Example usage for java.util Set retainAll

List of usage examples for java.util Set retainAll

Introduction

In this page you can find the example usage for java.util Set retainAll.

Prototype

boolean retainAll(Collection<?> c);

Source Link

Document

Retains only the elements in this set that are contained in the specified collection (optional operation).

Usage

From source file:edu.usc.polar.CompositeNERAgreementParser.java

public static void CompositeNER(String doc, String args[]) {
    try {/* w ww. j  a v a  2 s  .c  o m*/
        String text;
        AutoDetectParser parser = new AutoDetectParser();
        BodyContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = new FileInputStream(doc);

        //   System.out.println(stream.toString());
        parser.parse(stream, handler, metadata);
        // return handler.toString();
        text = handler.toString();
        String metaValue = metadata.toString();
        System.out.println(metaValue + "Desc:: " + metadata.get("description"));

        String[] example = new String[1];
        example[0] = text;
        String name = doc.replace("C:\\Users\\Snehal\\Documents\\TREC-Data\\Data", "polar.usc.edu");
        name = name.replace("\\", ".");
        Map<String, Set<String>> list = getCoreNLP(text);
        Map<String, Set<String>> list1 = getOpenNLP(text);
        Map<String, Set<String>> list2 = getNLTKRest(text);

        Set<String> NLTKRestSet = combineSets(list2);
        Set<String> coreNLPSet = combineSets(list);
        Set<String> openNLPSet = combineSets(list1);

        /* 
         System.out.println("list coreNLP"+JSONStringify(coreNLPSet).toJSONString());
         System.out.println("list openNLPSet"+openNLPSet);
         System.out.println("list NLTKRestSet"+NLTKRestSet);          
         */
        JSONObject jsonObj = new JSONObject();
        jsonObj.put("DOI", name);
        jsonObj.put("OpenNLP", JSONStringify(openNLPSet));
        jsonObj.put("NLTKRest", JSONStringify(NLTKRestSet));
        jsonObj.put("CoreNLP", JSONStringify(coreNLPSet));

        Set<String> union = new HashSet();
        union.addAll(NLTKRestSet);
        union.addAll(coreNLPSet);
        union.addAll(openNLPSet);

        jsonObj.put("Union", JSONStringify(union));
        Set<String> intersection = new HashSet();
        intersection.addAll(union);
        intersection.retainAll(coreNLPSet);
        intersection.retainAll(openNLPSet);
        intersection.retainAll(NLTKRestSet);
        jsonObj.put("Agreement", JSONStringify(intersection));
        /*
        System.out.println(name+"\n"+openNLPSet.size()+openNLPSet.toString()+
          "\n"+coreNLPSet.size()+coreNLPSet.toString()+
          "\n"+NLTKRestSet.size()+NLTKRestSet.toArray()+
          "\n"+intersection.size()+intersection.toArray()+
          "\n"+union.size()+union.toArray());
        */

        //jsonObj.put("metadata",metaValue.replaceAll("\\s\\s+|\n|\t"," "));             

        jsonArray.add(jsonObj);
        if (intersection.size() > 0) {
            jsonAgree.add(jsonObj);
            JSONArray jArr = new JSONArray();
            jArr.add(jsonObj);
            metadata.add("CompositeNER", jArr.toJSONString());
        }

    } catch (Exception e) {
        System.out.println("ERROR : OpenNLP" + "|File Name"
                + doc.replaceAll("C:\\Users\\Snehal\\Documents\\TREC-Data", "") + " direct" + e.toString());
    }
}

From source file:org.apache.lens.cube.parse.StorageUtil.java

private static Map<String, Set<FactPartition>> getMaxCoveringStorage(
        final Map<String, Set<FactPartition>> storageCoveringMap, Set<FactPartition> queriedParts) {
    int coveringcount = 0;
    int maxCoveringCount = 0;
    String maxCoveringStorage = null;
    Set<FactPartition> maxCoveringSet = null;
    for (Map.Entry<String, Set<FactPartition>> entry : storageCoveringMap.entrySet()) {
        Set<FactPartition> coveringSet = new TreeSet<FactPartition>();
        coveringSet.addAll(entry.getValue());
        coveringSet.retainAll(queriedParts);
        coveringcount = coveringSet.size();
        if (coveringcount > maxCoveringCount) {
            maxCoveringCount = coveringcount;
            maxCoveringStorage = entry.getKey();
            maxCoveringSet = coveringSet;
        }/*www.ja va2  s.co m*/
    }
    return Collections.singletonMap(maxCoveringStorage, maxCoveringSet);
}

From source file:org.talend.core.classloader.ClassLoaderFactory.java

/**
 * DOC ycbai Comment method "getCustomClassLoader".
 * /* w w w . j a  v a2  s.  co m*/
 * @param index
 * @param libraries
 * @return the classLoader by specific libraries
 */
public static DynamicClassLoader getCustomClassLoader(String index, Set<String> libraries) {
    if (libraries == null || libraries.size() == 0) {
        return null;
    }

