List of usage examples for weka.classifiers AbstractClassifier forName
public static Classifier forName(String classifierName, String[] options) throws Exception
From source file:reactivetechnologies.sentigrade.WekaConfiguration.java
License:Open Source License
@Bean(name = CACHED_INCR_CLASSIFIER_BEAN) @Scope(scopeName = ConfigurableBeanFactory.SCOPE_PROTOTYPE) public AbstractClassificationModelEngine getClassifier(String domain) throws Exception { Classifier c = null;/*ww w . j av a2s .c om*/ try { c = AbstractClassifier.forName(wekaClassifier, StringUtils.hasText(options) ? Utils.splitOptions(options) : null); } catch (Exception e) { c = (Classifier) ApplicationContextWrapper.newInstance(wekaClassifier); if (StringUtils.hasText(options)) { Method m = ReflectionUtils.findMethod(c.getClass(), "setOptions"); if (m != null) ReflectionUtils.invokeMethod(m, c, (Object[]) Utils.splitOptions(options)); } } CachedClassificationModelEngine cached = new CachedClassificationModelEngine(c); cached.setDomain(domain); return cached; }
From source file:se.de.hu_berlin.informatik.faultlocalizer.machinelearn.WekaFaultLocalizer.java
License:Open Source License
/** * Builds and trains a classifier.// w w w . ja va 2s . c o m * * @param name * FQCN of the classifier * @param options * options to pass to the classifier * @param trainingSet * training set to build the classifier with * @return trained classifier */ public Classifier buildClassifier(final String name, final String[] options, final Instances trainingSet) { try { final Classifier classifier = AbstractClassifier.forName(this.classifierName, options); classifier.buildClassifier(trainingSet); return classifier; } catch (final Exception e1) { // NOCS: Weka throws only raw exceptions Log.err(this, "Unable to create classifier " + this.classifierName); throw new RuntimeException(e1); } }
From source file:tclass.ExpSeg.java
License:Open Source License
public static void main(String[] args) throws Exception { Debug.setDebugLevel(Debug.PROGRESS); ExpSeg thisExp = new ExpSeg(); thisExp.parseArgs(args);/* ww w .j a va 2 s . co m*/ DomDesc domDesc = new DomDesc(thisExp.domDescFile); ClassStreamVecI trainStreamData = new ClassStreamVec(thisExp.trainDataFile, domDesc); ClassStreamVecI testStreamData = new ClassStreamVec(thisExp.testDataFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Data read in"); Settings settings = new Settings(thisExp.settingsFile, domDesc); EventExtractor evExtractor = settings.getEventExtractor(); // Global data is likely to be included in every model; so we // might as well calculated now GlobalCalc globalCalc = settings.getGlobalCalc(); ClassStreamAttValVecI trainGlobalData = globalCalc.applyGlobals(trainStreamData); ClassStreamAttValVecI testGlobalData = globalCalc.applyGlobals(testStreamData); // And we might as well extract the events. Debug.dp(Debug.PROGRESS, "PROGRESS: Globals calculated."); Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size() + " Test: " + testGlobalData.size()); // System.out.println(trainEventData.toString()); // Now we want the clustering algorithms only to cluster // instances of each class. Make an array of clusterers, // one per class. int numTestStreams = testGlobalData.size(); int numClasses = domDesc.getClassDescVec().size(); TimeDivision td = new TimeDivision(domDesc, thisExp.numDivs); ClassStreamAttValVecI trainDivData = td.timeDivide(trainStreamData); ClassStreamAttValVecI testDivData = td.timeDivide(testStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Segmentation performed"); Combiner c = new Combiner(); ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData, trainDivData); ClassStreamAttValVecI testAtts = c.combine(testGlobalData, testDivData); trainStreamData = null; testStreamData = null; System.gc(); // So now we have the raw data in the correct form for each // attributor. // And now, we can construct a learner for each case. // Well, for now, I'm going to do something completely crazy. // Let's run each classifier nonetheless over the whole data // ... and see what the hell happens. Maybe some voting scheme // is possible!! This is a strange form of ensemble // classifier. // Each naive bayes algorithm only gets one Debug.setDebugLevel(Debug.PROGRESS); int[] selectedIndices = null; String[] classifierSpec = Utils.splitOptions(thisExp.learnerStuff); if (classifierSpec.length == 0) { throw new Exception("Invalid classifier specification string"); } String classifierName = classifierSpec[0]; classifierSpec[0] = ""; Classifier learner = AbstractClassifier.forName(classifierName, classifierSpec); Debug.dp(Debug.PROGRESS, "PROGRESS: Beginning format conversion for class "); Instances data = WekaBridge.makeInstances(trainAtts, "Train "); Debug.dp(Debug.PROGRESS, "PROGRESS: Conversion complete. Starting learning"); if (thisExp.featureSel) { Debug.dp(Debug.PROGRESS, "PROGRESS: Doing feature selection"); BestFirst bfs = new BestFirst(); CfsSubsetEval cfs = new CfsSubsetEval(); cfs.buildEvaluator(data); selectedIndices = bfs.search(cfs, data); // Now extract the features. System.err.print("Selected features: "); String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += ("last"); System.err.println(featureString); // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } learner.buildClassifier(data); Debug.dp(Debug.PROGRESS, "Learnt classifier: \n" + learner.toString()); WekaClassifier wekaClassifier; wekaClassifier = new WekaClassifier(learner); Debug.dp(Debug.PROGRESS, "PROGRESS: Learning complete. "); System.err.println(">>> Testing stage <<<"); // First, print the results of using the straight testers. ClassificationVecI classns; classns = (ClassificationVecI) testAtts.getClassVec().clone(); StreamAttValVecI savvi = testAtts.getStreamAttValVec(); data = WekaBridge.makeInstances(testAtts, "Test "); if (thisExp.featureSel) { String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += "last"; // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } for (int j = 0; j < numTestStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } System.err.println(">>> Learner <<<"); int numCorrect = 0; for (int j = 0; j < numTestStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Test accuracy for classifier: " + numCorrect + " of " + numTestStreams + " (" + numCorrect * 100.0 / numTestStreams + "%)"); }
From source file:tclass.ExpSingle.java
License:Open Source License
public static void main(String[] args) throws Exception { Debug.setDebugLevel(Debug.PROGRESS); ExpSingle thisExp = new ExpSingle(); thisExp.parseArgs(args);/*from ww w .ja v a 2 s. c o m*/ mem("PARSE"); DomDesc domDesc = new DomDesc(thisExp.domDescFile); ClassStreamVecI trainStreamData = new ClassStreamVec(thisExp.trainDataFile, domDesc); ClassStreamVecI testStreamData = new ClassStreamVec(thisExp.testDataFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Data read in"); mem("DATAIN"); Settings settings = new Settings(thisExp.settingsFile, domDesc); EventExtractor evExtractor = settings.getEventExtractor(); // Global data is likely to be included in every model; so we // might as well calculated now GlobalCalc globalCalc = settings.getGlobalCalc(); ClassStreamAttValVecI trainGlobalData = globalCalc.applyGlobals(trainStreamData); ClassStreamAttValVecI testGlobalData = globalCalc.applyGlobals(testStreamData); // And we might as well extract the events. Debug.dp(Debug.PROGRESS, "PROGRESS: Globals calculated."); mem("GLOBAL"); Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size() + " Test: " + testGlobalData.size()); ClassStreamEventsVecI trainEventData = evExtractor.extractEvents(trainStreamData); ClassStreamEventsVecI testEventData = evExtractor.extractEvents(testStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Events extracted"); mem("EVENTEXTRACT"); // System.out.println(trainEventData.toString()); // Now we want the clustering algorithms only to cluster // instances of each class. Make an array of clusterers, // one per class. int numTestStreams = testEventData.size(); int numClasses = domDesc.getClassDescVec().size(); EventDescVecI eventDescVec = evExtractor.getDescription(); EventClusterer eventClusterer = settings.getEventClusterer(); Debug.dp(Debug.PROGRESS, "PROGRESS: Data rearranged."); mem("REARRANGE"); //And now load it up. StreamEventsVecI trainEventSEV = trainEventData.getStreamEventsVec(); ClassificationVecI trainEventCV = trainEventData.getClassVec(); int numTrainStreams = trainEventCV.size(); ClusterVecI clusters = eventClusterer.clusterEvents(trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete"); Debug.dp(Debug.PROGRESS, "Clusters are:"); Debug.dp(Debug.PROGRESS, "\n" + eventClusterer.getMapping()); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete. "); mem("CLUSTER"); // But wait! There's more! There is always more. // The first thing was only useful for clustering. // Now attribution. We want to attribute all the data. So we are going // to have one dataset for each learner. // First set up the attributors. Attributor attribs = new Attributor(domDesc, clusters, eventClusterer.getDescription()); Debug.dp(Debug.PROGRESS, "PROGRESS: AttributorMkr complete."); mem("MAKEATTRIBUTOR"); ClassStreamAttValVecI trainEventAtts = attribs.attribute(trainStreamData, trainEventData); ClassStreamAttValVecI testEventAtts = attribs.attribute(testStreamData, testEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Attribution complete."); mem("ATTRIBUTION"); // Combine all data sources. For now, globals go in every // one. Combiner c = new Combiner(); ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData, trainEventAtts); ClassStreamAttValVecI testAtts = c.combine(testGlobalData, testEventAtts); mem("COMBINATION"); trainStreamData = null; testStreamData = null; trainEventSEV = null; trainEventCV = null; if (!thisExp.makeDesc) { clusters = null; eventClusterer = null; } attribs = null; System.gc(); mem("GARBAGECOLLECT"); // So now we have the raw data in the correct form for each // attributor. // And now, we can construct a learner for each case. // Well, for now, I'm going to do something completely crazy. // Let's run each classifier nonetheless over the whole data // ... and see what the hell happens. Maybe some voting scheme // is possible!! This is a strange form of ensemble // classifier. // Each naive bayes algorithm only gets one Debug.setDebugLevel(Debug.PROGRESS); int[] selectedIndices = null; String[] classifierSpec = Utils.splitOptions(thisExp.learnerStuff); if (classifierSpec.length == 0) { throw new Exception("Invalid classifier specification string"); } String classifierName = classifierSpec[0]; classifierSpec[0] = ""; Classifier learner = AbstractClassifier.forName(classifierName, classifierSpec); Debug.dp(Debug.PROGRESS, "PROGRESS: Beginning format conversion for class "); Instances data = WekaBridge.makeInstances(trainAtts, "Train "); Debug.dp(Debug.PROGRESS, "PROGRESS: Conversion complete. Starting learning"); mem("ATTCONVERSION"); if (thisExp.featureSel) { Debug.dp(Debug.PROGRESS, "PROGRESS: Doing feature selection"); BestFirst bfs = new BestFirst(); CfsSubsetEval cfs = new CfsSubsetEval(); cfs.buildEvaluator(data); selectedIndices = bfs.search(cfs, data); // Now extract the features. System.err.print("Selected features: "); String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += ("last"); System.err.println(featureString); // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } learner.buildClassifier(data); mem("POSTLEARNER"); Debug.dp(Debug.PROGRESS, "Learnt classifier: \n" + learner.toString()); WekaClassifier wekaClassifier; wekaClassifier = new WekaClassifier(learner); if (thisExp.makeDesc) { // Section for making description more readable. Assumes that // learner.toString() returns a string with things that look like // feature names. String concept = learner.toString(); StringTokenizer st = new StringTokenizer(concept, " \t\r\n", true); int evId = 1; String evIndex = ""; while (st.hasMoreTokens()) { boolean appendColon = false; String curTok = st.nextToken(); GClust clust = (GClust) ((ClusterVec) clusters).elCalled(curTok); if (clust != null) { // Skip the spaces st.nextToken(); // Get a < or > String cmp = st.nextToken(); String qual = ""; if (cmp.equals("<=")) { qual = " HAS NO "; } else { qual = " HAS "; } // skip spaces st.nextToken(); // Get the number. String conf = st.nextToken(); if (conf.endsWith(":")) { conf = conf.substring(0, conf.length() - 1); appendColon = true; } float minconf = Float.valueOf(conf).floatValue(); EventI[] res = clust.getBounds(minconf); String name = clust.getName(); int dashPos = name.indexOf('-'); int undPos = name.indexOf('_'); String chan = name.substring(0, dashPos); String evType = name.substring(dashPos + 1, undPos); EventDescI edi = clust.eventDesc(); if (qual == " HAS NO " && thisExp.learnerStuff.startsWith(weka.classifiers.trees.J48.class.getName())) { System.out.print("OTHERWISE"); } else { System.out.print("IF " + chan + qual + res[2] + " (*" + evId + ")"); int numParams = edi.numParams(); evIndex += "*" + evId + ": " + evType + "\n"; for (int i = 0; i < numParams; i++) { evIndex += " " + edi.paramName(i) + "=" + res[2].valOf(i) + " r=[" + res[0].valOf(i) + "," + res[1].valOf(i) + "]\n"; } evId++; } evIndex += "\n"; if (appendColon) { System.out.print(" THEN"); } } else { System.out.print(curTok); } } System.out.println("\nEvent index"); System.out.println("-----------"); System.out.print(evIndex); mem("POSTDESC"); // Now this is going to be messy as fuck. Really. What do we needs? Well, // we need to read in the data; look up some info, that we // assume came from a GainClusterer ... // Sanity check. // GClust clust = (GClust) ((ClusterVec) clusters).elCalled("alpha-inc_0"); // System.out.println("INSANE!: " + clust.getDescription()); // EventI[] res = clust.getBounds(1); // System.out.println("For clust settings: min event = " + res[0].toString() + " and max event = " + res[1].toString()); } Debug.dp(Debug.PROGRESS, "PROGRESS: Learning complete. "); int numCorrect = 0; ClassificationVecI classns; if (thisExp.trainResults) { System.err.println(">>> Training performance <<<"); classns = (ClassificationVecI) trainAtts.getClassVec().clone(); for (int j = 0; j < numTrainStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } for (int j = 0; j < numTrainStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Training results for classifier: " + numCorrect + " of " + numTrainStreams + " (" + numCorrect * 100.0 / numTrainStreams + "%)"); } mem("POSTTRAIN"); System.err.println(">>> Testing