List of usage examples for weka.classifiers.functions LinearRegression LinearRegression
public LinearRegression()
From source file:org.jaqpot.algorithm.resource.WekaMLR.java
License:Open Source License
@POST @Path("training") public Response training(TrainingRequest request) { try {/*from w w w .java2 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 {/*from w w w. jav a 2s . co 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.trainer.MlrRegression.java
License:Open Source License
@Override public Model train(Instances data) throws JaqpotException { try {/*from www . j av a 2s . c o m*/ getTask().getMeta().addComment( "Dataset successfully retrieved and converted " + "into a weka.core.Instances object"); UpdateTask firstTaskUpdater = new UpdateTask(getTask()); firstTaskUpdater.setUpdateMeta(true); firstTaskUpdater.setUpdateTaskStatus(true);//TODO: Is this necessary? try { firstTaskUpdater.update(); } catch (DbException ex) { throw new JaqpotException(ex); } finally { try { firstTaskUpdater.close(); } catch (DbException ex) { throw new JaqpotException(ex); } } Instances trainingSet = data; getTask().getMeta().addComment("The downloaded dataset is now preprocessed"); firstTaskUpdater = new UpdateTask(getTask()); firstTaskUpdater.setUpdateMeta(true); firstTaskUpdater.setUpdateTaskStatus(true);//TODO: Is this necessary? try { firstTaskUpdater.update(); } catch (DbException ex) { throw new JaqpotException(ex); } finally { try { firstTaskUpdater.close(); } catch (DbException ex) { throw new JaqpotException(ex); } } /* SET CLASS ATTRIBUTE */ Attribute target = trainingSet.attribute(targetUri.toString()); if (target == null) { throw new BadParameterException("The prediction feature you provided was not found in the dataset"); } else { if (!target.isNumeric()) { throw new QSARException("The prediction feature you provided is not numeric."); } } trainingSet.setClass(target); /* Very important: place the target feature at the end! (target = last)*/ int numAttributes = trainingSet.numAttributes(); int classIndex = trainingSet.classIndex(); Instances orderedTrainingSet = null; List<String> properOrder = new ArrayList<String>(numAttributes); for (int j = 0; j < numAttributes; j++) { if (j != classIndex) { properOrder.add(trainingSet.attribute(j).name()); } } properOrder.add(trainingSet.attribute(classIndex).name()); try { orderedTrainingSet = InstancesUtil.sortByFeatureAttrList(properOrder, trainingSet, -1); } catch (JaqpotException ex) { logger.error("Improper dataset - training will stop", ex); throw ex; } orderedTrainingSet.setClass(orderedTrainingSet.attribute(targetUri.toString())); /* START CONSTRUCTION OF MODEL */ Model m = new Model(Configuration.getBaseUri().augment("model", getUuid().toString())); m.setAlgorithm(getAlgorithm()); m.setCreatedBy(getTask().getCreatedBy()); m.setDataset(datasetUri); m.addDependentFeatures(dependentFeature); try { dependentFeature.loadFromRemote(); } catch (ServiceInvocationException ex) { Logger.getLogger(MlrRegression.class.getName()).log(Level.SEVERE, null, ex); } Set<LiteralValue> depFeatTitles = null; if (dependentFeature.getMeta() != null) { depFeatTitles = dependentFeature.getMeta().getTitles(); } String depFeatTitle = dependentFeature.getUri().toString(); if (depFeatTitles != null) { depFeatTitle = depFeatTitles.iterator().next().getValueAsString(); m.getMeta().addTitle("MLR model for " + depFeatTitle) .addDescription("MLR model for the prediction of " + depFeatTitle + " (uri: " + dependentFeature.getUri() + " )."); } else { m.getMeta().addTitle("MLR model for the prediction of the feature with URI " + depFeatTitle) .addComment("No name was found for the feature " + depFeatTitle); } /* * COMPILE THE LIST OF INDEPENDENT FEATURES with the exact order in which * these appear in the Instances object (training set). */ m.setIndependentFeatures(independentFeatures); /* CREATE PREDICTED FEATURE AND POST IT TO REMOTE SERVER */ String predictionFeatureUri = null; Feature predictedFeature = publishFeature(m, dependentFeature.getUnits(), "Predicted " + depFeatTitle + " by MLR