Example usage for org.apache.commons.collections4.bag HashBag HashBag

Introduction

In this page you can find the example usage for org.apache.commons.collections4.bag HashBag HashBag.

Prototype

public HashBag() 

Source Link

Document

Constructs an empty HashBag .

Usage

From source file:edu.gslis.ts.RunQuery.java

public static void main(String[] args) {
    try {//  w  ww . j  a  v  a2s.  co m
        // Get the commandline options
        Options options = createOptions();
        CommandLineParser parser = new GnuParser();
        CommandLine cmd = parser.parse(options, args);

        String inputPath = cmd.getOptionValue("input");
        String eventsPath = cmd.getOptionValue("events");
        String stopPath = cmd.getOptionValue("stop");
        int queryId = Integer.valueOf(cmd.getOptionValue("query"));

        List<String> ids = FileUtils.readLines(new File(inputPath + File.separator + "ids.txt"));

        Stopper stopper = new Stopper(stopPath);
        Map<Integer, FeatureVector> queries = readEvents(eventsPath, stopper);

        FeatureVector query = queries.get(queryId);

        Pairtree ptree = new Pairtree();
        Bag<String> words = new HashBag<String>();

        for (String streamId : ids) {

            String ppath = ptree.mapToPPath(streamId.replace("-", ""));

            String inpath = inputPath + File.separator + ppath + File.separator + streamId + ".xz";
            //                System.out.println(inpath);
            File infile = new File(inpath);
            InputStream in = new XZInputStream(new FileInputStream(infile));

            TTransport inTransport = new TIOStreamTransport(new BufferedInputStream(in));
            TBinaryProtocol inProtocol = new TBinaryProtocol(inTransport);
            inTransport.open();
            final StreamItem item = new StreamItem();

            while (true) {
                try {
                    item.read(inProtocol);
                    //                        System.out.println("Read " + item.stream_id);

                } catch (TTransportException tte) {
                    // END_OF_FILE is used to indicate EOF and is not an exception.
                    if (tte.getType() != TTransportException.END_OF_FILE)
                        tte.printStackTrace();
                    break;
                }
            }

            // Do something with this document...
            String docText = item.getBody().getClean_visible();

            StringTokenizer itr = new StringTokenizer(docText);
            while (itr.hasMoreTokens()) {
                words.add(itr.nextToken());
            }

            inTransport.close();

        }

        for (String term : words.uniqueSet()) {
            System.out.println(term + ":" + words.getCount(term));
        }

    } catch (Exception e) {
        e.printStackTrace();
    }
}

---

From source file:com.mikenimer.familydam.services.photos.MetadataKeywordsListServlet.java

@Override
protected void doGet(SlingHttpServletRequest request, SlingHttpServletResponse response)
        throws SlingServletException, IOException {
    String path = "/content/dam";

    if (request.getRequestParameter("path") != null) {
        path = request.getRequestParameter("path").getString();
    }/* w ww .  j  a va 2s.  c o m*/

    try {
        Bag bag = new HashBag();

        String stmt = "select * from [fd:image] WHERE ISDESCENDANTNODE([" + path + "])";

        Session session = request.getResourceResolver().adaptTo(Session.class);
        Query query = session.getWorkspace().getQueryManager().createQuery(stmt, Query.JCR_SQL2);
        //query.setLimit(limit);
        //query.setOffset(offset);
        QueryResult results = query.execute();

        // Execute the query and get the results ...
        // (This is the same as before.)
        //javax.jcr.QueryResult result = query.execute();

        NodeIterator nodeIterator = results.getNodes();
        while (nodeIterator.hasNext()) {
            Node n = nodeIterator.nextNode();
            if (n.hasNode("metadata")) {
                Node metaNode = n.getNode("metadata");
                if (metaNode.hasProperty("keywords")) {
                    String keywords = metaNode.getProperty("keywords").getString();
                    String[] keys = keywords.split(",");
                    for (String key : keys) {
                        bag.add(key);
                    }
                }
            }
        }

        Set set = bag.uniqueSet();

        // find scale ratio, we need a 1-12 range

        final JSONWriter w = new JSONWriter(response.getWriter());
        w.setTidy(true);
        w.array();
        for (Object word : set) {
            w.object();
            w.key("word").value(word.toString().toLowerCase());
            w.key("count").value(bag.getCount(word));
            w.key("size").value(Math.max(1.5, Math.min(5, bag.getCount(word) * .05)) + "rem");

            // todo try this.
            // $size = min(max(round(( $size_max*($count-$count_min))/($count_max-$count_min),2), $size_min),$size_max);
            w.endObject();
        }
        w.endArray();

        //writeJsonObject(w, tree);

    } catch (Exception re) {
        re.printStackTrace();
        throw new SlingServletException(new javax.servlet.ServletException(re));
    }
}

---

From source file:de.tudarmstadt.ukp.dkpro.core.frequency.phrasedetection.FrequencyCounter.java

@Override
public void initialize(UimaContext context) throws ResourceInitializationException {
    super.initialize(context);
    if (sortByAlphabet && sortByCount) {
        throw new ResourceInitializationException(
                new IllegalArgumentException("Can only sort either by count or alphabetically."));
    }/*from ww  w  .  j  a  v a  2s .  c  o  m*/

    unigrams = new HashBag<>();
    bigrams = new HashBag<>();

    /* set feature path to default */
    if (featurePath == null) {
        featurePath = DEFAULT_FEATURE_PATH;
    }

