Examples with NETaggerLevel1 edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 used on opensource projects

Example 1 with NETaggerLevel1

use of edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 in project cogcomp-nlp by CogComp.

the class LearningCurveMultiDataset method getLearningCurve.

/**
     * use fixedNumIterations=-1 if you want to use the automatic convergence criterion
     * <p>
     * NB: assuming column format
     */
public static void getLearningCurve(Vector<Data> trainDataSet, Vector<Data> testDataSet, int fixedNumIterations) throws Exception {
    double bestF1Level1 = -1;
    int bestRoundLevel1 = 0;
    // Get the directory name (<configname>.model is appended in LbjTagger/Parameters.java:139)
    String modelPath = ParametersForLbjCode.currentParameters.pathToModelFile;
    String modelPathDir = modelPath.substring(0, modelPath.lastIndexOf("/"));
    if (IOUtils.exists(modelPathDir)) {
        if (!IOUtils.isDirectory(modelPathDir)) {
            String msg = "ERROR: " + NAME + ".getLearningCurve(): model directory '" + modelPathDir + "' already exists as a (non-directory) file.";
            logger.error(msg);
            throw new IOException(msg);
        } else
            logger.warn(NAME + ".getLearningCurve(): writing to existing model path '" + modelPathDir + "'...");
    } else {
        IOUtils.mkdir(modelPathDir);
    }
    NETaggerLevel1.Parameters paramLevel1 = new NETaggerLevel1.Parameters();
    paramLevel1.baseLTU = new SparseAveragedPerceptron(ParametersForLbjCode.currentParameters.learningRatePredictionsLevel1, 0, ParametersForLbjCode.currentParameters.thicknessPredictionsLevel1);
    logger.info("Level 1 classifier learning rate = " + ParametersForLbjCode.currentParameters.learningRatePredictionsLevel1 + ", thickness = " + ParametersForLbjCode.currentParameters.thicknessPredictionsLevel1);
    NETaggerLevel1 tagger1 = new NETaggerLevel1(paramLevel1, modelPath + ".level1", modelPath + ".level1.lex");
    tagger1.forget();
    for (int dataId = 0; dataId < trainDataSet.size(); dataId++) {
        Data trainData = trainDataSet.elementAt(dataId);
        if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
            PredictionsAndEntitiesConfidenceScores.getAndMarkEntities(trainData, NEWord.LabelToLookAt.GoldLabel);
            TwoLayerPredictionAggregationFeatures.setLevel1AggregationFeatures(trainData, true);
        }
    }
    // preextract the L1 test and train data.
    String path = ParametersForLbjCode.currentParameters.pathToModelFile;
    String trainPathL1 = path + ".level1.prefetchedTrainData";
    File deleteme = new File(trainPathL1);
    if (deleteme.exists())
        deleteme.delete();
    String testPathL1 = path + ".level1.prefetchedTestData";
    deleteme = new File(testPathL1);
    if (deleteme.exists())
        deleteme.delete();
    logger.info("Pre-extracting the training data for Level 1 classifier, saving to " + trainPathL1);
    BatchTrainer bt1train = prefetchAndGetBatchTrainer(tagger1, trainDataSet, trainPathL1);
    logger.info("Pre-extracting the testing data for Level 1 classifier, saving to " + testPathL1);
    BatchTrainer bt1test = prefetchAndGetBatchTrainer(tagger1, testDataSet, testPathL1);
    Parser testParser1 = bt1test.getParser();
    for (int i = 0; (fixedNumIterations == -1 && i < 200 && i - bestRoundLevel1 < 10) || (fixedNumIterations > 0 && i <= fixedNumIterations); ++i) {
        bt1train.train(1);
        testParser1.reset();
        TestDiscrete simpleTest = new TestDiscrete();
        simpleTest.addNull("O");
        TestDiscrete.testDiscrete(simpleTest, tagger1, null, testParser1, true, 0);
        double f1Level1 = simpleTest.getOverallStats()[2];
        if (f1Level1 > bestF1Level1) {
            bestF1Level1 = f1Level1;
            bestRoundLevel1 = i;
            tagger1.save();
        }
