Java Code Examples for weka.core.Instance#relationalValue()

/**
 * Calculate the distance from one data point to a bag
 *
 * @param center the data point in instance space
 * @param bag the bag 
 * @return the double value as the distance.
 */
public double minBagDistance (Instance center, Instance bag){
  double distance;
  double minDistance = Double.MAX_VALUE;
  Instances temp = bag.relationalValue(1);  
  //calculate the distance from the data point to each instance in the bag and return the minimum distance 
  for (int i=0; i<temp.numInstances(); i++){
    distance =0;
    for (int j=0; j<center.numAttributes(); j++)
      distance += (center.value(j)-temp.instance(i).value(j))*(center.value(j)-temp.instance(i).value(j));

    if (minDistance>distance)
      minDistance = distance;
  }
  return Math.sqrt(minDistance); 
}
 

/**A getting started with relational attributes in Weka. Once you have the basics
         * there are a range of tools for manipulating them in
         * package utilities.multivariate_tools
         *
         * See https://weka.wikispaces.com/Multi-instance+classification
         * for more
         * */
        public static void gettingStarted(){
//Load a multivariate data set
            String path="\\\\cmptscsvr.cmp.uea.ac.uk\\ueatsc\\Data\\Multivariate\\univariateConcatExample";
            Instances train =DatasetLoading.loadData(path);
            System.out.println(" univariate data = "+train);
            path="\\\\cmptscsvr.cmp.uea.ac.uk\\ueatsc\\Data\\Multivariate\\multivariateConcatExample";
            train =DatasetLoading.loadData(path);
            System.out.println(" multivariate data = "+train);
//Recover the first instance
            Instance first=train.instance(0);
//Split into separate dimensions
            Instances split=first.relationalValue(0);
            System.out.println(" A single multivariate case split into 3 instances with no class values= "+split);
            for(Instance ins:split)
                System.out.println("Dimension of first case =" +ins);
//Extract as arrays
            double[][] d = new double[split.numInstances()][];
            for(int i=0;i<split.numInstances();i++)
                d[i]=split.instance(i).toDoubleArray();


        }
 

public static void summariseData(){
            String path="Z:\\Data\\MultivariateTSCProblems\\";
            OutFile out=new OutFile("Z:\\Data\\MultivariateTSCProblems\\SummaryData.csv");
            out.writeLine("problem,numTrainCases,numTestCases,numDimensions,seriesLength,numClasses");
            for(String prob: DatasetLists.mtscProblems2018){
                Instances train =DatasetLoading.loadData(path+prob+"\\"+prob+"_TRAIN");
                Instances test =DatasetLoading.loadData(path+prob+"\\"+prob+"_TEST");
                System.out.println("PROBLEM "+prob);
                System.out.println("Num train instances ="+train.numInstances());
                System.out.println("Num test instances ="+test.numInstances());
                System.out.println("num attributes (should be 2!)="+train.numAttributes());
                System.out.println("num classes="+train.numClasses());
                Instance temp=train.instance(0);
                Instances x= temp.relationalValue(0);
                System.out.println(" number of dimensions "+x.numInstances());
                System.out.println(" number of attributes per dimension "+x.numAttributes());
                out.writeLine(prob+","+train.numInstances()+","+test.numInstances()+","+x.numInstances()+","+x.numAttributes()+","+train.numClasses());

//            System.out.println(" Object type ="+x);

            }



        }
 

/**A getting started with relational attributes in Weka. Once you have the basics
 * there are a range of tools for manipulating them in 
 * package utilities.multivariate_tools 
 * 
 * See https://weka.wikispaces.com/Multi-instance+classification
 * for more     
 * */
    public static void gettingStarted(){
//Load a multivariate data set
        String path="\\\\cmptscsvr.cmp.uea.ac.uk\\ueatsc\\Data\\Multivariate\\univariateConcatExample";
        Instances train = DatasetLoading.loadDataNullable(path);
        System.out.println(" univariate data = "+train);
        path="\\\\cmptscsvr.cmp.uea.ac.uk\\ueatsc\\Data\\Multivariate\\multivariateConcatExample";
        train = DatasetLoading.loadDataNullable(path);
        System.out.println(" multivariate data = "+train);
//Recover the first instance
        Instance first=train.instance(0);
//Split into separate dimensions
        Instances split=first.relationalValue(0);
        System.out.println(" A single multivariate case split into 3 instances with no class values= "+split);
        for(Instance ins:split)
            System.out.println("Dimension of first case =" +ins);
//Extract as arrays
        double[][] d = new double[split.numInstances()][];
        for(int i=0;i<split.numInstances();i++)
           d[i]=split.instance(i).toDoubleArray();

