Example usage for java.util HashSet size

List of usage examples for java.util HashSet size

  1. HOME
  2. Java
  3. java
  4. java.util.*
  5. HashSet
  6. size

Introduction

In this page you can find the example usage for java.util HashSet size.

Prototype

public int size()

Source Link

Document

Returns the number of elements in this set (its cardinality).

Usage

From source file:amie.keys.CombinationsExplorationNew.java

/**
 * Construction of the maps from properties -> id and id -> properties
 *///from  www  .  ja  va  2  s . c  om
private static HashSet<HashSet<Integer>> buildDictionaries(List<List<String>> nonKeys,
        List<Integer> propertiesList) {
    int id = 0;
    HashSet<HashSet<Integer>> result = new HashSet<>();
    for (List<String> nonKey : nonKeys) {
        //    System.out.println("nonkey:" + nonKey);
        HashSet<Integer> nonKeyInt = new HashSet<>();
        for (int k = 0; k < nonKey.size(); ++k) {
            // Ignore 
            String property = nonKey.get(k);
            // boolean supportCutProperty =false;
            //                if (getPropertySupport(property) < support) {
            //      System.out.println("getPropertySupport(property):"+getPropertySupport(property));
            //   supportCutProperty = true;
            //  System.out.println("ee");
            //                    continue;
            //                }

            //**** Debugging code ***/
            /**List<String> testingProperties = Arrays.asList("db:campus", "db:mascot", "db:officialschoolcolour", "db:athletics", "db:country");          
             if (getPropertySupport(property) < support || !testingProperties.contains(property)) {
                continue;
             }**/
            //**** Debugging code ***/

            if (!property2Id.containsKey(property)) {
                property2Id.put(property, id);
                id2Property.put(id, property);
                // if(!supportCutProperty){
                propertiesList.add(id);//}
                ++id;
            }
            Integer idProperty = property2Id.get(property);
            nonKeyInt.add(idProperty);
        }
        //System.out.println("propertyList:"+propertiesList);
        if (nonKeyInt.size() != 0) {
            result.add(nonKeyInt);
            //   System.out.println("nonKeyInt!:" + nonKeyInt + " " + nonKeyInt.size() + "\n");
        }
    }
    // System.out.println("id2Property:"+id2Property);
    // System.out.println("nonKeysInt:" + result.size() + "\n");

    result = simplifyHashNonKeySet(result);
    //System.out.println("nonKeysInt:" + result.size() + "\n");
    return result;
}

From source file:org.apache.sysml.hops.codegen.opt.PlanSelectionFuseCostBased.java

private void createAndAddMultiAggPlans(CPlanMemoTable memo, ArrayList<Hop> roots) {
    //collect full aggregations as initial set of candidates
    HashSet<Long> fullAggs = new HashSet<>();
    Hop.resetVisitStatus(roots);/*from   w w w  .  jav a2s  . c  o  m*/
    for (Hop hop : roots)
        rCollectFullAggregates(hop, fullAggs);
    Hop.resetVisitStatus(roots);

    //remove operators with assigned multi-agg plans
    fullAggs.removeIf(p -> memo.contains(p, TemplateType.MAGG));

    //check applicability for further analysis
    if (fullAggs.size() <= 1)
        return;

    if (LOG.isTraceEnabled()) {
        LOG.trace("Found across-partition ua(RC) aggregations: "
                + Arrays.toString(fullAggs.toArray(new Long[0])));
    }

    //collect information for all candidates 
    //(subsumed aggregations, and inputs to fused operators) 
    List<AggregateInfo> aggInfos = new ArrayList<>();
    for (Long hopID : fullAggs) {
        Hop aggHop = memo.getHopRefs().get(hopID);
        AggregateInfo tmp = new AggregateInfo(aggHop);
        for (int i = 0; i < aggHop.getInput().size(); i++) {
            Hop c = HopRewriteUtils.isMatrixMultiply(aggHop) && i == 0
                    ? aggHop.getInput().get(0).getInput().get(0)
                    : aggHop.getInput().get(i);
            rExtractAggregateInfo(memo, c, tmp, TemplateType.CELL);
        }
        if (tmp._fusedInputs.isEmpty()) {
            if (HopRewriteUtils.isMatrixMultiply(aggHop)) {
                tmp.addFusedInput(aggHop.getInput().get(0).getInput().get(0).getHopID());
                tmp.addFusedInput(aggHop.getInput().get(1).getHopID());
            } else
                tmp.addFusedInput(aggHop.getInput().get(0).getHopID());
        }
        aggInfos.add(tmp);
    }

    if (LOG.isTraceEnabled()) {
        LOG.trace("Extracted across-partition ua(RC) aggregation info: ");
        for (AggregateInfo info : aggInfos)
            LOG.trace(info);
    }

