List of usage examples for java.util TreeMap put
public V put(K key, V value)
From source file:edu.csun.ecs.cs.multitouchj.application.touchpong.TouchPong.java
public static void main(String[] args) { LinkedList<String> arguments = new LinkedList<String>(); for (String argument : args) { arguments.add(argument);/*w w w. j av a 2s . c om*/ } TreeMap<String, String> parameters = new TreeMap<String, String>(); if (arguments.contains("-ix")) { parameters.put(ObjectObserverMoteJ.Parameter.InverseX.toString(), ""); } if (arguments.contains("-iy")) { parameters.put(ObjectObserverMoteJ.Parameter.InverseY.toString(), ""); } TouchPong touchPong = new TouchPong(); touchPong.run(parameters); }
From source file:TwitterClustering.java
public static void main(String[] args) throws FileNotFoundException, IOException { // TODO code application logic here File outFile = new File(args[3]); Scanner s = new Scanner(new File(args[1])).useDelimiter(","); JSONParser parser = new JSONParser(); Set<Cluster> clusterSet = new HashSet<Cluster>(); HashMap<String, Tweet> tweets = new HashMap(); FileWriter fw = new FileWriter(outFile.getAbsoluteFile()); BufferedWriter bw = new BufferedWriter(fw); // init/*w w w . j a va 2 s. c o m*/ try { Object obj = parser.parse(new FileReader(args[2])); JSONArray jsonArray = (JSONArray) obj; for (int i = 0; i < jsonArray.size(); i++) { Tweet twt = new Tweet(); JSONObject jObj = (JSONObject) jsonArray.get(i); String text = jObj.get("text").toString(); long sum = 0; for (int y = 0; y < text.toCharArray().length; y++) { sum += (int) text.toCharArray()[y]; } String[] token = text.split(" "); String tID = jObj.get("id").toString(); Set<String> mySet = new HashSet<String>(Arrays.asList(token)); twt.setAttributeValue(sum); twt.setText(mySet); twt.setTweetID(tID); tweets.put(tID, twt); } // preparing initial clusters int i = 0; while (s.hasNext()) { String id = s.next();// id Tweet t = tweets.get(id.trim()); clusterSet.add(new Cluster(i + 1, t, new LinkedList())); i++; } Iterator it = tweets.entrySet().iterator(); for (int l = 0; l < 2; l++) { // limit to 25 iterations while (it.hasNext()) { Map.Entry me = (Map.Entry) it.next(); // calculate distance to each centroid Tweet p = (Tweet) me.getValue(); HashMap<Cluster, Float> distMap = new HashMap(); for (Cluster clust : clusterSet) { distMap.put(clust, jaccardDistance(p.getText(), clust.getCentroid().getText())); } HashMap<Cluster, Float> sorted = (HashMap<Cluster, Float>) sortByValue(distMap); sorted.keySet().iterator().next().getMembers().add(p); } // calculate new centroid and update Clusterset for (Cluster clust : clusterSet) { TreeMap<String, Long> tDistMap = new TreeMap(); Tweet newCentroid = null; Long avgSumDist = new Long(0); for (int j = 0; j < clust.getMembers().size(); j++) { avgSumDist += clust.getMembers().get(j).getAttributeValue(); tDistMap.put(clust.getMembers().get(j).getTweetID(), clust.getMembers().get(j).getAttributeValue()); } if (clust.getMembers().size() != 0) { avgSumDist /= (clust.getMembers().size()); } ArrayList<Long> listValues = new ArrayList<Long>(tDistMap.values()); if (tDistMap.containsValue(findClosestNumber(listValues, avgSumDist))) { // found closest newCentroid = tweets .get(getKeyByValue(tDistMap, findClosestNumber(listValues, avgSumDist))); clust.setCentroid(newCentroid); } } } // create an iterator Iterator iterator = clusterSet.iterator(); // check values while (iterator.hasNext()) { Cluster c = (Cluster) iterator.next(); bw.write(c.getId() + "\t"); System.out.print(c.getId() + "\t"); for (Tweet t : c.getMembers()) { bw.write(t.getTweetID() + ", "); System.out.print(t.getTweetID() + ","); } bw.write("\n"); System.out.println(""); } System.out.println(""); System.out.println("SSE " + sumSquaredErrror(clusterSet)); } catch (Exception e) { e.printStackTrace(); } finally { bw.close(); fw.close(); } }
From source file:cosmos.example.BuildingPermitsExample.java
