_" + quantifierFile.getName() + ".txt"; BufferedWriter writer = new BufferedWriter(new FileWriter(quantificationName)); IShortIterator iterator = test.getCategoryDB().getCategories(); while (iterator.hasNext()) { short category = iterator.next(); String prefix = quantifierFile.getName() + "\t" + indexName + "\t" + test.getCategoryDB().getCategoryName(category) + "\t" + category + "\t" + trueQuantification.getQuantification(category) + "\t"; writer.write(prefix + ccQuantification.getName() + "\t" + ccQuantification.getQuantification(category) + "\n"); writer.write(prefix + paQuantification.getName() + "\t" + paQuantification.getQuantification(category) + "\n"); writer.write(prefix + accQuantification.getName() + "\t" + accQuantification.getQuantification(category) + "\n"); writer.write(prefix + maxQuantification.getName() + "\t" + maxQuantification.getQuantification(category) + "\n"); writer.write(prefix + sccQuantification.getName() + "\t" + sccQuantification.getQuantification(category) + "\n"); writer.write(prefix + spaQuantification.getName() + "\t" + spaQuantification.getQuantification(category) + "\n"); } writer.close(); BufferedWriter bfs = new BufferedWriter(new FileWriter(quantifierFile.getParent() + Os.pathSeparator() + indexName + "_" + quantifierFile.getName() + "_rates.txt")); TShortDoubleHashMap simpleTPRs = ((CCQuantifier) quantifiers[0]).getSimpleTPRs(); TShortDoubleHashMap simpleFPRs = ((CCQuantifier) quantifiers[0]).getSimpleFPRs(); TShortDoubleHashMap maxTPRs = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]).getInternalQuantifier()) .getSimpleTPRs(); TShortDoubleHashMap maxFPRs = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]).getInternalQuantifier()) .getSimpleFPRs(); TShortDoubleHashMap scaledTPRs = ((PAQuantifier) quantifiers[1]).getScaledTPRs(); TShortDoubleHashMap scaledFPRs = ((PAQuantifier) quantifiers[1]).getScaledFPRs(); ContingencyTableSet simpleContingencyTableSet = ((CCQuantifier) quantifiers[0]).getContingencyTableSet(); ContingencyTableSet maxContingencyTableSet = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]) .getInternalQuantifier()).getContingencyTableSet(); short[] cats = simpleTPRs.keys(); for (int i = 0; i < cats.length; ++i) { short cat = cats[i]; String catName = test.getCategoryDB().getCategoryName(cat); ContingencyTable simpleContingencyTable = simpleContingencyTableSet.getCategoryContingencyTable(cat); ContingencyTable maxContingencyTable = maxContingencyTableSet.getCategoryContingencyTable(cat); double simpleTPR = simpleTPRs.get(cat); double simpleFPR = simpleFPRs.get(cat); double maxTPR = maxTPRs.get(cat); double maxFPR = maxFPRs.get(cat); double scaledTPR = scaledTPRs.get(cat); double scaledFPR = scaledFPRs.get(cat); String line = indexName + "_" + quantifierFile.getName() + "\ttest\tsimple\t" + catName + "\t" + cat + "\t" + simpleContingencyTable.tp() + "\t" + simpleContingencyTable.fp() + "\t" + simpleContingencyTable.fn() + "\t" + simpleContingencyTable.tn() + "\t" + simpleTPR + "\t" + simpleFPR + "\n"; bfs.write(line); line = indexName + "_" + quantifierFile.getName() + "\ttest\tmax\t" + catName + "\t" + cat + "\t" + maxContingencyTable.tp() + "\t" + maxContingencyTable.fp() + "\t" + maxContingencyTable.fn() + "\t" + maxContingencyTable.tn() + "\t" + maxTPR + "\t" + maxFPR + "\n"; bfs.write(line); line = indexName + "_" + quantifierFile.getName() + "\ttest\tscaled\t" + catName + "\t" + cat + "\t" + simpleContingencyTable.tp() + "\t" + simpleContingencyTable.fp() + "\t" + simpleContingencyTable.fn() + "\t" + simpleContingencyTable.tn() + "\t" + scaledTPR + "\t" + scaledFPR + "\n"; bfs.write(line); } bfs.close(); }