    //sort aggregations by num dependencies to simplify merging
    //clusters of aggregations with parallel dependencies
    aggInfos = aggInfos.stream().sorted(Comparator.comparing(a -> a._inputAggs.size()))
            .collect(Collectors.toList());

    //greedy grouping of multi-agg candidates
    boolean converged = false;
    while (!converged) {
        AggregateInfo merged = null;
        for (int i = 0; i < aggInfos.size(); i++) {
            AggregateInfo current = aggInfos.get(i);
            for (int j = i + 1; j < aggInfos.size(); j++) {
                AggregateInfo that = aggInfos.get(j);
                if (current.isMergable(that)) {
                    merged = current.merge(that);
                    aggInfos.remove(j);
                    j--;
                }
            }
        }
        converged = (merged == null);
    }

    if (LOG.isTraceEnabled()) {
        LOG.trace("Merged across-partition ua(RC) aggregation info: ");
        for (AggregateInfo info : aggInfos)
            LOG.trace(info);
    }

    //construct and add multiagg template plans (w/ max 3 aggregations)
    for (AggregateInfo info : aggInfos) {
        if (info._aggregates.size() <= 1)
            continue;
        Long[] aggs = info._aggregates.keySet().toArray(new Long[0]);
        MemoTableEntry me = new MemoTableEntry(TemplateType.MAGG, aggs[0], aggs[1],
                (aggs.length > 2) ? aggs[2] : -1, aggs.length);
        for (int i = 0; i < aggs.length; i++) {
            memo.add(memo.getHopRefs().get(aggs[i]), me);
            addBestPlan(aggs[i], me);
            if (LOG.isTraceEnabled())
                LOG.trace("Added multiagg* plan: " + aggs[i] + " " + me);

        }
    }
}

From source file:edu.nyu.vida.data_polygamy.exp.NoiseExp.java

void load2DData(String aggregateFile, String graphFile, int year) {
    String[] s = null;/*w  w w.ja va 2 s  . c  om*/
    IntOpenHashSet nodeSet = new IntOpenHashSet();
    try {
        BufferedReader buf = new BufferedReader(new FileReader(aggregateFile));
        s = Utilities.getLine(buf, ",");
        //System.out.println(s[0]);
        while (true) {
            if (s == null) {
                break;
            }
            String attr = Utilities.splitString(s[0], ":")[1].trim();
            Attribute a = attributes.get(attr);
            if (a == null) {
                a = new Attribute();
                attributes.put(attr, a);
            }
            s = Utilities.getLine(buf, ":");
            int sid = Integer.parseInt(s[1].trim());
            nodeSet.add(sid);
            s = Utilities.getLine(buf, ",");
            while (s != null && s.length > 0) {
                int month = Integer.parseInt(Utilities.splitString(s[0], ":")[1].trim());
                s = Utilities.getLine(buf, ",");
                HashSet<SpatioTemporalVal> set = new HashSet<SpatioTemporalVal>();
                while (s != null && s.length == 2) {
                    if (month / 100 == year) {
                        int time = Integer.parseInt(s[0]);
                        float value = Float.parseFloat(s[1]);

                        SpatioTemporalVal val = new SpatioTemporalVal(sid, time, value);

                        ArrayList<Float> vals = (values.get(attr) == null) ? new ArrayList<Float>()
                                : values.get(attr);
                        vals.add(value);
                        values.put(attr, vals);

                        set.add(val);
                    }
                    s = Utilities.getLine(buf, ",");
                }
                if (set.size() > 0) {
                    ArrayList<SpatioTemporalVal> monthlyArr = a.data.get(month);
                    if (monthlyArr == null) {
                        monthlyArr = new ArrayList<>();
                        a.data.put(month, monthlyArr);
                    }
                    monthlyArr.addAll(set);
                }
            }

            if (dataAttributesHashSet.contains(attr)) {
                attributes.put(attr, a);
            }
            s = Utilities.getLine(buf, ",");
        }
        buf.close();

        for (Attribute a : attributes.values()) {
            for (ArrayList<SpatioTemporalVal> arr : a.data.values()) {
                Collections.sort(arr);
            }
            a.nodeSet = nodeSet;
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}

From source file:it.iit.genomics.cru.structures.bridges.uniprot.UniprotkbUtils.java

