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(); }
public Lofs(Graph pattern, List<DataSet> dataSets) throws IllegalArgumentException { if (pattern == null) { throw new IllegalArgumentException("Pattern must be specified."); } if (dataSets == null) { throw new IllegalArgumentException("Data set must be specified."); } this.pattern = pattern; this.dataSets = dataSets; regressions = new ArrayList<Regression>(); this.variables = dataSets.get(0).getVariables(); for (DataSet dataSet : dataSets) { regressions.add(new RegressionDataset(dataSet)); } }
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(); }
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; }