Example usage for weka.classifiers.functions LinearRegression coefficients

Introduction

In this page you can find the example usage for weka.classifiers.functions LinearRegression coefficients.

Prototype

public double[] coefficients() 

Source Link

Document

Returns the coefficients for this linear model.

Usage

From source file:edu.utexas.cs.tactex.utils.RegressionUtils.java

License:Open Source License

public static WekaLinRegData createWekaLinRegData(int timeslot, Instances X, Double[] yvals,
        ArrayList<Double> candidateLambdas) throws Exception {
    WekaLinRegData result;/*from   w w  w  .j  a v  a 2 s. c  o  m*/

    // normalize
    Standardize standardize = new Standardize();
    try {
        standardize.setInputFormat(X);
    } catch (Exception e) {
        log.error("PolyRegCust.predictNumSubs() data standardizing exception", e);
        throw e;
    }
    Instances nrmFeatures = RegressionUtils.featureNormalize(X, standardize);
    log.info("normalized features " + nrmFeatures);

    // add y to X since this is what weka expects
    Instances Xy = RegressionUtils.addYforWeka(nrmFeatures, yvals);

    // run cross validation for lambda
    Double bestLambda = findBestRegularizationParameter(Xy, candidateLambdas);
    if (null == bestLambda) {
        String message = "best regularization parameter is null, cannot predict";
        log.error(message);
        throw new Exception(message);
    }

    // run linear regression
    LinearRegression linearRegression = RegressionUtils.createLinearRegression();
    linearRegression.setRidge(bestLambda);
    try {
        linearRegression.buildClassifier(Xy);
        log.info("theta " + Arrays.toString(linearRegression.coefficients()));
    } catch (Exception e) {
        log.error("PolyRegCust.predictNumSubs() buildClassifier exception", e);
        throw e;
    }

    result = new WekaLinRegData(standardize, linearRegression, timeslot);
    return result;
}

---

From source file:org.jaqpot.algorithm.resource.WekaMLR.java

License:Open Source License

@POST
@Path("training")
public Response training(TrainingRequest request) {

    try {/* ww w . j  a  va 2  s.  co m*/
        if (request.getDataset().getDataEntry().isEmpty()
                || request.getDataset().getDataEntry().get(0).getValues().isEmpty()) {
            return Response.status(Response.Status.BAD_REQUEST).entity(
                    ErrorReportFactory.badRequest("Dataset is empty", "Cannot train model on empty dataset"))
                    .build();
        }
        List<String> features = request.getDataset().getDataEntry().stream().findFirst().get().getValues()
                .keySet().stream().collect(Collectors.toList());

        Instances data = InstanceUtils.createFromDataset(request.getDataset(), request.getPredictionFeature());

        LinearRegression linreg = new LinearRegression();
        String[] linRegOptions = { "-S", "1", "-C" };
        linreg.setOptions(linRegOptions);
        linreg.buildClassifier(data);

        WekaModel model = new WekaModel();
        model.setClassifier(linreg);

        String pmml = PmmlUtils.createRegressionModel(features, request.getPredictionFeature(),
                linreg.coefficients(), "MLR");

        TrainingResponse response = new TrainingResponse();
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        ObjectOutput out = new ObjectOutputStream(baos);
        out.writeObject(model);
        String base64Model = Base64.getEncoder().encodeToString(baos.toByteArray());
        response.setRawModel(base64Model);
        List<String> independentFeatures = features.stream()
                .filter(feature -> !feature.equals(request.getPredictionFeature()))
                .collect(Collectors.toList());
        response.setIndependentFeatures(independentFeatures);
        response.setPmmlModel(pmml);
        String predictionFeatureName = request.getDataset().getFeatures().stream()
                .filter(f -> f.getURI().equals(request.getPredictionFeature())).findFirst().get().getName();
        response.setAdditionalInfo(Arrays.asList(request.getPredictionFeature(), predictionFeatureName));

        response.setPredictedFeatures(Arrays.asList("Weka MLR prediction of " + predictionFeatureName));

        return Response.ok(response).build();
    } catch (Exception ex) {
        Logger.getLogger(WekaMLR.class.getName()).log(Level.SEVERE, null, ex);
        return Response.status(Response.Status.INTERNAL_SERVER_ERROR).entity(ex.getMessage()).build();
    }
}

