Examples with FileNotFoundException java.io.FileNotFoundException used on opensource projects

Example 46 with FileNotFoundException

use of java.io.FileNotFoundException in project CoreNLP by stanfordnlp.

the class ATBArabicDataset method build.

public void build() {
    for (File path : pathsToData) {
        if (splitFilter == null) {
            treebank.loadPath(path, treeFileExtension, false);
        } else {
            treebank.loadPath(path, splitFilter);
        }
    }
    PrintWriter outfile = null;
    PrintWriter flatFile = null;
    try {
        outfile = new PrintWriter(new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outFileName), "UTF-8")));
        flatFile = (makeFlatFile) ? new PrintWriter(new BufferedWriter(new OutputStreamWriter(new FileOutputStream(flatFileName), "UTF-8"))) : null;
        treebank.apply(new ArabicRawTreeNormalizer(outfile, flatFile));
        outputFileList.add(outFileName);
        if (makeFlatFile) {
            outputFileList.add(flatFileName);
            toStringBuffer.append(" Made flat files\n");
        }
    } catch (UnsupportedEncodingException e) {
        System.err.printf("%s: Filesystem does not support UTF-8 output\n", this.getClass().getName());
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        System.err.printf("%s: Could not open %s for writing\n", this.getClass().getName(), outFileName);
    } finally {
        if (outfile != null)
            outfile.close();
        if (flatFile != null)
            flatFile.close();
    }
}

Example 47 with FileNotFoundException

use of java.io.FileNotFoundException in project CoreNLP by stanfordnlp.

the class ArabicSegmenter method evaluate.

/**
   * Evaluate accuracy when the input is gold segmented text *with* segmentation
   * markers and morphological analyses. In other words, the evaluation file has the
   * same format as the training data.
   *
   * @param pwOut
   */
private void evaluate(PrintWriter pwOut) {
    log.info("Starting evaluation...");
    boolean hasSegmentationMarkers = true;
    boolean hasTags = true;
    DocumentReaderAndWriter<CoreLabel> docReader = new ArabicDocumentReaderAndWriter(hasSegmentationMarkers, hasTags, hasDomainLabels, domain, tf);
    ObjectBank<List<CoreLabel>> lines = classifier.makeObjectBankFromFile(flags.testFile, docReader);
    PrintWriter tedEvalGoldTree = null, tedEvalParseTree = null;
    PrintWriter tedEvalGoldSeg = null, tedEvalParseSeg = null;
    if (tedEvalPrefix != null) {
        try {
            tedEvalGoldTree = new PrintWriter(tedEvalPrefix + "_gold.ftree");
            tedEvalGoldSeg = new PrintWriter(tedEvalPrefix + "_gold.segmentation");
            tedEvalParseTree = new PrintWriter(tedEvalPrefix + "_parse.ftree");
            tedEvalParseSeg = new PrintWriter(tedEvalPrefix + "_parse.segmentation");
        } catch (FileNotFoundException e) {
            System.err.printf("%s: %s%n", ArabicSegmenter.class.getName(), e.getMessage());
        }
    }
    Counter<String> labelTotal = new ClassicCounter<>();
    Counter<String> labelCorrect = new ClassicCounter<>();
    int total = 0;
    int correct = 0;
    for (List<CoreLabel> line : lines) {
        final String[] inputTokens = tedEvalSanitize(IOBUtils.IOBToString(line).replaceAll(":", "#pm#")).split(" ");
        final String[] goldTokens = tedEvalSanitize(IOBUtils.IOBToString(line, ":")).split(" ");
        line = classifier.classify(line);
        final String[] parseTokens = tedEvalSanitize(IOBUtils.IOBToString(line, ":")).split(" ");
        for (CoreLabel label : line) {
            // Do not evaluate labeling of whitespace
            String observation = label.get(CoreAnnotations.CharAnnotation.class);
            if (!observation.equals(IOBUtils.getBoundaryCharacter())) {
                total++;
                String hypothesis = label.get(CoreAnnotations.AnswerAnnotation.class);
                String reference = label.get(CoreAnnotations.GoldAnswerAnnotation.class);
                labelTotal.incrementCount(reference);
                if (hypothesis.equals(reference)) {
                    correct++;
                    labelCorrect.incrementCount(reference);
                }
            }
        }
        if (tedEvalParseSeg != null) {
            tedEvalGoldTree.printf("(root");
            tedEvalParseTree.printf("(root");
            int safeLength = inputTokens.length;
            if (inputTokens.length != goldTokens.length) {
                log.info("In generating TEDEval files: Input and gold do not have the same number of tokens");
                log.info("    (ignoring any extras)");
                log.info("  input: " + Arrays.toString(inputTokens));
                log.info("  gold: " + Arrays.toString(goldTokens));
                safeLength = Math.min(inputTokens.length, goldTokens.length);
            }
            if (inputTokens.length != parseTokens.length) {
                log.info("In generating TEDEval files: Input and parse do not have the same number of tokens");
                log.info("    (ignoring any extras)");
                log.info("  input: " + Arrays.toString(inputTokens));
                log.info("  parse: " + Arrays.toString(parseTokens));
                safeLength = Math.min(inputTokens.length, parseTokens.length);
            }
            for (int i = 0; i < safeLength; i++) {
                for (String segment : goldTokens[i].split(":")) tedEvalGoldTree.printf(" (seg %s)", segment);
                tedEvalGoldSeg.printf("%s\t%s%n", inputTokens[i], goldTokens[i]);
                for (String segment : parseTokens[i].split(":")) tedEvalParseTree.printf(" (seg %s)", segment);
                tedEvalParseSeg.printf("%s\t%s%n", inputTokens[i], parseTokens[i]);
            }
            tedEvalGoldTree.printf(")%n");
            tedEvalGoldSeg.println();
            tedEvalParseTree.printf(")%n");
            tedEvalParseSeg.println();
        }
    }
    double accuracy = ((double) correct) / ((double) total);
    accuracy *= 100.0;
    pwOut.println("EVALUATION RESULTS");
    pwOut.printf("#datums:\t%d%n", total);
    pwOut.printf("#correct:\t%d%n", correct);
    pwOut.printf("accuracy:\t%.2f%n", accuracy);
    pwOut.println("==================");
    // Output the per label accuracies
    pwOut.println("PER LABEL ACCURACIES");
    for (String refLabel : labelTotal.keySet()) {
        double nTotal = labelTotal.getCount(refLabel);
        double nCorrect = labelCorrect.getCount(refLabel);
        double acc = (nCorrect / nTotal) * 100.0;
        pwOut.printf(" %s\t%.2f%n", refLabel, acc);
    }
    if (tedEvalParseSeg != null) {
        tedEvalGoldTree.close();
        tedEvalGoldSeg.close();
        tedEvalParseTree.close();
        tedEvalParseSeg.close();
    }
}

