Java Discretize类代码示例

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Initializes a symmetrical uncertainty attribute evaluator. Discretizes all
 * attributes that are numeric.
 * 
 * @param data set of instances serving as training data
 * @throws Exception if the evaluator has not been generated successfully
 */
@Override
public void buildEvaluator(Instances data) throws Exception {

  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = data;
  m_classIndex = m_trainInstances.classIndex();
  m_numInstances = m_trainInstances.numInstances();
  Discretize disTransform = new Discretize();
  disTransform.setUseBetterEncoding(true);
  disTransform.setInputFormat(m_trainInstances);
  m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
  m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Initializes a gain ratio attribute evaluator. Discretizes all attributes
 * that are numeric.
 * 
 * @param data set of instances serving as training data
 * @throws Exception if the evaluator has not been generated successfully
 */
@Override
public void buildEvaluator(Instances data) throws Exception {

  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = data;
  m_classIndex = m_trainInstances.classIndex();
  m_numInstances = m_trainInstances.numInstances();
  Discretize disTransform = new Discretize();
  disTransform.setUseBetterEncoding(true);
  disTransform.setInputFormat(m_trainInstances);
  m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
  m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * ensure that all variables are nominal and that there are no missing values
 * 
 * @param instances data set to check and quantize and/or fill in missing
 *          values
 * @return filtered instances
 * @throws Exception if a filter (Discretize, ReplaceMissingValues) fails
 */
protected Instances normalizeDataSet(Instances instances) throws Exception {

  m_nNonDiscreteAttribute = -1;
  Enumeration<Attribute> enu = instances.enumerateAttributes();
  while (enu.hasMoreElements()) {
    Attribute attribute = enu.nextElement();
    if (attribute.type() != Attribute.NOMINAL) {
      m_nNonDiscreteAttribute = attribute.index();
    }
  }

  if ((m_nNonDiscreteAttribute > -1)
    && (instances.attribute(m_nNonDiscreteAttribute).type() != Attribute.NOMINAL)) {
    m_DiscretizeFilter = new Discretize();
    m_DiscretizeFilter.setInputFormat(instances);
    instances = Filter.useFilter(instances, m_DiscretizeFilter);
  }

  m_MissingValuesFilter = new ReplaceMissingValues();
  m_MissingValuesFilter.setInputFormat(instances);
  instances = Filter.useFilter(instances, m_MissingValuesFilter);

  return instances;
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Initializes a symmetrical uncertainty attribute evaluator. 
 * Discretizes all attributes that are numeric.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully
 */
public void buildEvaluator (Instances data)
  throws Exception {

  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = data;
  m_classIndex = m_trainInstances.classIndex();
  m_numAttribs = m_trainInstances.numAttributes();
  m_numInstances = m_trainInstances.numInstances();
  Discretize disTransform = new Discretize();
  disTransform.setUseBetterEncoding(true);
  disTransform.setInputFormat(m_trainInstances);
  m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
  m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Initializes a gain ratio attribute evaluator.
 * Discretizes all attributes that are numeric.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully
 */
public void buildEvaluator (Instances data)
  throws Exception {
  
  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = data;
  m_classIndex = m_trainInstances.classIndex();
  m_numAttribs = m_trainInstances.numAttributes();
  m_numInstances = m_trainInstances.numInstances();
  Discretize disTransform = new Discretize();
  disTransform.setUseBetterEncoding(true);
  disTransform.setInputFormat(m_trainInstances);
  m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
  m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Generates a attribute evaluator. Has to initialize all fields of the 
 * evaluator that are not being set via options.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully
 */
public void buildEvaluator (Instances data) throws Exception {
  
  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = new Instances(data);
  m_trainInstances.deleteWithMissingClass();
  m_classIndex = m_trainInstances.classIndex();
  m_numAttribs = m_trainInstances.numAttributes();
  m_numInstances = m_trainInstances.numInstances();

  m_disTransform = new Discretize();
  m_disTransform.setUseBetterEncoding(true);
  m_disTransform.setInputFormat(m_trainInstances);
  m_trainInstances = Filter.useFilter(m_trainInstances, m_disTransform);
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Build the no-split node
 *
 * @param instances an <code>Instances</code> value
 * @exception Exception if an error occurs
 */
public final void buildClassifier(Instances instances) throws Exception {
  m_nb = new NaiveBayesUpdateable();
  m_disc = new Discretize();
  m_disc.setInputFormat(instances);
  Instances temp = Filter.useFilter(instances, m_disc);
  m_nb.buildClassifier(temp);
  if (temp.numInstances() >= 5) {
    m_errors = crossValidate(m_nb, temp, new Random(1));
  }
  m_numSubsets = 1;
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Generates a attribute evaluator. Has to initialize all fields of the 
 * evaluator that are not being set via options.
 *
 * CFS also discretises attributes (if necessary) and initializes
 * the correlation matrix.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully
 */
public void buildEvaluator (Instances data)
  throws Exception {