stage <<<"); // First, print the results of using the straight testers. classns = (ClassificationVecI) testAtts.getClassVec().clone(); StreamAttValVecI savvi = testAtts.getStreamAttValVec(); data = WekaBridge.makeInstances(testAtts, "Test "); if (thisExp.featureSel) { String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += "last"; // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } for (int j = 0; j < numTestStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } System.err.println(">>> Learner <<<"); numCorrect = 0; for (int j = 0; j < numTestStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Test accuracy for classifier: " + numCorrect + " of " + numTestStreams + " (" + numCorrect * 100.0 / numTestStreams + "%)"); mem("POSTTEST"); }
From source file:tclass.ExpSingleLM.java
License:Open Source License
public static void main(String[] args) throws Exception { Debug.setDebugLevel(Debug.PROGRESS); ExpSingleLM thisExp = new ExpSingleLM(); thisExp.parseArgs(args);/*from w ww . j a v a2 s .com*/ mem("PARSE"); DomDesc domDesc = new DomDesc(thisExp.domDescFile); ClassStreamVecI trainStreamData = new ClassStreamVec(thisExp.trainDataFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Training data read in"); mem("TRAINDATAIN"); Settings settings = new Settings(thisExp.settingsFile, domDesc); EventExtractor evExtractor = settings.getEventExtractor(); // Global data is likely to be included in every model; so we // might as well calculated now GlobalCalc globalCalc = settings.getGlobalCalc(); ClassStreamAttValVecI trainGlobalData = globalCalc.applyGlobals(trainStreamData); // And we might as well extract the events. Debug.dp(Debug.PROGRESS, "PROGRESS: Training data globals calculated."); mem("TRAINGLOBAL"); Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size()); ClassStreamEventsVecI trainEventData = evExtractor.extractEvents(trainStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Training events extracted"); mem("EVENTEXTRACT"); // System.out.println(trainEventData.toString()); // Now we want the clustering algorithms only to cluster // instances of each class. Make an array of clusterers, // one per class. int numClasses = domDesc.getClassDescVec().size(); EventDescVecI eventDescVec = evExtractor.getDescription(); EventClusterer eventClusterer = settings.getEventClusterer(); Debug.dp(Debug.PROGRESS, "PROGRESS: Data rearranged."); mem("REARRANGE"); //And now load it up. StreamEventsVecI trainEventSEV = trainEventData.getStreamEventsVec(); ClassificationVecI trainEventCV = trainEventData.getClassVec(); int numTrainStreams = trainEventCV.size(); ClusterVecI clusters = eventClusterer.clusterEvents(trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete"); Debug.dp(Debug.PROGRESS, "Clusters are:"); Debug.dp(Debug.PROGRESS, "\n" + eventClusterer.getMapping()); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete. "); mem("CLUSTER"); // But wait! There's more! There is always more. // The first thing was only useful for clustering. // Now attribution. We want to attribute all the data. So we are going // to have one dataset for each learner. // First set up the attributors. Attributor attribs = new Attributor(domDesc, clusters, eventClusterer.getDescription()); Debug.dp(Debug.PROGRESS, "PROGRESS: AttributorMkr complete."); mem("MAKEATTRIBUTOR"); ClassStreamAttValVecI trainEventAtts = attribs.attribute(trainStreamData, trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Training data Attribution complete."); mem("TRAINATTRIBUTION"); // Combine all data sources. For now, globals go in every // one. Combiner c = new Combiner(); ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData, trainEventAtts); mem("TRAINCOMBINATION"); trainStreamData = null; trainEventSEV = null; trainEventCV = null; System.gc(); mem("TRAINGC"); // So now we have the raw data in the correct form for each // attributor. // And now, we can construct a learner for each case. // Well, for now, I'm going to do something completely crazy. // Let's run each classifier nonetheless over the whole data // ... and see what the hell happens. Maybe some voting scheme // is possible!! This is a strange form of ensemble // classifier. // Each naive bayes algorithm only gets one Debug.setDebugLevel(Debug.PROGRESS); int[] selectedIndices = null; String[] classifierSpec = Utils.splitOptions(thisExp.learnerStuff); if (classifierSpec.length == 0) { throw new Exception("Invalid classifier specification string"); } String classifierName = classifierSpec[0]; classifierSpec[0] = ""; Classifier learner = AbstractClassifier.forName(classifierName, classifierSpec); Debug.dp(Debug.PROGRESS, "PROGRESS: Beginning format conversion for class "); Instances data = WekaBridge.makeInstances(trainAtts, "Train "); Debug.dp(Debug.PROGRESS, "PROGRESS: Conversion complete. Starting