Example 48 with FileNotFoundException

use of java.io.FileNotFoundException in project CoreNLP by stanfordnlp.

the class FTBDataset method makeSplitSet.

private Set<String> makeSplitSet(String splitFileName) {
    splitFileName = DataFilePaths.convert(splitFileName);
    Set<String> splitSet = Generics.newHashSet();
    LineNumberReader reader = null;
    try {
        reader = new LineNumberReader(new FileReader(splitFileName));
        for (String line; (line = reader.readLine()) != null; ) {
            splitSet.add(line.trim());
        }
        reader.close();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        System.err.printf("%s: Error reading %s (line %d)%n", this.getClass().getName(), splitFileName, reader.getLineNumber());
        e.printStackTrace();
    }
    return splitSet;
}

Example 49 with FileNotFoundException

use of java.io.FileNotFoundException in project CoreNLP by stanfordnlp.

the class ConfusionMatrixTSV method main.

public static void main(String[] args) {
    if (args.length < 1) {
        System.err.printf("Usage: java %s answers_file%n", ConfusionMatrix.class.getName());
        System.exit(-1);
    }
    try {
        ConfusionMatrix<String> cm = new ConfusionMatrix<>();
        String answersFile = args[0];
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(answersFile), "UTF-8"));
        String line = br.readLine();
        for (; line != null; line = br.readLine()) {
            String[] tokens = line.split("\\s");
            if (tokens.length != 3) {
                System.err.printf("ignoring bad line");
                continue;
            //System.exit(-1);
            }
            cm.add(tokens[2], tokens[1]);
        }
        System.out.println(cm.toString());
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 50 with FileNotFoundException

use of java.io.FileNotFoundException in project CoreNLP by stanfordnlp.

the class TreeToTSV method main.

public static void main(String[] args) {
    if (args.length < 1) {
        System.err.printf("Usage: java %s tree_file%n", TreeToTSV.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        StringBuilder sb = new StringBuilder();
        String nl = System.getProperty("line.separator");
        Pattern nePattern = Pattern.compile("^grup\\.nom\\.");
        Pattern npPattern = Pattern.compile("^np0000.$");
        for (Tree tree; (tree = tr.readTree()) != null; ) {
            for (Tree t : tree) {
                if (!t.isPreTerminal())
                    continue;
                char type = 'O';
                Tree grandma = t.ancestor(1, tree);
                String grandmaValue = ((CoreLabel) grandma.label()).value();
                // grup.nom.x
                if (nePattern.matcher(grandmaValue).find())
                    type = grandmaValue.charAt(9);
                else // else check the pos for np0000x or not
                {
                    String pos = ((CoreLabel) t.label()).value();
                    if (npPattern.matcher(pos).find())
                        type = pos.charAt(6);
                }
                Tree wordNode = t.firstChild();
                String word = ((CoreLabel) wordNode.label()).value();
                sb.append(word).append("\t");
                switch(type) {
                    case 'p':
                        sb.append("PERS");
                        break;
                    case 'l':
                        sb.append("LUG");
                        break;
                    case 'o':
                        sb.append("ORG");
                        break;
                    case '0':
                        sb.append("OTROS");
                        break;
                    default:
                        sb.append("O");
                }
                sb.append(nl);
            }
            sb.append(nl);
        }
        System.out.print(sb.toString());
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}