/**
 *
 * @param refSeqs/*from w  ww .j a v a2s.c  o  m*/
 * @return
 * @throws BridgesRemoteAccessException
 */
public MapOfMap<String, MoleculeEntry> getUniprotEntriesFromRefSeqs(Collection<String> refSeqs)
        throws BridgesRemoteAccessException {
    String tool = UNIPROT_TOOL;

    MapOfMap<String, MoleculeEntry> refseq2uniprots = new MapOfMap<>(refSeqs);

    if (refSeqs.isEmpty()) {
        return refseq2uniprots;
    }

    HashSet<String> refs2get = new HashSet<>();

    try {
        for (String refseq : refSeqs) {
            if (cache.containsKey(refseq.toUpperCase().split("\\.")[0])) {
                refseq2uniprots.addAll(refseq, cache.get(refseq.toUpperCase().split("\\.")[0]));
            } else {
                refs2get.add(refseq);

                // if size == limit, do query
                if (refs2get.size() == maxQueries) {

                    String location = UNIPROT_SERVER + tool + "/?" + "query=keyword:181+AND+organism:"
                            + URLEncoder.encode("\"" + taxid + "\"", "UTF-8")
                            + "+AND+(database%3A(type%3Arefseq+"
                            + URLEncoder.encode(
                                    "" + StringUtils.join(refs2get, ") OR database:(type:refseq ") + "",
                                    "UTF-8")
                            + "))";

                    Collection<MoleculeEntry> uniprotEntries = getUniprotEntriesXML(location);

                    for (MoleculeEntry entry : uniprotEntries) {
                        for (String xref : entry.getRefseqs()) {
                            if (xref.endsWith(".")) {
                                xref = xref.substring(0, xref.length() - 1);
                            }
                            if (refseq2uniprots.containsKey(xref.trim())) {
                                refseq2uniprots.add(xref, entry);
                            } else if (refseq2uniprots.containsKey(xref.split("[.]")[0])) {
                                refseq2uniprots.add(xref.split("[.]")[0], entry);
                            }
                        }
                    }
                    refs2get.clear();
                }

            }
        }

        if (refs2get.isEmpty()) {
            return refseq2uniprots;
        }

        String location = UNIPROT_SERVER + tool + "/?" + "query=keyword:181+AND+organism:"
                + URLEncoder.encode("\"" + taxid + "\"", "UTF-8") + "+AND+(database%3A(type%3Arefseq+"
                + URLEncoder.encode("" + StringUtils.join(refs2get, ") OR database:(type:refseq ") + "",
                        "UTF-8")
                + "))";

        Collection<MoleculeEntry> uniprotEntries = getUniprotEntriesXML(location);

        for (MoleculeEntry entry : uniprotEntries) {
            for (String xref : entry.getRefseqs()) {
                if (xref.endsWith(".")) {
                    xref = xref.substring(0, xref.length() - 1);
                }
                if (refseq2uniprots.containsKey(xref.trim())) {
                    refseq2uniprots.add(xref, entry);
                } else if (refseq2uniprots.containsKey(xref.split("[.]")[0])) {
                    refseq2uniprots.add(xref.split("[.]")[0], entry);
                }
            }
        }

    } catch (UnsupportedEncodingException e) {
        logger.error("cannot get proteins for " + StringUtils.join(refSeqs, ", "), e);
    }

    return refseq2uniprots;
}

From source file:hms.hwestra.interactionrebuttal.InteractionRebuttal.java

public void prepareDataForCelltypeSpecificEQTLMapping(DoubleMatrixDataset<String, String> rawExpressionDataset,
        String inexpraw, String outdirectory, Double correlationThreshold, String celltypeSpecificProbeFile,
        String mdsComponentFile, String cellCountFile, String gte, Integer threads) throws IOException {
    String rawExpressionDataFile = inexpraw;
    // 7. select Cell type specific probes
    System.out.println("Loading list of cell type specific probes from: " + celltypeSpecificProbeFile);
    HashSet<String> cellTypeSpecificProbeSet = new HashSet<String>();
    TextFile cellSpecificProbeTF = new TextFile(celltypeSpecificProbeFile, TextFile.R);
    cellTypeSpecificProbeSet.addAll(cellSpecificProbeTF.readAsArrayList());
    cellSpecificProbeTF.close();/*  w ww .j av a  2s  . c o m*/

    if (cellTypeSpecificProbeSet.isEmpty()) {
        System.err.println("Error: " + celltypeSpecificProbeFile + " is empty!");
        System.exit(-1);
    } else {
        System.out.println(cellTypeSpecificProbeSet.size() + " cell type specific probes loaded.");
    }

