List of usage examples for weka.core Attribute Attribute
public Attribute(String attributeName, int index)
From source file:TextDirectoryLoader.java
License:Open Source License
/** * Determines and returns (if possible) the structure (internally the * header) of the data set as an empty set of instances. * * @return the structure of the data set as an empty * set of Instances//from w ww .jav a2s . co m * @throws IOException if an error occurs */ public Instances getStructure() throws IOException { if (getDirectory() == null) { throw new IOException("No directory/source has been specified"); } // determine class labels, i.e., sub-dirs if (m_structure == null) { String directoryPath = getDirectory().getAbsolutePath(); FastVector atts = new FastVector(); FastVector classes = new FastVector(); File dir = new File(directoryPath); String[] subdirs = dir.list(); for (int i = 0; i < subdirs.length; i++) { File subdir = new File(directoryPath + File.separator + subdirs[i]); if (subdir.isDirectory()) classes.addElement(subdirs[i]); } atts.addElement(new Attribute("text", (FastVector) null)); if (m_OutputFilename) atts.addElement(new Attribute("filename", (FastVector) null)); // make sure that the name of the class attribute is unlikely to // clash with any attribute created via the StringToWordVector filter atts.addElement(new Attribute("@@class@@", classes)); String relName = directoryPath.replaceAll("/", "_"); relName = relName.replaceAll("\\\\", "_").replaceAll(":", "_"); m_structure = new Instances(relName, atts, 0); m_structure.setClassIndex(m_structure.numAttributes() - 1); } return m_structure; }
From source file:MultiClassClassifier.java
License:Open Source License
/** * Builds the classifiers./* w w w .j a va2 s.com*/ * * @param insts the training data. * @throws Exception if a classifier can't be built */ public void buildClassifier(Instances insts) throws Exception { Instances newInsts; // can classifier handle the data? getCapabilities().testWithFail(insts); // remove instances with missing class insts = new Instances(insts); insts.deleteWithMissingClass(); if (m_Classifier == null) { throw new Exception("No base classifier has been set!"); } m_ZeroR = new ZeroR(); m_ZeroR.buildClassifier(insts); m_TwoClassDataset = null; int numClassifiers = insts.numClasses(); if (numClassifiers <= 2) { m_Classifiers = Classifier.makeCopies(m_Classifier, 1); m_Classifiers[0].buildClassifier(insts); m_ClassFilters = null; } else if (m_Method == METHOD_1_AGAINST_1) { // generate fastvector of pairs FastVector pairs = new FastVector(); for (int i = 0; i < insts.numClasses(); i++) { for (int j = 0; j < insts.numClasses(); j++) { if (j <= i) continue; int[] pair = new int[2]; pair[0] = i; pair[1] = j; pairs.addElement(pair); } } numClassifiers = pairs.size(); m_Classifiers = Classifier.makeCopies(m_Classifier, numClassifiers); m_ClassFilters = new Filter[numClassifiers]; m_SumOfWeights = new double[numClassifiers]; // generate the classifiers for (int i = 0; i < numClassifiers; i++) { RemoveWithValues classFilter = new RemoveWithValues(); classFilter.setAttributeIndex("" + (insts.classIndex() + 1)); classFilter.setModifyHeader(true); classFilter.setInvertSelection(true); classFilter.setNominalIndicesArr((int[]) pairs.elementAt(i)); Instances tempInstances = new Instances(insts, 0); tempInstances.setClassIndex(-1); classFilter.setInputFormat(tempInstances); newInsts = Filter.useFilter(insts, classFilter); if (newInsts.numInstances() > 0) { newInsts.setClassIndex(insts.classIndex()); m_Classifiers[i].buildClassifier(newInsts); m_ClassFilters[i] = classFilter; m_SumOfWeights[i] = newInsts.sumOfWeights(); } else { m_Classifiers[i] = null; m_ClassFilters[i] = null; } } // construct a two-class header version of the dataset m_TwoClassDataset = new Instances(insts, 0); int classIndex = m_TwoClassDataset.classIndex(); m_TwoClassDataset.setClassIndex(-1); m_TwoClassDataset.deleteAttributeAt(classIndex); FastVector