model", datasetUri, featureService); m.addPredictedFeatures(predictedFeature); predictionFeatureUri = predictedFeature.getUri().toString(); getTask().getMeta().addComment("Prediction feature " + predictionFeatureUri + " was created."); firstTaskUpdater = new UpdateTask(getTask()); firstTaskUpdater.setUpdateMeta(true); firstTaskUpdater.setUpdateTaskStatus(true);//TODO: Is this necessary? try { firstTaskUpdater.update(); } catch (DbException ex) { throw new JaqpotException(ex); } finally { try { firstTaskUpdater.close(); } catch (DbException ex) { throw new JaqpotException(ex); } } /* ACTUAL TRAINING OF THE MODEL USING WEKA */ LinearRegression linreg = new LinearRegression(); String[] linRegOptions = { "-S", "1", "-C" }; try { linreg.setOptions(linRegOptions); linreg.buildClassifier(orderedTrainingSet); } catch (final Exception ex) {// illegal options or could not build the classifier! String message = "MLR Model could not be trained"; logger.error(message, ex); throw new JaqpotException(message, ex); } try { // evaluate classifier and print some statistics Evaluation eval = new Evaluation(orderedTrainingSet); eval.evaluateModel(linreg, orderedTrainingSet); String stats = eval.toSummaryString("\nResults\n======\n", false); ActualModel am = new ActualModel(linreg); am.setStatistics(stats); m.setActualModel(am); } catch (NotSerializableException ex) { String message = "Model is not serializable"; logger.error(message, ex); throw new JaqpotException(message, ex); } catch (final Exception ex) {// illegal options or could not build the classifier! String message = "MLR Model could not be trained"; logger.error(message, ex); throw new JaqpotException(message, ex); } m.getMeta().addPublisher("OpenTox").addComment("This is a Multiple Linear Regression Model"); //save the instances being predicted to abstract trainer for calculating DoA predictedInstances = orderedTrainingSet; excludeAttributesDoA.add(dependentFeature.getUri().toString()); return m; } catch (QSARException ex) { String message = "QSAR Exception: cannot train MLR model"; logger.error(message, ex); throw new JaqpotException(message, ex); } }
From source file:org.opentox.qsar.processors.trainers.regression.MLRTrainer.java
License:Open Source License
/** * Trains the MLR model given an Instances object with the training data. The prediction * feature (class attributre) is specified in the constructor of the class. * @param data The training data as <code>weka.core.Instances</code> object. * @return The QSARModel corresponding to the trained model. * @throws QSARException In case the model cannot be trained * <p>/* w w w . ja va 2s . c o m*/ * <table> * <thead> * <tr> * <td><b>Code</b></td><td><b>Explanation</b></td> * </tr> * </thead> * <tbody> * <tr> * <td>XQReg1</td><td>Could not train the an model</td> * </tr> * <tr> * <td>XQReg2</td><td>Could not generate PMML representation for the model</td> * </tr> * <tr> * <td>XQReg202</td><td>The prediction feature you provided is not a valid numeric attribute of the dataset</td> * </tr> * </tbody> * </table> * </p> * @throws NullPointerException * In case the provided training data is null. */ public QSARModel train(Instances data) throws QSARException { // GET A UUID AND DEFINE THE TEMPORARY FILE WHERE THE TRAINING DATA // ARE STORED IN ARFF FORMAT PRIOR TO TRAINING. final String rand = java.util.UUID.randomUUID().toString(); final String temporaryFilePath = ServerFolders.temp + "/" + rand + ".arff"; final File tempFile = new File(temporaryFilePath); // SAVE THE DATA IN THE TEMPORARY FILE try { ArffSaver dataSaver = new ArffSaver(); dataSaver.setInstances(data); dataSaver.setDestination(new FileOutputStream(tempFile)); dataSaver.writeBatch(); } catch (final IOException ex) { tempFile.delete(); throw new RuntimeException( "Unexpected condition while trying to save the " + "dataset in a temporary ARFF file", ex); } LinearRegression linreg = new LinearRegression(); String[] linRegOptions = { "-S", "1", "-C" }; try { linreg.setOptions(linRegOptions); linreg.buildClassifier(data); } catch (final Exception ex) {// illegal options or could not build the classifier! String message = "MLR Model could