    // 1. load gene expression data
    System.out.println("Loading gene expression data.");

    double[][] rawExpressionData = rawExpressionDataset.getRawData();

    // determine the number of cell type specific probes in this dataset
    int probeCounter = 0;
    List<String> probes = rawExpressionDataset.rowObjects;
    for (int i = 0; i < probes.size(); i++) {
        if (cellTypeSpecificProbeSet.contains(probes.get(i))) {
            probeCounter++;
        }
    }

    if (probeCounter == 0) {
        System.err
                .println("Error: none of the cell type specific probes defined in " + celltypeSpecificProbeFile
                        + " are present in expression dataset: " + rawExpressionDataset.fileName);
        System.exit(-1);
    } else {
        System.out.println(probeCounter + " of the cell type specific probes are in your dataset.");
    }

    System.out.println("Now reloading the gene expression data for the samples that passed the QC.");
    // 6. Remove samples with r < 0.9 for PC1
    // reload expression file, include only samples that pass QC...
    //        rawExpressionDataset = new DoubleMatrixDataset<String, String>(rawExpressionDataFile);
    //        rawExpressionData = rawExpressionDataset.getRawData();

    //        // quantile normalize, log2 transform again, because the number of samples might have been changed..
    //        QuantileNormalization.quantilenormalize(rawExpressionData);
    //        Log2Transform.log2transform(rawExpressionData);
    rawExpressionData = rawExpressionDataset.rawData;

    // collect data for cell type specific probes
    double[][] probeData = new double[probeCounter][rawExpressionDataset.colObjects.size()];
    probeCounter = 0;
    ArrayList<String> cellTypeSpecificProbeDatasetRowNames = new ArrayList<String>();
    for (int i = 0; i < probes.size(); i++) {
        if (cellTypeSpecificProbeSet.contains(probes.get(i))) {
            probeData[probeCounter] = rawExpressionData[i];
            cellTypeSpecificProbeDatasetRowNames.add(probes.get(i));
            probeCounter++;
        }
    }

    // initiate cell type specific probe correlation matrix
    double[][] celltypeSpecificCorrelationMatrix = new double[probeCounter][probeCounter];
    for (int i = 0; i < probeCounter; i++) {
        for (int j = i + 1; j < probeCounter; j++) {
            double r = Correlation.correlate(probeData[i], probeData[j]);
            celltypeSpecificCorrelationMatrix[i][j] = r;
            celltypeSpecificCorrelationMatrix[j][i] = r;
        }
        celltypeSpecificCorrelationMatrix[i][i] = 1;
    }

    // save the correlation matrix
    DoubleMatrixDataset<String, String> probeCorrelationMatrixOut = new DoubleMatrixDataset<String, String>();
    probeCorrelationMatrixOut.colObjects = cellTypeSpecificProbeDatasetRowNames;
    probeCorrelationMatrixOut.rowObjects = cellTypeSpecificProbeDatasetRowNames;
    probeCorrelationMatrixOut.rawData = celltypeSpecificCorrelationMatrix;
    probeCorrelationMatrixOut.recalculateHashMaps();
    //        probeCorrelationMatrixOut.save(outdirectory + "CelltypeSpecificProbeCorrelationMatrix.txt.gz");

    // 9. PCA over cell specific probe correlation matrix
    DoubleMatrixDataset<String, String> cellTypeSpecificDataset = new DoubleMatrixDataset<String, String>(
            probeData);
    cellTypeSpecificDataset.colObjects = rawExpressionDataset.colObjects;
    cellTypeSpecificDataset.rowObjects = cellTypeSpecificProbeDatasetRowNames;
    //        cellTypeSpecificDataset.save(expressionOutputDirectory + "CellTypeSpecificProbeExpression.txt.gz");
    cellTypeSpecificDataset.transposeDataset();
    Normalizer n = new Normalizer();
    // calculate first Principal Component over the cell type specific probe matrix...
    Pair<DoubleMatrixDataset<String, String>, DoubleMatrixDataset<String, String>> PCAResults = n.calculatePCA(
            cellTypeSpecificDataset, celltypeSpecificCorrelationMatrix,
            outdirectory + "CellTypeSpecificProbePCA", 1);

    // 10. PC1 scores: cell specific proxy -- write to file for future use...
    DoubleMatrixDataset<String, String> cellSpecificPCScores = PCAResults.getLeft();

