List of usage examples for java.util LinkedHashSet size
int size();
From source file:Main.java
public static void main(String[] args) { LinkedHashSet<Integer> lhashSet = new LinkedHashSet<Integer>(); System.out.println("Size of LinkedHashSet : " + lhashSet.size()); lhashSet.add(new Integer("1")); lhashSet.add(new Integer("2")); lhashSet.add(new Integer("3")); System.out.println(lhashSet.size()); lhashSet.remove(new Integer("1")); System.out.println(lhashSet.size()); }
From source file:nl.systemsgenetics.functionenrichmentoftransqtls.CorrelateSumChi2ToPathways.java
/** * @param args the command line arguments *///from w ww. j av a2 s. c o m public static void main(String[] args) throws IOException { final File pathwayMatrixFile = new File(args[0]); final File significantTermsFile = new File(args[1]); final File sumChi2MatrixFile = new File(args[2]); final File transQtlEnrichmentsMatrixFile = new File(args[3]); System.out.println("Pathway file: " + pathwayMatrixFile.getPath()); System.out.println("Pathway significant terms file: " + significantTermsFile.getPath()); System.out.println("SumChi2 file: " + sumChi2MatrixFile.getPath()); System.out.println("Output file: " + transQtlEnrichmentsMatrixFile.getPath()); LinkedHashSet<String> significantTerms = loadSignificantTerms(significantTermsFile); DoubleMatrixDataset<String, String> pathwayMatrix = DoubleMatrixDataset .loadDoubleData(pathwayMatrixFile.getPath()); DoubleMatrixDataset<String, String> sumChi2Matrix = DoubleMatrixDataset .loadDoubleData(sumChi2MatrixFile.getPath()); LinkedHashSet<String> genesInBoth = new LinkedHashSet<String>(); for (String gene : pathwayMatrix.getHashRows().keySet()) { if (sumChi2Matrix.containsRow(gene)) { genesInBoth.add(gene); } } pathwayMatrix = pathwayMatrix.viewColSelection(significantTerms); pathwayMatrix = pathwayMatrix.viewRowSelection(genesInBoth); DoubleMatrixDataset<String, String> transQtlEnrichmentsMatrix = new DoubleMatrixDataset<String, String>( pathwayMatrix.getHashCols(), sumChi2Matrix.getHashCols()); sumChi2Matrix = sumChi2Matrix.viewRowSelection(genesInBoth); System.out.println("Genes in both datasets: " + genesInBoth.size()); System.out.println("Pathways to test: " + pathwayMatrix.columns()); final SimpleRegression regression = new SimpleRegression(); final DoubleRandomEngine randomEngine = new DRand(); StudentT tDistColt = new StudentT(sumChi2Matrix.rows() / 2 - 2, randomEngine); for (String trait : sumChi2Matrix.getColObjects()) { System.out.println("Trait: " + trait); DoubleMatrix1D traitSumChi2 = sumChi2Matrix.getCol(trait); for (String pathway : pathwayMatrix.getColObjects()) { DoubleMatrix1D pathwayScores = pathwayMatrix.getCol(pathway); regression.clear(); for (int i = 0; i < traitSumChi2.size(); ++i) { //System.out.println(traitSumChi2.get(i) + " & " + pathwayScores.get(i)); regression.addData(traitSumChi2.get(i), pathwayScores.get(i)); } double r = regression.getR(); //System.out.println(trait + " " + pathway + " " + r); double t = r / (Math.sqrt((1 - r * r) / (double) (traitSumChi2.size() / 2 - 2))); double pValue; double zScore; if (t < 0) { pValue = tDistColt.cdf(t); if (pValue < 2.0E-323) { pValue = 2.0E-323; } zScore = Probability.normalInverse(pValue); } else { pValue = tDistColt.cdf(-t); if (pValue < 2.0E-323) { pValue = 2.0E-323; } zScore = -Probability.normalInverse(pValue); } pValue *= 2; transQtlEnrichmentsMatrix.setElement(pathway, trait, zScore); } } transQtlEnrichmentsMatrix.save(transQtlEnrichmentsMatrixFile); }
From source file:nl.systemsgenetics.genenetworkbackend.hpo.TestDiseaseGenePerformance.java
