List of usage examples for weka.core Instances insertAttributeAt
public void insertAttributeAt(Attribute att, int position)
From source file:br.puc_rio.ele.lvc.interimage.datamining.DataParser.java
License:Apache License
@SuppressWarnings({ "unchecked", "rawtypes" })
public Instances parseData(Object objData) {
try {//w w w .ja va 2s.c o m
Instances dataInstance;
DataBag values = (DataBag) objData;
int numAttributes = values.iterator().next().size(); // N_Features + 1 Class
int bagSize = 0; // To set the number of train samples
// To find the number of samples (instances in a bag)
for (Iterator<Tuple> it = values.iterator(); it.hasNext();) {
it.next();
bagSize = bagSize + 1;
}
// Code for find the different classes names in the input
String[] inputClass = new String[bagSize]; // String vector with the samples class's names
int index = 0;
for (Iterator<Tuple> it = values.iterator(); it.hasNext();) {
Tuple tuple = it.next();
inputClass[index] = DataType.toString(tuple.get(numAttributes - 1));
index = index + 1;
}
HashSet classSet = new HashSet(Arrays.asList(inputClass));
String[] classValue = (String[]) classSet.toArray(new String[0]);
// To set the classes names in the attribute for the instance
FastVector classNames = new FastVector();
for (int i = 0; i < classValue.length; i++)
classNames.addElement(classValue[i]);
// Creating the instance model N_Features + 1_ClassNames
FastVector atts = new FastVector();
for (int i = 0; i < numAttributes - 1; i++)
atts.addElement(new Attribute("att" + i));
dataInstance = new Instances("MyRelation", atts, numAttributes);
dataInstance.insertAttributeAt(new Attribute("ClassNames", classNames), numAttributes - 1);
// To set the instance values for the dataInstance model created
Instance tmpData = new DenseInstance(numAttributes);
index = 0;
for (Iterator<Tuple> it = values.iterator(); it.hasNext();) {
Tuple tuple = it.next();
for (int i = 0; i < numAttributes - 1; i++)
tmpData.setValue((weka.core.Attribute) atts.elementAt(i), DataType.toDouble(tuple.get(i)));
//tmpData.setValue((weka.core.Attribute) atts.elementAt(numAttributes-1), DataType.toString(tuple.get(numAttributes-1)));
dataInstance.add(tmpData);
dataInstance.instance(index).setValue(numAttributes - 1,
DataType.toString(tuple.get(numAttributes - 1)));
index = index + 1;
}
// Setting the class index
dataInstance.setClassIndex(dataInstance.numAttributes() - 1);
return dataInstance;
} catch (Exception e) {
System.err.println("Failed to process input; error - " + e.getMessage());
return null;
}
}
From source file:br.puc_rio.ele.lvc.interimage.datamining.DataParser.java
License:Apache License
@SuppressWarnings({ "unchecked", "rawtypes" })
public Instances parseData(BufferedReader buff) {
try {/*from w ww . j ava 2 s . c o m*/
Instances dataInstance;
//DataBag values = (DataBag)objData;
int numAttributes = 0; // N_Features + 1 Class
List<String> inputClass = new ArrayList<String>();
List<String[]> dataset = new ArrayList<String[]>();
// To find the number of samples (instances in a bag)
String line;
while ((line = buff.readLine()) != null) {
if (!line.isEmpty()) {
String[] data = line.split(",");
if (numAttributes == 0)
numAttributes = data.length;
inputClass.add(data[data.length - 1]);
dataset.add(data);
}
}
HashSet classSet = new HashSet(inputClass);
String[] classValue = (String[]) classSet.toArray(new String[0]);
// To set the classes names in the attribute for the instance
FastVector classNames = new FastVector();
for (int i = 0; i < classValue.length; i++)
classNames.addElement(classValue[i]);
// Creating the instance model N_Features + 1_ClassNames
FastVector atts = new FastVector();
for (int i = 0; i < numAttributes - 1; i++)
atts.addElement(new Attribute("att" + i));
dataInstance = new Instances("MyRelation", atts, numAttributes);
