@Test
public void test2() {
RandomUtil.getInstance().setSeed(2999983L);
int sampleSize = 1000;
List<Node> variableNodes = new ArrayList<>();
ContinuousVariable x1 = new ContinuousVariable("X1");
ContinuousVariable x2 = new ContinuousVariable("X2");
ContinuousVariable x3 = new ContinuousVariable("X3");
ContinuousVariable x4 = new ContinuousVariable("X4");
ContinuousVariable x5 = new ContinuousVariable("X5");
variableNodes.add(x1);
variableNodes.add(x2);
variableNodes.add(x3);
variableNodes.add(x4);
variableNodes.add(x5);
Graph _graph = new EdgeListGraph(variableNodes);
SemGraph graph = new SemGraph(_graph);
graph.addDirectedEdge(x1, x3);
graph.addDirectedEdge(x2, x3);
graph.addDirectedEdge(x3, x4);
graph.addDirectedEdge(x2, x4);
graph.addDirectedEdge(x4, x5);
graph.addDirectedEdge(x2, x5);
SemPm semPm = new SemPm(graph);
SemIm semIm = new SemIm(semPm);
DataSet dataSet = semIm.simulateData(sampleSize, false);
print(semPm);
GeneralizedSemPm _semPm = new GeneralizedSemPm(semPm);
GeneralizedSemIm _semIm = new GeneralizedSemIm(_semPm, semIm);
DataSet _dataSet = _semIm.simulateDataMinimizeSurface(sampleSize, false);
print(_semPm);
// System.out.println(_dataSet);
for (int j = 0; j < dataSet.getNumColumns(); j++) {
double[] col = dataSet.getDoubleData().getColumn(j).toArray();
double[] _col = _dataSet.getDoubleData().getColumn(j).toArray();
double mean = StatUtils.mean(col);
double _mean = StatUtils.mean(_col);
double variance = StatUtils.variance(col);
double _variance = StatUtils.variance(_col);
assertEquals(mean, _mean, 0.3);
assertEquals(1.0, variance / _variance, .2);
}
}
private double score(Node y, List<Node> parents) {
if (score == Score.andersonDarling) {
return andersonDarlingPASquareStar(y, parents);
} else if (score == Score.kurtosis) {
return Math.abs(StatUtils.kurtosis(residual(y, parents)));
} else if (score == Score.skew) {
return Math.abs(StatUtils.skewness(residual(y, parents)));
} else if (score == Score.fifthMoment) {
return Math.abs(StatUtils.standardizedFifthMoment(residual(y, parents)));
} else if (score == Score.absoluteValue) {
return localScoreA(y, parents);
}
throw new IllegalStateException();
}
public boolean isIndependent(Node x, Node y, List<Node> z) {
int[] all = new int[z.size() + 2];
all[0] = variablesMap.get(x);
all[1] = variablesMap.get(y);
for (int i = 0; i < z.size(); i++) {
all[i + 2] = variablesMap.get(z.get(i));
}
int sampleSize = data.get(0).rows();
List<Double> pValues = new ArrayList<Double>();
for (int m = 0; m < ncov.size(); m++) {
TetradMatrix _ncov = ncov.get(m).getSelection(all, all);
TetradMatrix inv = _ncov.inverse();
double r = -inv.get(0, 1) / sqrt(inv.get(0, 0) * inv.get(1, 1));
double fisherZ =
sqrt(sampleSize - z.size() - 3.0) * 0.5 * (Math.log(1.0 + r) - Math.log(1.0 - r));
double pValue;
if (Double.isInfinite(fisherZ)) {
pValue = 0;
} else {
pValue = 2.0 * (1.0 - RandomUtil.getInstance().normalCdf(0, 1, abs(fisherZ)));
}
pValues.add(pValue);
}
double _cutoff = alpha;
if (fdr) {
_cutoff = StatUtils.fdrCutoff(alpha, pValues, false);
}
Collections.sort(pValues);
int index = (int) round((1.0 - percent) * pValues.size());
this.pValue = pValues.get(index);
// if (this.pValue == 0) {
// System.out.println("Zero pvalue "+ SearchLogUtils.independenceFactMsg(x, y, z,
// getPValue()));
// }
boolean independent = this.pValue > _cutoff;
if (verbose) {
if (independent) {
TetradLogger.getInstance()
.log("independencies", SearchLogUtils.independenceFactMsg(x, y, z, getPValue()));
// System.out.println(SearchLogUtils.independenceFactMsg(x, y, z, getPValue()));
} else {
TetradLogger.getInstance()
.log("dependencies", SearchLogUtils.dependenceFactMsg(x, y, z, getPValue()));
}
}
return independent;
}
/**
* Determines whether variable x is independent of variable y given a list of conditioning
* variables z.
