List of usage examples for weka.core Instances instance
publicInstance instance(int index)
From source file:br.com.ufu.lsi.rebfnetwork.RBFModel.java
License:Open Source License
/** * Method used to pre-process the data, perform clustering, and * set the initial parameter vector.// ww w .j a v a 2s . c om */ protected Instances initializeClassifier(Instances data) throws Exception { // can classifier handle the data? getCapabilities().testWithFail(data); data = new Instances(data); data.deleteWithMissingClass(); // Make sure data is shuffled Random random = new Random(m_Seed); if (data.numInstances() > 2) { random = data.getRandomNumberGenerator(m_Seed); } data.randomize(random); double y0 = data.instance(0).classValue(); // This stuff is not relevant in classification case int index = 1; while (index < data.numInstances() && data.instance(index).classValue() == y0) { index++; } if (index == data.numInstances()) { // degenerate case, all class values are equal // we don't want to deal with this, too much hassle throw new Exception("All class values are the same. At least two class values should be different"); } double y1 = data.instance(index).classValue(); // Replace missing values m_ReplaceMissingValues = new ReplaceMissingValues(); m_ReplaceMissingValues.setInputFormat(data); data = Filter.useFilter(data, m_ReplaceMissingValues); // Remove useless attributes m_AttFilter = new RemoveUseless(); m_AttFilter.setInputFormat(data); data = Filter.useFilter(data, m_AttFilter); // only class? -> build ZeroR model if (data.numAttributes() == 1) { System.err.println( "Cannot build model (only class attribute present in data after removing useless attributes!), " + "using ZeroR model instead!"); m_ZeroR = new weka.classifiers.rules.ZeroR(); m_ZeroR.buildClassifier(data); return data; } else { m_ZeroR = null; } // Transform attributes m_NominalToBinary = new NominalToBinary(); m_NominalToBinary.setInputFormat(data); data = Filter.useFilter(data, m_NominalToBinary); m_Filter = new Normalize(); ((Normalize) m_Filter).setIgnoreClass(true); m_Filter.setInputFormat(data); data = Filter.useFilter(data, m_Filter); double z0 = data.instance(0).classValue(); // This stuff is not relevant in classification case double z1 = data.instance(index).classValue(); m_x1 = (y0 - y1) / (z0 - z1); // no division by zero, since y0 != y1 guaranteed => z0 != z1 ??? m_x0 = (y0 - m_x1 * z0); // = y1 - m_x1 * z1 m_classIndex = data.classIndex(); m_numClasses = data.numClasses(); m_numAttributes = data.numAttributes(); // Run k-means SimpleKMeans skm = new SimpleKMeans(); skm.setMaxIterations(10000); skm.setNumClusters(m_numUnits); Remove rm = new Remove(); data.setClassIndex(-1); rm.setAttributeIndices((m_classIndex + 1) + ""); rm.setInputFormat(data); Instances dataRemoved = Filter.useFilter(data, rm); data.setClassIndex(m_classIndex); skm.buildClusterer(dataRemoved); Instances centers = skm.getClusterCentroids(); if (centers.numInstances() < m_numUnits) { m_numUnits = centers.numInstances(); } // Set up arrays OFFSET_WEIGHTS = 0; if (m_useAttributeWeights) { OFFSET_ATTRIBUTE_WEIGHTS = (m_numUnits + 1) * m_numClasses; OFFSET_CENTERS = OFFSET_ATTRIBUTE_WEIGHTS + m_numAttributes; } else { OFFSET_ATTRIBUTE_WEIGHTS = -1; OFFSET_CENTERS = (m_numUnits + 1) * m_numClasses; } OFFSET_SCALES = OFFSET_CENTERS + m_numUnits * m_numAttributes; switch (m_scaleOptimizationOption) { case USE_GLOBAL_SCALE: m_RBFParameters = new double[OFFSET_SCALES + 1]; break; case USE_SCALE_PER_UNIT_AND_ATTRIBUTE: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits * m_numAttributes]; break; default: m_RBFParameters = new double[OFFSET_SCALES + m_numUnits]; break; } // Set initial radius based on distance to nearest other basis function double maxMinDist = -1; for (int i = 0; i < centers.numInstances(); i++) { double minDist = Double.MAX_VALUE; for (int j = i + 1; j < centers.numInstances(); j++) { double dist = 0; for (int k = 0; k < centers.numAttributes(); k++) { if (k != centers.classIndex()) { double diff = centers.instance(i).value(k) - centers.instance(j).value(k); dist += diff * diff; } } if (dist < minDist) { minDist = dist; } } if ((minDist != Double.MAX_VALUE) && (minDist > maxMinDist)) { maxMinDist = minDist; } } // Initialize parameters if (m_scaleOptimizationOption == USE_GLOBAL_SCALE) { m_RBFParameters[OFFSET_SCALES] = Math.sqrt(maxMinDist); } for (int i = 0; i < m_numUnits; i++) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT) { m_RBFParameters[OFFSET_SCALES + i] = Math.sqrt(maxMinDist); } int k = 0; for (int j = 0; j < m_numAttributes; j++) { if (k == centers.classIndex()) { k++; } if (j != data.classIndex()) { if (m_scaleOptimizationOption == USE_SCALE_PER_UNIT_AND_ATTRIBUTE) { m_RBFParameters[OFFSET_SCALES + (i * m_numAttributes + j)] = Math.sqrt(maxMinDist); } m_RBFParameters[OFFSET_CENTERS + (i * m_numAttributes) + j] = centers.instance(i).value(k); k++; } } } if (m_useAttributeWeights) { for (int j = 0; j < m_numAttributes; j++) { if (j != data.classIndex()) { m_RBFParameters[OFFSET_ATTRIBUTE_WEIGHTS + j] = 1.0; } } } initializeOutputLayer(random); return data; }
From source file:br.fapesp.myutils.MyUtils.java
License:Open Source License
public static void print_dataset_as_matrix(Instances data) { for (int i = 0; i < data.numInstances(); i++) { for (int j = 0; j < data.numAttributes(); j++) System.out.print(data.instance(i).value(j) + " "); System.out.println();//from w w w . j a va 2 s . co m } }
From source file:br.fapesp.myutils.MyUtils.java
License:Open Source License
public static Instances genGaussianDatasetWithSigmaEvolution(double[][] centers, double[][] sigmas, double[][] sigmas2, int pointsPerCluster, long seed, boolean randomize) { Instances dataset1 = genGaussianDataset(centers, sigmas, pointsPerCluster, seed, randomize, false); Instances dataset2 = genGaussianDataset(centers, sigmas2, pointsPerCluster, seed + 59387, randomize, false); for (int i = 0; i < dataset2.numInstances(); i++) dataset1.add(dataset2.instance(i)); return dataset1; }
From source file:br.fapesp.myutils.MyUtils.java
License:Open Source License
/** * Convert an Instances data set to a doubles matrix. * @param data// ww w . ja v a 2 s .c o m * @return data as a double array */ public static double[][] convertInstancesToDoubleMatrix(Instances data) { int N = data.numInstances(); int m = data.numAttributes(); double[][] ddata = new double[N][m]; double[] temp; for (int i = 0; i < N; i++) { temp = data.instance(i).toDoubleArray(); for (int j = 0; j < m; j++) ddata[i][j] = temp[j]; } return (ddata); }
From source file:br.puc_rio.ele.lvc.interimage.datamining.DataParser.java
License:Apache License
@SuppressWarnings({ "unchecked", "rawtypes" })
public Instances parseData(Object objData) {
try {//from ww w .j ava 2s .c om
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 w w . ja va 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:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private double E(Instances inst, boolean change_weights) throws Exception { double loglk = 0.0, sOW = 0.0; for (int l = 0; l < inst.numInstances(); l++) { Instance in = inst.instance(l); loglk += in.weight() * logDensityForInstance(in); sOW += in.weight();/*from w w w .ja v a 2 s . co m*/ if (change_weights) { m_weights[l] = distributionForInstance(in); } } // reestimate priors if (change_weights) { estimate_priors(inst); } return loglk / sOW; }