classLabels = new FastVector(); classLabels.addElement("class0"); classLabels.addElement("class1"); m_TwoClassDataset.insertAttributeAt(new Attribute("class", classLabels), classIndex); m_TwoClassDataset.setClassIndex(classIndex); } else { // use error correcting code style methods Code code = null; switch (m_Method) { case METHOD_ERROR_EXHAUSTIVE: code = new ExhaustiveCode(numClassifiers); break; case METHOD_ERROR_RANDOM: code = new RandomCode(numClassifiers, (int) (numClassifiers * m_RandomWidthFactor), insts); break; case METHOD_1_AGAINST_ALL: code = new StandardCode(numClassifiers); break; default: throw new Exception("Unrecognized correction code type"); } numClassifiers = code.size(); m_Classifiers = Classifier.makeCopies(m_Classifier, numClassifiers); m_ClassFilters = new MakeIndicator[numClassifiers]; for (int i = 0; i < m_Classifiers.length; i++) { m_ClassFilters[i] = new MakeIndicator(); MakeIndicator classFilter = (MakeIndicator) m_ClassFilters[i]; classFilter.setAttributeIndex("" + (insts.classIndex() + 1)); classFilter.setValueIndices(code.getIndices(i)); classFilter.setNumeric(false); classFilter.setInputFormat(insts); newInsts = Filter.useFilter(insts, m_ClassFilters[i]); m_Classifiers[i].buildClassifier(newInsts); } } m_ClassAttribute = insts.classAttribute(); }
From source file:TextDirectoryToArff.java
License:Open Source License
public Instances createDataset(String directoryPath) throws Exception { FastVector atts = new FastVector(2); atts.addElement(new Attribute("filename", (FastVector) null)); atts.addElement(new Attribute("contents", (FastVector) null)); Instances data = new Instances("text_files_in_" + directoryPath, atts, 0); File dir = new File(directoryPath); String[] files = dir.list();/*from www. j a v a2 s. c o m*/ for (int i = 0; i < files.length; i++) { if (files[i].endsWith(".txt")) { try { double[] newInst = new double[2]; newInst[0] = (double) data.attribute(0).addStringValue(files[i]); File txt = new File(directoryPath + File.separator + files[i]); InputStreamReader is; is = new InputStreamReader(new FileInputStream(txt)); StringBuffer txtStr = new StringBuffer(); int c; while ((c = is.read()) != -1) { txtStr.append((char) c); } newInst[1] = (double) data.attribute(1).addStringValue(txtStr.toString()); data.add(new Instance(1.0, newInst)); } catch (Exception e) { //System.err.println("failed to convert file: " + directoryPath + File.separator + files[i]); } } } return data; }
From source file:PCADetector.java
License:Apache License
public Instances getInstances() { int numAtts = m_oriDataMatrix.size(); if (numAtts < 0) return null; ArrayList<Attribute> atts = new ArrayList<Attribute>(numAtts); for (int att = 0; att < numAtts; att++) { atts.add(new Attribute(Integer.toString(att), att)); }/* ww w .j a va 2s .c o m*/ int numInstances = m_oriDataMatrix.get(0).size(); if (numInstances <= 0) return null; Instances dataset = new Instances("MetricInstances", atts, numInstances); for (int inst = 0; inst < numInstances; inst++) { Instance newInst = new DenseInstance(numAtts); for (int att = 0; att < numAtts; att++) { newInst.setValue(att, m_oriDataMatrix.get(att).get(inst)); } dataset.add(newInst); } return dataset; }
From source file:activeSegmentation.feature.FeatureExtraction.java
License:Open Source License
