Example usage for edu.stanford.nlp.util StringUtils argsToProperties

List of usage examples for edu.stanford.nlp.util StringUtils argsToProperties

  1. HOME
  2. Java
  3. edu.stanford.nlp
  4. edu.stanford.nlp.util.*
  5. StringUtils
  6. argsToProperties

Introduction

In this page you can find the example usage for edu.stanford.nlp.util StringUtils argsToProperties.

Prototype

public static Properties argsToProperties(String[] args, Map<String, Integer> flagsToNumArgs)

Source Link

Document

Analogous to #argsToMap .

Usage

From source file:ilcc.ccgparser.nnparser.IncNNParser.java

public static void main(String[] args) throws IOException, Exception {

    String trainAutoFile, trainConllFile, trainPargFile, testAutoFile, testPargFile, testConllFile, outAutoFile,
            outPargFile, modelFile, embedFile;

    String home = "/home/ambati/ilcc/projects/parsing/experiments/english/ccg/";
    trainAutoFile = home + "data/final/train.gccg.auto";
    trainConllFile = home + "data/final/train.accg.conll2";
    trainPargFile = home + "data/final/train.gccg.parg";
    trainAutoFile = home + "data/final/devel.gccg.auto";
    trainConllFile = home + "data/final/devel.accg.conll";
    trainPargFile = home + "data/final/devel.gccg.parg";
    //testAutoFile = home+"data/final/devel.gccg.auto";
    testAutoFile = "";
    testPargFile = home + "data/final/devel.gccg.pargx";
    testConllFile = home + "data/final/devel.accg.conllx";
    outAutoFile = home + "models/out1.txt";
    outPargFile = home + "models/out2.txt";
    modelFile = home + "models/nnccg.model.txt.gz";
    embedFile = "/home/ambati/ilcc/tools/neural-networks/embeddings/turian/embeddings.raw";

    if (args.length == 0) {
        args = new String[] { "-trainCoNLL", trainConllFile, "-trainAuto", trainAutoFile, "-trainParg",
                trainPargFile, "-testCoNLL", testConllFile, "-testAuto", testAutoFile, "-testParg",
                testPargFile, "-outParg", outPargFile, "-model", modelFile, "-beam", "1", "-embedFile",
                embedFile, "-maxIter", "1", "-lookAhead", "" + false
                //"-isTrain", "true", "-beam", 1, "-debug", "false", "-early", false
        };//from  w  ww. java 2  s .  c om
    }

    Properties props = StringUtils.argsToProperties(args, numArgs);
    IncNNParser incnnpar = new IncNNParser(props);

    long start;

    System.err.println("Started Training: " + new Date(System.currentTimeMillis()) + "\n");
    start = (long) (System.currentTimeMillis());
    if (props.getProperty("trainCoNLL") != null)
        incnnpar.train(props.getProperty("trainCoNLL"), props.getProperty("testCoNLL"),
                props.getProperty("model"), props.getProperty("embedFile"), props.getProperty("preModel"));
    System.err.println("Training Time: " + (System.currentTimeMillis() - start) / 1000.0 + " (s)");

    System.err.println("Loading Model: " + new Date(System.currentTimeMillis()) + "\n");
    incnnpar.loadModelFile(props.getProperty("model"));

    System.err.println("Started Parsing: " + new Date(System.currentTimeMillis()) + "\n");
    start = (long) (System.currentTimeMillis());
    incnnpar.test(props.getProperty("testCoNLL"), props.getProperty("testAuto"), props.getProperty("testParg"));
    System.err.println("Parsing Time: " + (System.currentTimeMillis() - start) / 1000.0 + " (s)");
}

From source file:ilcc.ccgparser.nnparser.IncNNParserGreedy.java

public static void main(String[] args) throws IOException, Exception {

    String trainAutoFile, trainConllFile, trainPargFile, testAutoFile, testPargFile, testConllFile, outAutoFile,
            outPargFile, modelFile, embedFile;

    String home = "/home/ambati/ilcc/projects/parsing/experiments/english/ccg/";
    trainAutoFile = home + "data/final/train.gccg.auto";
    trainConllFile = home + "data/final/train.accg.conll2";
    trainPargFile = home + "data/final/train.gccg.parg";
    trainAutoFile = home + "data/final/devel.gccg.auto";
    trainConllFile = home + "data/final/devel.accg.conll";
    trainPargFile = home + "data/final/devel.gccg.parg";
    //testAutoFile = home+"data/final/devel.gccg.auto";
    testAutoFile = "";
    testPargFile = home + "data/final/devel.gccg.pargx";
    testConllFile = home + "data/final/devel.accg.conllx";
    outAutoFile = home + "models/out1.txt";
    outPargFile = home + "models/out2.txt";
    modelFile = home + "models/nnccg.model.txt.gz";
    embedFile = "/home/ambati/ilcc/tools/neural-networks/embeddings/turian/embeddings.raw";

    if (args.length == 0) {
        args = new String[] { "-trainCoNLL", trainConllFile, "-trainAuto", trainAutoFile, "-trainParg",
                trainPargFile, "-testCoNLL", testConllFile, "-testAuto", testAutoFile, "-testParg",
                testPargFile, "-outParg", outPargFile, "-model", modelFile, "-beam", "1", "-embedFile",
                embedFile, "-maxIter", "1",
                //"-isTrain", "true", "-beam", 1, "-debug", "false", "-early", false
        };/*from  w w w  .  j  a  v  a  2 s .co m*/
    }