    
    }
 

public static void testSimpleClassifier() throws Exception{
    String path="Z:\\Data\\MultivariateTSCProblems\\";
    for(int i=15;i<DatasetLists.mtscProblems2018.length;i++){
        String prob=DatasetLists.mtscProblems2018[i]; 
        System.out.println("PROBLEM "+prob);        
        Instances train =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TRAIN");
        Instances test =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TEST");
        System.out.println("Num train instances ="+train.numInstances());
        System.out.println("Num test instances ="+test.numInstances());
        System.out.println("num attributes (should be 2!)="+train.numAttributes());
        System.out.println("num classes="+train.numClasses());
        Instance temp=train.instance(0);
        Instances x= temp.relationalValue(0);
        System.out.println(" number of dimensions "+x.numInstances());
        System.out.println(" number of attributes per dimension "+x.numAttributes());
        NN_ED_I nb = new NN_ED_I();
        nb.buildClassifier(train);
        double a=ClassifierTools.accuracy(test, nb);
        System.out.println("Problem ="+prob+" 1-NN ED accuracy  ="+a);

    }
    
    
    
}
 

public static void summariseMultivariateData(){
        String path="Z:\\Data\\MultivariateTSCProblems\\";
        OutFile out=new OutFile("Z:\\Data\\MultivariateTSCProblems\\SummaryData.csv");
        out.writeLine("problem,numTrainCases,numTestCases,numDimensions,seriesLength,numClasses");
        for(int i=0;i<DatasetLists.mtscProblems2018.length;i++){
            String prob=DatasetLists.mtscProblems2018[i]; 
            System.out.println("PROBLEM "+prob);        
            Instances train =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TRAIN");
            Instances test =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TEST");
            System.out.println("Num train instances ="+train.numInstances());
            System.out.println("Num test instances ="+test.numInstances());
            System.out.println("num attributes (should be 2!)="+train.numAttributes());
            System.out.println("num classes="+train.numClasses());
            Instance temp=train.instance(0);
            Instances x= temp.relationalValue(0);
            System.out.println(" number of dimensions "+x.numInstances());
            System.out.println(" number of attributes per dimension "+x.numAttributes());
            out.writeLine(prob+","+train.numInstances()+","+test.numInstances()+","+x.numInstances()+","+x.numAttributes()+","+train.numClasses());

//            System.out.println(" Object type ="+x);

        }
        
        
        
    }
 

/**
 * Wether the instances of two exemplars are or  are not equal
 * @param exemplar1 first exemplar
 * @param exemplar2 second exemplar
 * @return if the instances of the exemplars are equal or not
 */
public boolean equalExemplars(Instance exemplar1, Instance exemplar2){
  if(exemplar1.relationalValue(1).numInstances() == 
      exemplar2.relationalValue(1).numInstances()){
    Instances instances1 = exemplar1.relationalValue(1);
    Instances instances2 = exemplar2.relationalValue(1);
    for(int i = 0; i < instances1.numInstances(); i++){
      Instance instance1 = instances1.instance(i);
      Instance instance2 = instances2.instance(i);
      for(int j = 0; j < instance1.numAttributes(); j++){
        if(instance1.value(j) != instance2.value(j)){
          return false;
        }
      }
    }
    return true;
      }
  return false;
}
 