From source file:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private void EM_Init(Instances inst) throws Exception { int i, j, k;// w w w . j ava2s . c om // run k means 10 times and choose best solution SimpleKMeans bestK = null; double bestSqE = Double.MAX_VALUE; for (i = 0; i < 10; i++) { SimpleKMeans sk = new SimpleKMeans(); sk.setSeed(m_rr.nextInt()); sk.setNumClusters(m_num_clusters); sk.setDisplayStdDevs(true); sk.buildClusterer(inst); if (sk.getSquaredError() < bestSqE) { bestSqE = sk.getSquaredError(); bestK = sk; } } // initialize with best k-means solution m_num_clusters = bestK.numberOfClusters(); m_weights = new double[inst.numInstances()][m_num_clusters]; m_model = new DiscreteEstimator[m_num_clusters][m_num_attribs]; m_modelNormal = new double[m_num_clusters][m_num_attribs][3]; m_priors = new double[m_num_clusters]; Instances centers = bestK.getClusterCentroids(); Instances stdD = bestK.getClusterStandardDevs(); double[][][] nominalCounts = bestK.getClusterNominalCounts(); double[] clusterSizes = bestK.getClusterSizes(); for (i = 0; i < m_num_clusters; i++) { Instance center = centers.instance(i); for (j = 0; j < m_num_attribs; j++) { if (inst.attribute(j).isNominal()) { m_model[i][j] = new DiscreteEstimator(m_theInstances.attribute(j).numValues(), true); for (k = 0; k < inst.attribute(j).numValues(); k++) { m_model[i][j].addValue(k, nominalCounts[i][j][k]); } } else { double minStdD = (m_minStdDevPerAtt != null) ? m_minStdDevPerAtt[j] : m_minStdDev; double mean = (center.isMissing(j)) ? inst.meanOrMode(j) : center.value(j); m_modelNormal[i][j][0] = mean; double stdv = (stdD.instance(i).isMissing(j)) ? ((m_maxValues[j] - m_minValues[j]) / (2 * m_num_clusters)) : stdD.instance(i).value(j); if (stdv < minStdD) { stdv = inst.attributeStats(j).numericStats.stdDev; if (Double.isInfinite(stdv)) { stdv = minStdD; } if (stdv < minStdD) { stdv = minStdD; } } if (stdv <= 0) { stdv = m_minStdDev; } m_modelNormal[i][j][1] = stdv; m_modelNormal[i][j][2] = 1.0; } } } for (j = 0; j < m_num_clusters; j++) { // m_priors[j] += 1.0; m_priors[j] = clusterSizes[j]; } Utils.normalize(m_priors); }
From source file:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private void estimate_priors(Instances inst) throws Exception { for (int i = 0; i < m_num_clusters; i++) { m_priors[i] = 0.0;//from ww w . j a v a 2 s . co m } for (int i = 0; i < inst.numInstances(); i++) { for (int j = 0; j < m_num_clusters; j++) { m_priors[j] += inst.instance(i).weight() * m_weights[i][j]; } } Utils.normalize(m_priors); }
From source file:br.ufrn.ia.core.clustering.EMIaProject.java
License:Open Source License
private void M(Instances inst) throws Exception { int i, j, l;/*from ww w . ja v a 2 s . c o m*/ new_estimators(); for (i = 0; i < m_num_clusters; i++) { for (j = 0; j < m_num_attribs; j++) { for (l = 0; l < inst.numInstances(); l++) { Instance in = inst.instance(l); if (!in.isMissing(j)) { if (inst.attribute(j).isNominal()) { m_model[i][j].addValue(in.value(j), in.weight() * m_weights[l][i]); } else { m_modelNormal[i][j][0] += (in.value(j) * in.weight() * m_weights[l][i]); m_modelNormal[i][j][2] += in.weight() * m_weights[l][i]; m_modelNormal[i][j][1] += (in.value(j) * in.value(j) * in.weight() * m_weights[l][i]); } } } } } // calcualte mean and std deviation for numeric attributes for (j = 0; j < m_num_attribs; j++) { if (!inst.attribute(j).isNominal()) { for (i = 0; i < m_num_clusters; i++) { if (m_modelNormal[i][j][2] <= 0) { m_modelNormal[i][j][1] = Double.MAX_VALUE; // m_modelNormal[i][j][0] = 0; m_modelNormal[i][j][0] = m_minStdDev; } else { // variance m_modelNormal[i][j][1] = (m_modelNormal[i][j][1] - (m_modelNormal[i][j][0] * m_modelNormal[i][j][0] / m_modelNormal[i][j][2])) / (m_modelNormal[i][j][2]); if (m_modelNormal[i][j][1] < 0) { m_modelNormal[i][j][1] = 0; } // std dev double minStdD = (m_minStdDevPerAtt != null) ? m_minStdDevPerAtt[j] : m_minStdDev; m_modelNormal[i][j][1] = Math.sqrt(m_modelNormal[i][j][1]); if ((m_modelNormal[i][j][1] <= minStdD)) { m_modelNormal[i][j][1] = inst.attributeStats(j).numericStats.stdDev; if ((m_modelNormal[i][j][1] <= minStdD)) { m_modelNormal[i][j][1] = minStdD; } } if ((m_modelNormal[i][j][1] <= 0)) { m_modelNormal[i][j][1] = m_minStdDev; } if (Double.isInfinite(m_modelNormal[i][j][1])) { m_modelNormal[i][j][1] = m_minStdDev; } // mean m_modelNormal[i][j][0] /= m_modelNormal[i][j][2]; } } } } }