    Properties props = StringUtils.argsToProperties(args, numArgs);
    IncNNParserGreedy incnnpar = new IncNNParserGreedy(props);

    long start;

    System.err.println("Started Training: " + new Date(System.currentTimeMillis()) + "\n");
    start = (long) (System.currentTimeMillis());
    if (props.getProperty("trainCoNLL") != null)
        incnnpar.train(props.getProperty("trainCoNLL"), props.getProperty("testCoNLL"),
                props.getProperty("model"), props.getProperty("embedFile"), props.getProperty("preModel"));
    System.err.println("Training Time: " + (System.currentTimeMillis() - start) / 1000.0 + " (s)");

    System.err.println("Loading Model: " + new Date(System.currentTimeMillis()) + "\n");
    incnnpar.loadModelFile(props.getProperty("model"));

    System.err.println("Started Parsing: " + new Date(System.currentTimeMillis()) + "\n");
    start = (long) (System.currentTimeMillis());
    incnnpar.test(props.getProperty("testCoNLL"), props.getProperty("testAuto"), props.getProperty("testParg"));
    System.err.println("Parsing Time: " + (System.currentTimeMillis() - start) / 1000.0 + " (s)");
}

From source file:ilcc.ccgparser.test.IncExtractProb.java

public static void main(String[] args) throws IOException, Exception {

    String testAutoFile, testConllFile, outFile, modelFile, embedFile;

    String home = "/home/ambati/ilcc/projects/parsing/experiments/english/ccg/useful/ccg-all/";
    modelFile = home + "models/nn.gincint.model.txt.gz";
    embedFile = "/home/ambati/ilcc/tools/neural-networks/embeddings/turian/embeddings.raw";
    testAutoFile = home + "/devel.per.b16incin.auto";
    testConllFile = home + "../../data/final/devel.innccg.conll";
    outFile = home + "/out1.txt";

    String eeg = "/home/ambati/ilcc/projects/parsing/experiments/eeg/data/";
    testAutoFile = eeg + "inc/wsj.eeg.inninc.auto";
    testConllFile = eeg + "inc/wsj.eeg.conll";
    outFile = eeg + "inc/wsj.eeg.inninc.out.txt";

    testAutoFile = eeg + "oracle/wsj.eeg.out.auto";
    testConllFile = eeg + "oracle/wsj.eeg.inc.conll";
    outFile = eeg + "oracle/wsj.eeg.out.allacts.txt";
    testConllFile = eeg + "oracle/wsj.eeg.conll";
    outFile = eeg + "oracle/wsj.eeg.out.txt";

    if (args.length == 0) {
        args = new String[] { "-testAuto", testAutoFile, "-testCoNLL", testConllFile, "-outFile", outFile,
                "-model", modelFile, "-embedFile", embedFile, };
    }//from  w  ww  .  ja  v a 2  s  .c  o  m

    Properties props = StringUtils.argsToProperties(args, numArgs);
    IncExtractProb incnnpar = new IncExtractProb(props);

    long start;
    System.err.println("Loading Model: " + new Date(System.currentTimeMillis()) + "\n");
    incnnpar.loadModelFile(props.getProperty("model"));

    System.err.println("Started Parsing: " + new Date(System.currentTimeMillis()) + "\n");
    start = (long) (System.currentTimeMillis());
    incnnpar.test(props.getProperty("testCoNLL"), props.getProperty("testAuto"), props.getProperty("outFile"));
    System.err.println("Parsing Time: " + (System.currentTimeMillis() - start) / 1000.0 + " (s)");
}

From source file:ilcc.ccgparser.test.IncGetGoldDerivation.java

public static void main(String[] args) throws IOException, Exception {

    String trainAutoFile, trainConllFile, trainPargFile, testAutoFile, testPargFile, testConllFile, outAutoFile,
            outPargFile, modelFile, algo;

    String eeg = "/home/ambati/ilcc/projects/parsing/experiments/eeg/data/";
    trainAutoFile = eeg + "oracle/wsj.eeg.auto";
    trainConllFile = eeg + "oracle/wsj.eeg.conll";
    outAutoFile = eeg + "oracle/wsj.eeg.out.auto";

    if (args.length == 0) {
        args = new String[] { "-trainCoNLL", trainConllFile, "-trainAuto", trainAutoFile, "-outAuto",
                outAutoFile, };//from  www. ja va2  s  . com
    }

    Properties props = StringUtils.argsToProperties(args, numArgs);

    IncParser parser;
    parser = new IncParserGreedy(props);
    BufferedWriter out = new BufferedWriter(new FileWriter(new File(props.getProperty("outAuto"))));
    if (props.getProperty("trainCoNLL") != null) {
        List<CCGJTreeNode> trees = parser.fillData();
        for (int i = 0; i < trees.size(); i++) {
            CCGJTreeNode tree = trees.get(i);
            if (tree != null)
                writeDeriv(i + 1, out, tree);
            else
                out.write("ID=" + (i + 1) + "\nError:No Derivation\n");
        }
    }
    out.close();
}