    //Ensure that the cellTypeSpecificPCScores correlate positively with the set of probes that we have used to determine this component:
    double[] pcScoresSamples = new double[cellSpecificPCScores.nrRows];
    for (int i = 0; i < cellSpecificPCScores.nrRows; i++) {
        pcScoresSamples[i] = cellSpecificPCScores.rawData[i][0];
    }
    cellTypeSpecificDataset.transposeDataset();
    int nrProbesCorrelatingPositively = 0;
    for (int i = 0; i < cellTypeSpecificDataset.rawData.length; i++) {
        double corr = JSci.maths.ArrayMath.correlation(pcScoresSamples, cellTypeSpecificDataset.rawData[i]);
        if (corr >= 0) {
            nrProbesCorrelatingPositively++;
        } else {
            nrProbesCorrelatingPositively--;
        }
    }
    if (nrProbesCorrelatingPositively < 0) {
        for (int i = 0; i < cellSpecificPCScores.nrRows; i++) {
            cellSpecificPCScores.rawData[i][0] = -cellSpecificPCScores.rawData[i][0];
        }
    }

    TextFile tfOutCellSpecific = new TextFile(outdirectory + "CellTypeProxyFile.txt", TextFile.W);
    tfOutCellSpecific.writeln("Sample\tCellCountProxyValue");
    for (int i = 0; i < cellSpecificPCScores.nrRows; i++) {
        tfOutCellSpecific
                .writeln(cellSpecificPCScores.rowObjects.get(i) + "\t" + cellSpecificPCScores.rawData[i][0]);
    }
    tfOutCellSpecific.close();

    File f = new File(outdirectory + "CellTypeSpecificProbePCA.PCAOverSamplesEigenvalues.txt.gz");
    f.delete();
    f = new File(outdirectory + "CellTypeSpecificProbePCA.PCAOverSamplesEigenvectors.txt.gz");
    f.delete();
    f = new File(outdirectory + "CellTypeSpecificProbePCA.PCAOverSamplesEigenvectorsTransposed.txt.gz");
    f.delete();
    f = new File(outdirectory + "CellTypeSpecificProbePCA.PCAOverSamplesPrincipalComponents.txt.gz");
    f.delete();

}

From source file:org.apache.roller.weblogger.business.WeblogEntryTest.java

public void testUpdateTags() throws Exception {

    WeblogEntryManager mgr = WebloggerFactory.getWeblogger().getWeblogEntryManager();

    // setup some test entries to use
    testWeblog = TestUtils.getManagedWebsite(testWeblog);
    testUser = TestUtils.getManagedUser(testUser);
    WeblogEntry entry = TestUtils.setupWeblogEntry("entry1", testWeblog.getDefaultCategory(), testWeblog,
            testUser);/* w ww .  j a v a  2  s.  c  o m*/
    entry.addTag("testWillStayTag");
    entry.addTag("testTagWillBeRemoved");
    String id = entry.getId();
    mgr.saveWeblogEntry(entry);
    TestUtils.endSession(true);

    entry = mgr.getWeblogEntry(id);
    assertEquals(2, entry.getTags().size());

    List updateTags = new ArrayList();
    updateTags.add("testwillstaytag");
    updateTags.add("testnewtag");
    updateTags.add("testnewtag3");
    entry.updateTags(updateTags);
    mgr.saveWeblogEntry(entry);
    TestUtils.endSession(true);

    entry = mgr.getWeblogEntry(id);
    HashSet tagNames = new HashSet();
    for (Iterator it = entry.getTags().iterator(); it.hasNext();) {
        WeblogEntryTag tagData = (WeblogEntryTag) it.next();
        tagNames.add(tagData.getName());
    }

    assertEquals(3, entry.getTags().size());
    assertEquals(3, tagNames.size());
    assertEquals(true, tagNames.contains("testwillstaytag"));
    assertEquals(true, tagNames.contains("testnewtag"));
    assertEquals(true, tagNames.contains("testnewtag3"));

    // teardown our test entry
    TestUtils.teardownWeblogEntry(id);
    TestUtils.endSession(true);
}