/** 
 * Updates the normalization of each attribute.
 * 
 * @param bag the exemplar to update the normalization for
 */
public void updateNormalization(Instance bag){
  int i, k;
  double min, max;
  Instances instances;
  Instance instance;
  // compute the min/max of each feature
  for (i = 0; i < m_TrainBags.attribute(1).relation().numAttributes(); i++) {
    min = m_Min[i] / m_MinNorm;
    max = m_Max[i] / m_MaxNorm;

    instances = bag.relationalValue(1);
    for (k=0;k<instances.numInstances();k++) {
      instance = instances.instance(k);
      if(instance.value(i) < min)
        min = instance.value(i);
      if(instance.value(i) > max)
        max = instance.value(i);
    }
    m_Min[i] = min * m_MinNorm;
    m_Max[i] = max * m_MaxNorm;
    m_Diffs[i]= max * m_MaxNorm - min * m_MinNorm;
  }
}
 

/**
 * Updates the minimum and maximum values for all the attributes
 * based on a new exemplar.
 *
 * @param ex the new exemplar
 */
private void updateMinMax(Instance ex) {	
  Instances insts = ex.relationalValue(1);
  for (int j = 0;j < m_Dimension; j++) {
    if (insts.attribute(j).isNumeric()){
      for(int k=0; k < insts.numInstances(); k++){
        Instance ins = insts.instance(k);
        if(!ins.isMissing(j)){
          if (Double.isNaN(m_MinArray[j])) {
            m_MinArray[j] = ins.value(j);
            m_MaxArray[j] = ins.value(j);
          } else {
            if (ins.value(j) < m_MinArray[j])
              m_MinArray[j] = ins.value(j);
            else if (ins.value(j) > m_MaxArray[j])
              m_MaxArray[j] = ins.value(j);
          }
        }
      }
    }
  }
}
 

/**
 * Computes the distribution for a given exemplar
 *
 * @param exmp the exemplar for which distribution is computed
 * @return the distribution
 * @throws Exception if the distribution can't be computed successfully
 */
public double[] distributionForInstance(Instance exmp) 
  throws Exception {

  // Extract the data
  Instances ins = exmp.relationalValue(1);
  if(m_Filter!=null)
    ins = Filter.useFilter(ins, m_Filter);

  ins = Filter.useFilter(ins, m_Missing);

  int nI = ins.numInstances(), nA = ins.numAttributes();
  double[][] dat = new double [nI][nA];
  for(int j=0; j<nI; j++){
    for(int k=0; k<nA; k++){ 
      dat[j][k] = ins.instance(j).value(k);
    }
  }

  // Compute the probability of the bag
  double [] distribution = new double[2];
  distribution[0]=0.0;  // log-Prob. for class 0

  for(int i=0; i<nI; i++){
    double exp = 0.0;
    for(int r=0; r<nA; r++)
      exp += (m_Par[r*2]-dat[i][r])*(m_Par[r*2]-dat[i][r])*
        m_Par[r*2+1]*m_Par[r*2+1];
    exp = Math.exp(-exp);

    // Prob. updated for one instance
    distribution[0] += Math.log(1.0-exp);
  }

  distribution[0] = Math.exp(distribution[0]);
  distribution[1] = 1.0-distribution[0];

  return distribution;
}
 

public static void formatCricket(){
    String path="Z:\\Data\\Multivariate Working Area\\Cricket\\";
    Instances[] data=new Instances[6];
    data[0]=DatasetLoading.loadDataNullable(path+"CricketXLeft.arff");
    data[1]=DatasetLoading.loadDataNullable(path+"CricketYLeft.arff");
    data[2]=DatasetLoading.loadDataNullable(path+"CricketZLeft.arff");
    data[3]=DatasetLoading.loadDataNullable(path+"CricketXRight.arff");
    data[4]=DatasetLoading.loadDataNullable(path+"CricketYRight.arff");
    data[5]=DatasetLoading.loadDataNullable(path+"CricketZRight.arff");
    Instances all=MultivariateInstanceTools.mergeToMultivariateInstances(data);
    OutFile out=new OutFile(path+"Cricket.arff");
    System.out.println("Cricket number of instances ="+all.numInstances());
        Instance temp=all.instance(0);
        Instances x= temp.relationalValue(0);
        System.out.println(" number of dimensions "+x.numInstances());
        System.out.println(" number of attributes per dimension "+x.numAttributes());
    out.writeString(all+"");
    Instances[] split= MultivariateInstanceTools.resampleMultivariateInstances(all, 0, 0.6);
    System.out.println("Train size ="+split[0].numInstances());
    System.out.println("Test size ="+split[1].numInstances());
     out=new OutFile(path+"Cricket_TRAIN.arff");
    out.writeString(split[0]+"");
     out=new OutFile(path+"Cricket_TEST.arff");
    out.writeString(split[1]+"");