dataInstance.insertAttributeAt(new Attribute("ClassNames", classNames), numAttributes - 1);
// To set the instance values for the dataInstance model created
Instance tmpData = new DenseInstance(numAttributes);
int index = 0;
for (int k = 0; k < dataset.size(); k++) {
for (int i = 0; i < numAttributes - 1; i++)
tmpData.setValue((weka.core.Attribute) atts.elementAt(i), DataType.toDouble(dataset.get(k)[i]));
//tmpData.setValue((weka.core.Attribute) atts.elementAt(numAttributes-1), DataType.toString(tuple.get(numAttributes-1)));
dataInstance.add(tmpData);
dataInstance.instance(index).setValue(numAttributes - 1,
DataType.toString(dataset.get(k)[numAttributes - 1]));
index = index + 1;
}
// Setting the class index
dataInstance.setClassIndex(dataInstance.numAttributes() - 1);
return dataInstance;
} catch (Exception e) {
System.err.println("Failed to process input; error - " + e.getMessage());
return null;
}
}
From source file:cezeri.feature.selection.FeatureSelectionInfluence.java
public static Influence[] getMostDiscriminativeFeature(String filePath, Classifier model) { Influence[] ret = null;//from w w w. j ava2 s .co m try { Instances data = DataSource.read(filePath); ret = new Influence[data.numAttributes() - 1]; data.setClassIndex(data.numAttributes() - 1); // other options int seed = 1; int folds = 10; // randomize data Instances randData = new Instances(data); Random rand = new Random(seed); randData.randomize(rand); Evaluation evalBase = getEvaluation(randData, model, folds); double accBase = evalBase.correct() / evalBase.numInstances() * 100; double nf = randData.numAttributes(); for (int j = 0; j < nf - 1; j++) { ret[j] = new Influence(); String str = randData.attribute(j).name(); Attribute att = randData.attribute(j); randData.deleteAttributeAt(j); Evaluation evalTemp = getEvaluation(randData, model, folds); double accTemp = evalTemp.correct() / evalTemp.numInstances() * 100; double tempInfluence = accBase - accTemp; ret[j].attributeName = str; ret[j].infVal = tempInfluence; randData.insertAttributeAt(att, j); } sortInfluenceArray(ret); } catch (Exception ex) { Logger.getLogger(FeatureSelectionInfluence.class.getName()).log(Level.SEVERE, null, ex); } return ret; }
From source file:cezeri.utils.FactoryInstance.java
public static Instances getSubsetData(Instances data, String[] attList) { Instances temp = new Instances(data); for (int i = 0; i < data.numAttributes(); i++) { if (!temp.attribute(0).equals(temp.classAttribute())) { temp.deleteAttributeAt(0);/*from ww w . j ava2s . c o m*/ } } double[][] m = new double[attList.length + 1][data.numInstances()]; for (int i = 0; i < attList.length; i++) { int n = attList.length - 1 - i; String str = attList[n]; Attribute t = data.attribute(str); double[] d = data.attributeToDoubleArray(t.index()); m[n] = d; temp.insertAttributeAt(t, 0); } m[attList.length] = data.attributeToDoubleArray(data.classIndex()); m = CMatrix.getInstance(m).transpose().get2DArrayDouble(); FastVector att = new FastVector(); for (int i = 0; i < temp.numAttributes(); i++) { att.addElement(temp.attribute(i)); } Instances ret = new Instances(temp.relationName(), att, m.length); for (int i = 0; i < m.length; i++) { Instance ins = new Instance(m[0].length); for (int j = 0; j < m[0].length; j++) { ins.setValue(j, m[i][j]); } ret.add(ins); } ret.setClassIndex(temp.classIndex()); return ret; }
From source file:classify.Classifier.java