From source file:apps.quantification.QuantifySVMPerf.java
public static void main(String[] args) throws IOException { String cmdLineSyntax = QuantifySVMPerf.class.getName() + " [OPTIONS] <path to svm_perf_classify> <testIndexDirectory> <quantificationModelDirectory>"; Options options = new Options(); OptionBuilder.withArgName("d"); OptionBuilder.withDescription("Dump confidences file"); OptionBuilder.withLongOpt("d"); OptionBuilder.isRequired(false);/*from w w w . ja v a 2s .c o m*/ OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("t"); OptionBuilder.withDescription("Path for temporary files"); OptionBuilder.withLongOpt("t"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("v"); OptionBuilder.withDescription("Verbose output"); OptionBuilder.withLongOpt("v"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("s"); OptionBuilder.withDescription("Don't delete temporary files in svm_perf format (default: delete)"); OptionBuilder.withLongOpt("s"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); SvmPerfClassifierCustomizer customizer = null; GnuParser parser = new GnuParser(); String[] remainingArgs = null; try { CommandLine line = parser.parse(options, args); remainingArgs = line.getArgs(); customizer = new SvmPerfClassifierCustomizer(remainingArgs[0]); if (line.hasOption("v")) customizer.printSvmPerfOutput(true); if (line.hasOption("s")) { System.out.println("Keeping temporary files."); customizer.setDeleteTestFiles(false); customizer.setDeletePredictionsFiles(false); } if (line.hasOption("t")) customizer.setTempPath(line.getOptionValue("t")); } catch (Exception exp) { System.err.println("Parsing failed. Reason: " + exp.getMessage()); HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } if (remainingArgs.length != 3) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } String indexFile = remainingArgs[1]; File file = new File(indexFile); String indexName = file.getName(); String indexPath = file.getParent(); String quantifierFilename = remainingArgs[2]; FileSystemStorageManager indexFssm = new FileSystemStorageManager(indexPath, false); indexFssm.open(); IIndex test = TroveReadWriteHelper.readIndex(indexFssm, indexName, TroveContentDBType.Full, TroveClassificationDBType.Full); indexFssm.close(); FileSystemStorageManager quantifierFssm = new FileSystemStorageManager(quantifierFilename, false); quantifierFssm.open(); SvmPerfDataManager classifierDataManager = new SvmPerfDataManager(customizer); FileSystemStorageManager fssm = new FileSystemStorageManager(quantifierFilename, false); fssm.open(); IQuantifier[] quantifiers = QuantificationLearner.read(fssm, classifierDataManager, ClassificationMode.PER_CATEGORY); fssm.close(); quantifierFssm.close(); Quantification ccQuantification = quantifiers[0].quantify(test); Quantification paQuantification = quantifiers[1].quantify(test); Quantification accQuantification = quantifiers[2].quantify(test); Quantification maxQuantification = quantifiers[3].quantify(test); Quantification sccQuantification = quantifiers[4].quantify(test); Quantification spaQuantification = quantifiers[5].quantify(test); Quantification trueQuantification = new Quantification("True", test.getClassificationDB()); File quantifierFile = new File(quantifierFilename); String quantificationName = quantifierFile.getParent() + Os.pathSeparator() + indexName + "_" + quantifierFile.getName() + ".txt"; BufferedWriter writer = new BufferedWriter(new