  // can evaluator handle data?
  getCapabilities().testWithFail(data);

  m_trainInstances = new Instances(data);
  m_trainInstances.deleteWithMissingClass();
  m_classIndex = m_trainInstances.classIndex();
  m_numAttribs = m_trainInstances.numAttributes();
  m_numInstances = m_trainInstances.numInstances();
  m_isNumeric = m_trainInstances.attribute(m_classIndex).isNumeric();

  if (!m_isNumeric) {
    m_disTransform = new Discretize();
    m_disTransform.setUseBetterEncoding(true);
    m_disTransform.setInputFormat(m_trainInstances);
    m_trainInstances = Filter.useFilter(m_trainInstances, m_disTransform);
  }

  m_std_devs = new double[m_numAttribs];
  m_corr_matrix = new float [m_numAttribs][];
  for (int i = 0; i < m_numAttribs; i++) {
    m_corr_matrix[i] = new float [i+1];
  }

  for (int i = 0; i < m_corr_matrix.length; i++) {
    m_corr_matrix[i][i] = 1.0f;
    m_std_devs[i] = 1.0;
  }

  for (int i = 0; i < m_numAttribs; i++) {
    for (int j = 0; j < m_corr_matrix[i].length - 1; j++) {
      m_corr_matrix[i][j] = -999;
    }
  }
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Creates split on numeric attribute.
 * 
 * @exception Exception if something goes wrong
 */
private void handleNumericAttribute(Instances trainInstances)
  throws Exception {

  m_c45S = new C45Split(m_attIndex, 2, m_sumOfWeights, true);
  m_c45S.buildClassifier(trainInstances);
  if (m_c45S.numSubsets() == 0) {
    return;
  }
  m_errors = 0;

  Instances[] trainingSets = new Instances[m_complexityIndex];
  trainingSets[0] = new Instances(trainInstances, 0);
  trainingSets[1] = new Instances(trainInstances, 0);
  int subset = -1;

  // populate the subsets
  for (int i = 0; i < trainInstances.numInstances(); i++) {
    Instance instance = trainInstances.instance(i);
    subset = m_c45S.whichSubset(instance);
    if (subset != -1) {
      trainingSets[subset].add((Instance) instance.copy());
    } else {
      double[] weights = m_c45S.weights(instance);
      for (int j = 0; j < m_complexityIndex; j++) {
        Instance temp = (Instance) instance.copy();
        if (weights.length == m_complexityIndex) {
          temp.setWeight(temp.weight() * weights[j]);
        } else {
          temp.setWeight(temp.weight() / m_complexityIndex);
        }
        trainingSets[j].add(temp);
      }
    }
  }

  /*
   * // compute weights (weights of instances per subset m_weights = new
   * double [m_complexityIndex]; for (int i = 0; i < m_complexityIndex; i++) {
   * m_weights[i] = trainingSets[i].sumOfWeights(); }
   * Utils.normalize(m_weights);
   */

  Random r = new Random(1);
  int minNumCount = 0;
  for (int i = 0; i < m_complexityIndex; i++) {
    if (trainingSets[i].numInstances() > 5) {
      minNumCount++;
      // Discretize the sets
      Discretize disc = new Discretize();
      disc.setInputFormat(trainingSets[i]);
      trainingSets[i] = Filter.useFilter(trainingSets[i], disc);

      trainingSets[i].randomize(r);
      trainingSets[i].stratify(5);
      NaiveBayesUpdateable fullModel = new NaiveBayesUpdateable();
      fullModel.buildClassifier(trainingSets[i]);

      // add the errors for this branch of the split
      m_errors += NBTreeNoSplit.crossValidate(fullModel, trainingSets[i], r);
    } else {
      for (int j = 0; j < trainingSets[i].numInstances(); j++) {
        m_errors += trainingSets[i].instance(j).weight();
      }
    }
  }

  // Check if minimum number of Instances in at least two
  // subsets.
  if (minNumCount > 1) {
    m_numSubsets = m_complexityIndex;
  }
}
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
  * Creates split on numeric attribute.
  *
  * @exception Exception if something goes wrong
  */
 private void handleNumericAttribute(Instances trainInstances)
      throws Exception {

   m_c45S = new C45Split(m_attIndex, 2, m_sumOfWeights, true);
   m_c45S.buildClassifier(trainInstances);
   if (m_c45S.numSubsets() == 0) {
     return;
   }
   m_errors = 0;

   Instances [] trainingSets = new Instances [m_complexityIndex];
   trainingSets[0] = new Instances(trainInstances, 0);
   trainingSets[1] = new Instances(trainInstances, 0);
   int subset = -1;
   