/** * Create training instances out of the user markings * @return set of instances (feature vectors in Weka format) *//*w w w .j a v a2 s. c om*/ @Override public void createTrainingInstance(List<String> classLabels, int classes, List<Vector<ArrayList<Roi>>> examples) { ArrayList<Attribute> attributes = createFeatureHeader(); attributes.add(new Attribute(Common.CLASS, addClasstoHeader(classes, classLabels))); // create initial set of instances trainingData = new Instances(Common.INSTANCE_NAME, attributes, 1); // Set the index of the class attribute trainingData.setClassIndex(filterManager.getNumOfFeatures()); for (int classIndex = 0; classIndex < classes; classIndex++) { int nl = 0; // Read all lists of examples for (int sliceNum = 1; sliceNum <= filterManager.getOriginalImageSize(); sliceNum++) for (int j = 0; j < examples.get(sliceNum - 1).get(classIndex).size(); j++) { Roi r = examples.get(sliceNum - 1).get(classIndex).get(j); nl += addRectangleRoiInstances(trainingData, classIndex, sliceNum, r); } IJ.log("# of pixels selected as " + classLabels.get(classIndex) + ": " + nl); } }
From source file:activeSegmentation.feature.FeatureExtraction.java
License:Open Source License
/** * Add training samples from a rectangular roi * //from ww w. j a va 2 s . c o m * @param trainingData set of instances to add to * @param classIndex class index value * @param sliceNum number of 2d slice being processed * @param r shape roi * @return number of instances added */ private Instances addRectangleRoiInstances(int sliceNum, List<String> classLabels, int classes) { Instances testingData; ArrayList<Attribute> attributes = createFeatureHeader(); attributes.add(new Attribute(Common.CLASS, addClasstoHeader(classes, classLabels))); System.out.println(attributes.toString()); // create initial set of instances testingData = new Instances(Common.INSTANCE_NAME, attributes, 1); // Set the index of the class attribute testingData.setClassIndex(filterManager.getNumOfFeatures()); for (int x = 0; x < originalImage.getWidth(); x++) { for (int y = 0; y < originalImage.getHeight(); y++) { testingData.add(filterManager.createInstance(x, y, 0, sliceNum)); } } // increase number of instances for this class System.out.println("SIZe" + testingData.size()); System.out.println(testingData.get(1).toString()); return testingData; }
From source file:adams.data.conversion.TimeseriesToWekaInstances.java
License:Open Source License
/** * Performs the actual conversion.// ww w . j av a 2s . co m * * @return the converted data * @throws Exception if something goes wrong with the conversion */ @Override protected Object doConvert() throws Exception { Instances result; ArrayList<Attribute> atts; Instance inst; Timeseries series; TimeseriesPoint point; double[] value; series = (Timeseries) m_Input; atts = new ArrayList<Attribute>(); atts.add(new Attribute("Timestamp", m_Format.getValue())); atts.add(new Attribute("Value")); result = new Instances(series.getID(), atts, series.size()); for (Object obj : series.toList()) { point = (TimeseriesPoint) obj; value = new double[2]; value[0] = point.getTimestamp().getTime(); value[1] = point.getValue(); inst = new DenseInstance(1.0, value); result.add(inst); } return result; }
From source file:adams.data.featureconverter.Weka.java
License:Open Source License
/** * Performs the actual generation of a row from the raw data. * /*from ww w.j av a 2s .c o m*/ * @param data the data of the row, elements can be null (= missing) * @return the dataset structure */ @Override protected Instances doGenerateHeader(HeaderDefinition header) { Instances result; ArrayList<Attribute> atts; ArrayList<String> values; int i; atts = new ArrayList<Attribute>(); for (i = 0; i < header.size(); i++) { switch (header.getType(i)) { case BOOLEAN: values = new ArrayList<String>(); values.add("yes"); values.add("no"); atts.add(new Attribute(header.getName(i), values)); break; case NUMERIC: atts.add(new Attribute(header.getName(i))); break; case STRING: case UNKNOWN: atts.add(new Attribute(header.getName(i), (List<String>) null)); break; } } result = new Instances(header.getDataset(), atts, 0); return result; }
From source file:adams.flow.sink.WekaCostBenefitAnalysis.java
License:Open Source License
