FileSequentialCollection fcollect5 = new FileSequentialCollection(Arrays.asList(args), new NumberRangeFileFilter(320, 410, true)); for (File fi: fcollect5) { System.out.println(fi);
int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); filter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) {
public void runTest(String[] args) { // get a parser from file LexicalizedParser pd = LexicalizedParser.loadModel(args[0]); op = pd.getOp(); // in case a serialized options was read in Treebank testTreebank = op.tlpParams.memoryTreebank(); int testlow = Integer.parseInt(args[2]); int testhigh = Integer.parseInt(args[3]); testTreebank.loadPath(args[1], new NumberRangeFileFilter(testlow, testhigh, true)); op.setOptionsOrWarn(args, 4, args.length); testOnTreebank(pd, new EnglishTreebankParserParams(), testTreebank, args[1], pd.stateIndex); } }
/** * This is hardwired to calculate the split categories from English * Penn Treebank sections 2-21 with a default cutoff of 300 (as used * in ACL03PCFG). It was added to upgrading of code in cases where no * Treebank was available, and the pre-stored list was being used). */ public static Set<String> getEnglishSplitCategories(String treebankRoot) { TreebankLangParserParams tlpParams = new EnglishTreebankParserParams(); Treebank trees = tlpParams.memoryTreebank(); trees.loadPath(treebankRoot, new NumberRangeFileFilter(200, 2199, true)); return getSplitCategories(trees, 300.0, tlpParams.treebankLanguagePack()); }
public static List<Tree> getTrees(String path, int low, int high, int minLength, int maxLength) { Treebank treebank = new DiskTreebank(in -> new PennTreeReader(in, new LabeledScoredTreeFactory(new WordFactory()), new BobChrisTreeNormalizer())); treebank.loadPath(path, new NumberRangeFileFilter(low, high, true)); List<Tree> trees = new ArrayList<>(); for (Tree tree : treebank) { if (tree.yield().size() <= maxLength && tree.yield().size() >= minLength) { trees.add(tree); } } return trees; }
int low = Integer.parseInt(args[i]); int high = Integer.parseInt(args[i + 1]); trainFilter = new NumberRangeFileFilter(low, high, true); i += 2;
LexicalizedParser lp = LexicalizedParser.trainFromTreebank(path, new NumberRangeFileFilter(trainLow, trainHigh, true), op); testTreebank.loadPath(path, new NumberRangeFileFilter(testLow, testHigh, true)); System.out.println("Currently " + new Date()); EvaluateTreebank evaluator = new EvaluateTreebank(lp);
int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); trainFilter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) { int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); testFilter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) { trainFilter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) { int testlow = Integer.parseInt(args[argIndex + 2]); int testhigh = Integer.parseInt(args[argIndex + 3]); testTreebank.loadPath(args[argIndex + 1], new NumberRangeFileFilter(testlow, testhigh, true));
trainTreebank.loadPath(path, new NumberRangeFileFilter(low, high, true));
testTreebank.loadPath(path, new NumberRangeFileFilter(testLow, testHigh, true)); if (op.testOptions.increasingLength) { Collections.sort(testTreebank, new TreeLengthComparator()); trainTreebank.loadPath(path, new NumberRangeFileFilter(trainLow, trainHigh, true)); Timing.tick("done.");
public static List<Tree> getTrees(String path, int low, int high, int minLength, int maxLength) { Treebank treebank = new DiskTreebank(new TreeReaderFactory() { public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(new WordFactory()), new BobChrisTreeNormalizer()); } }); treebank.loadPath(path, new NumberRangeFileFilter(low, high, true)); List<Tree> trees = new ArrayList<Tree>(); for (Tree tree : treebank) { if (tree.yield().size() <= maxLength && tree.yield().size() >= minLength) { trees.add(tree); } } return trees; }
public static List<Tree> getTrees(String path, int low, int high, int minLength, int maxLength) { Treebank treebank = new DiskTreebank(new TreeReaderFactory() { public TreeReader newTreeReader(Reader in) { return new PennTreeReader(in, new LabeledScoredTreeFactory(new WordFactory()), new BobChrisTreeNormalizer()); } }); treebank.loadPath(path, new NumberRangeFileFilter(low, high, true)); List<Tree> trees = new ArrayList<Tree>(); for (Tree tree : treebank) { if (tree.yield().size() <= maxLength && tree.yield().size() >= minLength) { trees.add(tree); } } return trees; }
FileSequentialCollection fcollect5 = new FileSequentialCollection(Arrays.asList(args), new NumberRangeFileFilter(320, 410, true)); for (File fi: fcollect5) { System.out.println(fi);
FileSequentialCollection fcollect5 = new FileSequentialCollection(Arrays.asList(args), new NumberRangeFileFilter(320, 410, true)); for (File fi: fcollect5) { System.out.println(fi);
FileSequentialCollection fcollect5 = new FileSequentialCollection(Arrays.asList(args), new NumberRangeFileFilter(320, 410, true)); for (File fi: fcollect5) { System.out.println(fi);
FileFilter trainTreeBankFilter = new NumberRangeFileFilter(startRange, endRange, true); trainTreeBank.loadPath(trainDirPath, trainTreeBankFilter);
int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); filter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) {
int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); filter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) {
private static void convertTrainingData() { Set<String> trees = Collections.newSetFromMap(new ConcurrentHashMap<>()); ForkJoinPool commonPool = ForkJoinPool.commonPool(); Future task1 = commonPool.submit(() -> { FileFilter trainTreeBankFilter = new NumberRangeFileFilter(1, 2502, true); loadTreeBank(trainTreeBankFilter, wsj, trees); return null; }); Future task2 = commonPool.submit(() -> { FileFilter extraTreeBankFilter = new ExtensionFileFilter(".mrg", true); loadTreeBank(extraTreeBankFilter, extra, trees); return null; }); try { task2.get(); task1.get(); } catch (InterruptedException | ExecutionException e) { e.printStackTrace(); } writeToFile(trees, tempLocation); }
int low = Integer.parseInt(args[argIndex]); int high = Integer.parseInt(args[argIndex + 1]); filter = new NumberRangeFileFilter(low, high, true); argIndex += 2; } catch (NumberFormatException e) {