   // populate the subsets
   for (int i = 0; i < trainInstances.numInstances(); i++) {
     Instance instance = trainInstances.instance(i);
     subset = m_c45S.whichSubset(instance);
     if (subset != -1) {
trainingSets[subset].add((Instance)instance.copy());
     } else {
double [] weights = m_c45S.weights(instance);
for (int j = 0; j < m_complexityIndex; j++) {
  Instance temp = (Instance)instance.copy();
  if (weights.length == m_complexityIndex) {
    temp.setWeight(temp.weight() * weights[j]);
  } else {
    temp.setWeight(temp.weight() / m_complexityIndex);
  }
  trainingSets[j].add(temp); 
}
     }
   }
   
   /*    // compute weights (weights of instances per subset
   m_weights = new double [m_complexityIndex];
   for (int i = 0; i < m_complexityIndex; i++) {
     m_weights[i] = trainingSets[i].sumOfWeights();
   }
   Utils.normalize(m_weights); */

   Random r = new Random(1);
   int minNumCount = 0;
   for (int i = 0; i < m_complexityIndex; i++) {
     if (trainingSets[i].numInstances() > 5) {
minNumCount++;
// Discretize the sets
	Discretize disc = new Discretize();
disc.setInputFormat(trainingSets[i]);
trainingSets[i] = Filter.useFilter(trainingSets[i], disc);

trainingSets[i].randomize(r);
trainingSets[i].stratify(5);
NaiveBayesUpdateable fullModel = new NaiveBayesUpdateable();
fullModel.buildClassifier(trainingSets[i]);

// add the errors for this branch of the split
m_errors += NBTreeNoSplit.crossValidate(fullModel, trainingSets[i], r);
     } else {
for (int j = 0; j < trainingSets[i].numInstances(); j++) {
  m_errors += trainingSets[i].instance(j).weight();
}
     }
   }
   
   // Check if minimum number of Instances in at least two
   // subsets.
   if (minNumCount > 1) {
     m_numSubsets = m_complexityIndex;
   }
 }
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
  * Creates split on numeric attribute.
  *
  * @exception Exception if something goes wrong
  */
 private void handleNumericAttribute(Instances trainInstances)
      throws Exception {

   m_c45S = new C45Split(m_attIndex, 2, m_sumOfWeights);
   m_c45S.buildClassifier(trainInstances);
   if (m_c45S.numSubsets() == 0) {
     return;
   }
   m_errors = 0;

   Instances [] trainingSets = new Instances [m_complexityIndex];
   trainingSets[0] = new Instances(trainInstances, 0);
   trainingSets[1] = new Instances(trainInstances, 0);
   int subset = -1;
   
   // populate the subsets
   for (int i = 0; i < trainInstances.numInstances(); i++) {
     Instance instance = trainInstances.instance(i);
     subset = m_c45S.whichSubset(instance);
     if (subset != -1) {
trainingSets[subset].add((Instance)instance.copy());
     } else {
double [] weights = m_c45S.weights(instance);
for (int j = 0; j < m_complexityIndex; j++) {
  Instance temp = (Instance)instance.copy();
  if (weights.length == m_complexityIndex) {
    temp.setWeight(temp.weight() * weights[j]);
  } else {
    temp.setWeight(temp.weight() / m_complexityIndex);
  }
  trainingSets[j].add(temp); 
}
     }
   }
   
   /*    // compute weights (weights of instances per subset
   m_weights = new double [m_complexityIndex];
   for (int i = 0; i < m_complexityIndex; i++) {
     m_weights[i] = trainingSets[i].sumOfWeights();
   }
   Utils.normalize(m_weights); */

   Random r = new Random(1);
   int minNumCount = 0;
   for (int i = 0; i < m_complexityIndex; i++) {
     if (trainingSets[i].numInstances() > 5) {
minNumCount++;
// Discretize the sets
	Discretize disc = new Discretize();
disc.setInputFormat(trainingSets[i]);
trainingSets[i] = Filter.useFilter(trainingSets[i], disc);

trainingSets[i].randomize(r);
trainingSets[i].stratify(5);
NaiveBayesUpdateable fullModel = new NaiveBayesUpdateable();
fullModel.buildClassifier(trainingSets[i]);

// add the errors for this branch of the split
m_errors += NBTreeNoSplit.crossValidate(fullModel, trainingSets[i], r);
     } else {
for (int j = 0; j < trainingSets[i].numInstances(); j++) {
  m_errors += trainingSets[i].instance(j).weight();
}
     }
   }
   
   // Check if minimum number of Instances in at least two
   // subsets.
   if (minNumCount > 1) {
     m_numSubsets = m_complexityIndex;
   }
 }
 

import weka.filters.supervised.attribute.Discretize; //导入依赖的package包/类
/**
 * Return the discretizer used at this node
 *
 * @return a <code>Discretize</code> value
 */
public Discretize getDiscretizer() {
  return m_disc;
}