FileWriter(quantificationName)); IShortIterator iterator = test.getCategoryDB().getCategories(); while (iterator.hasNext()) { short category = iterator.next(); String prefix = quantifierFile.getName() + "\t" + indexName + "\t" + test.getCategoryDB().getCategoryName(category) + "\t" + category + "\t" + trueQuantification.getQuantification(category) + "\t"; writer.write(prefix + ccQuantification.getName() + "\t" + ccQuantification.getQuantification(category) + "\n"); writer.write(prefix + paQuantification.getName() + "\t" + paQuantification.getQuantification(category) + "\n"); writer.write(prefix + accQuantification.getName() + "\t" + accQuantification.getQuantification(category) + "\n"); writer.write(prefix + maxQuantification.getName() + "\t" + maxQuantification.getQuantification(category) + "\n"); writer.write(prefix + sccQuantification.getName() + "\t" + sccQuantification.getQuantification(category) + "\n"); writer.write(prefix + spaQuantification.getName() + "\t" + spaQuantification.getQuantification(category) + "\n"); } writer.close(); BufferedWriter bfs = new BufferedWriter(new FileWriter(quantifierFile.getParent() + Os.pathSeparator() + indexName + "_" + quantifierFile.getName() + "_rates.txt")); TShortDoubleHashMap simpleTPRs = ((CCQuantifier) quantifiers[0]).getSimpleTPRs(); TShortDoubleHashMap simpleFPRs = ((CCQuantifier) quantifiers[0]).getSimpleFPRs(); TShortDoubleHashMap maxTPRs = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]).getInternalQuantifier()) .getSimpleTPRs(); TShortDoubleHashMap maxFPRs = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]).getInternalQuantifier()) .getSimpleFPRs(); TShortDoubleHashMap scaledTPRs = ((PAQuantifier) quantifiers[1]).getScaledTPRs(); TShortDoubleHashMap scaledFPRs = ((PAQuantifier) quantifiers[1]).getScaledFPRs(); ContingencyTableSet simpleContingencyTableSet = ((CCQuantifier) quantifiers[0]).getContingencyTableSet(); ContingencyTableSet maxContingencyTableSet = ((CCQuantifier) ((ScaledQuantifier) quantifiers[3]) .getInternalQuantifier()).getContingencyTableSet(); short[] cats = simpleTPRs.keys(); for (int i = 0; i < cats.length; ++i) { short cat = cats[i]; String catName = test.getCategoryDB().getCategoryName(cat); ContingencyTable simpleContingencyTable = simpleContingencyTableSet.getCategoryContingencyTable(cat); ContingencyTable maxContingencyTable = maxContingencyTableSet.getCategoryContingencyTable(cat); double simpleTPR = simpleTPRs.get(cat); double simpleFPR = simpleFPRs.get(cat); double maxTPR = maxTPRs.get(cat); double maxFPR = maxFPRs.get(cat); double scaledTPR = scaledTPRs.get(cat); double scaledFPR = scaledFPRs.get(cat); String line = indexName + "_" + quantifierFile.getName() + "\ttest\tsimple\t" + catName + "\t" + cat + "\t" + simpleContingencyTable.tp() + "\t" + simpleContingencyTable.fp() + "\t" + simpleContingencyTable.fn() + "\t" + simpleContingencyTable.tn() + "\t" + simpleTPR + "\t" + simpleFPR + "\n"; bfs.write(line); line = indexName + "_" + quantifierFile.getName() + "\ttest\tmax\t" + catName + "\t" + cat + "\t" + maxContingencyTable.tp() + "\t" + maxContingencyTable.fp() + "\t" + maxContingencyTable.fn() + "\t" + maxContingencyTable.tn() + "\t" + maxTPR + "\t" + maxFPR + "\n"; bfs.write(line); line = indexName + "_" + quantifierFile.getName() + "\ttest\tscaled\t" + catName + "\t" + cat + "\t" + simpleContingencyTable.tp() + "\t" + simpleContingencyTable.fp() + "\t" + simpleContingencyTable.fn() + "\t" + simpleContingencyTable.tn() + "\t" + scaledTPR + "\t" + scaledFPR + "\n"; bfs.write(line); } bfs.close(); }