        logger.info(i + " rounds.  Best so far for Level1 : (" + bestRoundLevel1 + ")=" + bestF1Level1);
    }
    logger.info("Level 1; best round : " + bestRoundLevel1 + "\tbest F1 : " + bestF1Level1);
    // trash the l2 prefetch data
    String trainPathL2 = path + ".level2.prefetchedTrainData";
    deleteme = new File(trainPathL2);
    if (deleteme.exists())
        deleteme.delete();
    String testPathL2 = path + ".level2.prefetchedTestData";
    deleteme = new File(testPathL1);
    if (deleteme.exists())
        deleteme.delete();
    NETaggerLevel2.Parameters paramLevel2 = new NETaggerLevel2.Parameters();
    paramLevel2.baseLTU = new SparseAveragedPerceptron(ParametersForLbjCode.currentParameters.learningRatePredictionsLevel2, 0, ParametersForLbjCode.currentParameters.thicknessPredictionsLevel2);
    NETaggerLevel2 tagger2 = new NETaggerLevel2(paramLevel2, ParametersForLbjCode.currentParameters.pathToModelFile + ".level2", ParametersForLbjCode.currentParameters.pathToModelFile + ".level2.lex");
    tagger2.forget();
    // Previously checked if PatternFeatures was in featuresToUse.
    if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
        logger.info("Level 2 classifier learning rate = " + ParametersForLbjCode.currentParameters.learningRatePredictionsLevel2 + ", thickness = " + ParametersForLbjCode.currentParameters.thicknessPredictionsLevel2);
        double bestF1Level2 = -1;
        int bestRoundLevel2 = 0;
        logger.info("Pre-extracting the training data for Level 2 classifier, saving to " + trainPathL2);
        BatchTrainer bt2train = prefetchAndGetBatchTrainer(tagger2, trainDataSet, trainPathL2);
        logger.info("Pre-extracting the testing data for Level 2 classifier, saving to " + testPathL2);
        BatchTrainer bt2test = prefetchAndGetBatchTrainer(tagger2, testDataSet, testPathL2);
        Parser testParser2 = bt2test.getParser();
        for (int i = 0; (fixedNumIterations == -1 && i < 200 && i - bestRoundLevel2 < 10) || (fixedNumIterations > 0 && i <= fixedNumIterations); ++i) {
            logger.info("Learning level 2 classifier; round " + i);
            bt2train.train(1);
            logger.info("Testing level 2 classifier;  on prefetched data, round: " + i);
            testParser2.reset();
            TestDiscrete simpleTest = new TestDiscrete();
            simpleTest.addNull("O");
            TestDiscrete.testDiscrete(simpleTest, tagger2, null, testParser2, true, 0);
            double f1Level2 = simpleTest.getOverallStats()[2];
            if (f1Level2 > bestF1Level2) {
                bestF1Level2 = f1Level2;
                bestRoundLevel2 = i;
                tagger2.save();
            }
            logger.info(i + " rounds.  Best so far for Level2 : (" + bestRoundLevel2 + ") " + bestF1Level2);
        }
        // trash the l2 prefetch data
        deleteme = new File(trainPathL2);
        if (deleteme.exists())
            deleteme.delete();
        deleteme = new File(testPathL1);
        if (deleteme.exists())
            deleteme.delete();
        logger.info("Level1: bestround=" + bestRoundLevel1 + "\t F1=" + bestF1Level1 + "\t Level2: bestround=" + bestRoundLevel2 + "\t F1=" + bestF1Level2);
    }
    /*
         * This will override the models forcing to save the iteration we're interested in- the
         * fixedNumIterations iteration, the last one. But note - both layers will be saved for this
         * iteration. If the best performance for one of the layers came before the final iteration,
         * we're in a small trouble- the performance will decrease
         */
    if (fixedNumIterations > -1) {
        tagger1.save();
        tagger2.save();
    }
}

Example 2 with NETaggerLevel1

use of edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 in project cogcomp-nlp by CogComp.

the class NEDisplayPredictions method test.