/** * @param args the command line arguments * @throws java.lang.Exception//from w w w . j a v a 2 s . c o m */ public static void main(String[] args) throws Exception { final File diseaseGeneHpoFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\HPO\\135\\ALL_SOURCES_ALL_FREQUENCIES_diseases_to_genes_to_phenotypes.txt"); final File ncbiToEnsgMapFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\ensgNcbiId.txt"); final File hgncToEnsgMapFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\ensgHgnc.txt"); final File ensgSymbolMappingFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\ensgHgnc.txt"); final File predictionMatrixFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_predictions_zscores.txt.gz"); final File predictionMatrixCorrelationFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_predictions_pathwayCorrelation.txt"); final File significantTermsFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_predictions_bonSigTerms.txt"); final double correctedPCutoff = 0.05; final File hpoOboFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\HPO\\135\\hp.obo"); final File hpoPredictionInfoFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\hpo_predictions_auc_bonferroni.txt"); final File hposToExcludeFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\hpoToExclude.txt"); final File skewnessFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\predictions\\skewnessSummary.txt"); final boolean randomize = true; final File annotationMatrixFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\PathwayMatrix\\ALL_SOURCES_ALL_FREQUENCIES_phenotype_to_genes.txt_matrix.txt.gz"); final File backgroundForRandomize = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\Data31995Genes05-12-2017\\PCA_01_02_2018\\PathwayMatrix\\Ensembl2Reactome_All_Levels.txt_genesInPathways.txt"); //final File backgroundForRandomize = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\expressedReactomeGenes.txt"); final boolean randomizeCustomBackground = true; Map<String, String> ensgSymbolMapping = loadEnsgToHgnc(ensgSymbolMappingFile); final File outputFile; final ArrayList<String> backgroundGenes; if (randomize) { if (randomizeCustomBackground) { System.err.println("First need to fix so ranking list contains all genes in background list"); return; // backgroundGenes = loadBackgroundGenes(backgroundForRandomize); // outputFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\hpoDiseaseBenchmarkRandomizedCustomBackground.txt"); } else { backgroundGenes = null; outputFile = new File( "C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\hpoDiseaseBenchmarkRandomizedExtraNorm.txt"); } } else { backgroundGenes = null; outputFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\hpoDiseaseBenchmarkExtraNorm.txt"); } final HashMap<String, ArrayList<String>> ncbiToEnsgMap = loadNcbiToEnsgMap(ncbiToEnsgMapFile); final HashMap<String, ArrayList<String>> hgncToEnsgMap = loadHgncToEnsgMap(hgncToEnsgMapFile); final HashSet<String> exludedHpo = loadHpoExclude(hposToExcludeFile); final SkewnessInfo skewnessInfo = new SkewnessInfo(skewnessFile); LinkedHashSet<String> significantTerms = loadSignificantTerms(significantTermsFile); DoubleMatrixDataset<String, String> predictionMatrix = DoubleMatrixDataset .loadDoubleData(predictionMatrixFile.getAbsolutePath()); DoubleMatrixDataset<String, String> predictionMatrixSignificant = predictionMatrix .viewColSelection(significantTerms); DoubleMatrixDataset<String, String> predictionMatrixSignificantCorrelationMatrix = DoubleMatrixDataset .loadDoubleData(predictionMatrixCorrelationFile.getAbsolutePath()); DiseaseGeneHpoData diseaseGeneHpoData = new DiseaseGeneHpoData(diseaseGeneHpoFile, ncbiToEnsgMap, hgncToEnsgMap, exludedHpo, new HashSet(predictionMatrix.getHashRows().keySet()), "OMIM"); //NOTE if one would use a differnt background this needs to be updated HashSet<String> diseaseGenes = new HashSet<>(diseaseGeneHpoData.getDiseaseGenes()); if (randomize) { diseaseGeneHpoData = diseaseGeneHpoData.getPermutation(1, backgroundGenes); } for (String gene : diseaseGenes) { if (!predictionMatrixSignificant.containsRow(gene)) { throw new Exception("Error: " + gene); } } int[] mapGeneIndexToDiseaseGeneIndex = new int[predictionMatrix.rows()]; ArrayList<String> predictedGenes = predictionMatrix.getRowObjects(); int g2 = 0; for (int g = 0; g < predictedGenes.size(); ++g) { mapGeneIndexToDiseaseGeneIndex[g] = diseaseGenes.contains(predictedGenes.get(g)) ? g2++ : -1; } DoubleMatrixDataset<String, String> annotationnMatrix = DoubleMatrixDataset .loadDoubleData(annotationMatrixFile.getAbsolutePath()); DoubleMatrixDataset<String, String> annotationMatrixSignificant = annotationnMatrix .viewColSelection(significantTerms); HashMap<String, MeanSd> hpoMeanSds = calculatePathayMeansOfAnnotatedGenes(predictionMatrixSignificant, annotationMatrixSignificant); Map<String, PredictionInfo> predictionInfo = HpoFinder.loadPredictionInfo(hpoPredictionInfoFile); Ontology hpoOntology = HpoFinder.loadHpoOntology(hpoOboFile); HpoFinder hpoFinder = new HpoFinder(hpoOntology, predictionInfo); final int totalGenes = predictionMatrixSignificant.rows(); final int totalDiseaseGenes = diseaseGenes.size(); final double[] geneScores = new double[totalGenes]; final double[] geneScoresDiseaseGenes = new double[totalDiseaseGenes]; final NaturalRanking naturalRanking = new NaturalRanking(NaNStrategy.FAILED, TiesStrategy.MAXIMUM); CSVWriter writer = new CSVWriter(new FileWriter(outputFile), '\t', '\0', '\0', "\n"); String[] outputLine = new String[16]; int c = 0; outputLine[c++] = "Disease"; outputLine[c++] = "Gene"; outputLine[c++] = "Hgnc"; outputLine[c++] = "Rank"; outputLine[c++] = "RankAmongDiseaseGenes"; outputLine[c++] = "Z-score"; outputLine[c++] = "HPO_skewness"; outputLine[c++] = "Other_mean_skewness"; outputLine[c++] = "Other_max_skewness"; outputLine[c++] = "HPO_phenotypic_match_score"; outputLine[c++] = "HPO_count"; outputLine[c++] = "HPO_sum_auc"; outputLine[c++] = "HPO_mean_auc"; outputLine[c++] = "HPO_median_auc"; outputLine[c++] = "HPO_terms"; outputLine[c++] = "HPO_terms_match_score"; writer.writeNext(outputLine); Random random = new Random(1); Mean meanCalculator = new Mean(); Median medianCalculator = new Median(); for (DiseaseGeneHpoData.DiseaseGene diseaseGene : diseaseGeneHpoData.getDiseaseGeneHpos()) { String gene = diseaseGene.getGene(); String disease = diseaseGene.getDisease(); if (!predictionMatrixSignificant.containsRow(gene)) { continue; } Set<String> geneHpos = diseaseGeneHpoData.getDiseaseEnsgHpos(diseaseGene); LinkedHashSet<String> geneHposPredictable = new LinkedHashSet<>(); for (String hpo : geneHpos) { geneHposPredictable .addAll(hpoFinder.getTermsToNames(hpoFinder.getPredictableTerms(hpo, correctedPCutoff))); } if (geneHposPredictable.isEmpty()) { continue; } // if(geneHposPredictable.size() > 1){ // String hpoSelected = geneHposPredictable.toArray(new String[geneHposPredictable.size()])[random.nextInt(geneHposPredictable.size())]; // geneHposPredictable = new LinkedHashSet<>(1); // geneHposPredictable.add(hpoSelected); // } DoubleMatrixDataset<String, String> predictionCaseTerms = predictionMatrixSignificant .viewColSelection(geneHposPredictable); DoubleMatrix2D predictionCaseTermsMatrix = predictionCaseTerms.getMatrix(); double denominator = Math.sqrt(geneHposPredictable.size()); for (int g = 0; g < totalGenes; ++g) { geneScores[g] = predictionCaseTermsMatrix.viewRow(g).zSum() / denominator; if (Double.isNaN(geneScores[g])) { geneScores[g] = 0; } g2 = mapGeneIndexToDiseaseGeneIndex[g]; if (g2 >= 0) { geneScoresDiseaseGenes[g2] = geneScores[g]; } } double[] geneRanks = naturalRanking.rank(geneScores); int diseaseGeneIndex = predictionMatrixSignificant.getRowIndex(gene); double[] geneRanksDiseaseGenes = naturalRanking.rank(geneScoresDiseaseGenes); int diseaseGeneIndexInDiseaseGenesOnly = mapGeneIndexToDiseaseGeneIndex[diseaseGeneIndex]; double zscore = geneScores[diseaseGeneIndex]; double rank = (totalGenes - geneRanks[diseaseGeneIndex]) + 1; double rankAmongDiseaseGenes = (totalDiseaseGenes - geneRanksDiseaseGenes[diseaseGeneIndexInDiseaseGenesOnly]) + 1; double hpoPhenotypicMatchScore = 0; StringBuilder individualMatchScore = new StringBuilder(); boolean notFirst = false; int usedHpos = 0; double[] aucs = new double[geneHposPredictable.size()]; double