}
 

public static void makeSingleDimensionFiles(String path, String[] probs,boolean overwrite){
        for(String prob: probs){
            System.out.println("Processing "+prob);
            if(prob.equals("InsectWingbeat")||prob.equals("FaceDetection")|| prob.equals("DuckDuckGeese"))
                continue;
            File f= new File(path+prob+"\\"+prob+"Dimension"+(1)+"_TRAIN.arff");

            if(f.exists()&&!overwrite)
                continue;
            Instances train =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TRAIN");
            Instances test =DatasetLoading.loadDataNullable(path+prob+"\\"+prob+"_TEST");
            System.out.println("PROBLEM "+prob);        
            System.out.println("Num train instances ="+train.numInstances());
            System.out.println("Num test instances ="+test.numInstances());
            System.out.println("num attributes (should be 2!)="+train.numAttributes());
            System.out.println("num classes="+train.numClasses());
            Instance temp=train.instance(0);
            Instances x= temp.relationalValue(0);
            System.out.println(" number of dimensions "+x.numInstances());
            System.out.println(" number of attributes per dimension "+x.numAttributes());
            Instances[] splitTest=MultivariateInstanceTools.splitMultivariateInstances(test);
            Instances[] splitTrain=MultivariateInstanceTools.splitMultivariateInstances(train);
            System.out.println(" Num split files ="+splitTest.length);
            for(int i=0;i<splitTrain.length;i++){
                System.out.println("Number of test instances = "+splitTest[i].numInstances());
                OutFile outTrain=new OutFile(path+prob+"\\"+prob+"Dimension"+(i+1)+"_TRAIN.arff");
                outTrain.writeLine(splitTrain[i].toString()+"");
                OutFile outTest=new OutFile(path+prob+"\\"+prob+"Dimension"+(i+1)+"_TEST.arff");
                outTest.writeLine(splitTest[i].toString()+"");
            }
            
//            System.out.println(" Object type ="+x);

        }   
    }
 

/**
 * Computes the distribution for a given exemplar
 *
 * @param exmp the exemplar for which distribution is computed
 * @return the distribution
 * @throws Exception if the distribution can't be computed successfully
 */
public double[] distributionForInstance(Instance exmp)
  throws Exception {

  // Extract the data
  Instances ins = exmp.relationalValue(1);
  if (m_Filter != null)
    ins = Filter.useFilter(ins, m_Filter);

  ins = Filter.useFilter(ins, m_Missing);

  int nI = ins.numInstances(), nA = ins.numAttributes();
  double[][] dat = new double [nI][nA];
  for (int j = 0; j < nI; j++){
    for (int k=0; k<nA; k++){
      dat[j][k] = ins.instance(j).value(k);
    }
  }
  //find the concept instance in the exemplar
  double min = Double.MAX_VALUE;
  double maxProb = -1.0;
  for (int j = 0; j < nI; j++){
    double exp = 0.0;
    for (int k = 0; k<nA; k++)  // for each attribute
      exp += (dat[j][k]-m_Par[k*2])*(dat[j][k]-m_Par[k*2])*m_Par[k*2+1]*m_Par[k*2+1];
    //the probability can be calculated as Math.exp(-exp)
    //to find the maximum Math.exp(-exp) is equivalent to find the minimum of (exp)
    if (exp < min)  {
      min     = exp;
      maxProb = Math.exp(-exp); //maximum probability of being positive   
    }
  }	