not be trained"; YaqpLogger.LOG.log(new Trace(getClass(), message + " :: " + ex)); throw new QSARException(Cause.XQReg1, message, ex); } try { generatePMML(linreg, data); } catch (final YaqpIOException ex) { String message = "Could not generate PMML representation for MLR model :: " + ex; throw new QSARException(Cause.XQReg2, message, ex); } // PERFORM THE TRAINING String[] generalOptions = { "-c", Integer.toString(data.classIndex() + 1), "-t", temporaryFilePath, /// Save the model in the following directory "-d", ServerFolders.models_weka + "/" + uuid }; try { Evaluation.evaluateModel(linreg, generalOptions); } catch (final Exception ex) { tempFile.delete(); throw new QSARException(Cause.XQReg350, "Unexpected condition while trying to train " + "an SVM model. Possible explanation : {" + ex.getMessage() + "}", ex); } ArrayList<Feature> independentFeatures = new ArrayList<Feature>(); for (int i = 0; i < data.numAttributes(); i++) { Feature f = new Feature(data.attribute(i).name()); if (data.classIndex() != i) { independentFeatures.add(f); } } Feature dependentFeature = new Feature(data.classAttribute().name()); Feature predictedFeature = dependentFeature; QSARModel model = new QSARModel(uuid.toString(), predictedFeature, dependentFeature, independentFeatures, YaqpAlgorithms.MLR, new User(), null, datasetUri, ModelStatus.UNDER_DEVELOPMENT); model.setParams(new HashMap<String, AlgorithmParameter>()); return model; }
From source file:Prediccion.Prediccion.java
License:Open Source License
@Override public void run() { try {/*from w w w . j a v a 2s.c om*/ ArrayList<Instances> pasos = cargarDatos(); System.err.println(pasos.size()); //Instanciamos el predictor ArrayList<WekaForecaster> forecaster = new ArrayList<>(24); for (int a = 0; a < 24; a++) { forecaster.add(new WekaForecaster()); } int a = 0; for (WekaForecaster fore : forecaster) { //Defimimos el atributo que queremos predecir fore.setFieldsToForecast("Total"); //Definimos el mtodo de prediccin a emplear. En este caso, regresin lineal porque //en el artculo es el que mejor ha funcionado fore.setBaseForecaster(new LinearRegression()); //Defimimos el atributo que "marca" el tiempo y su peridiocidad fore.getTSLagMaker().setTimeStampField("Intervalo"); fore.getTSLagMaker().setMinLag(1); fore.getTSLagMaker().setMaxLag(1); fore.getTSLagMaker().setPeriodicity(TSLagMaker.Periodicity.WEEKLY); fore.buildForecaster(pasos.get(a), System.out); // System.err.println(pasos.get(a).toString()); //System.err.printf("Termin"); fore.primeForecaster(pasos.get(a)); List<List<NumericPrediction>> forecast = fore.forecast(1, System.out); System.err.println("==== " + a + " ===="); // output the predictions. Outer list is over the steps; inner list is over // the targets for (int i = 0; i < 1; i++) { List<NumericPrediction> predsAtStep = forecast.get(i); for (int j = 0; j < 1; j++) { NumericPrediction predForTarget = predsAtStep.get(j); System.err.print("" + predForTarget.predicted() + " "); } System.err.println(); } a++; } /* // path to the Australian wine data included with the time series forecasting // package String pathToWineData = weka.core.WekaPackageManager.PACKAGES_DIR.toString() + File.separator + "timeseriesForecasting" + File.separator + "sample-data" + File.separator + "wine.arff"; // load the wine data Instances wine = new Instances(new BufferedReader(new FileReader(pathToWineData))); // new forecaster WekaForecaster forecaster = new WekaForecaster(); // set the targets we want to forecast. This method calls // setFieldsToLag() on the lag maker object for us forecaster.setFieldsToForecast("Fortified,Dry-white"); // default underlying classifier is SMOreg (SVM) - we'll use // gaussian processes for regression instead forecaster.setBaseForecaster(new GaussianProcesses()); forecaster.getTSLagMaker().setTimeStampField("Date"); // date time stamp forecaster.getTSLagMaker().setMinLag(1); forecaster.getTSLagMaker().setMaxLag(12); // monthly data // add a month of the year indicator field forecaster.getTSLagMaker().setAddMonthOfYear(true); // add a quarter of the year indicator field