/** * Plots the token (the panel and dialog have already been created at * this stage).//from w ww. j a v a 2s . c o m * * @param token the token to display */ @Override protected void display(Token token) { Evaluation eval; Attribute classAtt; Attribute classAttToUse; int classValue; ThresholdCurve tc; Instances result; ArrayList<String> newNames; CostBenefitAnalysis cbAnalysis; PlotData2D tempd; boolean[] cp; int n; try { if (token.getPayload() instanceof WekaEvaluationContainer) eval = (Evaluation) ((WekaEvaluationContainer) token.getPayload()) .getValue(WekaEvaluationContainer.VALUE_EVALUATION); else eval = (Evaluation) token.getPayload(); if (eval.predictions() == null) { getLogger().severe("No predictions available from Evaluation object!"); return; } classAtt = eval.getHeader().classAttribute(); m_ClassIndex.setData(classAtt); classValue = m_ClassIndex.getIntIndex(); tc = new ThresholdCurve(); result = tc.getCurve(eval.predictions(), classValue); // Create a dummy class attribute with the chosen // class value as index 0 (if necessary). classAttToUse = eval.getHeader().classAttribute(); if (classValue != 0) { newNames = new ArrayList<>(); newNames.add(classAtt.value(classValue)); for (int k = 0; k < classAtt.numValues(); k++) { if (k != classValue) newNames.add(classAtt.value(k)); } classAttToUse = new Attribute(classAtt.name(), newNames); } // assemble plot data tempd = new PlotData2D(result); tempd.setPlotName(result.relationName()); tempd.m_alwaysDisplayPointsOfThisSize = 10; // specify which points are connected cp = new boolean[result.numInstances()]; for (n = 1; n < cp.length; n++) cp[n] = true; tempd.setConnectPoints(cp); // add plot m_CostBenefitPanel.setCurveData(tempd, classAttToUse); } catch (Exception e) { handleException("Failed to display token: " + token, e); } }
From source file:adams.flow.sink.WekaCostBenefitAnalysis.java
License:Open Source License
/** * Creates a new panel for the token.//from ww w. j a v a 2 s .co m * * @param token the token to display in a new panel, can be null * @return the generated panel */ public AbstractDisplayPanel createDisplayPanel(Token token) { AbstractDisplayPanel result; String name; if (token != null) name = "Cost curve (" + getEvaluation(token).getHeader().relationName() + ")"; else name = "Cost curve"; result = new AbstractComponentDisplayPanel(name) { private static final long serialVersionUID = -3513994354297811163L; protected CostBenefitAnalysis m_VisualizePanel; @Override protected void initGUI() { super.initGUI(); setLayout(new BorderLayout()); m_VisualizePanel = new CostBenefitAnalysis(); add(m_VisualizePanel, BorderLayout.CENTER); } @Override public void display(Token token) { try { Evaluation eval = getEvaluation(token); Attribute classAtt = eval.getHeader().classAttribute(); m_ClassIndex.setData(classAtt); int classValue = m_ClassIndex.getIntIndex(); ThresholdCurve tc = new ThresholdCurve(); Instances result = tc.getCurve(eval.predictions(), classValue); // Create a dummy class attribute with the chosen // class value as index 0 (if necessary). Attribute classAttToUse = eval.getHeader().classAttribute(); if (classValue != 0) { ArrayList<String> newNames = new ArrayList<>(); newNames.add(classAtt.value(classValue)); for (int k = 0; k < classAtt.numValues(); k++) { if (k != classValue) newNames.add(classAtt.value(k)); } classAttToUse = new Attribute(classAtt.name(), newNames); } // assemble plot data PlotData2D tempd = new PlotData2D(result); tempd.setPlotName(result.relationName()); tempd.m_alwaysDisplayPointsOfThisSize = 10; // specify which points are connected boolean[] cp = new boolean[result.numInstances()]; for (int n = 1; n < cp.length; n++) cp[n] = true; tempd.setConnectPoints(cp); // add plot m_VisualizePanel.setCurveData(tempd, classAttToUse); } catch (Exception e) { getLogger().log(Level.SEVERE, "Failed to display token: " + token, e); } } @Override public JComponent supplyComponent() { return m_VisualizePanel; } @Override public void clearPanel() { } public void cleanUp() { } }; if (token != null) result.display(token); return result; }