public static void main(String[] args) throws Exception { BuildingPermitsExample example = new BuildingPermitsExample(); new JCommander(example, args); File inputFile = new File(example.fileName); Preconditions.checkArgument(inputFile.exists() && inputFile.isFile() && inputFile.canRead(), "Expected " + example.fileName + " to be a readable file"); String zookeepers;//from w w w.jav a 2s.c om String instanceName; Connector connector; MiniAccumuloCluster mac = null; File macDir = null; // Use the MiniAccumuloCluster is requested if (example.useMiniAccumuloCluster) { macDir = Files.createTempDir(); String password = "password"; MiniAccumuloConfig config = new MiniAccumuloConfig(macDir, password); config.setNumTservers(1); mac = new MiniAccumuloCluster(config); mac.start(); zookeepers = mac.getZooKeepers(); instanceName = mac.getInstanceName(); ZooKeeperInstance instance = new ZooKeeperInstance(instanceName, zookeepers); connector = instance.getConnector("root", new PasswordToken(password)); } else { // Otherwise connect to a running instance zookeepers = example.zookeepers; instanceName = example.instanceName; ZooKeeperInstance instance = new ZooKeeperInstance(instanceName, zookeepers); connector = instance.getConnector(example.username, new PasswordToken(example.password)); } // Instantiate an instance of Cosmos Cosmos cosmos = new CosmosImpl(zookeepers); // Create a definition for the data we want to load Store id = Store.create(connector, new Authorizations(), AscendingIndexIdentitySet.create()); // Register the definition with Cosmos so it can track its progress. cosmos.register(id); // Load all of the data from our inputFile LoadBuildingPermits loader = new LoadBuildingPermits(cosmos, id, inputFile); loader.run(); // Finalize the SortableResult which will prevent future writes to the data set cosmos.finalize(id); // Flush the ingest traces to the backend so we can see the results; id.sendTraces(); // Get back the Set of Columns that we've ingested. Set<Column> schema = Sets.newHashSet(cosmos.columns(id)); log.debug("\nColumns: " + schema); Iterator<Column> iter = schema.iterator(); while (iter.hasNext()) { Column c = iter.next(); // Remove the internal ID field and columns that begin with CONTRACTOR_ if (c.equals(LoadBuildingPermits.ID) || c.name().startsWith("CONTRACTOR_")) { iter.remove(); } } Iterable<Index> indices = Iterables.transform(schema, new Function<Column, Index>() { @Override public Index apply(Column col) { return Index.define(col); } }); // Ensure that we have locality groups set as we expect log.info("Ensure locality groups are set"); id.optimizeIndices(indices); // Compact down the data for this SortableResult log.info("Issuing compaction for relevant data"); id.consolidate(); final int numTopValues = 10; // Walk through each column in the result set for (Column c : schema) { Stopwatch sw = new Stopwatch(); sw.start(); // Get the number of times we've seen each value in a given column CloseableIterable<Entry<RecordValue<?>, Long>> groupingsInColumn = cosmos.groupResults(id, c); log.info(c.name() + ":"); // Iterate over the counts, collecting the top N values in each column TreeMap<Long, RecordValue<?>> topValues = Maps.newTreeMap(); for (Entry<RecordValue<?>, Long> entry : groupingsInColumn) { if (topValues.size() == numTopValues) { Entry<Long, RecordValue<?>> least = topValues.pollFirstEntry(); if (least.getKey() < entry.getValue()) { topValues.put(entry.getValue(), entry.getKey()); } else { topValues.put(least.getKey(), least.getValue()); } } else if (topValues.size() < numTopValues) { topValues.put(entry.getValue(), entry.getKey()); } } for (Long key : topValues.descendingKeySet()) { log.info(topValues.get(key).value() + " occurred " + key + " times"); } sw.stop(); log.info("Took " + sw.toString() + " to run query.\n"); } log.info("Deleting records"); // Delete the records we've ingested if (!example.useMiniAccumuloCluster) { // Because I'm lazy and don't want to wait around to run the BatchDeleter when we're just going // to rm -rf the directory in a few secs. cosmos.delete(id); } // And shut down Cosmos cosmos.close(); log.info("Cosmos stopped"); // If we were using MAC, also stop that if (example.useMiniAccumuloCluster && null != mac) { mac.stop(); if (null != macDir) { FileUtils.deleteDirectory(macDir); } } }