    DynamicClassLoader classLoader = getClassLoader(index);
    if (classLoader == null) {
        classLoader = createCustomClassLoader(index, libraries);
    } else {
        boolean changed;
        Set<String> oldLibraries = classLoader.getLibraries();
        Set<String> oldLibrariesClone = new HashSet<String>(oldLibraries);
        changed = oldLibrariesClone.retainAll(libraries);
        if (!changed) {
            Set<String> newLibrariesClone = new HashSet<String>(libraries);
            changed = newLibrariesClone.retainAll(oldLibraries);
        }
        if (changed) {
            File libFolder = new File(classLoader.getLibStorePath());
            if (libFolder.exists()) {
                FilesUtils.removeFolder(libFolder, true);
            }
            classLoader = createCustomClassLoader(index, libraries);
        }
    }

    return classLoader;
}

From source file:ubic.pubmedgate.interactions.evaluation.RecallCuratorsCombined.java

public static void splitBySentences() throws Exception {
    String baseFolder = Config.config.getString("whitetext.iteractions.ppiBaseFolder")
            + "Saved Results/SL/CC/NegFixFullOnUnseen/";
    String corpusFilename = Config.config.getString("whitetext.iteractions.ppiBaseFolder")
            + "Corpora/Original-Modified/WhiteTextUnseen.orig.xml";
    String trainingSet = "WhiteTextNegFixFull";
    String testSet = "WhiteTextUnseen";
    String annotationSet = "Mallet";

    SLOutputReader SLReader = new SLOutputReader(trainingSet, testSet, baseFolder);
    log.info("Score size:" + SLReader.getScores().size());

    GateInterface p2g = new GateInterface();
    p2g.setUnSeenCorpNull();/*www.  j  ava  2  s . co  m*/
    p2g.setNamedCorpNull("PubMedUnseenJNChem");
    // p2g.setNamedCorpNull("PubMedUnseenJCN");
    p2g.setNamedCorpNull("PubMedUnseenMScan1");
    p2g.setNamedCorpNull("PubMedUnseenMScan2");
    AirolaXMLReader XMLReader = new AirolaXMLReader(corpusFilename, p2g, annotationSet);

    Set<String> sentences = XMLReader.getAllSentences();
    log.info("All sentences:" + sentences.size());
    List<String> posPredictedPairs = SLReader.getPositivePredictions();
    StringToStringSetMap sentenceIDToPairs = XMLReader.getSentenceIDToPairs();
    int sentencesWithPosPrecitions = 0;
    int sentencesWithOnlyNegPrecitions = 0;
    int pairsFromSenPosPrecitions = 0;
    int posPairsFromSenPosPrecitions = 0;
    Set<String> pairsFromSenPosPrecitionsSet = new HashSet<String>();
    int pairsFromSenOnlyNegPrecitions = 0;
    Set<String> pairsFromSenOnlyNegPrecitionsSet = new HashSet<String>();
    Set<String> pairsToUse = new HashSet<String>();
    log.info("All pairs:" + SLReader.getAll().size());

    for (String sentence : sentences) {
        Set<String> pairs = new HashSet<String>(sentenceIDToPairs.get(sentence));
        int pairCount = pairs.size();
        pairs.retainAll(posPredictedPairs);
        if (pairs.size() > 0) {
            sentencesWithPosPrecitions++;
            pairsFromSenPosPrecitions += pairCount;
            // just positives
            posPairsFromSenPosPrecitions += pairs.size();
            pairsFromSenPosPrecitionsSet.addAll(sentenceIDToPairs.get(sentence));
        } else {
            sentencesWithOnlyNegPrecitions++;
            pairsFromSenOnlyNegPrecitions += pairCount;
            pairsFromSenOnlyNegPrecitionsSet.addAll(sentenceIDToPairs.get(sentence));
        }

    }
    log.info("sentencesWithOnlyNegPrecitions:" + sentencesWithOnlyNegPrecitions);
    log.info("pairsFromSenOnlyNegPrecitions:" + pairsFromSenOnlyNegPrecitions);
    log.info("");
    log.info("sentencesWithPosPrecitions:" + sentencesWithPosPrecitions);
    log.info("pairsFromSenPosPrecitions:" + pairsFromSenPosPrecitions);
    log.info("posPairsFromSenPosPrecitions, positive pairs in sentences with at least one positive:"
            + posPairsFromSenPosPrecitions);
    log.info("pairsToUse:" + pairsToUse.size());

    RecallCuratorsCombined combined = new RecallCuratorsCombined();
    combined.load6000Set();

    combined.printAllStats();
    System.out.println();
    System.out.println();

    combined.retainPairs(pairsFromSenPosPrecitionsSet);
    combined.printAllStats();
    System.out.println();
    System.out.println();

    combined = new RecallCuratorsCombined();
    combined.load6000Set();
    combined.retainPairs(pairsFromSenOnlyNegPrecitionsSet);
    combined.printAllStats();