public static void setAttributeValues(Instances data) { Instance example;/* w ww.ja v a 2 s .com*/ String[][] savedData = new String[data.numInstances()][10]; for (int i = 0; i < data.numInstances(); i++) { example = data.instance(i); savedData[i][0] = example.stringValue(0); savedData[i][1] = example.stringValue(3); savedData[i][2] = example.stringValue(4); savedData[i][3] = example.stringValue(5); savedData[i][4] = example.stringValue(6); savedData[i][5] = example.stringValue(8); savedData[i][6] = example.stringValue(9); savedData[i][7] = example.stringValue(11); savedData[i][8] = example.stringValue(12); savedData[i][9] = example.stringValue(15); } //add in values for discrete attributes //A1 FastVector attVals = new FastVector(); attVals.addElement("b"); attVals.addElement("a"); data.deleteAttributeAt(0); data.insertAttributeAt(new Attribute("A1", attVals), 0); //A4 attVals = new FastVector(); attVals.addElement("u"); attVals.addElement("y"); attVals.addElement("l"); attVals.addElement("t"); data.deleteAttributeAt(3); data.insertAttributeAt(new Attribute("A4", attVals), 3); //A5 attVals = new FastVector(); attVals.addElement("g"); attVals.addElement("p"); attVals.addElement("gg"); data.deleteAttributeAt(4); data.insertAttributeAt(new Attribute("A5", attVals), 4); //A6 attVals = new FastVector(); attVals.addElement("c"); attVals.addElement("d"); attVals.addElement("cc"); attVals.addElement("i"); attVals.addElement("j"); attVals.addElement("k"); attVals.addElement("m"); attVals.addElement("r"); attVals.addElement("q"); attVals.addElement("w"); attVals.addElement("x"); attVals.addElement("e"); attVals.addElement("aa"); attVals.addElement("ff"); data.deleteAttributeAt(5); data.insertAttributeAt(new Attribute("A6", attVals), 5); //A7 attVals = new FastVector(); attVals.addElement("v"); attVals.addElement("h"); attVals.addElement("bb"); attVals.addElement("j"); attVals.addElement("n"); attVals.addElement("z"); attVals.addElement("dd"); attVals.addElement("ff"); attVals.addElement("o"); data.deleteAttributeAt(6); data.insertAttributeAt(new Attribute("A7", attVals), 6); //A9 attVals = new FastVector(); attVals.addElement("t"); attVals.addElement("f"); data.deleteAttributeAt(8); data.insertAttributeAt(new Attribute("A9", attVals), 8); //A10 attVals = new FastVector(); attVals.addElement("t"); attVals.addElement("f"); data.deleteAttributeAt(9); data.insertAttributeAt(new Attribute("A10", attVals), 9); //A12 attVals = new FastVector(); attVals.addElement("t"); attVals.addElement("f"); data.deleteAttributeAt(11); data.insertAttributeAt(new Attribute("A12", attVals), 11); //A13 attVals = new FastVector(); attVals.addElement("g"); attVals.addElement("p"); attVals.addElement("s"); data.deleteAttributeAt(12); data.insertAttributeAt(new Attribute("A13", attVals), 12); //Class attVals = new FastVector(); attVals.addElement("+"); attVals.addElement("-"); data.deleteAttributeAt(15); data.insertAttributeAt(new Attribute("C", attVals), 15); for (int i = 0; i < data.numInstances(); i++) { if (!"?".equals(savedData[i][0])) { data.instance(i).setValue(0, savedData[i][0]); } if (!"?".equals(savedData[i][1])) { data.instance(i).setValue(3, savedData[i][1]); } if (!"?".equals(savedData[i][2])) { data.instance(i).setValue(4, savedData[i][2]); } if (!"?".equals(savedData[i][3])) { data.instance(i).setValue(5, savedData[i][3]); } if (!"?".equals(savedData[i][4])) { data.instance(i).setValue(6, savedData[i][4]); } if (!"?".equals(savedData[i][5])) { data.instance(i).setValue(8, savedData[i][5]); } if (!"?".equals(savedData[i][6])) { data.instance(i).setValue(9, savedData[i][6]); } if (!"?".equals(savedData[i][7])) { data.instance(i).setValue(11, savedData[i][7]); } if (!"?".equals(savedData[i][8])) { data.instance(i).setValue(12, savedData[i][8]); } if (!"?".equals(savedData[i][9])) { data.instance(i).setValue(15, savedData[i][9]); } } }
From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java
License:Open Source License