/**
     * Display the predictions, the gazetteer matches and the labels.
     * 
     * @param testDatapath path to test data.
     * @param dataFormat the data format.
     * @param verbose report more.
     * @throws Exception
     */
public static void test(String testDatapath, String dataFormat, boolean verbose) throws Exception {
    Data testData = new Data(testDatapath, testDatapath, dataFormat, new String[] {}, new String[] {});
    ExpressiveFeaturesAnnotator.annotate(testData);
    Vector<Data> data = new Vector<>();
    data.addElement(testData);
    NETaggerLevel1 taggerLevel1 = new NETaggerLevel1(ParametersForLbjCode.currentParameters.pathToModelFile + ".level1", ParametersForLbjCode.currentParameters.pathToModelFile + ".level1.lex");
    NETaggerLevel2 taggerLevel2 = null;
    if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
        taggerLevel2 = new NETaggerLevel2(ParametersForLbjCode.currentParameters.pathToModelFile + ".level2", ParametersForLbjCode.currentParameters.pathToModelFile + ".level2.lex");
    }
    for (int i = 0; i < data.size(); i++) Decoder.annotateDataBIO(data.elementAt(i), taggerLevel1, taggerLevel2);
    reportPredictions(data.get(0));
}

Example 3 with NETaggerLevel1

use of edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 in project cogcomp-nlp by CogComp.

the class NETagPlain method init.

/**
     * assumes ParametersForLbjCode has been initialized
     */
public static void init() {
    String modelFile = ParametersForLbjCode.currentParameters.pathToModelFile;
    logger.info("Initializing tagger level 1...");
    tagger1 = new NETaggerLevel1(modelFile + ".level1", modelFile + ".level1.lex");
    if (ParametersForLbjCode.currentParameters.featuresToUse.containsKey("PredictionsLevel1")) {
        logger.info("Initializing tagger level 2...");
        tagger2 = new NETaggerLevel2(modelFile + ".level2", modelFile + ".level2.lex");
    }
}

Example 4 with NETaggerLevel1

use of edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 in project cogcomp-nlp by CogComp.

the class Parameters method loadClassifierModels.

public static void loadClassifierModels(ParametersForLbjCode config, ParametersForLbjCode outter) {
    if (outter.debug) {
        logger.debug("Reading the model at: " + config.pathToModelFile + ".level1");
    }
    config.taggerLevel1 = new NETaggerLevel1(config.pathToModelFile + ".level1", config.pathToModelFile + ".level1.lex");
    if (outter.debug) {
        logger.debug("Reading the model at: " + config.pathToModelFile + ".level2");
    }
    config.taggerLevel2 = new NETaggerLevel2(config.pathToModelFile + ".level2", config.pathToModelFile + ".level2.lex");
    logger.debug("## Parameters.loadClassifierModels(): set taggerLevel1 and taggerLevel2 in config passed as argument.");
}

Example 5 with NETaggerLevel1

use of edu.illinois.cs.cogcomp.ner.LbjFeatures.NETaggerLevel1 in project cogcomp-nlp by CogComp.

the class ModelLoader method load.