    /* init sequence generator */
    try {
        sequenceGenerator = new PhraseSequenceGenerator.Builder().featurePath(featurePath)
                .coveringType(coveringType).lowercase(lowercase).stopwordsFile(stopwordsFile)
                .stopwordsReplacement(stopwordsReplacement).filterRegex(filterRegex)
                .filterRegexReplacement(regexReplacement).buildStringSequenceGenerator();
    } catch (IOException e) {
        throw new ResourceInitializationException(e);
    }
}

---

From source file:de.tudarmstadt.ukp.dkpro.core.io.ditop.DiTopWriter.java

@Override
public void initialize(UimaContext context) throws ResourceInitializationException {
    super.initialize(context);

    try {//w  w  w .  j  a v  a2 s.co m
        model = ParallelTopicModel.read(modelLocation);
        collectionDir = new File(targetLocation, corpusName + "_" + model.getNumTopics());
        if (collectionDir.exists()) {
            getLogger().warn(String.format("%s' already exists, overwriting content.", collectionDir));
        }
        collectionDir.mkdirs();
        initializeTopicFile();
    } catch (Exception e) {
        throw new ResourceInitializationException(e);
    }

    collectionValuesSet = collectionValues == null ? Collections.<String>emptySet()
            : new HashSet<>(Arrays.asList(collectionValues));
    collectionCounter = new HashBag<>();
}

---

From source file:org.michaelevans.colorart.library.ColorArt.java

private int findEdgeColor() {
    int height = mBitmap.getHeight();
    int width = mBitmap.getWidth();

    mImageColors = new HashBag();
    HashBag leftImageColors = new HashBag();
    for (int x = 0; x < width; x++) {
        for (int y = 0; y < height; y++) {
            if (x == 0) {
                leftImageColors.add(Integer.valueOf(mBitmap.getPixel(x, y)));
            }//from  w w w .j a  v a  2  s . c om
            mImageColors.add(Integer.valueOf(mBitmap.getPixel(x, y)));
        }
    }

    ArrayList<CountedColor> sortedColors = new ArrayList<CountedColor>();

    int randomColorThreshold = (int) (height * COLOR_THRESHOLD_MINIMUM_PERCENTAGE);
    Iterator<Integer> iterator = leftImageColors.iterator();
    while (iterator.hasNext()) {
        Integer color = iterator.next();
        int colorCount = leftImageColors.getCount(color);
        if (colorCount < randomColorThreshold) {
            continue;
        }

        CountedColor container = new CountedColor(color, colorCount);
        sortedColors.add(container);
    }

    Collections.sort(sortedColors);

    CountedColor proposedEdgeColor = null;
    Iterator<CountedColor> sortedColorIterator = sortedColors.iterator();
    if (!sortedColorIterator.hasNext()) {
        return Color.BLACK;
    }

    proposedEdgeColor = sortedColorIterator.next();
    if (!proposedEdgeColor.isBlackOrWhite()) {
        return proposedEdgeColor.getColor();
    }

    while (sortedColorIterator.hasNext()) {
        CountedColor nextProposedColor = sortedColorIterator.next();
        double edgeColorRatio = (double) nextProposedColor.getCount() / proposedEdgeColor.getCount();
        if (edgeColorRatio <= EDGE_COLOR_DISCARD_THRESHOLD) {
            break;
        }

        if (!nextProposedColor.isBlackOrWhite()) {
            proposedEdgeColor = nextProposedColor;
            break;
        }
    }

    return proposedEdgeColor.getColor();
}

---

From source file:pltag.parser.semantics.classifier.IncrementalSemanticsWidget.java

private IncrementalSemanticsWidget(Map<Predicate, Proposition> propositions, int timestamp,
        boolean fullSentence) {
    this.propositions = propositions;
    predicatesWithSense = new HashSet<Predicate>();
    predicates = new HashSet<String>();
    argWords = new HashBag<String>();
    argRoles = new HashSet<Pair<Integer, Argument>>();
    incompleteArcs = new HashBag<String>();
    this.timestamp = timestamp;
    this.fullSentence = fullSentence;
}

---

From source file:uniol.apt.analysis.cycles.lts.AllSmallCyclesHavePVOne.java

static private Bag<String> getParikhVectorReaching(SpanningTree<TransitionSystem, Arc, State> tree,
        State state) {// w  w w .  j  av a 2s  . c  om
    Bag<String> result = new HashBag<>();
    while (!state.equals(tree.getStartNode())) {
        Arc arc = tree.getPredecessorEdge(state);
        result.add(arc.getLabel());
        state = arc.getSource();
    }
    return result;
}

---

From source file:uniol.apt.analysis.synthesize.separation.KBoundedSeparation.java

private Bag<State> expand(Bag<State> input, Event event, int g, boolean forward) {
    TransitionSystem ts = utility.getTransitionSystem();
    Bag<State> result = new HashBag<State>();

    for (State state : ts.getNodes()) {
        int increment = 0;
        for (Arc arc : forward ? state.getPostsetEdges() : state.getPresetEdges()) {
            if (arc.getEvent().equals(event)) {
                int value = getGradient(input, arc) - g;
                if (!forward)
                    value = -value;/*from  www . jav  a2s.  c  o m*/
                if (value > increment)
                    increment = value;
            }
        }
        result.add(state, input.getCount(state) + increment);
    }

    return result;
}

---