public static void testCOMT2() throws Exception { BestConf bestconf = new BestConf(); Instances trainingSet = DataIOFile.loadDataFromArffFile("data/trainingBestConf0.arff"); trainingSet.setClassIndex(trainingSet.numAttributes() - 1); Instances samplePoints = LHSInitializer.getMultiDimContinuous(bestconf.getAttributes(), InitialSampleSetSize, false); samplePoints.insertAttributeAt(trainingSet.classAttribute(), samplePoints.numAttributes()); samplePoints.setClassIndex(samplePoints.numAttributes() - 1); COMT2 comt = new COMT2(samplePoints, COMT2Iteration); comt.buildClassifier(trainingSet);// w ww . ja v a2 s. c o m Evaluation eval = new Evaluation(trainingSet); eval.evaluateModel(comt, trainingSet); System.err.println(eval.toSummaryString()); Instance best = comt.getInstanceWithPossibleMaxY(samplePoints.firstInstance()); Instances bestInstances = new Instances(trainingSet, 2); bestInstances.add(best); DataIOFile.saveDataToXrffFile("data/trainingBestConf_COMT2.arff", bestInstances); //now we output the training set with the class value updated as the predicted value Instances output = new Instances(trainingSet, trainingSet.numInstances()); Enumeration<Instance> enu = trainingSet.enumerateInstances(); while (enu.hasMoreElements()) { Instance ins = enu.nextElement(); double[] values = ins.toDoubleArray(); values[values.length - 1] = comt.classifyInstance(ins); output.add(ins.copy(values)); } DataIOFile.saveDataToXrffFile("data/trainingBestConf0_predict.xrff", output); }
From source file:cn.ict.zyq.bestConf.cluster.Main.AutoTestAdjust.java
License:Open Source License
public Instances runExp(Instances samplePoints, String perfAttName) { Instances retVal = null;//from w w w .j a va 2s.c o m if (samplePoints.attribute(perfAttName) == null) { Attribute performance = new Attribute(perfAttName); samplePoints.insertAttributeAt(performance, samplePoints.numAttributes()); } int pos = samplePoints.numInstances(); int count = 0; for (int i = 0; i < pos; i++) { Instance ins = samplePoints.get(i); HashMap hm = new HashMap(); int tot = 0; for (int j = 0; j < ins.numAttributes(); j++) { hm.put(ins.attribute(j).name(), ins.value(ins.attribute(j))); } boolean testRet; if (Double.isNaN(ins.value(ins.attribute(ins.numAttributes() - 1)))) { testRet = this.startTest(hm, i, isInterrupt); double y = 0; if (!testRet) {// the setting does not work, we skip it y = -1; count++; if (count >= targetTestErrorNum) { System.out.println( "There must be somthing wrong with the system. Please check and restart....."); System.exit(1); } } else { y = getPerformanceByType(performanceType); count = 0; } ins.setValue(samplePoints.numAttributes() - 1, y); writePerfstoFile(ins); } else { continue; } } retVal = samplePoints; retVal.setClassIndex(retVal.numAttributes() - 1); return retVal; }
From source file:cn.ict.zyq.bestConf.cluster.Main.AutoTestAdjust.java
License:Open Source License
@Override public Instances collectPerfs(Instances samplePoints, String perfAttName) { Instances retVal = null;//from w w w .jav a2s . c o m if (samplePoints.attribute(perfAttName) == null) { Attribute performance = new Attribute(perfAttName); samplePoints.insertAttributeAt(performance, samplePoints.numAttributes()); } File perfFolder = new File(perfsfilepath); int tot = 0; if (perfFolder.exists()) { //let's get all the name set for the sample points Iterator<Instance> itr = samplePoints.iterator(); TreeSet<String> insNameSet = new TreeSet<String>(); HashMap<String, Integer> mapping = new HashMap<String, Integer>(); int pos = 0; while (itr.hasNext()) { String mdstr = getMD5(itr.next()); insNameSet.add(mdstr); mapping.put(mdstr, new Integer(pos++)); } //now we collect File[] perfFiles = perfFolder.listFiles(new PerfsFileFilter(insNameSet)); tot = perfFiles.length; if (tot > 0) isInterrupt = true; for (int i = 0; i < tot; i++) { Instance ins = samplePoints.get(mapping.get(perfFiles[i].getName())); double[] results = getPerf(perfFiles[i].getAbsolutePath()); if (results != null) { ins.setValue(samplePoints.numAttributes() - 1, results[0]); } } } retVal = samplePoints; retVal.setClassIndex(retVal.numAttributes() - 1); System.out.println("Total number of collected performances is : " + tot); return retVal; }