---

From source file:org.jaqpot.algorithms.resource.WekaMLR.java

License:Open Source License

@POST
@Path("training")
public Response training(TrainingRequest request) {

    try {/* w ww.ja va2 s  .c  o  m*/
        if (request.getDataset().getDataEntry().isEmpty()
                || request.getDataset().getDataEntry().get(0).getValues().isEmpty()) {
            return Response.status(Response.Status.BAD_REQUEST)
                    .entity("Dataset is empty. Cannot train model on empty dataset.").build();
        }
        List<String> features = request.getDataset().getDataEntry().stream().findFirst().get().getValues()
                .keySet().stream().collect(Collectors.toList());

        Instances data = InstanceUtils.createFromDataset(request.getDataset(), request.getPredictionFeature());

        LinearRegression linreg = new LinearRegression();
        String[] linRegOptions = { "-S", "1", "-C" };
        linreg.setOptions(linRegOptions);
        linreg.buildClassifier(data);

        WekaModel model = new WekaModel();
        model.setClassifier(linreg);

        String pmml = PmmlUtils.createRegressionModel(features, request.getPredictionFeature(),
                linreg.coefficients(), "MLR");

        TrainingResponse response = new TrainingResponse();
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        ObjectOutput out = new ObjectOutputStream(baos);
        out.writeObject(model);
        String base64Model = Base64.getEncoder().encodeToString(baos.toByteArray());
        response.setRawModel(base64Model);
        List<String> independentFeatures = features.stream()
                .filter(feature -> !feature.equals(request.getPredictionFeature()))
                .collect(Collectors.toList());
        response.setIndependentFeatures(independentFeatures);
        response.setPmmlModel(pmml);
        String predictionFeatureName = request.getDataset().getFeatures().stream()
                .filter(f -> f.getURI().equals(request.getPredictionFeature())).findFirst().get().getName();
        response.setAdditionalInfo(Arrays.asList(request.getPredictionFeature(), predictionFeatureName));

        response.setPredictedFeatures(Arrays.asList("Weka MLR prediction of " + predictionFeatureName));

        return Response.ok(response).build();
    } catch (Exception ex) {
        Logger.getLogger(WekaMLR.class.getName()).log(Level.SEVERE, null, ex);
        return Response.status(Response.Status.INTERNAL_SERVER_ERROR).entity(ex.getMessage()).build();
    }
}

---

From source file:org.opentox.jaqpot3.qsar.util.PMMLGenerator.java

License:Open Source License

private static String generateMLR(Model model) throws JaqpotException {
    LinearRegression wekaModel = (LinearRegression) model.getActualModel();
    String uuid = model.getUri().getId();
    String PMMLIntro = Configuration.getStringProperty("pmml.intro");
    StringBuilder pmml = new StringBuilder();
    try {/*from   w ww .  ja va 2s  . c o m*/
        final double[] coefficients = wekaModel.coefficients();
        pmml.append("<?xml version=\"1.0\" ?>");
        pmml.append(PMMLIntro);
        pmml.append("<Model ID=\"" + uuid + "\" Name=\"MLR Model\">\n");
        pmml.append("<AlgorithmID href=\"" + Configuration.BASE_URI + "/algorithm/mlr\"/>\n");
        //  URI trainingDatasetURI = URI.create(model.getDataset().getUri());