  // Compute the probability of the bag
  double[] distribution = new double[2];
  distribution[1] = maxProb; 
  distribution[0] = 1.0 - distribution[1];  //mininum prob. of being negative

  return distribution;
}
 

public static void formatCricket(){
    String path="Z:\\Data\\Multivariate Working Area\\Cricket\\";
    Instances[] data=new Instances[6];
    data[0]=DatasetLoading.loadData(path+"CricketXLeft.arff");
    data[1]=DatasetLoading.loadData(path+"CricketYLeft.arff");
    data[2]=DatasetLoading.loadData(path+"CricketZLeft.arff");
    data[3]=DatasetLoading.loadData(path+"CricketXRight.arff");
    data[4]=DatasetLoading.loadData(path+"CricketYRight.arff");
    data[5]=DatasetLoading.loadData(path+"CricketZRight.arff");
    Instances all=MultivariateInstanceTools.mergeToMultivariateInstances(data);
    OutFile out=new OutFile(path+"Cricket.arff");
    System.out.println("Cricket number of instances ="+all.numInstances());
    Instance temp=all.instance(0);
    Instances x= temp.relationalValue(0);
    System.out.println(" number of dimensions "+x.numInstances());
    System.out.println(" number of attributes per dimension "+x.numAttributes());
    out.writeString(all+"");
    Instances[] split= MultivariateInstanceTools.resampleMultivariateInstances(all, 0, 0.6);
    System.out.println("Train size ="+split[0].numInstances());
    System.out.println("Test size ="+split[1].numInstances());
    out=new OutFile(path+"Cricket_TRAIN.arff");
    out.writeString(split[0]+"");
    out=new OutFile(path+"Cricket_TEST.arff");
    out.writeString(split[1]+"");


}
 

public static void makeSingleDimensionFiles(){
            String path="Z:\\Data\\MultivariateTSCProblems\\";
            for(String prob: DatasetLists.mtscProblems2018){

                File f= new File(path+prob+"\\"+prob+"Dimension"+(1)+"_TRAIN.arff");
                if(!f.exists()){
                    Instances train =DatasetLoading.loadData(path+prob+"\\"+prob+"_TRAIN");
                    Instances test =DatasetLoading.loadData(path+prob+"\\"+prob+"_TEST");
                    System.out.println("PROBLEM "+prob);
                    System.out.println("Num train instances ="+train.numInstances());
                    System.out.println("Num test instances ="+test.numInstances());
                    System.out.println("num attributes (should be 2!)="+train.numAttributes());
                    System.out.println("num classes="+train.numClasses());
                    Instance temp=train.instance(0);
                    Instances x= temp.relationalValue(0);
                    System.out.println(" number of dimensions "+x.numInstances());
                    System.out.println(" number of attributes per dimension "+x.numAttributes());
                    Instances[] splitTest=MultivariateInstanceTools.splitMultivariateInstances(test);
                    Instances[] splitTrain=MultivariateInstanceTools.splitMultivariateInstances(train);
                    System.out.println(" Num split files ="+splitTest.length);
                    for(int i=0;i<splitTrain.length;i++){
                        System.out.println("Number of test instances = "+splitTest[i].numInstances());
                        OutFile outTrain=new OutFile(path+prob+"\\"+prob+"Dimension"+(i+1)+"_TRAIN.arff");
                        outTrain.writeLine(splitTrain[i].toString()+"");
                        OutFile outTest=new OutFile(path+prob+"\\"+prob+"Dimension"+(i+1)+"_TEST.arff");
                        outTest.writeLine(splitTest[i].toString()+"");

                    }
                }

//            System.out.println(" Object type ="+x);

            }
        }
 

/**
 * Computes the distribution for a given exemplar
 *
 * @param exmp the exemplar for which distribution is computed
 * @return the distribution
 * @throws Exception if the distribution can't be computed successfully
 */
public double[] distributionForInstance(Instance exmp) 
  throws Exception {

