Ejemplo n.º 1
0
  private double pValue(Node node, List<Node> parents) {
    List<Double> _residuals = new ArrayList<Double>();

    Node _target = node;
    List<Node> _regressors = parents;
    Node target = getVariable(variables, _target.getName());
    List<Node> regressors = new ArrayList<Node>();

    for (Node _regressor : _regressors) {
      Node variable = getVariable(variables, _regressor.getName());
      regressors.add(variable);
    }

    DATASET:
    for (int m = 0; m < dataSets.size(); m++) {
      RegressionResult result = regressions.get(m).regress(target, regressors);
      TetradVector residualsSingleDataset = result.getResiduals();

      for (int h = 0; h < residualsSingleDataset.size(); h++) {
        if (Double.isNaN(residualsSingleDataset.get(h))) {
          continue DATASET;
        }
      }

      DoubleArrayList _residualsSingleDataset =
          new DoubleArrayList(residualsSingleDataset.toArray());

      double mean = Descriptive.mean(_residualsSingleDataset);
      double std =
          Descriptive.standardDeviation(
              Descriptive.variance(
                  _residualsSingleDataset.size(),
                  Descriptive.sum(_residualsSingleDataset),
                  Descriptive.sumOfSquares(_residualsSingleDataset)));

      for (int i2 = 0; i2 < _residualsSingleDataset.size(); i2++) {
        //                _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2) - mean) /
        // std);
        if (isMeanCenterResiduals()) {
          _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2) - mean));
        }
        //                _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2)));
      }

      for (int k = 0; k < _residualsSingleDataset.size(); k++) {
        _residuals.add(_residualsSingleDataset.get(k));
      }
    }

    double[] _f = new double[_residuals.size()];

    for (int k = 0; k < _residuals.size(); k++) {
      _f[k] = _residuals.get(k);
    }

    return new AndersonDarlingTest(_f).getP();
  }
  private double[] dependencePvalsLinear(Node x, Node y, List<Node> z) {
    if (!variablesPerNode.containsKey(x)) {
      throw new IllegalArgumentException("Unrecogized node: " + x);
    }

    if (!variablesPerNode.containsKey(y)) {
      throw new IllegalArgumentException("Unrecogized node: " + y);
    }

    for (Node node : z) {
      if (!variablesPerNode.containsKey(node)) {
        throw new IllegalArgumentException("Unrecogized node: " + node);
      }
    }

    List<Node> yzDumList = new ArrayList<>();
    List<Node> yzList = new ArrayList<>();
    yzList.add(y);
    yzList.addAll(z);
    // List<Node> zList = new ArrayList<>();

    yzDumList.addAll(variablesPerNode.get(y));
    for (Node _z : z) {
      yzDumList.addAll(variablesPerNode.get(_z));
      // zList.addAll(variablesPerNode.get(_z));
    }

    int[] _rows = getNonMissingRows(x, y, z);
    regression.setRows(_rows);

    RegressionResult result;

    try {
      result = regression.regress(x, yzDumList);
    } catch (Exception e) {
      return null;
    }

    double[] pVec = new double[yzList.size()];
    double[] pCoef = result.getP();

    // skip intercept at 0
    int coeffInd = 1;

    for (int i = 0; i < pVec.length; i++) {
      List<Node> curDummy = variablesPerNode.get(yzList.get(i));
      if (curDummy.size() == 1) {
        pVec[i] = pCoef[coeffInd];
        coeffInd++;
        continue;
      } else {
        pVec[i] = 0;
      }

      for (Node n : curDummy) {
        pVec[i] += Math.log(pCoef[coeffInd]);
        coeffInd++;
      }

      if (pVec[i] == Double.NEGATIVE_INFINITY) pVec[i] = 0.0;
      else
        pVec[i] =
            1.0
                - new ChiSquaredDistribution(2 * curDummy.size())
                    .cumulativeProbability(-2 * pVec[i]);
    }

    return pVec;
  }
Ejemplo n.º 3
0
  private double andersonDarlingPASquareStarB(Node node, List<Node> parents) {
    List<Double> _residuals = new ArrayList<Double>();