        pmml.append("<DatasetID href=\"" + URLEncoder.encode(model.getDataset().toString(),
                Configuration.getStringProperty("jaqpot.urlEncoding")) + "\"/>\n");
        pmml.append("<AlgorithmParameters />\n");
        //            pmml.append("<FeatureDefinitions>\n");
        //            for (Feature feature : model.getIndependentFeatures()) {
        //                pmml.append("<link href=\"" + feature.getUri().toString() + "\"/>\n");
        //            }
        //            pmml.append("<target index=\"" + data.attribute(model.getPredictedFeature().getUri().toString()).index() + "\" name=\"" + model.getPredictedFeature().getUri().toString() + "\"/>\n");
        //            pmml.append("</FeatureDefinitions>\n");
        pmml.append("<Timestamp>" + java.util.GregorianCalendar.getInstance().getTime() + "</Timestamp>\n");
        pmml.append("</Model>\n");
        pmml.append("<DataDictionary numberOfFields=\"" + model.getIndependentFeatures().size() + "\" >\n");
        for (Feature feature : model.getIndependentFeatures()) {
            pmml.append("<DataField name=\"" + feature.getUri().toString()
                    + "\" optype=\"continuous\" dataType=\"double\" />\n");
        }
        pmml.append("</DataDictionary>\n");
        // RegressionModel
        pmml.append("<RegressionModel modelName=\"" + uuid.toString() + "\""
                + " functionName=\"regression\" modelType=\"linearRegression\""
                + " algorithmName=\"linearRegression\"" + " targetFieldName=\""
                + model.getDependentFeatures().iterator().next().getUri().toString() + "\"" + ">\n");
        // RegressionModel::MiningSchema
        pmml.append("<MiningSchema>\n");
        for (Feature feature : model.getIndependentFeatures()) {
            pmml.append("<MiningField name=\"" + feature.getUri().toString() + "\" />\n");

        }
        pmml.append("<MiningField name=\"" + model.getDependentFeatures().iterator().next().getUri().toString()
                + "\" " + "usageType=\"predicted\"/>\n");
        pmml.append("</MiningSchema>\n");
        // RegressionModel::RegressionTable
        pmml.append("<RegressionTable intercept=\"" + coefficients[coefficients.length - 1] + "\">\n");
        for (int k = 0; k < model.getIndependentFeatures().size(); k++) {
            pmml.append("<NumericPredictor name=\"" + model.getIndependentFeatures().get(k).getUri().toString()
                    + "\" " + " exponent=\"1\" " + "coefficient=\"" + coefficients[k] + "\"/>\n");

        }
        pmml.append("</RegressionTable>\n");
        pmml.append("</RegressionModel>\n");
        pmml.append("</PMML>\n\n");
    } catch (UnsupportedEncodingException ex) {
        String message = "Character Encoding :'" + Configuration.getStringProperty("jaqpot.urlEncoding")
                + "' is not supported.";
        logger.debug(message, ex);
        throw new JaqpotException(message, ex);
    } catch (Exception ex) {
        String message = "Unexpected exception was caught while generating"
                + " the PMML representaition of a trained model.";
        logger.error(message, ex);
        throw new JaqpotException(message, ex);
    }
    return pmml.toString();
}

---

From source file:org.opentox.jaqpot3.qsar.util.PMMLProcess.java

License:Open Source License

private static String generateMLR(Model model) throws JaqpotException {
    LinearRegression wekaModel = (LinearRegression) model.getActualModel().getSerializableActualModel();
    byte[] pmmlFile = model.getActualModel().getPmml();