forecaster.getTSLagMaker().setAddQuarterOfYear(true); // build the model forecaster.buildForecaster(wine, System.out); // prime the forecaster with enough recent historical data // to cover up to the maximum lag. In our case, we could just supply // the 12 most recent historical instances, as this covers our maximum // lag period forecaster.primeForecaster(wine); // forecast for 12 units (months) beyond the end of the // training data <<List<List<NumericPrediction>> forecast = forecaster.forecast(12, System.out); // output the predictions. Outer list is over the steps; inner list is over // the targets for (int i = 0; i < 12; i++) { List<NumericPrediction> predsAtStep = forecast.get(i); for (int j = 0; j < 2; j++) { NumericPrediction predForTarget = predsAtStep.get(j); System.out.print("" + predForTarget.predicted() + " "); } System.out.println(); } // we can continue to use the trained forecaster for further forecasting // by priming with the most recent historical data (as it becomes available). // At some stage it becomes prudent to re-build the model using current // historical data. */ } catch (Exception ex) { ex.printStackTrace(); } }
From source file:src.BestFirst.java
License:Open Source License
/** * Searches the attribute subset space by best first search * * @param data the training instances.//from w w w.ja v a 2 s.c o m * @return an array (not necessarily ordered) of selected attribute indexes * @throws Exception if the search can't be completed */ public int[] search(Instances data, TSLagMaker tsLagMaker, List<String> overlayFields) throws Exception { long startTime = System.currentTimeMillis(), stopTime; TSWrapper tsWrapper = new TSWrapper(); tsWrapper.buildEvaluator(data); String m_EvaluationMeasure = "RMSE"; tsWrapper.setM_EvaluationMeasure(m_EvaluationMeasure); System.out.println("Using " + m_EvaluationMeasure + " as a evaluation Measure"); LinearRegression linearRegression = new LinearRegression(); linearRegression.setOptions(weka.core.Utils.splitOptions("-S 1 -R 1E-6")); MLPRegressor mlpRegressor = new MLPRegressor(); mlpRegressor.setOptions(weka.core.Utils.splitOptions("-P 5 -E 5 -N 2")); tsWrapper.setM_BaseClassifier(mlpRegressor); System.out.println("Using best First and MLPReg as classifier."); m_numAttribs = data.numAttributes(); SubsetHandler subsetHandler = new SubsetHandler(); subsetHandler.setM_numAttribs(m_numAttribs); m_totalEvals = 0; int i, j; int best_size = 0; int size = 0; int done; int searchDirection = m_searchDirection; BitSet best_group, temp_group; int stale; double best_merit; double merit; boolean z; boolean added; Double bias = 0.; Hashtable<String, Double> lookForExistingSubsets = new Hashtable<String, Double>(); int insertCount = 0; LinkedList2 prioQueueList = new LinkedList2(m_maxStale); best_merit = -Double.MAX_VALUE; stale = 0; int startSetPercentage = 0; best_group = subsetHandler.getStartSet(startSetPercentage); m_startRange.setUpper(m_numAttribs - 1); if (!(getStartSet().equals(""))) m_starting = m_startRange.getSelection(); // If a starting subset has been supplied, then initialise the bitset if (m_starting != null) { for (i = 0; i < m_starting.length; i++) if ((m_starting[i]) != m_classIndex) best_group.set(m_starting[i]); best_size = m_starting.length; m_totalEvals++; } else { if (m_searchDirection == SELECTION_BACKWARD) { //setStartSet("1-last"); //m_starting = new int[m_numAttribs]; // init initial subset to all attributes for (i = 11, j = 0; i < m_numAttribs; i++) { if (i != m_classIndex) { best_group.set(i); //m_starting[j++] = i; } } best_size = m_numAttribs - 1; m_totalEvals++; } } // evaluate the initial subset best_merit = -tsWrapper.evaluateSubset(best_group, tsLagMaker, overlayFields, false); //printGroup(best_group, m_numAttribs); System.out.println("Merit:" + best_merit); System.out.print("Group: "); subsetHandler.printGroup(best_group); System.out.println("\n"); m_totalEvals++; // add the initial group to the list and the hash table Object[] best = new Object[1]; best[0] = best_group.clone(); prioQueueList.addToList(best, best_merit); String hashedGroup = best_group.toString(); lookForExistingSubsets.put(hashedGroup, new