Beispiel #1
0
 /**
  * Compute the JS divergence between an instance and a cluster, used for training data
  *
  * @param instIdx index of the instance
  * @param input statistics of the input data
  * @param T the whole partition
  * @param t index of the cluster
  * @param pi1
  * @param pi2
  * @return the JS divergence
  */
 private double JS(int instIdx, Input input, Partition T, int t, double pi1, double pi2) {
   if (Math.min(pi1, pi2) <= 0) {
     System.out.format(
         "Warning: zero or negative weights in JS calculation! (pi1 %s, pi2 %s)\n", pi1, pi2);
     return 0;
   }
   Instance inst = m_data.instance(instIdx);
   double kl1 = 0.0, kl2 = 0.0, tmp = 0.0;
   for (int i = 0; i < inst.numValues(); i++) {
     tmp = input.Py_x.get(inst.index(i), instIdx);
     if (tmp != 0) {
       kl1 += tmp * Math.log(tmp / (tmp * pi1 + pi2 * T.Py_t.get(inst.index(i), t)));
     }
   }
   for (int i = 0; i < m_numAttributes; i++) {
     if ((tmp = T.Py_t.get(i, t)) != 0) {
       kl2 += tmp * Math.log(tmp / (input.Py_x.get(i, instIdx) * pi1 + pi2 * tmp));
     }
   }
   return pi1 * kl1 + pi2 * kl2;
 }
Beispiel #2
0
  /**
   * Put an instance into a new cluster and update.
   *
   * @param instIdx instance to be updated
   * @param newt index of the new cluster this instance has been assigned to
   * @param T the current working partition
   * @param Px an array of prior probabilities of the instances
   */
  private void updateAssignment(int instIdx, int newt, Partition T, double Px, Matrix Py_x) {
    T.Pt_x[instIdx] = newt;

    // update probability of attributes in the cluster
    double mass = Px + T.Pt[newt];
    double pi1 = Px / mass;
    double pi2 = T.Pt[newt] / mass;
    for (int i = 0; i < m_numAttributes; i++) {
      T.Py_t.set(i, newt, pi1 * Py_x.get(i, instIdx) + pi2 * T.Py_t.get(i, newt));
    }

    T.Pt[newt] = mass;
  }