learning"); mem("ATTCONVERSION"); if (thisExp.featureSel) { Debug.dp(Debug.PROGRESS, "PROGRESS: Doing feature selection"); BestFirst bfs = new BestFirst(); CfsSubsetEval cfs = new CfsSubsetEval(); cfs.buildEvaluator(data); selectedIndices = bfs.search(cfs, data); // Now extract the features. System.err.print("Selected features: "); String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += ("last"); System.err.println(featureString); // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } learner.buildClassifier(data); mem("POSTLEARNER"); Debug.dp(Debug.PROGRESS, "Learnt classifier: \n" + learner.toString()); WekaClassifier wekaClassifier; wekaClassifier = new WekaClassifier(learner); if (thisExp.makeDesc) { // Section for making description more readable. Assumes that // learner.toString() returns a string with things that look like // feature names. String concept = learner.toString(); StringTokenizer st = new StringTokenizer(concept, " \t\r\n", true); int evId = 1; String evIndex = ""; while (st.hasMoreTokens()) { boolean appendColon = false; String curTok = st.nextToken(); GClust clust = (GClust) ((ClusterVec) clusters).elCalled(curTok); if (clust != null) { // Skip the spaces st.nextToken(); // Get a < or > String cmp = st.nextToken(); String qual = ""; if (cmp.equals("<=")) { qual = " HAS NO "; } else { qual = " HAS "; } // skip spaces st.nextToken(); // Get the number. String conf = st.nextToken(); if (conf.endsWith(":")) { conf = conf.substring(0, conf.length() - 1); appendColon = true; } float minconf = Float.valueOf(conf).floatValue(); EventI[] res = clust.getBounds(minconf); String name = clust.getName(); int dashPos = name.indexOf('-'); int undPos = name.indexOf('_'); String chan = name.substring(0, dashPos); String evType = name.substring(dashPos + 1, undPos); EventDescI edi = clust.eventDesc(); if (qual == " HAS NO " && thisExp.learnerStuff.startsWith(weka.classifiers.trees.J48.class.getName())) { System.out.print("OTHERWISE"); } else { System.out.print("IF " + chan + qual + res[2] + " (*" + evId + ")"); int numParams = edi.numParams(); evIndex += "*" + evId + ": " + evType + "\n"; for (int i = 0; i < numParams; i++) { evIndex += " " + edi.paramName(i) + "=" + res[2].valOf(i) + " r=[" + res[0].valOf(i) + "," + res[1].valOf(i) + "]\n"; } evId++; } evIndex += "\n"; if (appendColon) { System.out.print(" THEN"); } } else { System.out.print(curTok); } } System.out.println("\nEvent index"); System.out.println("-----------"); System.out.print(evIndex); mem("POSTDESC"); // Now this is going to be messy as fuck. Really. What do we needs? Well, // we need to read in the data; look up some info, that we // assume came from a GainClusterer ... // Sanity check. // GClust clust = (GClust) ((ClusterVec) clusters).elCalled("alpha-inc_0"); // System.out.println("INSANE!: " + clust.getDescription()); // EventI[] res = clust.getBounds(1); // System.out.println("For clust settings: min event = " + res[0].toString() + " and max event = " + res[1].toString()); } Debug.dp(Debug.PROGRESS, "PROGRESS: Learning complete. "); int numCorrect = 0; ClassificationVecI classns; if (thisExp.trainResults) { System.err.println(">>> Training performance <<<"); classns = (ClassificationVecI) trainAtts.getClassVec().clone(); for (int j = 0; j < numTrainStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } for (int j = 0; j < numTrainStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Training results for classifier: " + numCorrect + " of " + numTrainStreams + " (" + numCorrect * 100.0 / numTrainStreams + "%)"); } mem("POSTTRAIN"); System.err.println(">>> Testing stage <<<"); // Stick testing stuff here. mem("TESTBEGIN"); ClassStreamVecI testStreamData = new ClassStreamVec(thisExp.testDataFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Test data read in"); mem("TESTREAD"); ClassStreamAttValVecI testGlobalData = globalCalc.applyGlobals(testStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Test data globals calculated"); mem("TESTGLOBALS"); Debug.dp(Debug.PROGRESS, "Test data: " + testGlobalData.size()); ClassStreamEventsVecI testEventData = evExtractor.extractEvents(testStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Test events extracted"); mem("TESTEVENTS"); int numTestStreams = testEventData.size(); ClassStreamAttValVecI testEventAtts = attribs.attribute(testStreamData, testEventData); mem("TESTATTRIBUTES"); ClassStreamAttValVecI testAtts = c.combine(testGlobalData, testEventAtts); mem("TESTCOMBINE"); testStreamData = null; System.gc(); // Do garbage collection. mem("TESTGC"); if (!thisExp.makeDesc) { clusters = null; eventClusterer = null; } attribs = null; // First, print the results of using the straight testers. classns = (ClassificationVecI) testAtts.getClassVec().clone(); StreamAttValVecI savvi = testAtts.getStreamAttValVec(); data = WekaBridge.makeInstances(testAtts, "Test "); if (thisExp.featureSel) { String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += "last"; // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } for (int j = 0; j < numTestStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } System.err.println(">>> Learner <<<"); numCorrect = 0; for (int j = 0; j < numTestStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Test accuracy for classifier: " + numCorrect + " of " + numTestStreams + " (" + numCorrect * 100.0 / numTestStreams + "%)"); mem("POSTTEST"); }