sumAucs = 0; int i = 0; for (String hpo : geneHposPredictable) { usedHpos++; MeanSd hpoMeanSd = hpoMeanSds.get(hpo); double hpoPredictionZ = predictionMatrixSignificant.getElement(gene, hpo); double hpoPredictionOutlierScore = ((hpoPredictionZ - hpoMeanSd.getMean()) / hpoMeanSd.getSd()); if (notFirst) { individualMatchScore.append(';'); } notFirst = true; individualMatchScore.append(hpoPredictionOutlierScore); hpoPhenotypicMatchScore += hpoPredictionOutlierScore; aucs[i++] = predictionInfo.get(hpo).getAuc(); sumAucs += predictionInfo.get(hpo).getAuc(); } double meanAuc = meanCalculator.evaluate(aucs); double medianAuc = medianCalculator.evaluate(aucs); if (usedHpos == 0) { hpoPhenotypicMatchScore = Double.NaN; } else { hpoPhenotypicMatchScore = hpoPhenotypicMatchScore / usedHpos; } String symbol = ensgSymbolMapping.get(gene); if (symbol == null) { symbol = ""; } c = 0; outputLine[c++] = disease; outputLine[c++] = gene; outputLine[c++] = symbol; outputLine[c++] = String.valueOf(rank); outputLine[c++] = String.valueOf(rankAmongDiseaseGenes); outputLine[c++] = String.valueOf(zscore); outputLine[c++] = String.valueOf(skewnessInfo.getHpoSkewness(gene)); outputLine[c++] = String.valueOf(skewnessInfo.getMeanSkewnessExHpo(gene)); outputLine[c++] = String.valueOf(skewnessInfo.getMaxSkewnessExHpo(gene)); outputLine[c++] = String.valueOf(hpoPhenotypicMatchScore); outputLine[c++] = String.valueOf(geneHposPredictable.size()); outputLine[c++] = String.valueOf(sumAucs); outputLine[c++] = String.valueOf(meanAuc); outputLine[c++] = String.valueOf(medianAuc); outputLine[c++] = String.join(";", geneHposPredictable); outputLine[c++] = individualMatchScore.toString(); writer.writeNext(outputLine); } writer.close(); }
From source file:Main.java
public static String convertSetToString(LinkedHashSet<String> set) { int length = set.size(); StringBuilder sb = new StringBuilder(); for (String item : set) { length--;/*from www .ja va 2s .c o m*/ sb.append(item); if (length != 0) { sb.append(","); } } return sb.toString(); }
From source file:com.datatorrent.stram.api.IotDev.java
public static URLClassLoader loadDependencies(LinkedHashSet<URL> launchDependencies) { URLClassLoader cl = URLClassLoader .newInstance(launchDependencies.toArray(new URL[launchDependencies.size()])); Thread.currentThread().setContextClassLoader(cl); StringCodecs.check();/*w w w .java 2 s. com*/ return cl; }
From source file:io.parallec.core.util.PcStringUtils.java
/** * Get the aggregated result human readable string for easy display. * /*from w w w.j a v a 2s. c o m*/ * * @param aggregateResultMap the aggregate result map * @return the aggregated result human */ public static String getAggregatedResultHuman(Map<String, LinkedHashSet<String>> aggregateResultMap) { StringBuilder res = new StringBuilder(); for (Entry<String, LinkedHashSet<String>> entry : aggregateResultMap.entrySet()) { LinkedHashSet<String> valueSet = entry.getValue(); res.append("[" + entry.getKey() + " COUNT: " + valueSet.size() + " ]:\n"); for (String str : valueSet) { res.append("\t" + str + "\n"); } res.append("###################################\n\n"); } return res.toString(); }
From source file:com.zxy.commons.lang.utils.StringsUtils.java
/** * List??//w w w . j ava 2 s. c om * * @param arrList ? * @return ???? */ public static List<String> removeDuplicate(List<String> arrList) { if (arrList == null || arrList.isEmpty()) { return new ArrayList<String>(); } LinkedHashSet<String> hSet = new LinkedHashSet<String>(arrList); List<String> tmp = new ArrayList<String>(hSet.size()); tmp.addAll(hSet); return tmp; }
From source file:com.vaadin.sass.testcases.scss.W3ConformanceTests.java