*
* @param x the one variable being compared.
* @param y the second variable being compared.
* @param z the list of conditioning variables.
* @return true iff x _||_ y | z.
* @throws RuntimeException if a matrix singularity is encountered.
*/
public boolean isIndependent(Node x, Node y, List<Node> z) {
TetradMatrix submatrix = subMatrix(x, y, z);
double r = 0;
try {
r = StatUtils.partialCorrelation(submatrix);
if (Double.isNaN((r)) || r < -1. || r > 1.) throw new RuntimeException();
} catch (Exception e) {
DepthChoiceGenerator gen = new DepthChoiceGenerator(z.size(), z.size());
int[] choice;
while ((choice = gen.next()) != null) {
try {
List<Node> z2 = new ArrayList<Node>(z);
z2.removeAll(GraphUtils.asList(choice, z));
submatrix = subMatrix(x, y, z2);
r = StatUtils.partialCorrelation(submatrix);
} catch (Exception e2) {
continue;
}
// if (Double.isNaN(r)) continue;
//
// if (r > 1.) r = 1.;
// if (r < -1.) r = -1.;
if (Double.isNaN(r) || r < -1. || r > 1.) continue;
break;
}
}
// Either dividing by a zero standard deviation (in which case it's dependent) or doing a
// regression
// (effectively) with a multicolliarity
if (Double.isNaN(r)) {
int[] _z = new int[z.size()];
// for (int i = 0; i < _z.length; i++) _z[i] = i + 2;
//
//// double varx = StatUtils.partialVariance(submatrix, 0, _z); // submatrix.get(0,
// 0);
//// double vary = StatUtils.partialVariance(submatrix, 1, _z); //submatrix.get(1,
// 1);
//
// double varx = submatrix.get(0, 0);
// double vary = submatrix.get(1, 1);
//
// if (varx * vary == 0) {
return true;
// }
}
if (r > 1.) r = 1.;
if (r < -1.) r = -1.;
this.fisherZ =
Math.sqrt(sampleSize() - z.size() - 3.0) * 0.5 * (Math.log(1.0 + r) - Math.log(1.0 - r));
if (Double.isNaN(this.fisherZ)) {
throw new IllegalArgumentException(
"The Fisher's Z "
+ "score for independence fact "
+ x
+ " _||_ "
+ y
+ " | "
+ z
+ " is undefined. r = "
+ r);
}
boolean independent = getPValue() > alpha;
if (independent) {
TetradLogger.getInstance()
.log("independencies", SearchLogUtils.independenceFactMsg(x, y, z, getPValue()));
} else {
TetradLogger.getInstance()
.log("dependencies", SearchLogUtils.dependenceFactMsg(x, y, z, getPValue()));
}
return independent;
}
@Test
public void testHistogram() {
RandomUtil.getInstance().setSeed(4829384L);
List<Node> nodes = new ArrayList<Node>();
for (int i = 0; i < 5; i++) {
nodes.add(new ContinuousVariable("X" + (i + 1)));
}
Dag trueGraph = new Dag(GraphUtils.randomGraph(nodes, 0, 5, 30, 15, 15, false));
int sampleSize = 1000;
// Continuous
SemPm semPm = new SemPm(trueGraph);
SemIm semIm = new SemIm(semPm);
DataSet data = semIm.simulateData(sampleSize, false);
Histogram histogram = new Histogram(data);
histogram.setTarget("X1");
histogram.setNumBins(20);
assertEquals(3.76, histogram.getMax(), 0.01);
assertEquals(-3.83, histogram.getMin(), 0.01);
assertEquals(1000, histogram.getN());
histogram.setTarget("X1");
histogram.setNumBins(10);
histogram.addConditioningVariable("X3", 0, 1);
histogram.addConditioningVariable("X4", 0, 1);
histogram.removeConditioningVariable("X3");
assertEquals(3.76, histogram.getMax(), 0.01);
assertEquals(-3.83, histogram.getMin(), 0.01);
assertEquals(188, histogram.getN());
double[] arr = histogram.getContinuousData("X2");
histogram.addConditioningVariable("X2", StatUtils.min(arr), StatUtils.mean(arr));
// Discrete
BayesPm bayesPm = new BayesPm(trueGraph);
BayesIm bayesIm = new MlBayesIm(bayesPm, MlBayesIm.RANDOM);
DataSet data2 = bayesIm.simulateData(sampleSize, false);
// For some reason these are giving different
// values when all of the unit tests are run are
// once. TODO They produce stable values when
// this particular test is run repeatedly.