From source file:tclass.TClass.java
License:Open Source License
public static void main(String[] args) throws Exception { Debug.setDebugLevel(Debug.PROGRESS); TClass thisExp = new TClass(); thisExp.parseArgs(args);/*from ww w . j av a 2s . c o m*/ DomDesc domDesc = new DomDesc(thisExp.domDescFile); ClassStreamVecI trainStreamData = new ClassStreamVec(thisExp.trainDataFile, domDesc); ClassStreamVecI testStreamData = new ClassStreamVec(thisExp.testDataFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Data read in"); Settings settings = new Settings(thisExp.settingsFile, domDesc); EventExtractor evExtractor = settings.getEventExtractor(); // Global data is likely to be included in every model; so we // might as well calculated now GlobalCalc globalCalc = settings.getGlobalCalc(); ClassStreamAttValVecI trainGlobalData = globalCalc.applyGlobals(trainStreamData); ClassStreamAttValVecI testGlobalData = globalCalc.applyGlobals(testStreamData); // And we might as well extract the events. Debug.dp(Debug.PROGRESS, "PROGRESS: Globals calculated."); Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size() + " Test: " + testGlobalData.size()); ClassStreamEventsVecI trainEventData = evExtractor.extractEvents(trainStreamData); ClassStreamEventsVecI testEventData = evExtractor.extractEvents(testStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Events extracted"); // System.out.println(trainEventData.toString()); // Now we want the clustering algorithms only to cluster // instances of each class. Make an array of clusterers, // one per class. int numTestStreams = testEventData.size(); int numClasses = domDesc.getClassDescVec().size(); EventDescVecI eventDescVec = evExtractor.getDescription(); EventClusterer eventClusterer = settings.getEventClusterer(); Debug.dp(Debug.PROGRESS, "PROGRESS: Data rearranged."); //And now load it up. StreamEventsVecI trainEventSEV = trainEventData.getStreamEventsVec(); ClassificationVecI trainEventCV = trainEventData.getClassVec(); int numTrainStreams = trainEventCV.size(); ClusterVecI clusters = eventClusterer.clusterEvents(trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete"); Debug.dp(Debug.PROGRESS, "Clusters are:"); Debug.dp(Debug.PROGRESS, "\n" + eventClusterer.getMapping()); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete. "); // But wait! There's more! There is always more. // The first thing was only useful for clustering. // Now attribution. We want to attribute all the data. So we are going // to have one dataset for each learner. // First set up the attributors. Attributor attribs = new Attributor(domDesc, clusters, eventClusterer.getDescription()); Debug.dp(Debug.PROGRESS, "PROGRESS: AttributorMkr complete."); ClassStreamAttValVecI trainEventAtts = attribs.attribute(trainStreamData, trainEventData); ClassStreamAttValVecI testEventAtts = attribs.attribute(testStreamData, testEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Attribution complete."); // Combine all data sources. For now, globals go in every // one. Combiner c = new Combiner(); ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData, trainEventAtts); ClassStreamAttValVecI testAtts = c.combine(testGlobalData, testEventAtts); trainStreamData = null; testStreamData = null; trainEventSEV = null; trainEventCV = null; if (!thisExp.makeDesc) { clusters = null; eventClusterer = null; } attribs = null; System.gc(); // So now we have the raw data in the correct form for each // attributor. // And now, we can construct a learner for each case. // Well, for now, I'm going to do something completely crazy. // Let's run each classifier nonetheless over the whole data // ... and see what the hell happens. Maybe some voting scheme // is possible!! This is a strange form of ensemble // classifier. // Each naive bayes algorithm only gets one Debug.setDebugLevel(Debug.PROGRESS); int[] selectedIndices = null; String[] classifierSpec = Utils.splitOptions(thisExp.learnerStuff); if (classifierSpec.length == 0) { throw new Exception("Invalid classifier specification string"); } String classifierName = classifierSpec[0]; classifierSpec[0] = ""; Classifier learner = AbstractClassifier.forName(classifierName, classifierSpec); Debug.dp(Debug.PROGRESS, "PROGRESS: Beginning format conversion for class "); Instances data = WekaBridge.makeInstances(trainAtts, "Train "); Debug.dp(Debug.PROGRESS, "PROGRESS: Conversion complete. Starting learning"); if (thisExp.featureSel) { Debug.dp(Debug.PROGRESS, "PROGRESS: Doing feature selection"); BestFirst bfs = new BestFirst(); CfsSubsetEval cfs = new CfsSubsetEval(); cfs.buildEvaluator(data); selectedIndices = bfs.search(cfs, data); // Now extract the features. System.err.print("Selected features: "); String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += ("last"); System.err.println(featureString); // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } learner.buildClassifier(data); Debug.dp(Debug.PROGRESS, "Learnt classifier: \n" + learner.toString()); WekaClassifier wekaClassifier; wekaClassifier = new WekaClassifier(learner); if (thisExp.makeDesc) { // Section for making description more readable. Assumes that // learner.toString() returns a string with things that look like // feature names. String concept = learner.toString(); StringTokenizer st = new StringTokenizer(concept, " \t\r\n", true); while (st.hasMoreTokens()) { boolean appendColon = false; String curTok = st.nextToken(); GClust clust = (GClust) ((ClusterVec) clusters).elCalled(curTok); if (clust != null) { // Skip the spaces st.nextToken(); // Get a < or > String cmp = st.nextToken(); String qual = ""; if (cmp.equals("<=")) { qual = " HAS NO "; } else { qual = " HAS "; } // skip spaces st.nextToken(); // Get the number. String conf = st.nextToken(); if (conf.endsWith(":")) { conf = conf.substring(0, conf.length() - 1); appendColon = true; } float minconf = Float.valueOf(conf).floatValue(); EventI[] res = clust.getBounds(minconf); String name = clust.getName(); int dashPos = name.indexOf('-'); int undPos = name.indexOf('_'); String chan = name.substring(0, dashPos); String evType = name.substring(dashPos + 1, undPos); EventDescI edi = clust.eventDesc(); System.out.print("Channel " + chan + qual + evType + " "); int numParams = edi.numParams(); for (int i = 0; i < numParams; i++) { System.out .print(edi.paramName(i) + " in [" + res[0].valOf(i) + "," + res[1].valOf(i) + "] "); } if (appendColon) { System.out.print(":"); } } else { System.out.print(curTok); } } // Now this is going to be messy as fuck. Really. What do we needs? Well, // we need to read in the data; look up some info, that we // assume came from a GainClusterer ... // Sanity check. // GClust clust = (GClust) ((ClusterVec) clusters).elCalled("alpha-inc_0"); // System.out.println("INSANE!: " + clust.getDescription()); // EventI[] res = clust.getBounds(1); // System.out.println("For clust settings: min event = " + res[0].toString() + " and max event = " + res[1].toString()); } Debug.dp(Debug.PROGRESS, "PROGRESS: Learning complete. "); int numCorrect = 0; ClassificationVecI classns; if (thisExp.trainResults) { System.err.println(">>> Training performance <<<"); classns = (ClassificationVecI) trainAtts.getClassVec().clone(); for (int j = 0; j < numTrainStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } for (int j = 0; j < numTrainStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Training results for classifier: " + numCorrect + " of " + numTrainStreams + " (" + numCorrect * 100.0 / numTrainStreams + "%)"); } System.err.println(">>> Testing stage <<<"); // First, print the results of using the straight testers. classns = (ClassificationVecI) testAtts.getClassVec().clone(); StreamAttValVecI savvi = testAtts.getStreamAttValVec(); data = WekaBridge.makeInstances(testAtts, "Test "); if (thisExp.featureSel) { String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += "last"; // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } for (int j = 0; j < numTestStreams; j++) { wekaClassifier.classify(data.instance(j), classns.elAt(j)); } System.err.println(">>> Learner <<<"); numCorrect = 0; for (int j = 0; j < numTestStreams; j++) { // System.out.print(classns.elAt(j).toString()); if (classns.elAt(j).getRealClass() == classns.elAt(j).getPredictedClass()) { numCorrect++; String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); System.err.println("Class " + realClassName + " CORRECTLY classified."); } else { String realClassName = domDesc.getClassDescVec().getClassLabel(classns.elAt(j).getRealClass()); String predictedClassName = domDesc.getClassDescVec() .getClassLabel(classns.elAt(j).getPredictedClass()); System.err.println( "Class " + realClassName + " INCORRECTLY classified as " + predictedClassName + "."); } } System.err.println("Test accuracy for classifier: " + numCorrect + " of " + numTestStreams + " (" + numCorrect * 100.0 / numTestStreams + "%)"); }
From source file:tclass.ToArff.java
License:Open Source License