From source file:de.ugoe.cs.cpdp.dataprocessing.TransferComponentAnalysis.java
License:Apache License
/** * <p>//w w w .j a v a2 s . c o m * Applies TCA to the test and training data. * </p> * * @param testdata * the test data * @param traindata * the training data */ private void applyTCA(Instances testdata, Instances traindata) { final int sizeTest = testdata.numInstances(); final int sizeTrain = traindata.numInstances(); final PrimitiveMatrix kernelMatrix = buildKernel(testdata, traindata); final PrimitiveMatrix kernelNormMatrix = buildKernelNormMatrix(sizeTest, sizeTrain); // L in // the // paper final PrimitiveMatrix centerMatrix = buildCenterMatrix(sizeTest, sizeTrain); // H in the // paper final double mu = 1.0; // default from the MATLAB implementation final PrimitiveMatrix muMatrix = buildMuMatrix(sizeTest, sizeTrain, mu); PrimitiveMatrix.FACTORY.makeEye(sizeTest + sizeTrain, sizeTest + sizeTrain); Console.traceln(Level.FINEST, "creating optimization matrix (dimension " + (sizeTest + sizeTrain) + ")"); final PrimitiveMatrix optimizationProblem = kernelMatrix.multiplyRight(kernelNormMatrix) .multiplyRight(kernelMatrix).add(muMatrix).invert().multiplyRight(kernelMatrix) .multiplyRight(centerMatrix).multiplyRight(kernelMatrix); Console.traceln(Level.FINEST, "optimization matrix created, now solving eigenvalue problem"); General eigenvalueDecomposition = new JamaEigenvalue.General(); eigenvalueDecomposition.compute(optimizationProblem); Console.traceln(Level.FINEST, "eigenvalue problem solved"); Array1D<ComplexNumber> eigenvaluesArray = eigenvalueDecomposition.getEigenvalues(); System.out.println(eigenvaluesArray.length); final Double[] eigenvalues = new Double[(int) eigenvaluesArray.length]; final int[] index = new int[(int) eigenvaluesArray.length]; // create kernel transformation matrix from eigenvectors for (int i = 0; i < eigenvaluesArray.length; i++) { eigenvalues[i] = eigenvaluesArray.doubleValue(i); index[i] = i; } SortUtils.quicksort(eigenvalues, index); final PrimitiveMatrix transformedKernel = kernelMatrix.multiplyRight( eigenvalueDecomposition.getV().selectColumns(Arrays.copyOfRange(index, 0, reducedDimension))); // update testdata and traindata for (int j = testdata.numAttributes() - 1; j >= 0; j--) { if (j != testdata.classIndex()) { testdata.deleteAttributeAt(j); traindata.deleteAttributeAt(j); } } for (int j = 0; j < reducedDimension; j++) { testdata.insertAttributeAt(new Attribute("kerneldim" + j), 1); traindata.insertAttributeAt(new Attribute("kerneldim" + j), 1); } for (int i = 0; i < sizeTrain; i++) { for (int j = 0; j < reducedDimension; j++) { traindata.instance(i).setValue(j + 1, transformedKernel.get(i, j)); } } for (int i = 0; i < sizeTest; i++) { for (int j = 0; j < reducedDimension; j++) { testdata.instance(i).setValue(j + 1, transformedKernel.get(i + sizeTrain, j)); } } }
From source file:de.ugoe.cs.cpdp.loader.NetgeneLoader.java
License:Apache License