From source file:process.PTBTokenizer.java

License:Open Source License

/**
 * Reads files given as arguments and print their tokens, by default as one
 * per line. This is useful either for testing or to run standalone to turn
 * a corpus into a one-token-per-line file of tokens. This main method
 * assumes that the input file is in utf-8 encoding, unless an encoding is
 * specified.//w w  w .  j a  v  a  2  s .  com
 * <p/>
 * Usage: <code>
 * java edu.stanford.nlp.process.PTBTokenizer [options] filename+
 * </code>
 * <p/>
 * Options:
 * <ul>
 * <li>-options options Set various tokenization options (see the
 * documentation in the class javadoc)
 * <li>-preserveLines Produce space-separated tokens, except when the
 * original had a line break, not one-token-per-line
 * <li>-encoding encoding Specifies a character encoding. If you do not
 * specify one, the default is utf-8 (not the platform default).
 * <li>-lowerCase Lowercase all tokens (on tokenization)
 * <li>-parseInside regex Names an XML-style element or a regular expression
 * over such elements. The tokenizer will only tokenize inside elements that
 * match this regex. (This is done by regex matching, not an XML parser, but
 * works well for simple XML documents, or other SGML-style documents, such
 * as Linguistic Data Consortium releases, which adopt the convention that a
 * line of a file is either XML markup or character data but never both.)
 * <li>-ioFileList file* The remaining command-line arguments are treated as
 * filenames that themselves contain lists of pairs of input-output
 * filenames (2 column, whitespace separated).
 * <li>-dump Print the whole of each CoreLabel, not just the value (word)
 * <li>-untok Heuristically untokenize tokenized text
 * <li>-h, -help Print usage info
 * </ul>
 * 
 * @param args
 *            Command line arguments
 * @throws IOException
 *             If any file I/O problem
 */
public static void main(String[] args) throws IOException {

    edu.stanford.nlp.process.PTBTokenizer<HasWord> abctesTokenizer;

    Properties options = StringUtils.argsToProperties(args, optionArgDefs());
    boolean showHelp = PropertiesUtils.getBool(options, "help", false);
    showHelp = PropertiesUtils.getBool(options, "h", showHelp);
    if (showHelp) {
        System.err.println("Usage: java edu.stanford.nlp.process.PTBTokenizer [options]* filename*");
        System.err.println(
                "  options: -h|-preserveLines|-lowerCase|-dump|-ioFileList|-encoding|-parseInside|-options");
        System.exit(0);
    }

    StringBuilder optionsSB = new StringBuilder();
    String tokenizerOptions = options.getProperty("options", null);
    if (tokenizerOptions != null) {
        optionsSB.append(tokenizerOptions);
    }
    boolean preserveLines = PropertiesUtils.getBool(options, "preserveLines", false);
    if (preserveLines) {
        optionsSB.append(",tokenizeNLs");
    }
    boolean inputOutputFileList = PropertiesUtils.getBool(options, "ioFileList", false);
    boolean lowerCase = PropertiesUtils.getBool(options, "lowerCase", false);
    boolean dump = PropertiesUtils.getBool(options, "dump", false);
    boolean untok = PropertiesUtils.getBool(options, "untok", false);
    String charset = options.getProperty("encoding", "utf-8");
    String parseInsideKey = options.getProperty("parseInside", null);
    Pattern parseInsidePattern = null;
    if (parseInsideKey != null) {
        try {
            parseInsidePattern = Pattern.compile("<(/?)(?:" + parseInsideKey + ")(?:\\s[^>]*?)?>");
        } catch (PatternSyntaxException e) {
            // just go with null parseInsidePattern
        }
    }

    // Other arguments are filenames
    String parsedArgStr = options.getProperty("", null);
    String[] parsedArgs = (parsedArgStr == null) ? null : parsedArgStr.split("\\s+");

    ArrayList<String> inputFileList = new ArrayList<String>();
    ArrayList<String> outputFileList = null;
    if (inputOutputFileList && parsedArgs != null) {
        outputFileList = new ArrayList<String>();
        for (String fileName : parsedArgs) {
            BufferedReader r = IOUtils.readerFromString(fileName, charset);
            for (String inLine; (inLine = r.readLine()) != null;) {
                String[] fields = inLine.split("\\s+");
                inputFileList.add(fields[0]);
                if (fields.length > 1) {
                    outputFileList.add(fields[1]);
                } else {
                    outputFileList.add(fields[0] + ".tok");
                }
            }
            r.close();
        }
    } else if (parsedArgs != null) {
        // Concatenate input files into a single output file
        inputFileList.addAll(Arrays.asList(parsedArgs));
    }

    if (untok) {
        untok(inputFileList, outputFileList, charset);
    } else {
        tok(inputFileList, outputFileList, charset, parseInsidePattern, optionsSB.toString(), preserveLines,
                dump, lowerCase);
    }
}