Double(best_merit)); System.out.println("StartsetPercentage:" + startSetPercentage + ", maxStale:" + m_maxStale); while (stale < m_maxStale) { added = false; if (m_searchDirection == SELECTION_BIDIRECTIONAL) { // bi-directional search done = 2; searchDirection = SELECTION_FORWARD; } else { done = 1; } // finished search? if (prioQueueList.size() == 0) { stale = m_maxStale; break; } // copy the attribute set at the head of the list temp_group = (BitSet) (prioQueueList.getLinkAt(0).getData()[0]); temp_group = (BitSet) temp_group.clone(); // remove the head of the list prioQueueList.removeLinkAt(0); // count the number of bits set (attributes) int kk; for (kk = 0, size = 0; kk < m_numAttribs; kk++) if (temp_group.get(kk)) size++; do { for (i = 11; i < m_numAttribs - 2; i++) { //setting it to 11 to skip overlay fields, time stamps etc. if (searchDirection == SELECTION_FORWARD) z = ((i != m_classIndex) && (!temp_group.get(i))); else z = ((i != m_classIndex) && (temp_group.get(i))); if (z) { // set the bit (attribute to add/delete) if (searchDirection == SELECTION_FORWARD) { temp_group.set(i); size++; } else { temp_group.clear(i); size--; } /* * if this subset has been seen before, then it is already in the * list (or has been fully expanded) */ hashedGroup = temp_group.toString(); if (lookForExistingSubsets.containsKey(hashedGroup) == false) { //System.out.println("Before eval:" + temp_group); merit = -tsWrapper.evaluateSubset(temp_group, tsLagMaker, overlayFields, false); System.out.println("Merit: " + merit); System.out.print("Group: "); subsetHandler.printGroup(temp_group); System.out.println("\n"); m_totalEvals++; hashedGroup = temp_group.toString(); lookForExistingSubsets.put(hashedGroup, new Double(merit)); insertCount++; // insert this one in the list } else merit = lookForExistingSubsets.get(hashedGroup).doubleValue(); Object[] add = new Object[1]; add[0] = temp_group.clone(); prioQueueList.addToList(add, merit); if (m_debug) { System.out.print("Group: "); subsetHandler.printGroup(temp_group); System.out.println("Merit: " + merit); } // is this better than the best? if (searchDirection == SELECTION_FORWARD) { z = (merit - best_merit) > 0.01; //they are both negative numbers; actually we are looking for the smallest error } else { if (merit == best_merit) { z = (size < best_size); } else { z = (merit > best_merit); } } if (z) { added = true; stale = 0; System.out.println("Setting best merit to:" + merit); best_merit = merit; // best_size = (size + best_size); best_size = size; best_group = (BitSet) (temp_group.clone()); } // unset this addition(deletion) if (searchDirection == SELECTION_FORWARD) { temp_group.clear(i); size--; } else { temp_group.set(i); size++; } } } if (done == 2) searchDirection = SELECTION_BACKWARD; done--; } while (done > 0); /* if we haven't added a new attribute subset then full expansion of this * node hasen't resulted in anything better */ if (!added) { stale++; System.out.println("Stale:" + stale); } } subsetHandler.printGroup(best_group); System.out.println("Best merit: " + best_merit); System.out.println(m_totalEvals); stopTime = System.currentTimeMillis(); System.out.println("Time taken for wrapper part:" + ((double) stopTime - startTime) / 1000); m_bestMerit = best_merit; subsetHandler.includesMoreThanXPercentOfFeatures(best_group, true, 0); tsWrapper.evaluateSubset(best_group, tsLagMaker, overlayFields, true); return attributeList(best_group); }
From source file:src.SimmulatedAnnealing.java
License:Open Source License