  // Extract the data
  Instances ins = exmp.relationalValue(1);
  if(m_Filter!=null)
    ins = Filter.useFilter(ins, m_Filter);

  ins = Filter.useFilter(ins, m_Missing);

  int nI = ins.numInstances(), nA = ins.numAttributes();
  double[][] dat = new double [nI][nA];
  for(int j=0; j<nI; j++){
    for(int k=0; k<nA; k++){ 
      dat[j][k] = ins.instance(j).value(k);
    }
  }

  // Compute the probability of the bag
  double [] distribution = new double[2];
  distribution[1]=0.0;  // Prob. for class 1

  for(int i=0; i<nI; i++){
    double exp = 0.0;
    for(int r=0; r<nA; r++)
      exp += (m_Par[r*2]-dat[i][r])*(m_Par[r*2]-dat[i][r])/
        ((m_Par[r*2+1])*(m_Par[r*2+1]));
    exp = Math.exp(-exp);

    // Prob. updated for one instance
    distribution[1] += exp/(double)nI;
    distribution[0] += (1.0-exp)/(double)nI;
  }

  return distribution;
}
 

/**
 * Creates a relational test dataset
 */
public static Instances makeTestDatasetRelational(
    int seed,
    int numInstances,
    int numClasses,
    int classType,
    int classIndex,
    int numRelationalNominal,
    int numRelationalString,
    int numRelationalNumeric,
    int numInstancesRelational)
    throws Exception {

  TestInstances testset = new TestInstances();
  testset.setSeed(seed);
  testset.setNumInstances(numInstances);
  testset.setNumClasses(numClasses);
  testset.setClassType(classType);
  testset.setClassIndex(classIndex);
  testset.setNumClasses(numClasses);
  testset.setMultiInstance(false);

  testset.setNumNominal(0);
  testset.setNumNumeric(0);
  testset.setNumString(0);
  testset.setNumDate(0);
  testset.setNumRelational(1);

  testset.setNumRelationalNominal(numRelationalNominal);
  testset.setNumRelationalString(numRelationalString);
  testset.setNumRelationalNumeric(numRelationalNumeric);
  testset.setNumInstancesRelational(numInstancesRelational);

  final Instances generated = testset.generate();

  // Remove random instances
  Random rand = new Random(42);
  for (Instance datum : generated) {
    final Instances rel = datum.relationalValue(0);
    RemovePercentage rp = new RemovePercentage();
    rp.setInputFormat(rel);
    rp.setPercentage(rand.nextDouble() * 100);
    final Instances rel2 = Filter.useFilter(rel, rp);
    final int i = generated.attribute(0).addRelation(rel2);
    datum.setValue(0, i);
  }
  return generated;
}
 

/**
 * Creates a relational test dataset
 */
public static Instances makeTestDatasetRelational(
    int seed,
    int numInstances,
    int numClasses,
    int classType,
    int classIndex,
    int numRelationalNominal,
    int numRelationalString,
    int numRelationalNumeric,
    int numInstancesRelational)
    throws Exception {

  TestInstances testset = new TestInstances();
  testset.setSeed(seed);
  testset.setNumInstances(numInstances);
  testset.setNumClasses(numClasses);
  testset.setClassType(classType);
  testset.setClassIndex(classIndex);
  testset.setNumClasses(numClasses);
  testset.setMultiInstance(false);

  testset.setNumNominal(0);
  testset.setNumNumeric(0);
  testset.setNumString(0);
  testset.setNumDate(0);
  testset.setNumRelational(1);

  testset.setNumRelationalNominal(numRelationalNominal);
  testset.setNumRelationalString(numRelationalString);
  testset.setNumRelationalNumeric(numRelationalNumeric);
  testset.setNumInstancesRelational(numInstancesRelational);

  final Instances generated = testset.generate();

  // Remove random instances
  Random rand = new Random(42);
  for (Instance datum : generated) {
    final Instances rel = datum.relationalValue(0);
    RemovePercentage rp = new RemovePercentage();
    rp.setInputFormat(rel);
    rp.setPercentage(rand.nextDouble() * 100);
    final Instances rel2 = Filter.useFilter(rel, rp);
    final int i = generated.attribute(0).addRelation(rel2);
    datum.setValue(0, i);
  }
  return generated;
}