From source file:edu.nyu.vida.data_polygamy.exp.NoiseExp.java

void load1DData(String aggregatesFile, int year) {
    String[] s = null;// ww  w.j av  a2  s.c o m
    try {
        BufferedReader buf = new BufferedReader(new FileReader(aggregatesFile));
        s = Utilities.getLine(buf, ",");
        while (true) {
            if (s == null) {
                break;
            }
            String attr = Utilities.splitString(s[0], ":")[1].trim();
            //System.out.println("Attribute: " + attr);
            Attribute a = new Attribute();
            a.nodeSet.add(0);
            s = Utilities.getLine(buf, ",");
            if (s != null && s.length > 0 && s[0].toLowerCase().startsWith("spatial")) {
                s = Utilities.getLine(buf, ",");
            }
            if (s == null || s.length == 0) {
                System.out.println("Empty: ---------------------- " + attr);
            }
            while (s != null && s.length > 0) {
                int month = Integer.parseInt(Utilities.splitString(s[0], ":")[1].trim());
                s = Utilities.getLine(buf, ",");
                HashSet<SpatioTemporalVal> set = new HashSet<SpatioTemporalVal>();
                while (s != null && s.length == 2) {
                    if (month / 100 == year) {
                        int time = Integer.parseInt(s[0]);
                        float value = Float.parseFloat(s[1]);

                        SpatioTemporalVal val = new SpatioTemporalVal(0, time, value);
                        set.add(val);

                        ArrayList<Float> vals = (values.get(attr) == null) ? new ArrayList<Float>()
                                : values.get(attr);
                        vals.add(value);
                        values.put(attr, vals);

                        set.add(val);
                    }
                    s = Utilities.getLine(buf, ",");
                }
                if (set.size() > 0) {
                    ArrayList<SpatioTemporalVal> arr = new ArrayList<SpatioTemporalVal>(set);
                    Collections.sort(arr);
                    a.data.put(month, arr);
                }
            }

            if (dataAttributesHashSet.contains(attr)) {
                attributes.put(attr, a);
            }
            s = Utilities.getLine(buf, ",");
        }
        buf.close();
    } catch (Exception e) {
        e.printStackTrace();
    }
}

From source file:org.isatools.isatab.export.pride.DraftPrideExporter.java

/**
 * walk across the experimental pipeline, passed to
 * {@link ExperimentalPipelineVisitor#visit(ProcessingVisitAction, uk.ac.ebi.bioinvindex.model.impl.processing.Node)}.
 *///from  ww w .ja  v a 2 s  . c  o m
public boolean visit(GraphElement graphElement) {
    if (graphElement instanceof Processing<?, ?>) {
        Processing<?, ?> processing = (Processing<?, ?>) graphElement;
        for (ProtocolApplication protoApp : processing.getProtocolApplications()) {
            // TODO: filter on the protocol type

            // Processes the protocol
            //
            Set<CvParam> cvparams = new HashSet<CvParam>();
            HashSet<UserParam> uparams = new HashSet<UserParam>();
            Protocol protocol = protoApp.getProtocol();
            if (protocol != null) {
                ProtocolType type = protocol.getType();
                if (type != null) {
                    ReferenceSource typeSrc = type.getSource();
                    if (typeSrc == null) {
                        throw new TabMissingValueException(i18n.msg("ontoterm_without_source", type));
                    }
                    uparams.add(new UserParamImpl("BioInvestigation Index Protocol Type", 0, type.getName()));
                    cvparams.add(
                            new CvParamImpl(type.getAcc(), type.getSource().getAcc(), type.getName(), 0, ""));
                }
                uparams.add(new UserParamImpl("BioInvestigation Index Protocol Name", 2 + uparams.size(),
                        protocol.getName()));
                uparams.add(new UserParamImpl("BioInvestigation Index Protocol Description", 2 + uparams.size(),
                        protocol.getDescription()));
            } else {
                log.trace("PRIDE exporting, no protocol defined for the processing " + processing.getAcc());
            }

            // Adds up the parameters
            //
            for (ParameterValue param : protoApp.getParameterValues()) {
                Parameter ptype = param.getType();
                Collection<Param> prideParams = exportPropertyValue(param, ptype.getOrder() + 3);

                if (ptype.getRole() == PropertyRole.FACTOR) {
                    prideExperimentParams.addAll(prideParams);
                }

                for (Param prideParam : prideParams) {
                    if (prideParam instanceof CvParam) {
                        cvparams.add((CvParam) prideParam);
                    } else if (prideParam instanceof UserParam) {
                        uparams.add((UserParam) prideParam);
                    }
                }
            }

            ProtocolStep prideProtoStep = new ProtocolStepImpl(prideProtoSteps.size(), cvparams, uparams);
            prideProtoSteps.add(prideProtoStep);
        }
    } else if (graphElement instanceof MaterialNode) {
        Material material = ((MaterialNode) graphElement).getMaterial();