    // combined.printDisagreements( "Accept" );

}

From source file:common.Utilities.java

public static double getCosineSim(Map<Integer, Integer> targetMap, Map<Integer, Integer> nMap) {
    Set<Integer> both = new HashSet<Integer>(targetMap.keySet());
    both.retainAll(nMap.keySet());
    double scalar = 0.0, norm1 = 0.0, norm2 = 0.0;
    for (int k : both)
        scalar += (targetMap.get(k) * nMap.get(k));
    for (int k : targetMap.keySet())
        norm1 += (targetMap.get(k) * targetMap.get(k));
    for (int k : nMap.keySet())
        norm2 += (nMap.get(k) * nMap.get(k));
    return scalar / Math.sqrt(norm1 * norm2);
}

From source file:common.Utilities.java

public static double getCosineFloatSim(Map<Integer, Double> targetMap, Map<Integer, Double> nMap) {
    Set<Integer> both = new HashSet<Integer>(targetMap.keySet());
    both.retainAll(nMap.keySet());
    double scalar = 0.0, norm1 = 0.0, norm2 = 0.0;
    for (int k : both)
        scalar += (targetMap.get(k) * nMap.get(k));
    for (int k : targetMap.keySet())
        norm1 += (targetMap.get(k) * targetMap.get(k));
    for (int k : nMap.keySet())
        norm2 += (nMap.get(k) * nMap.get(k));
    return scalar / Math.sqrt(norm1 * norm2);
}

From source file:tools.xor.util.ClassUtil.java

public static boolean intersectsTags(String[] tags, String[] otherTags) {
    Set<String> commonTags = new HashSet<String>(Arrays.asList(tags));
    commonTags.retainAll(new HashSet<String>(Arrays.asList(otherTags)));
    if (commonTags.isEmpty()) {
        // applies to different tags so they do not overlap
        return false;
    }// w  ww  .  j a  v a2 s.  c  o m

    return true;
}

From source file:common.Utilities.java

public static double getJaccardSim(Map<Integer, Integer> targetMap, Map<Integer, Integer> nMap) {
    Set<Integer> unionSet = new HashSet<Integer>(targetMap.keySet());
    Set<Integer> intersectSet = new HashSet<Integer>(targetMap.keySet());
    unionSet.addAll(nMap.keySet());//from ww w  .java2  s.  co  m
    intersectSet.retainAll(nMap.keySet());
    return (double) intersectSet.size() / (double) unionSet.size();
}

From source file:common.Utilities.java

public static double getJaccardFloatSim(Map<Integer, Double> targetMap, Map<Integer, Double> nMap) {
    Set<Integer> unionSet = new HashSet<Integer>(targetMap.keySet());
    Set<Integer> intersectSet = new HashSet<Integer>(targetMap.keySet());
    unionSet.addAll(nMap.keySet());/*from   w ww . j  av  a2 s .  c  o  m*/
    intersectSet.retainAll(nMap.keySet());
    return (double) intersectSet.size() / (double) unionSet.size();
}

From source file:org.apache.accumulo.core.util.LocalityGroupUtil.java

public static Map<String, Set<ByteSequence>> getLocalityGroups(AccumuloConfiguration acuconf)
        throws LocalityGroupConfigurationError {
    Map<String, Set<ByteSequence>> result = new HashMap<String, Set<ByteSequence>>();
    String[] groups = acuconf.get(Property.TABLE_LOCALITY_GROUPS).split(",");
    for (String group : groups) {
        if (group.length() > 0)
            result.put(group, new HashSet<ByteSequence>());
    }//w w w .  java 2  s .  com
    HashSet<ByteSequence> all = new HashSet<ByteSequence>();
    for (Entry<String, String> entry : acuconf) {
        String property = entry.getKey();
        String value = entry.getValue();
        String prefix = Property.TABLE_LOCALITY_GROUP_PREFIX.getKey();
        if (property.startsWith(prefix)) {
            // this property configures a locality group, find out which one:
            String group = property.substring(prefix.length());
            String[] parts = group.split("\\.");
            group = parts[0];
            if (result.containsKey(group)) {
                if (parts.length == 1) {
                    Set<ByteSequence> colFamsSet = decodeColumnFamilies(value);
                    if (!Collections.disjoint(all, colFamsSet)) {
                        colFamsSet.retainAll(all);
                        throw new LocalityGroupConfigurationError("Column families " + colFamsSet + " in group "
                                + group + " is already used by another locality group");
                    }

                    all.addAll(colFamsSet);
                    result.put(group, colFamsSet);
                }
            }
        }
    }
    // result.put("", all);
    return result;
}