public static void main(String[] args) throws Exception { Debug.setDebugLevel(Debug.PROGRESS); ToArff thisExp = new ToArff(); thisExp.parseArgs(args);// w ww . j av a 2s. c o m DomDesc domDesc = new DomDesc(thisExp.domDescFile); ClassStreamVecI trainStreamData = new ClassStreamVec(thisExp.inFile, domDesc); Debug.dp(Debug.PROGRESS, "PROGRESS: Data read in"); Settings settings = new Settings(thisExp.settingsFile, domDesc); EventExtractor evExtractor = settings.getEventExtractor(); // Global data is likely to be included in every model; so we // might as well calculated now GlobalCalc globalCalc = settings.getGlobalCalc(); ClassStreamAttValVecI trainGlobalData = globalCalc.applyGlobals(trainStreamData); // And we might as well extract the events. Debug.dp(Debug.PROGRESS, "PROGRESS: Globals calculated."); Debug.dp(Debug.PROGRESS, "Train: " + trainGlobalData.size()); ClassStreamEventsVecI trainEventData = evExtractor.extractEvents(trainStreamData); Debug.dp(Debug.PROGRESS, "PROGRESS: Events extracted"); // System.out.println(trainEventData.toString()); // Now we want the clustering algorithms only to cluster // instances of each class. Make an array of clusterers, // one per class. int numClasses = domDesc.getClassDescVec().size(); EventDescVecI eventDescVec = evExtractor.getDescription(); EventClusterer eventClusterer = settings.getEventClusterer(); Debug.dp(Debug.PROGRESS, "PROGRESS: Data rearranged."); //And now load it up. StreamEventsVecI trainEventSEV = trainEventData.getStreamEventsVec(); ClassificationVecI trainEventCV = trainEventData.getClassVec(); int numTrainStreams = trainEventCV.size(); ClusterVecI clusters = eventClusterer.clusterEvents(trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete"); Debug.dp(Debug.PROGRESS, "Clusters are:"); Debug.dp(Debug.PROGRESS, "\n" + eventClusterer.getMapping()); Debug.dp(Debug.PROGRESS, "PROGRESS: Clustering complete. "); // But wait! There's more! There is always more. // The first thing was only useful for clustering. // Now attribution. We want to attribute all the data. So we are going // to have one dataset for each learner. // First set up the attributors. Attributor attribs = new Attributor(domDesc, clusters, eventClusterer.getDescription()); Debug.dp(Debug.PROGRESS, "PROGRESS: AttributorMkr complete."); ClassStreamAttValVecI trainEventAtts = attribs.attribute(trainStreamData, trainEventData); Debug.dp(Debug.PROGRESS, "PROGRESS: Attribution complete."); // Combine all data sources. For now, globals go in every // one. Combiner c = new Combiner(); ClassStreamAttValVecI trainAtts = c.combine(trainGlobalData, trainEventAtts); trainStreamData = null; trainEventSEV = null; trainEventCV = null; if (!thisExp.makeDesc) { clusters = null; eventClusterer = null; } attribs = null; System.gc(); // So now we have the raw data in the correct form for each // attributor. // And now, we can construct a learner for each case. // Well, for now, I'm going to do something completely crazy. // Let's run each classifier nonetheless over the whole data // ... and see what the hell happens. Maybe some voting scheme // is possible!! This is a strange form of ensemble // classifier. // Each naive bayes algorithm only gets one Debug.setDebugLevel(Debug.PROGRESS); int[] selectedIndices = null; String[] classifierSpec = Utils.splitOptions(thisExp.learnerStuff); if (classifierSpec.length == 0) { throw new Exception("Invalid classifier specification string"); } String classifierName = classifierSpec[0]; classifierSpec[0] = ""; Classifier learner = AbstractClassifier.forName(classifierName, classifierSpec); Debug.dp(Debug.PROGRESS, "PROGRESS: Beginning format conversion for class "); Instances data = WekaBridge.makeInstances(trainAtts, "Train "); Debug.dp(Debug.PROGRESS, "PROGRESS: Conversion complete. Starting learning"); if (thisExp.featureSel) { Debug.dp(Debug.PROGRESS, "PROGRESS: Doing feature selection"); BestFirst bfs = new BestFirst(); CfsSubsetEval cfs = new CfsSubsetEval(); cfs.buildEvaluator(data); selectedIndices = bfs.search(cfs, data); // Now extract the features. System.err.print("Selected features: "); String featureString = new String(); for (int j = 0; j < selectedIndices.length; j++) { featureString += (selectedIndices[j] + 1) + ","; } featureString += ("last"); System.err.println(featureString); // Now apply the filter. Remove af = new Remove(); af.setInvertSelection(true); af.setAttributeIndices(featureString); af.setInputFormat(data); data = Filter.useFilter(data, af); } try { FileWriter fw = new FileWriter(thisExp.outFile); fw.write(data.toString()); fw.close(); } catch (Exception e) { throw new Exception("Could not write to output file. "); } }
From source file:tr.gov.ulakbim.jDenetX.classifiers.WEKAClassifier.java
License:Open Source License
public void createWekaClassifier(String[] options) throws Exception { String classifierName = options[0]; String[] newoptions = options.clone(); newoptions[0] = ""; this.classifier = AbstractClassifier.forName(classifierName, newoptions); }