From source file:cc.twittertools.util.VerifySubcollection.java
@SuppressWarnings("static-access") public static void main(String[] args) throws Exception { Options options = new Options(); options.addOption(OptionBuilder.withArgName("dir").hasArg().withDescription("source collection directory") .create(COLLECTION_OPTION)); options.addOption(//from www. j ava 2s . com OptionBuilder.withArgName("file").hasArg().withDescription("list of tweetids").create(ID_OPTION)); CommandLine cmdline = null; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); System.exit(-1); } if (!cmdline.hasOption(COLLECTION_OPTION) || !cmdline.hasOption(ID_OPTION)) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(ExtractSubcollection.class.getName(), options); System.exit(-1); } String collectionPath = cmdline.getOptionValue(COLLECTION_OPTION); LongOpenHashSet tweetids = new LongOpenHashSet(); File tweetidsFile = new File(cmdline.getOptionValue(ID_OPTION)); if (!tweetidsFile.exists()) { System.err.println("Error: " + tweetidsFile + " does not exist!"); System.exit(-1); } LOG.info("Reading tweetids from " + tweetidsFile); FileInputStream fin = new FileInputStream(tweetidsFile); BufferedReader br = new BufferedReader(new InputStreamReader(fin)); String s; while ((s = br.readLine()) != null) { tweetids.add(Long.parseLong(s)); } br.close(); fin.close(); LOG.info("Read " + tweetids.size() + " tweetids."); File file = new File(collectionPath); if (!file.exists()) { System.err.println("Error: " + file + " does not exist!"); System.exit(-1); } LongOpenHashSet seen = new LongOpenHashSet(); TreeMap<Long, String> tweets = Maps.newTreeMap(); PrintStream out = new PrintStream(System.out, true, "UTF-8"); StatusStream stream = new JsonStatusCorpusReader(file); Status status; int cnt = 0; while ((status = stream.next()) != null) { if (!tweetids.contains(status.getId())) { LOG.error("tweetid " + status.getId() + " doesn't belong in collection"); continue; } if (seen.contains(status.getId())) { LOG.error("tweetid " + status.getId() + " already seen!"); continue; } tweets.put(status.getId(), status.getJsonObject().toString()); seen.add(status.getId()); cnt++; } LOG.info("total of " + cnt + " tweets in subcollection."); for (Map.Entry<Long, String> entry : tweets.entrySet()) { out.println(entry.getValue()); } stream.close(); out.close(); }
From source file:module.entities.NameFinder.RegexNameFinder.java
/** * @param args the command line arguments *//*from ww w . j a v a 2 s . c o m*/ public static void main(String[] args) throws SQLException, IOException { if (args.length == 1) { Config.configFile = args[0]; } long lStartTime = System.currentTimeMillis(); Timestamp startTime = new Timestamp(lStartTime); System.out.println("Regex Name Finder process started at: " + startTime); DB.initPostgres(); regexerId = DB.LogRegexFinder(lStartTime); initLexicons(); JSONObject obj = new JSONObject(); TreeMap<Integer, String> consultations = DB.getDemocracitConsultationBody(); Document doc; int count = 0; TreeMap<Integer, String> consFoundNames = new TreeMap<>(); TreeMap<Integer, String> consFoundRoles = new TreeMap<>(); for (int consId : consultations.keySet()) { String consBody = consultations.get(consId); String signName = "", roleName = ""; doc = Jsoup.parse(consBody); Elements allPars = new Elements(); Elements paragraphs = doc.select("p"); for (Element par : paragraphs) { if (par.html().contains("<br>")) { String out = "<p>" + par.html().replaceAll("<br>", "</p><p>") + "</p>"; Document internal_doc = Jsoup.parse(out); Elements subparagraphs = internal_doc.select("p"); allPars.addAll(subparagraphs); } else { allPars.add(par); } // System.out.println(formatedText); } String signature = getSignatureFromParagraphs(allPars); // System.out.println(signature); if (signature.contains("#")) { String[] sign_tokens = signature.split("#"); signName = sign_tokens[0]; if (sign_tokens.length > 1) { roleName = sign_tokens[1]; } consFoundNames.put(consId, signName.trim()); consFoundRoles.put(consId, roleName.trim()); count++; } else { System.err.println("--" + consId); } // } DB.insertDemocracitConsultationMinister(consFoundNames, consFoundRoles); TreeMap<Integer, String> consultationsCompletedText = DB.getDemocracitCompletedConsultationBody(); Document doc2; TreeMap<Integer, String> complConsFoundNames = new TreeMap<>(); int count2 = 0; for (int consId : consultationsCompletedText.keySet()) { String consBody = consultationsCompletedText.get(consId); String signName = "", roleName = ""; doc2 = Jsoup.parse(consBody); // if (doc.text().contains("<br>")) { // doc.text().replaceAll("(<[Bb][Rr]>)+", "<p>"); // } Elements allPars = new Elements(); Elements paragraphs = doc2.select("p"); for (Element par : paragraphs) { if (par.html().contains("<br>")) { String out = "<p>" + par.html().replaceAll("<br>", "</p><p>") + "</p>"; Document internal_doc = Jsoup.parse(out); Elements subparagraphs = internal_doc.select("p"); allPars.addAll(subparagraphs); } else { allPars.add(par); } } String signature = getSignatureFromParagraphs(allPars); if (signature.contains("#")) { String[] sign_tokens = signature.split("#"); signName = sign_tokens[0]; if (sign_tokens.length > 1) { roleName = sign_tokens[1]; } consFoundNames.put(consId, signName.trim()); consFoundRoles.put(consId, roleName.trim()); // System.out.println(consId); // System.out.println(signName.trim()); // System.out.println("***************"); count2++; } else { System.err.println("++" + consId); } } DB.insertDemocracitConsultationMinister(complConsFoundNames, consFoundRoles); long lEndTime = System.currentTimeMillis(); System.out.println("Regex Name Finder process finished at: " + startTime); obj.put("message", "Regex Name Finder finished with no errors"); obj.put("details", ""); DB.UpdateLogRegexFinder(lEndTime, regexerId, obj); DB.close(); }
From source file:cht.Parser.java
public static void main(String[] args) throws IOException { // TODO get from google drive boolean isUnicode = false; boolean isRemoveInputFileOnComplete = false; int rowNum;//from w ww. j av a 2s.c om int colNum; Gson gson = new GsonBuilder().setPrettyPrinting().create(); Properties prop = new Properties(); try { prop.load(new FileInputStream("config.txt")); } catch (IOException ex) { ex.printStackTrace(); } String inputFilePath = prop.getProperty("inputFile"); String outputDirectory = prop.getProperty("outputDirectory"); System.out.println(outputDirectory); // optional String unicode = prop.getProperty("unicode"); String removeInputFileOnComplete = prop.getProperty("removeInputFileOnComplete"); inputFilePath = inputFilePath.trim(); outputDirectory = outputDirectory.trim(); if (unicode != null) { isUnicode = Boolean.parseBoolean(unicode.trim()); } if (removeInputFileOnComplete != null) { isRemoveInputFileOnComplete = Boolean.parseBoolean(removeInputFileOnComplete.trim()); } Writer out = null; FileInputStream in = null; final String newLine = System.getProperty("line.separator").toString(); final String separator = File.separator; try { in = new FileInputStream(inputFilePath); Workbook workbook = new XSSFWorkbook(in); Sheet sheet = workbook.getSheetAt(0); rowNum = sheet.getLastRowNum() + 1; colNum = sheet.getRow(0).getPhysicalNumberOfCells(); for (int j = 1; j < colNum; ++j) { String outputFilename = sheet.getRow(0).getCell(j).getStringCellValue(); // guess directory int slash = outputFilename.indexOf('/'); if (slash != -1) { // has directory outputFilename = outputFilename.substring(0, slash) + separator + outputFilename.substring(slash + 1); } String outputPath = FilenameUtils.concat(outputDirectory, outputFilename); System.out.println("--Writing " + outputPath); out = new OutputStreamWriter(new FileOutputStream(outputPath), "UTF-8"); TreeMap<String, Object> map = new TreeMap<String, Object>(); for (int i = 1; i < rowNum; i++) { try { String key = sheet.getRow(i).getCell(0).getStringCellValue(); //String value = ""; Cell tmp = sheet.getRow(i).getCell(j); if (tmp != null) { // not empty string! value = sheet.getRow(i).getCell(j).getStringCellValue(); } if (!key.equals("") && !key.startsWith("#") && !key.startsWith(".")) { value = isUnicode ? StringEscapeUtils.escapeJava(value) : value; int firstdot = key.indexOf("."); String keyName, keyAttribute; if (firstdot > 0) {// a.b.c.d keyName = key.substring(0, firstdot); // a keyAttribute = key.substring(firstdot + 1); // b.c.d TreeMap oldhash = null; Object old = null; if (map.get(keyName) != null) { old = map.get(keyName); if (old instanceof TreeMap == false) { System.out.println("different type of key:" + key); continue; } oldhash = (TreeMap) old; } else { oldhash = new TreeMap(); } int firstdot2 = keyAttribute.indexOf("."); String rootName, childName; if (firstdot2 > 0) {// c, d.f --> d, f rootName = keyAttribute.substring(0, firstdot2); childName = keyAttribute.substring(firstdot2 + 1); } else {// c, d -> d, null rootName = keyAttribute; childName = null; } TreeMap<String, Object> object = myPut(oldhash, rootName, childName); map.put(keyName, object); } else {// c, d -> d, null keyName = key; keyAttribute = null; // simple string mode map.put(key, value); } } } catch (Exception e) { // just ingore empty rows } } String json = gson.toJson(map); // output json out.write(json + newLine); out.close(); } in.close(); System.out.println("\n---Complete!---"); System.out.println("Read input file from " + inputFilePath); System.out.println(colNum - 1 + " output files ate generated at " + outputDirectory); System.out.println(rowNum + " records are generated for each output file."); System.out.println("output file is ecoded as unicode? " + (isUnicode ? "yes" : "no")); if (isRemoveInputFileOnComplete) { File input = new File(inputFilePath); input.deleteOnExit(); System.out.println("Deleted " + inputFilePath); } } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { if (in != null) { in.close(); } } }
From source file:de.tudarmstadt.ukp.experiments.dip.wp1.documents.Step8GoldDataAggregator.java
public static void main(String[] args) throws Exception { String inputDir = args[0] + "/"; // output dir File outputDir = new File(args[1]); File turkersConfidence = new File(args[2]); if (outputDir.exists()) { outputDir.delete();/* www. j ava 2 s.co m*/ } outputDir.mkdir(); List<String> annotatorsIDs = new ArrayList<>(); // for (File f : FileUtils.listFiles(new File(inputDir), new String[] { "xml" }, false)) { // QueryResultContainer queryResultContainer = QueryResultContainer // .fromXML(FileUtils.readFileToString(f, "utf-8")); // for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) { // for (QueryResultContainer.MTurkRelevanceVote relevanceVote : rankedResults.mTurkRelevanceVotes) { // if (!annotatorsIDs.contains(relevanceVote.turkID)) // annotatorsIDs.add(relevanceVote.turkID); // } // } // } HashMap<String, Integer> countVotesForATurker = new HashMap<>(); // creates temporary file with format for mace // Hashmap annotations: key is the id of a document and a sentence // Value is an array votes[] of turkers decisions: true or false (relevant or not) // the length of this array equals the number of annotators in List<String> annotatorsIDs. // If an annotator worked on the task his decision is written in the array otherwise the value is NULL // key: queryID + clueWebID + sentenceID // value: true and false annotations TreeMap<String, Annotations> annotations = new TreeMap<>(); for (File f : FileUtils.listFiles(new File(inputDir), new String[] { "xml" }, false)) { QueryResultContainer queryResultContainer = QueryResultContainer .fromXML(FileUtils.readFileToString(f, "utf-8")); System.out.println("Reading " + f.getName()); for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) { String documentID = rankedResults.clueWebID; for (QueryResultContainer.MTurkRelevanceVote relevanceVote : rankedResults.mTurkRelevanceVotes) { Integer turkerID; if (!annotatorsIDs.contains(relevanceVote.turkID)) { annotatorsIDs.add(relevanceVote.turkID); turkerID = annotatorsIDs.size() - 1; } else { turkerID = annotatorsIDs.indexOf(relevanceVote.turkID); } Integer count = countVotesForATurker.get(relevanceVote.turkID); if (count == null) { count = 0; } count++; countVotesForATurker.put(relevanceVote.turkID, count); String id; List<Integer> trueVotes; List<Integer> falseVotes; for (QueryResultContainer.SingleSentenceRelevanceVote singleSentenceRelevanceVote : relevanceVote.singleSentenceRelevanceVotes) if (!"".equals(singleSentenceRelevanceVote.sentenceID)) { id = f.getName() + "_" + documentID + "_" + singleSentenceRelevanceVote.sentenceID; Annotations turkerVotes = annotations.get(id); if (turkerVotes == null) { trueVotes = new ArrayList<>(); falseVotes = new ArrayList<>(); turkerVotes = new Annotations(trueVotes, falseVotes); } trueVotes = turkerVotes.trueAnnotations; falseVotes = turkerVotes.falseAnnotations; if ("true".equals(singleSentenceRelevanceVote.relevant)) { // votes[turkerID] = true; trueVotes.add(turkerID); } else if ("false".equals(singleSentenceRelevanceVote.relevant)) { // votes[turkerID] = false; falseVotes.add(turkerID); } else { throw new IllegalStateException("Annotation value of sentence " + singleSentenceRelevanceVote.sentenceID + " in " + rankedResults.clueWebID + " equals " + singleSentenceRelevanceVote.relevant); } try { int allVotesCount = trueVotes.size() + falseVotes.size(); if (allVotesCount > 5) { System.err.println(id + " doesn't have 5 annotators: true: " + trueVotes.size() + " false: " + falseVotes.size()); // nasty hack, we're gonna strip some data; true votes first /* we can't do that, it breaks something down the line int toRemove = allVotesCount - 5; if (trueVotes.size() >= toRemove) { trueVotes = trueVotes .subList(0, trueVotes.size() - toRemove); } else if ( falseVotes.size() >= toRemove) { falseVotes = falseVotes .subList(0, trueVotes.size() - toRemove); } */ System.err.println("Adjusted: " + id + " doesn't have 5 annotators: true: " + trueVotes.size() + " false: " + falseVotes.size()); } } catch (IllegalStateException e) { e.printStackTrace(); } turkerVotes.trueAnnotations = trueVotes; turkerVotes.falseAnnotations = falseVotes; annotations.put(id, turkerVotes); } else { throw new IllegalStateException( "Empty Sentence ID in " + f.getName() + " for turker " + turkerID); } } } } File tmp = printHashMap(annotations, annotatorsIDs.size()); String file = TEMP_DIR + "/" + tmp.getName(); MACE.main(new String[] { "--prefix", file }); //gets the keys of the documents and sentences ArrayList<String> lines = (ArrayList<String>) FileUtils.readLines(new File(file + ".prediction")); int i = 0; TreeMap<String, TreeMap<String, ArrayList<HashMap<String, String>>>> ids = new TreeMap<>(); ArrayList<HashMap<String, String>> sentences; if (lines.size() != annotations.size()) { throw new IllegalStateException( "The size of prediction file is " + lines.size() + "but expected " + annotations.size()); } for (Map.Entry entry : annotations.entrySet()) { //1001.xml_clueweb12-1905wb-13-07360_8783 String key = (String) entry.getKey(); String[] IDs = key.split("_"); if (IDs.length > 2) { String queryID = IDs[0]; String clueWebID = IDs[1]; String sentenceID = IDs[2]; TreeMap<String, ArrayList<HashMap<String, String>>> clueWebIDs = ids.get(queryID); if (clueWebIDs == null) { clueWebIDs = new TreeMap<>(); } sentences = clueWebIDs.get(clueWebID); if (sentences == null) { sentences = new ArrayList<>(); } HashMap<String, String> sentence = new HashMap<>(); sentence.put(sentenceID, lines.get(i)); sentences.add(sentence); clueWebIDs.put(clueWebID, sentences); ids.put(queryID, clueWebIDs); } else { throw new IllegalStateException("Wrong ID " + key); } i++; } for (Map.Entry entry : ids.entrySet()) { TreeMap<Integer, String> value = (TreeMap<Integer, String>) entry.getValue(); String queryID = (String) entry.getKey(); QueryResultContainer queryResultContainer = QueryResultContainer .fromXML(FileUtils.readFileToString(new File(inputDir, queryID), "utf-8")); for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) { for (Map.Entry val : value.entrySet()) { String