        // Get the factors
        for (CharacteristicValue characteristic : material.getCharacteristicValues()) {
            Characteristic ctype = characteristic.getType();

            if (ctype.getRole() == PropertyRole.FACTOR) {
                prideExperimentParams.addAll(exportPropertyValue(characteristic, ctype.getOrder()));
            }
        }
    } else if (graphElement instanceof DataNode) {
        Data data = ((DataNode) graphElement).getData();
        String dataTypeAcc = data.getType().getAcc();

        if ("bii:ms_spec_raw_data".equals(dataTypeAcc)) {
            mzDataPath = data.getUrl();
        }

        // Get the proteins files from the MS/SPEC run material
        if ("bii:ms_spec_derived_data".equals(dataTypeAcc)
                || "bii:ms_spec_normalized_data".equals(dataTypeAcc)) {
            String identificationsPath = StringUtils.trimToNull(data.getSingleAnnotationValue("proteinsFile"));
            if (identificationsPath != null) {
                this.identificationsPath = importPath + "/" + identificationsPath;
            }

            String peptidesPath = StringUtils.trimToNull(data.getSingleAnnotationValue("peptidesFile"));
            if (peptidesPath != null) {
                this.peptidesPath = importPath + "/" + peptidesPath;
            }

            String modificationsPath = StringUtils.trimToNull(data.getSingleAnnotationValue("ptmsFile"));
            if (modificationsPath != null) {
                this.modificationsPath = importPath + "/" + modificationsPath;
            }
        }

    }
    // if graphElement

    return true;
}

From source file:amie.keys.CSAKey.java

/**
 *
 * @param ruleToExtendWith//from   w  w  w  .j  a v  a 2 s  .  c  om
 * @param ruleToGraphFirstLevel
 * @param ruleToGraphLastLevel
 * @param kb
 */
private void discoverConditionalKeysPerLevel(HashMap<Rule, HashSet<String>> ruleToExtendWith,
        HashMap<Rule, Graph> ruleToGraphFirstLevel, HashMap<Rule, Graph> ruleToGraphLastLevel,
        Set<Rule> output) {
    //System.out.println("discoverConditionalKeysPerLevel()");
    HashMap<Rule, Graph> ruleToGraphThisLevel = new HashMap<>();
    for (Rule currentRule : ruleToExtendWith.keySet()) {
        Graph graph = ruleToGraphLastLevel.get(currentRule);
        //System.out.println("Current rule: " + currentRule+ " Graph:"+graph);
        for (String conditionProperty : ruleToExtendWith.get(currentRule)) {
            if (Utilities.getRelationIds(currentRule, property2Id).last() > property2Id
                    .get(conditionProperty)) {
                Graph currentGraphNew = (Graph) graph.clone();
                Integer propertyId = property2Id.get(conditionProperty);
                HashSet<Integer> propertiesSet = new HashSet<>();
                propertiesSet.add(propertyId);
                Node node = currentGraphNew.createOrGetNode(propertiesSet); //Before it was createNode
                node.toExplore = false;
                Iterable<Rule> conditions = Utilities.getConditions(currentRule, conditionProperty,
                        (int) support, kb);
                for (Rule conditionRule : conditions) {
                    Rule complementaryRule = getComplementaryRule(conditionRule);
                    if (!ruleToGraphFirstLevel.containsKey(complementaryRule)) {
                        // We should never fall in this case
                        for (Rule r : ruleToGraphFirstLevel.keySet()) {
                            System.out.println(r.getDatalogBasicRuleString());
                        }
                        System.out.println(complementaryRule.getDatalogBasicRuleString());
                        System.out.println(complementaryRule + " not found in the first level graph");
                    }

                    Graph complementaryGraphNew = ruleToGraphFirstLevel.get(complementaryRule);
                    //System.out.println("Complementary rule: " + complementaryRule + "\tThread " + Thread.currentThread().getId() + "\t" + complementaryGraphNew);
                    Graph newGraphNew = (Graph) currentGraphNew.clone();
                    HashSet<Integer> conditionProperties = new HashSet<>();
                    conditionProperties.addAll(getRelations(conditionRule, property2Id));
                    conditionProperties.addAll(getRelations(currentRule, property2Id));
                    //System.out.println("currentGraph:"+currentGraphNew);
                    //System.out.println("clone of currentGraph:"+newGraphNew);
                    newGraphNew = mergeGraphs(newGraphNew, complementaryGraphNew, newGraphNew.topGraphNodes(),
                            conditionProperties);
                    //System.out.println("newMergeGraph:"+newGraphNew);
                    discoverConditionalKeysForComplexConditions(newGraphNew, newGraphNew.topGraphNodes(),
                            conditionRule, output);
                    ruleToGraphThisLevel.put(conditionRule, newGraphNew);
                }
            }
        }
    }
    HashMap<Rule, HashSet<String>> newRuleToExtendWith = new HashMap<>();
    for (Rule conRule : ruleToGraphThisLevel.keySet()) {
        Graph newGraphNew = ruleToGraphThisLevel.get(conRule);
        for (Node node : newGraphNew.topGraphNodes()) {
            HashSet<String> properties = new HashSet<>();
            if (node.toExplore) {
                Iterator<Integer> it = node.set.iterator();
                int prop = it.next();
                String propertyStr = id2Property.get(prop);
                properties.add(propertyStr);
            }
            if (properties.size() != 0) {
                newRuleToExtendWith.put(conRule, properties);
            }
        }
    }