    String uuid = model.getUri().getId();
    String PMMLIntro = Configuration.getStringProperty("pmml.intro");
    StringBuilder pmml = new StringBuilder();
    try {// w ww . ja  v a 2  s  .  c  om
        final double[] coefficients = wekaModel.coefficients();
        pmml.append("<?xml version=\"1.0\" ?>");
        pmml.append(PMMLIntro);
        pmml.append("<Model ID=\"" + uuid + "\" Name=\"MLR Model\">\n");
        pmml.append("<AlgorithmID href=\"" + Configuration.BASE_URI + "algorithm/mlr\"/>\n");

        pmml.append("<AlgorithmParameters />\n");
        pmml.append("<Timestamp>" + java.util.GregorianCalendar.getInstance().getTime() + "</Timestamp>\n");
        pmml.append("</Model>\n");
        pmml.append("<DataDictionary numberOfFields=\"" + model.getIndependentFeatures().size() + "\" >\n");
        for (Feature feature : model.getIndependentFeatures()) {
            pmml.append("<DataField name=\"" + feature.getUri().toString()
                    + "\" optype=\"continuous\" dataType=\"double\" />\n");
        }
        pmml.append("</DataDictionary>\n");

        if (pmmlFile != null) {
            if (pmmlFile.length > 0) {
                String TrDictionaryString = getTransformationDictionaryXML(pmmlFile);
                pmml.append(TrDictionaryString + "\n");
            }
        }

        String dependentFeatures = (model.getDependentFeatures().isEmpty()) ? ""
                : model.getDependentFeatures().iterator().next().getUri().toString();
        // RegressionModel
        pmml.append("<RegressionModel modelName=\"" + uuid.toString() + "\""
                + " functionName=\"regression\" modelType=\"linearRegression\""
                + " algorithmName=\"linearRegression\">\n");
        // RegressionModel::MiningSchema
        pmml.append("<MiningSchema>\n");
        for (Feature feature : model.getIndependentFeatures()) {
            pmml.append("<MiningField name=\"" + feature.getUri().toString() + "\" />\n");

        }

        pmml.append("<MiningField name=\"" + dependentFeatures + "\" " + "usageType=\"predicted\"/>\n");
        pmml.append("</MiningSchema>\n");
        // RegressionModel::RegressionTable
        pmml.append("<RegressionTable intercept=\"" + coefficients[coefficients.length - 1] + "\">\n");

        int k = 0;

        for (k = 0; k < model.getIndependentFeatures().size(); k++) {
            pmml.append("<NumericPredictor name=\"" + model.getIndependentFeatures().get(k).getUri().toString()
                    + "\" " + " exponent=\"1\" " + "coefficient=\"" + coefficients[k] + "\"/>\n");
        }

        if (pmmlFile != null) {
            if (pmmlFile.length > 0) {
                PMML pmmlObject = loadPMMLObject(pmmlFile);
                TransformationDictionary trDir = pmmlObject.getTransformationDictionary();
                if (trDir != null) {
                    int trDirSize = trDir.getDerivedFields().size();
                    int j = 0;
                    while (j < trDirSize) {
                        pmml.append("<NumericPredictor name=\""
                                + trDir.getDerivedFields().get(j).getName().toString() + "\" "
                                + " exponent=\"1\" " + "coefficient=\"" + coefficients[k] + "\"/>\n");
                        ++k;
                        ++j;
                    }
                }
            }
        }
        pmml.append("</RegressionTable>\n");
        pmml = getPMMLStats(pmml, model.getDataset().toString(),
                model.getActualModel().getStatistics().toString());
        pmml.append("</RegressionModel>\n");
        pmml.append("</PMML>\n\n");
    } catch (UnsupportedEncodingException ex) {
        String message = "Character Encoding :'" + Configuration.getStringProperty("jaqpot.urlEncoding")
                + "' is not supported.";
        logger.debug(message, ex);
        throw new JaqpotException(message, ex);
    } catch (Exception ex) {
        String message = "Unexpected exception was caught while generating"
                + " the PMML representaition of a trained model.";
        logger.error(message, ex);
        throw new JaqpotException(message, ex);
    }
    return pmml.toString();
}