/**
 * Load the models wherever they are found. Check file system first, then classpath, and finally get it
 * from Minio datastore.
 * @param rm the resource manager.
 * @param training if we are training.
 * @param viewName the name of the view identifies the model.
 * @param cp the parameters for the calling model.
 */
public static void load(ResourceManager rm, String viewName, boolean training, ParametersForLbjCode cp) {
    // the loaded built into the model will check the local file system and the jar files in the classpath.
    String modelPath = cp.pathToModelFile;
    String modelFilePath = modelPath + ".level1";
    java.io.File modelFile = new File(modelFilePath);
    NETaggerLevel1 tagger1 = null;
    NETaggerLevel2 tagger2 = null;
    if (modelFile.exists()) {
        tagger1 = new NETaggerLevel1(modelPath + ".level1", modelPath + ".level1.lex");
        logger.info("Reading L1 model from file : " + modelPath + ".level2");
        if (cp.featuresToUse.containsKey("PredictionsLevel1")) {
            tagger2 = new NETaggerLevel2(modelPath + ".level2", modelPath + ".level2.lex");
            logger.info("Reading L2 model from file : " + modelPath + ".level2");
        } else {
            logger.info("L2 model not required.");
        }
    } else if (IOUtilities.existsInClasspath(NETaggerLevel1.class, modelFilePath)) {
        tagger1 = new NETaggerLevel1(modelPath + ".level1", modelPath + ".level1.lex");
        logger.info("Reading L1 model from classpath : " + modelPath + ".level2");
        if (cp.featuresToUse.containsKey("PredictionsLevel1")) {
            tagger2 = new NETaggerLevel2(modelPath + ".level2", modelPath + ".level2.lex");
            logger.info("Reading L2 model from classpath : " + modelPath + ".level2");
        } else {
            logger.info("L2 model not required.");
        }
    } else if (training) {
        // we are training a new model, so it it doesn't exist, we don't care, just create a
        // container.
        tagger1 = new NETaggerLevel1(modelPath + ".level1", modelPath + ".level1.lex");
        logger.info("Reading L1 model from file : " + modelPath + ".level2");
        if (cp.featuresToUse.containsKey("PredictionsLevel1")) {
            tagger2 = new NETaggerLevel2(modelPath + ".level2", modelPath + ".level2.lex");
            logger.info("Reading L2 model from file : " + modelPath + ".level2");
        } else {
            logger.info("L2 model not required.");
        }
    } else {
        // all else has filed, load from the datastore, create artifact ids based on the view
        // name and training data designation.
        String dataset;
        String lowercaseViewName = viewName.toLowerCase();
        if (lowercaseViewName.contains(ViewNames.NER_CONLL.toLowerCase())) {
            dataset = "enron-conll";
        } else if (lowercaseViewName.contains(ViewNames.NER_ONTONOTES.toLowerCase())) {
            dataset = "ontonotes";
        } else {
            // not a standard model, and we can't find it on the command line.
            throw new IllegalArgumentException("The NER models could not be found at \"" + modelPath + "\", and no default with view name " + viewName);
        }
        String data_split;
        if (!rm.containsKey(NerBaseConfigurator.TRAINED_ON))
            data_split = NerBaseConfigurator.TRAINED_ON_ALL_DATA;
        else
            data_split = rm.getString(NerBaseConfigurator.TRAINED_ON);
        try {
            Datastore ds = new Datastore(new ResourceConfigurator().getConfig(rm));
            String artifact_id = "ner-model-" + dataset + "-" + data_split;
            File modelDir = ds.getDirectory("edu.illinois.cs.cogcomp.ner", artifact_id, 4.0, false);
            String model = "";
            if (modelDir.getPath().contains("conll")) {
                model = modelDir.getPath() + "/model/EnronCoNLL.model";
            } else {
                model = modelDir.getPath() + "/model/OntoNotes.model";
            }
            tagger1 = new NETaggerLevel1(model + ".level1", model + ".level1.lex");
            if (cp.featuresToUse.containsKey("PredictionsLevel1")) {
                tagger2 = new NETaggerLevel2(model + ".level2", model + ".level2.lex");
            }
        } catch (InvalidPortException | DatastoreException | InvalidEndpointException e) {
            e.printStackTrace();
        }
    }
    cp.taggerLevel1 = tagger1;
    cp.taggerLevel2 = tagger2;
}