protected static Collection<URI> scrapeIndexForTests(String url, String regexp, int maxTests, Collection<URI> excludeUrls) throws Exception { URI baseUrl = new URI(url); Document doc = Jsoup.connect(url).timeout(10000).get(); Elements elems = doc.select(String.format("a[href~=%s]", regexp)); LinkedHashSet<URI> tests = new LinkedHashSet<URI>(); for (Element e : elems) { URI testUrl = new URI(e.attr("href")); if (!testUrl.isAbsolute()) { testUrl = baseUrl.resolve(testUrl); }/*from w w w . j a va2 s . c o m*/ if (tests.size() < maxTests) { if (!excludeUrls.contains(testUrl)) { tests.add(testUrl); } } else { break; } } return tests; }
From source file:com.ery.ertc.estorm.util.DNS.java
/** * Returns all the IPs associated with the provided interface, if any, in textual form. * /* w ww .ja v a 2s .co m*/ * @param strInterface * The name of the network interface or subinterface to query (eg eth0 or eth0:0) or the string "default" * @param returnSubinterfaces * Whether to return IPs associated with subinterfaces of the given interface * @return A string vector of all the IPs associated with the provided interface * @throws UnknownHostException * If an UnknownHostException is encountered in querying the default interface or the given interface can not be found * */ public static String[] getIPs(String strInterface, boolean returnSubinterfaces) throws UnknownHostException { if ("default".equals(strInterface)) { return new String[] { InetAddress.getLocalHost().getHostAddress() }; } NetworkInterface netIf; try { netIf = NetworkInterface.getByName(strInterface); if (netIf == null) { netIf = getSubinterface(strInterface); if (netIf == null) { throw new UnknownHostException("Unknown interface " + strInterface); } } } catch (SocketException e) { LOG.warn("Unable to get IP for interface " + strInterface, e); return new String[] { InetAddress.getLocalHost().getHostAddress() }; } // NB: Using a LinkedHashSet to preserve the order for callers // that depend on a particular element being 1st in the array. // For example, getDefaultIP always returns the first element. LinkedHashSet<InetAddress> allAddrs = new LinkedHashSet<InetAddress>(); allAddrs.addAll(Collections.list(netIf.getInetAddresses())); if (!returnSubinterfaces) { allAddrs.removeAll(getSubinterfaceInetAddrs(netIf)); } String ips[] = new String[allAddrs.size()]; int i = 0; for (InetAddress addr : allAddrs) { ips[i++] = addr.getHostAddress(); } return ips; }
From source file:com.buaa.cfs.net.DNS.java
/** * Returns all the IPs associated with the provided interface, if any, in textual form. * * @param strInterface The name of the network interface or sub-interface to query (eg eth0 or eth0:0) or the * string "default" * @param returnSubinterfaces Whether to return IPs associated with subinterfaces of the given interface * * @return A string vector of all the IPs associated with the provided interface. The local host IP is returned if * the interface name "default" is specified or there is an I/O error looking for the given interface. * * @throws UnknownHostException If the given interface is invalid *//*from w w w .j a v a2s .c o m*/ public static String[] getIPs(String strInterface, boolean returnSubinterfaces) throws UnknownHostException { if ("default".equals(strInterface)) { return new String[] { cachedHostAddress }; } NetworkInterface netIf; try { netIf = NetworkInterface.getByName(strInterface); if (netIf == null) { netIf = getSubinterface(strInterface); } } catch (SocketException e) { LOG.warn("I/O error finding interface " + strInterface + ": " + e.getMessage()); return new String[] { cachedHostAddress }; } if (netIf == null) { throw new UnknownHostException("No such interface " + strInterface); } // NB: Using a LinkedHashSet to preserve the order for callers // that depend on a particular element being 1st in the array. // For example, getDefaultIP always returns the first element. LinkedHashSet<InetAddress> allAddrs = new LinkedHashSet<InetAddress>(); allAddrs.addAll(Collections.list(netIf.getInetAddresses())); if (!returnSubinterfaces) { allAddrs.removeAll(getSubinterfaceInetAddrs(netIf)); } String ips[] = new String[allAddrs.size()]; int i = 0; for (InetAddress addr : allAddrs) { ips[i++] = addr.getHostAddress(); } return ips; }