/** * Searches the attribute subset space by best first search * * @param data the training instances.//ww w .j ava 2 s. c o m * @return an array (not necessarily ordered) of selected attribute indexes * @throws Exception if the search can't be completed */ public int[] search(Instances data, TSLagMaker tsLagMaker, List<String> overlayFields) throws Exception { long startTime = System.currentTimeMillis(), stopTime; m_totalEvals = 0; int m_totalEvals = 0; TSWrapper tsWrapper = new TSWrapper(); tsWrapper.buildEvaluator(data); String m_EvaluationMeasure = "RMSE"; tsWrapper.setM_EvaluationMeasure(m_EvaluationMeasure); System.out.println("Using " + m_EvaluationMeasure + " as a evaluation Measure"); LinearRegression linearRegression = new LinearRegression(); linearRegression.setOptions(weka.core.Utils.splitOptions("-S 1 -R 1E-6")); MLPRegressor mlpRegressor = new MLPRegressor(); mlpRegressor.setOptions(weka.core.Utils.splitOptions("-P 4 -E 4 -N 2")); tsWrapper.setM_BaseClassifier(mlpRegressor); System.out.println("Using SA and MLPRegressor as classifier."); m_numAttribs = data.numAttributes(); SubsetHandler subsetHandler = new SubsetHandler(); subsetHandler.setM_numAttribs(m_numAttribs); BitSet best_group; best_group = subsetHandler.getStartSet(0); double temperature = 0.4, initialTemp = temperature, dropRate = 0.00012, limit = 0.0000001; double best_merit; int changedAltoughWorseCounter = 0; Hashtable<String, Double> lookForExistingSubsets = new Hashtable<String, Double>(); // evaluate the initial subset subsetHandler.printGroup(best_group); best_merit = -tsWrapper.evaluateSubset(best_group, tsLagMaker, overlayFields, false); m_totalEvals++; String subset_string = best_group.toString(); lookForExistingSubsets.put(subset_string, best_merit); System.out.println("Initial group w/ numAttribs: " + m_numAttribs + " temp: " + temperature + " drop rate:" + dropRate + " limit:" + limit); System.out.println("Merit: " + best_merit); TheVeryBest theVeryBest = new TheVeryBest((BitSet) best_group.clone(), best_merit); ArrayList<Boolean> changedAlthoughWorse = new ArrayList<Boolean>(); while (temperature > limit) { changedAltoughWorseCounter = 0; BitSet s_new = subsetHandler.changeBits((BitSet) best_group.clone(), 1); subset_string = s_new.toString(); if (!lookForExistingSubsets.containsKey(subset_string)) { double s_new_merit = -tsWrapper.evaluateSubset(s_new, tsLagMaker, overlayFields, false); m_totalEvals++; System.out.println("New merit: " + s_new_merit); lookForExistingSubsets.put(subset_string, s_new_merit); if (decisionFunction(s_new_merit - best_merit, temperature, best_merit, initialTemp)) { if (best_merit - s_new_merit > 0) //it means this is a worse set than the best set, and we still change the best set to it. changedAlthoughWorse.add(true); best_group = (BitSet) s_new.clone(); best_merit = s_new_merit; } else changedAlthoughWorse.add(false); for (int j = 0; j < changedAlthoughWorse.size(); j++) if (changedAlthoughWorse.get(j)) changedAltoughWorseCounter++; System.out.println("Percentage of worse sets accepted:" + (float) changedAltoughWorseCounter * 100 / changedAlthoughWorse.size() + " Arraylist size:" + changedAlthoughWorse.size() + " changedAlthoughworse counter:" + changedAltoughWorseCounter); if (best_merit > theVeryBest.getMerit()) //we have negative values for the scores, so bigger is better theVeryBest.setNewSet((BitSet) best_group.clone(), best_merit); temperature = temperature / (float) (1 + dropRate * (m_totalEvals - 1)); } } System.out.println("Best merit: " + theVeryBest.getMerit()); System.out.println(m_totalEvals); stopTime = System.currentTimeMillis(); System.out.println("Time taken for wrapper part:" + ((double) stopTime - startTime) / 1000); subsetHandler.printGroup(theVeryBest.getSubset()); subsetHandler.includesMoreThanXPercentOfFeatures(theVeryBest.getSubset(), true, 0); tsWrapper.evaluateSubset(theVeryBest.getSubset(), tsLagMaker, overlayFields, true); return attributeList(theVeryBest.getSubset()); }
From source file:textmining.TextMining.java
private static String Regression_on_Polarity(Instances instances) throws Exception { Classifier regression = (Classifier) new LinearRegression(); String[] options = weka.core.Utils.splitOptions("-S 2 -R 1.0E-8"); return setOptions(regression, instances, options); }
From source file:wekimini.learning.LinearRegressionModelBuilder.java
public LinearRegressionModelBuilder() { classifier = new LinearRegression(); featureSelectionType = FeatureSelectionType.NONE; ((LinearRegression) classifier).setAttributeSelectionMethod( new SelectedTag(LinearRegression.SELECTION_NONE, LinearRegression.TAGS_SELECTION)); ((LinearRegression) classifier).setEliminateColinearAttributes(removeColinear); }