    Node _target = node;
    List<Node> _regressors = parents;
    Node target = getVariable(variables, _target.getName());
    List<Node> regressors = new ArrayList<Node>();

    for (Node _regressor : _regressors) {
      Node variable = getVariable(variables, _regressor.getName());
      regressors.add(variable);
    }

    double sum = 0.0;

    DATASET:
    for (int m = 0; m < dataSets.size(); m++) {
      RegressionResult result = regressions.get(m).regress(target, regressors);
      TetradVector residualsSingleDataset = result.getResiduals();

      for (int h = 0; h < residualsSingleDataset.size(); h++) {
        if (Double.isNaN(residualsSingleDataset.get(h))) {
          continue DATASET;
        }
      }

      DoubleArrayList _residualsSingleDataset =
          new DoubleArrayList(residualsSingleDataset.toArray());

      double mean = Descriptive.mean(_residualsSingleDataset);
      double std =
          Descriptive.standardDeviation(
              Descriptive.variance(
                  _residualsSingleDataset.size(),
                  Descriptive.sum(_residualsSingleDataset),
                  Descriptive.sumOfSquares(_residualsSingleDataset)));

      // By centering the individual residual columns, all moments of the mixture become weighted
      // averages of the moments
      // of the individual columns.
      // http://en.wikipedia.org/wiki/Mixture_distribution#Finite_and_countable_mixtures
      for (int i2 = 0; i2 < _residualsSingleDataset.size(); i2++) {
        //                _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2) - mean) /
        // std);
        //                _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2)) / std);
        if (isMeanCenterResiduals()) {
          _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2) - mean));
        }
      }

      double[] _f = new double[_residuals.size()];

      for (int k = 0; k < _residuals.size(); k++) {
        _f[k] = _residuals.get(k);
      }

      sum += new AndersonDarlingTest(_f).getASquaredStar();
    }

    return sum / dataSets.size();
  }
Ejemplo n.º 4
0
  private double localScoreB(Node node, List<Node> parents) {

    double score = 0.0;
    double maxScore = Double.NEGATIVE_INFINITY;

    Node _target = node;
    List<Node> _regressors = parents;
    Node target = getVariable(variables, _target.getName());
    List<Node> regressors = new ArrayList<Node>();

    for (Node _regressor : _regressors) {
      Node variable = getVariable(variables, _regressor.getName());
      regressors.add(variable);
    }

    DATASET:
    for (int m = 0; m < dataSets.size(); m++) {
      RegressionResult result = regressions.get(m).regress(target, regressors);
      TetradVector residualsSingleDataset = result.getResiduals();
      DoubleArrayList _residualsSingleDataset =
          new DoubleArrayList(residualsSingleDataset.toArray());

      for (int h = 0; h < residualsSingleDataset.size(); h++) {
        if (Double.isNaN(residualsSingleDataset.get(h))) {
          continue DATASET;
        }
      }

      double mean = Descriptive.mean(_residualsSingleDataset);
      double std =
          Descriptive.standardDeviation(
              Descriptive.variance(
                  _residualsSingleDataset.size(),
                  Descriptive.sum(_residualsSingleDataset),
                  Descriptive.sumOfSquares(_residualsSingleDataset)));

      for (int i2 = 0; i2 < _residualsSingleDataset.size(); i2++) {
        _residualsSingleDataset.set(i2, (_residualsSingleDataset.get(i2) - mean) / std);
      }

      double[] _f = new double[_residualsSingleDataset.size()];

      for (int k = 0; k < _residualsSingleDataset.size(); k++) {
        _f[k] = _residualsSingleDataset.get(k);
      }

      DoubleArrayList f = new DoubleArrayList(_f);

      for (int k = 0; k < f.size(); k++) {
        f.set(k, Math.abs(f.get(k)));
      }

      double _mean = Descriptive.mean(f);
      double diff = _mean - Math.sqrt(2.0 / Math.PI);
      score += diff * diff;

      if (score > maxScore) {
        maxScore = score;
      }
    }

    double avg = score / dataSets.size();

    return avg;
  }