@Override public Instances load(File fileMetricsFile) { // first determine all files String path = fileMetricsFile.getParentFile().getAbsolutePath(); String project = fileMetricsFile.getName().split("_")[0]; File bugsFile = new File(path + "/" + project + "_bugs_per_file.csv"); File networkMetrics = new File(path + "/" + project + "_network_metrics.csv"); Instances metricsData = null;//from w w w. j av a 2 s . c o m try { CSVLoader wekaCsvLoader = new CSVLoader(); wekaCsvLoader.setSource(fileMetricsFile); metricsData = wekaCsvLoader.getDataSet(); wekaCsvLoader.setSource(bugsFile); Instances bugsData = wekaCsvLoader.getDataSet(); wekaCsvLoader.setSource(networkMetrics); Instances networkData = wekaCsvLoader.getDataSet(); metricsData.setRelationName(project); // fix nominal attributes (i.e., NA values) for (int j = 2; j < networkData.numAttributes(); j++) { if (networkData.attribute(j).isNominal()) { String attributeName = networkData.attribute(j).name(); double[] tmpVals = new double[networkData.size()]; // get temporary values for (int i = 0; i < networkData.size(); i++) { Instance inst = networkData.instance(i); if (!inst.isMissing(j)) { String val = networkData.instance(i).stringValue(j); try { tmpVals[i] = Double.parseDouble(val); } catch (NumberFormatException e) { // not a number, using 0.0; tmpVals[i] = 0.0; } } else { tmpVals[i] = 0.0; } } // replace attribute networkData.deleteAttributeAt(j); networkData.insertAttributeAt(new Attribute(attributeName), j); for (int i = 0; i < networkData.size(); i++) { networkData.instance(i).setValue(j, tmpVals[i]); } } } // fix string attributes for (int j = 2; j < networkData.numAttributes(); j++) { if (networkData.attribute(j).isString()) { String attributeName = networkData.attribute(j).name(); double[] tmpVals = new double[networkData.size()]; // get temporary values for (int i = 0; i < networkData.size(); i++) { Instance inst = networkData.instance(i); if (!inst.isMissing(j)) { String val = networkData.instance(i).stringValue(j); try { tmpVals[i] = Double.parseDouble(val); } catch (NumberFormatException e) { // not a number, using 0.0; tmpVals[i] = 0.0; } } else { tmpVals[i] = 0.0; } } // replace attribute networkData.deleteAttributeAt(j); networkData.insertAttributeAt(new Attribute(attributeName), j); for (int i = 0; i < networkData.size(); i++) { networkData.instance(i).setValue(j, tmpVals[i]); } } } Map<String, Integer> filenames = new HashMap<>(); for (int j = 0; j < metricsData.size(); j++) { filenames.put(metricsData.instance(j).stringValue(0), j); } // merge with network data int attributeIndex; for (int j = 2; j < networkData.numAttributes(); j++) { attributeIndex = metricsData.numAttributes(); metricsData.insertAttributeAt(networkData.attribute(j), attributeIndex); for (int i = 0; i < networkData.size(); i++) { Integer instanceIndex = filenames.get(networkData.instance(i).stringValue(1)); if (instanceIndex != null) { metricsData.instance(instanceIndex).setValue(attributeIndex, networkData.instance(i).value(j)); } } } // add bug information attributeIndex = metricsData.numAttributes(); final ArrayList<String> classAttVals = new ArrayList<String>(); classAttVals.add("0"); classAttVals.add("1"); final Attribute classAtt = new Attribute("bug", classAttVals); metricsData.insertAttributeAt(classAtt, attributeIndex); for (int i = 0; i < bugsData.size(); i++) { if (bugsData.instance(i).value(2) > 0.0d) { Integer instanceIndex = filenames.get(bugsData.instance(i).stringValue(1)); if (instanceIndex != null) { metricsData.instance(instanceIndex).setValue(attributeIndex, 1.0); } } } // remove filenames metricsData.deleteAttributeAt(0); Attribute eigenvector = metricsData.attribute("eigenvector"); if (eigenvector != null) { for (int j = 0; j < metricsData.numAttributes(); j++) { if (metricsData.attribute(j) == eigenvector) { metricsData.deleteAttributeAt(j); } } } metricsData.setClassIndex(metricsData.numAttributes() - 1); // set all missing values to 0 for (int i = 0; i < metricsData.size(); i++) { for (int j = 0; j < metricsData.numAttributes(); j++) { if (metricsData.instance(i).isMissing(j)) { metricsData.instance(i).setValue(j, 0.0d); } } } } catch (IOException e) { Console.traceln(Level.SEVERE, "failure reading file: " + e.getMessage()); metricsData = null; } return metricsData; }