    if (newRuleToExtendWith.size() != 0) {
        discoverConditionalKeysPerLevel(newRuleToExtendWith, ruleToGraphFirstLevel, ruleToGraphThisLevel,
                output);
    }

    //System.out.println("discoverConditionalKeysPerLevel()");

}

From source file:it.iit.genomics.cru.structures.bridges.uniprot.UniprotkbUtils.java

/**
 *
 * @param ensemblGeneIDs// w w w  . j  ava  2  s  . c o  m
 * @return
 * @throws BridgesRemoteAccessException
 */
public MapOfMap<String, MoleculeEntry> getUniprotEntriesFromEnsembl(Collection<String> ensemblGeneIDs)
        throws BridgesRemoteAccessException {
    String tool = UNIPROT_TOOL;

    MapOfMap<String, MoleculeEntry> ensembl2uniprots = new MapOfMap<>(ensemblGeneIDs);

    if (ensemblGeneIDs.isEmpty()) {
        return ensembl2uniprots;
    }

    HashSet<String> refs2get = new HashSet<>();

    try {

        for (String ensemblGeneID : ensemblGeneIDs) {
            if (cache.containsKey(ensemblGeneID.toUpperCase().split("\\.")[0])) {
                ensembl2uniprots.addAll(ensemblGeneID, cache.get(ensemblGeneID.toUpperCase().split("\\.")[0]));
            } else {
                refs2get.add(ensemblGeneID);

                // if size == limit, do query
                if (refs2get.size() == maxQueries) {
                    String location = UNIPROT_SERVER + tool + "/?" + "query=keyword:181+AND+organism:"
                            + URLEncoder.encode("\"" + taxid + "\"", "UTF-8")
                            + "+AND+(database%3A(type%3Aensembl+"
                            + URLEncoder.encode(
                                    "" + StringUtils.join(refs2get, ") OR database:(type:ensembl ") + "",
                                    "UTF-8")
                            + "))";

                    Collection<MoleculeEntry> uniprotEntries = getUniprotEntriesXML(location);

                    for (MoleculeEntry entry : uniprotEntries) {
                        for (String xref : entry.getEnsemblGenes()) {
                            if (xref.endsWith(".")) {
                                xref = xref.substring(0, xref.length() - 1);
                            }
                            if (ensembl2uniprots.containsKey(xref.trim())) {
                                ensembl2uniprots.add(xref, entry);
                            } else if (ensembl2uniprots.containsKey(xref.split("[.]")[0])) {
                                ensembl2uniprots.add(xref.split("[.]")[0], entry);
                            }
                        }
                    }
                    refs2get.clear();
                }
            }
        }

        if (refs2get.isEmpty()) {
            return ensembl2uniprots;
        }

        String location = UNIPROT_SERVER + tool + "/?" + "query=keyword:181+AND+organism:"
                + URLEncoder.encode("\"" + taxid + "\"", "UTF-8") + "+AND+(database%3A(type%3Aensembl+"
                + URLEncoder.encode("" + StringUtils.join(refs2get, ") OR database:(type:ensembl ") + "",
                        "UTF-8")
                + "))";

        Collection<MoleculeEntry> uniprotEntries = getUniprotEntriesXML(location);

        for (MoleculeEntry entry : uniprotEntries) {
            for (String xref : entry.getEnsemblGenes()) {
                if (xref.endsWith(".")) {
                    xref = xref.substring(0, xref.length() - 1);
                }
                if (ensembl2uniprots.containsKey(xref.trim())) {
                    ensembl2uniprots.add(xref, entry);
                } else if (ensembl2uniprots.containsKey(xref.split("[.]")[0])) {
                    ensembl2uniprots.add(xref.split("[.]")[0], entry);
                }
            }
        }

    } catch (UnsupportedEncodingException e) {
        logger.error("cannot get proteins for " + StringUtils.join(ensemblGeneIDs, ", "), e);
    }

    return ensembl2uniprots;
}