Histogram histogram2 = new Histogram(data2);
histogram2.setTarget("X1");
int[] frequencies1 = histogram2.getFrequencies();
// assertEquals(928, frequencies1[0]);
// assertEquals(72, frequencies1[1]);
histogram2.setTarget("X1");
histogram2.addConditioningVariable("X2", 0);
histogram2.addConditioningVariable("X3", 1);
int[] frequencies = histogram2.getFrequencies();
// assertEquals(377, frequencies[0]);
// assertEquals(28, frequencies[1]);
}
@Test
public void test3() {
RandomUtil.getInstance().setSeed(49293843L);
List<Node> variableNodes = new ArrayList<>();
ContinuousVariable x1 = new ContinuousVariable("X1");
ContinuousVariable x2 = new ContinuousVariable("X2");
ContinuousVariable x3 = new ContinuousVariable("X3");
ContinuousVariable x4 = new ContinuousVariable("X4");
ContinuousVariable x5 = new ContinuousVariable("X5");
variableNodes.add(x1);
variableNodes.add(x2);
variableNodes.add(x3);
variableNodes.add(x4);
variableNodes.add(x5);
Graph _graph = new EdgeListGraph(variableNodes);
SemGraph graph = new SemGraph(_graph);
graph.setShowErrorTerms(true);
Node e1 = graph.getExogenous(x1);
Node e2 = graph.getExogenous(x2);
Node e3 = graph.getExogenous(x3);
Node e4 = graph.getExogenous(x4);
Node e5 = graph.getExogenous(x5);
graph.addDirectedEdge(x1, x3);
graph.addDirectedEdge(x1, x2);
graph.addDirectedEdge(x2, x3);
graph.addDirectedEdge(x3, x4);
graph.addDirectedEdge(x2, x4);
graph.addDirectedEdge(x4, x5);
graph.addDirectedEdge(x2, x5);
graph.addDirectedEdge(x5, x1);
GeneralizedSemPm pm = new GeneralizedSemPm(graph);
List<Node> variablesNodes = pm.getVariableNodes();
print(variablesNodes);
List<Node> errorNodes = pm.getErrorNodes();
print(errorNodes);
try {
pm.setNodeExpression(x1, "cos(b1) + a1 * X5 + E_X1");
pm.setNodeExpression(x2, "a2 * X1 + E_X2");
pm.setNodeExpression(x3, "tan(a3*X2 + a4*X1) + E_X3");
pm.setNodeExpression(x4, "0.1 * E^X2 + X3 + E_X4");
pm.setNodeExpression(x5, "0.1 * E^X4 + a6* X2 + E_X5");
pm.setNodeExpression(e1, "U(0, 1)");
pm.setNodeExpression(e2, "U(0, 1)");
pm.setNodeExpression(e3, "U(0, 1)");
pm.setNodeExpression(e4, "U(0, 1)");
pm.setNodeExpression(e5, "U(0, 1)");
GeneralizedSemIm im = new GeneralizedSemIm(pm);
print(im);
DataSet dataSet = im.simulateDataNSteps(1000, false);
// System.out.println(dataSet);
double[] d1 = dataSet.getDoubleData().getColumn(0).toArray();
double[] d2 = dataSet.getDoubleData().getColumn(1).toArray();
double cov = StatUtils.covariance(d1, d2);
assertEquals(-0.002, cov, 0.001);
} catch (ParseException e) {
e.printStackTrace();
}
}