---

From source file:org.opentox.qsar.processors.trainers.regression.MLRTrainer.java

License:Open Source License

/**
 * Generates the PMML representation of the model and stores in the hard
 * disk.//w  w  w .  j  av  a2 s . c o m
 * @param coefficients The vector of the coefficients of the MLR model.
 * @param model_id The id of the generated model.
 * TODO: build the XML using some XML editor
 */
// <editor-fold defaultstate="collapsed" desc="PMML generation routine!">
private void generatePMML(final LinearRegression wekaModel, final Instances data) throws YaqpIOException {
    final double[] coefficients = wekaModel.coefficients();
    StringBuilder pmml = new StringBuilder();
    pmml.append("<?xml version=\"1.0\" ?>");
    pmml.append(PMMLIntro);
    pmml.append("<Model ID=\"" + uuid.toString() + "\" Name=\"MLR Model\">\n");
    pmml.append("<AlgorithmID href=\"" + Configuration.BASE_URI + "/algorithm/mlr\"/>\n");
    pmml.append("<DatasetID href=\"" + datasetUri + "\"/>\n");
    pmml.append("<AlgorithmParameters />\n");
    pmml.append("<FeatureDefinitions>\n");
    for (int k = 1; k <= data.numAttributes(); k++) {
        pmml.append("<link href=\"" + data.attribute(k - 1).name() + "\"/>\n");
    }
    pmml.append("<target index=\"" + data.attribute(predictionFeature).index() + "\" name=\""
            + predictionFeature + "\"/>\n");
    pmml.append("</FeatureDefinitions>\n");
    pmml.append("<Timestamp>" + java.util.GregorianCalendar.getInstance().getTime() + "</Timestamp>\n");
    pmml.append("</Model>\n");

    pmml.append("<DataDictionary numberOfFields=\"" + data.numAttributes() + "\" >\n");
    for (int k = 0; k <= data.numAttributes() - 1; k++) {
        pmml.append("<DataField name=\"" + data.attribute(k).name()
                + "\" optype=\"continuous\" dataType=\"double\" />\n");
    }
    pmml.append("</DataDictionary>\n");
    // RegressionModel
    pmml.append("<RegressionModel modelName=\"" + uuid.toString() + "\"" + " functionName=\"regression\""
            + " modelType=\"linearRegression\"" + " algorithmName=\"linearRegression\"" + " targetFieldName=\""
            + data.classAttribute().name() + "\"" + ">\n");
    // RegressionModel::MiningSchema
    pmml.append("<MiningSchema>\n");
    for (int k = 0; k <= data.numAttributes() - 1; k++) {
        if (k != data.classIndex()) {
            pmml.append("<MiningField name=\"" + data.attribute(k).name() + "\" />\n");
        }
    }
    pmml.append("<MiningField name=\"" + data.attribute(data.classIndex()).name() + "\" "
            + "usageType=\"predicted\"/>\n");
    pmml.append("</MiningSchema>\n");
    // RegressionModel::RegressionTable
    pmml.append("<RegressionTable intercept=\"" + coefficients[coefficients.length - 1] + "\">\n");

    for (int k = 0; k <= data.numAttributes() - 1; k++) {

        if (!(predictionFeature.equals(data.attribute(k).name()))) {
            pmml.append("<NumericPredictor name=\"" + data.attribute(k).name() + "\" " + " exponent=\"1\" "
                    + "coefficient=\"" + coefficients[k] + "\"/>\n");
        }
    }
    pmml.append("</RegressionTable>\n");
    pmml.append("</RegressionModel>\n");
    pmml.append("</PMML>\n\n");
    try {
        FileWriter fwriter = new FileWriter(ServerFolders.models_pmml + "/" + uuid.toString());
        BufferedWriter writer = new BufferedWriter(fwriter);
        writer.write(pmml.toString());
        writer.flush();
        writer.close();
    } catch (IOException ex) {
        throw new YaqpIOException(Cause.XQReg3, "Could not write data to PMML file :" + uuid.toString(), ex);
    }
}

---