/**
* Calculates the sample likelihood and BIC score for i given its parents in a simple SEM model.
*/
private double localSemScore(int i, int[] parents) {
try {
ICovarianceMatrix cov = getCovMatrix();
double varianceY = cov.getValue(i, i);
double residualVariance = varianceY;
int n = sampleSize();
int p = parents.length;
int k = (p * (p + 1)) / 2 + p;
// int k = (p + 1) * (p + 1);
// int k = p + 1;
TetradMatrix covxx = cov.getSelection(parents, parents);
TetradMatrix covxxInv = covxx.inverse();
TetradVector covxy = cov.getSelection(parents, new int[] {i}).getColumn(0);
TetradVector b = covxxInv.times(covxy);
residualVariance -= covxy.dotProduct(b);
if (residualVariance <= 0 && verbose) {
out.println(
"Nonpositive residual varianceY: resVar / varianceY = "
+ (residualVariance / varianceY));
return Double.NaN;
}
double c = getPenaltyDiscount();
// return -n * log(residualVariance) - 2 * k; //AIC
return -n * Math.log(residualVariance) - c * k * Math.log(n);
// return -n * log(residualVariance) - c * k * (log(n) - log(2 * PI));
} catch (Exception e) {
e.printStackTrace();
throw new RuntimeException(e);
// throwMinimalLinearDependentSet(parents, cov);
}
}
public void rtest4() {
System.out.println("SHD\tP");
// System.out.println("MB1\tMB2\tMB3\tMB4\tMB5\tMB6");
Graph mim = DataGraphUtils.randomSingleFactorModel(5, 5, 8, 0, 0, 0);
Graph mimStructure = structure(mim);
SemPm pm = new SemPm(mim);
SemImInitializationParams params = new SemImInitializationParams();
params.setCoefRange(0.5, 1.5);
NumberFormat nf = new DecimalFormat("0.0000");
int totalError = 0;
int errorCount = 0;
int maxScore = 0;
int maxNumMeasures = 0;
double maxP = 0.0;
for (int r = 0; r < 1; r++) {
SemIm im = new SemIm(pm, params);
DataSet data = im.simulateData(1000, false);
mim = GraphUtils.replaceNodes(mim, data.getVariables());
List<List<Node>> trueClusters = MimUtils.convertToClusters2(mim);
CovarianceMatrix _cov = new CovarianceMatrix(data);
ICovarianceMatrix cov = DataUtils.reorderColumns(_cov);
String algorithm = "FOFC";
Graph searchGraph;
List<List<Node>> partition;
if (algorithm.equals("FOFC")) {
FindOneFactorClusters fofc =
new FindOneFactorClusters(cov, TestType.TETRAD_WISHART, 0.001f);
searchGraph = fofc.search();
searchGraph = GraphUtils.replaceNodes(searchGraph, data.getVariables());
partition = MimUtils.convertToClusters2(searchGraph);
} else if (algorithm.equals("BPC")) {
TestType testType = TestType.TETRAD_WISHART;
TestType purifyType = TestType.TETRAD_BASED2;
BuildPureClusters bpc = new BuildPureClusters(data, 0.001, testType, purifyType);
searchGraph = bpc.search();
partition = MimUtils.convertToClusters2(searchGraph);
} else {
throw new IllegalStateException();
}
mimStructure = GraphUtils.replaceNodes(mimStructure, data.getVariables());
List<String> latentVarList = reidentifyVariables(mim, data, partition, 2);
Graph mimbuildStructure;
Mimbuild2 mimbuild = new Mimbuild2();
mimbuild.setAlpha(0.001);
mimbuild.setMinClusterSize(3);
try {
mimbuildStructure = mimbuild.search(partition, latentVarList, cov);
} catch (Exception e) {
e.printStackTrace();
continue;
}
mimbuildStructure = GraphUtils.replaceNodes(mimbuildStructure, data.getVariables());
mimbuildStructure = condense(mimStructure, mimbuildStructure);
// Graph mimSubgraph = new EdgeListGraph(mimStructure);
//
// for (Node node : mimSubgraph.getNodes()) {
// if (!mimStructure.getNodes().contains(node)) {
// mimSubgraph.removeNode(node);
// }
// }
int shd = SearchGraphUtils.structuralHammingDistance(mimStructure, mimbuildStructure);
boolean impureCluster = containsImpureCluster(partition, trueClusters);
double pValue = mimbuild.getpValue();
boolean pBelow05 = pValue < 0.05;
boolean numClustersGreaterThan5 = partition.size() != 5;
boolean error = false;
// boolean condition = impureCluster || numClustersGreaterThan5 || pBelow05;
// boolean condition = numClustersGreaterThan5 || pBelow05;
boolean condition = numClustered(partition) == 40;
if (!condition && (shd > 5)) {
error = true;
}
if (!condition) {
totalError += shd;
errorCount++;
}
// if (numClustered(partition) > maxNumMeasures) {
// maxNumMeasures = numClustered(partition);
// maxP = pValue;
// maxScore = shd;
// System.out.println("maxNumMeasures = " + maxNumMeasures);
// System.out.println("maxScore = " + maxScore);
// System.out.println("maxP = " + maxP);
// System.out.println("clusters = " + clusterSizes(partition, trueClusters));
// }
// else
if (pValue > maxP) {
maxScore = shd;
maxP = mimbuild.getpValue();
maxNumMeasures = numClustered(partition);
System.out.println("maxNumMeasures = " + maxNumMeasures);
System.out.println("maxScore = " + maxScore);
System.out.println("maxP = " + maxP);
System.out.println("clusters = " + clusterSizes(partition, trueClusters));
}
System.out.print(
shd
+ "\t"
+ nf.format(pValue)
+ " "
// + (error ? 1 : 0) + " "
// + (pBelow05 ? "P < 0.05 " : "")
// + (impureCluster ? "Impure cluster " : "")
// + (numClustersGreaterThan5 ? "# Clusters != 5 " : "")
// + clusterSizes(partition, trueClusters)
+ numClustered(partition));
System.out.println();
}
System.out.println("\nAvg SHD for not-flagged cases = " + (totalError / (double) errorCount));
System.out.println("maxNumMeasures = " + maxNumMeasures);
System.out.println("maxScore = " + maxScore);
System.out.println("maxP = " + maxP);
}