clueWebID = (String) val.getKey(); if (clueWebID.equals(rankedResults.clueWebID)) { List<QueryResultContainer.SingleSentenceRelevanceVote> goldEstimatedLabels = new ArrayList<>(); List<QueryResultContainer.SingleSentenceRelevanceVote> turkersVotes = new ArrayList<>(); int size = 0; int hitSize = 0; String hitID = ""; for (QueryResultContainer.MTurkRelevanceVote vote : rankedResults.mTurkRelevanceVotes) { if (!hitID.equals(vote.hitID)) { hitID = vote.hitID; hitSize = vote.singleSentenceRelevanceVotes.size(); size = size + hitSize; turkersVotes.addAll(vote.singleSentenceRelevanceVotes); } else { if (vote.singleSentenceRelevanceVotes.size() != hitSize) { hitSize = vote.singleSentenceRelevanceVotes.size(); size = size + hitSize; turkersVotes.addAll(vote.singleSentenceRelevanceVotes); } } } ArrayList<HashMap<String, String>> sentenceList = (ArrayList<HashMap<String, String>>) val .getValue(); if (sentenceList.size() != turkersVotes.size()) { try { throw new IllegalStateException("Expected size of annotations is " + turkersVotes.size() + "but found " + sentenceList.size() + " for document " + rankedResults.clueWebID + " in " + queryID); } catch (IllegalStateException ex) { ex.printStackTrace(); } } for (QueryResultContainer.SingleSentenceRelevanceVote s : turkersVotes) { String valSentence = null; for (HashMap<String, String> anno : sentenceList) { if (anno.keySet().contains(s.sentenceID)) { valSentence = anno.get(s.sentenceID); } } QueryResultContainer.SingleSentenceRelevanceVote singleSentenceVote = new QueryResultContainer.SingleSentenceRelevanceVote(); singleSentenceVote.sentenceID = s.sentenceID; if (("false").equals(valSentence)) { singleSentenceVote.relevant = "false"; } else if (("true").equals(valSentence)) { singleSentenceVote.relevant = "true"; } else { throw new IllegalStateException("Annotation value of sentence " + singleSentenceVote.sentenceID + " equals " + val.getValue()); } goldEstimatedLabels.add(singleSentenceVote); } rankedResults.goldEstimatedLabels = goldEstimatedLabels; } } } File outputFile = new File(outputDir, queryID); FileUtils.writeStringToFile(outputFile, queryResultContainer.toXML(), "utf-8"); System.out.println("Finished " + outputFile); } ArrayList<String> annotators = (ArrayList<String>) FileUtils.readLines(new File(file + ".competence")); FileWriter fileWriter; StringBuilder sb = new StringBuilder(); for (int j = 0; j < annotatorsIDs.size(); j++) { String[] s = annotators.get(0).split("\t"); Float score = Float.parseFloat(s[j]); String turkerID = annotatorsIDs.get(j); System.out.println(turkerID + " " + score + " " + countVotesForATurker.get(turkerID)); sb.append(turkerID).append(" ").append(score).append(" ").append(countVotesForATurker.get(turkerID)) .append("\n"); } fileWriter = new FileWriter(turkersConfidence); fileWriter.append(sb.toString()); fileWriter.close(); }
From source file:cn.tata.t2s.ssm.util.AcmeCorpPhysicalNamingStrategy.java
private static Map<String, String> buildAbbreviationMap() { TreeMap<String, String> abbreviationMap = new TreeMap<>(String.CASE_INSENSITIVE_ORDER); abbreviationMap.put("account", "acct"); abbreviationMap.put("number", "num"); return abbreviationMap; }
From source file:it.zero11.acme.utils.JWKUtils.java
public static TreeMap<String, Object> getWebKey(PublicKey publicKey) { TreeMap<String, Object> key = new TreeMap<>(); if (publicKey instanceof RSAPublicKey) { key.put("kty", "RSA"); key.put("e", TextCodec.BASE64URL.encode(toIntegerBytes(((RSAPublicKey) publicKey).getPublicExponent()))); key.put("n", TextCodec.BASE64URL.encode(toIntegerBytes(((RSAPublicKey) publicKey).getModulus()))); return key; } else {// w ww.ja va 2s .co m throw new IllegalArgumentException(); } }
From source file:com.kpb.other.AcmeCorpPhysicalNamingStrategy.java
private static Map<String, String> buildAbbreviationMap() { TreeMap<String, String> abbreviationMap = new TreeMap<String, String>(String.CASE_INSENSITIVE_ORDER); abbreviationMap.put("account", "acct"); abbreviationMap.put("number", "num"); return abbreviationMap; }