private List<String> getNames(List<Node> nodes) {
List<String> names = new ArrayList<String>();
for (Node node : nodes) {
names.add(node.getName());
}
return names;
}
private Graph condense(Graph mimStructure, Graph mimbuildStructure) {
// System.out.println("Uncondensed: " + mimbuildStructure);
Map<Node, Node> substitutions = new HashMap<Node, Node>();
for (Node node : mimbuildStructure.getNodes()) {
for (Node _node : mimStructure.getNodes()) {
if (node.getName().startsWith(_node.getName())) {
substitutions.put(node, _node);
break;
}
substitutions.put(node, node);
}
}
HashSet<Node> nodes = new HashSet<Node>(substitutions.values());
Graph graph = new EdgeListGraph(new ArrayList<Node>(nodes));
for (Edge edge : mimbuildStructure.getEdges()) {
Node node1 = substitutions.get(edge.getNode1());
Node node2 = substitutions.get(edge.getNode2());
if (node1 == node2) continue;
if (graph.isAdjacentTo(node1, node2)) continue;
graph.addEdge(new Edge(node1, node2, edge.getEndpoint1(), edge.getEndpoint2()));
}
// System.out.println("Condensed: " + graph);
return graph;
}
private Graph changeLatentNames(Graph full, Clusters measurements, List<String> latentVarList) {
Graph g2 = null;
try {
g2 = (Graph) new MarshalledObject(full).get();
} catch (IOException e) {
e.printStackTrace();
} catch (ClassNotFoundException e) {
e.printStackTrace();
}
for (int i = 0; i < measurements.getNumClusters(); i++) {
List<String> d = measurements.getCluster(i);
String latentName = latentVarList.get(i);
for (Node node : full.getNodes()) {
if (!(node.getNodeType() == NodeType.LATENT)) {
continue;
}
List<Node> _children = full.getChildren(node);
_children.removeAll(ReidentifyVariables.getLatents(full));
List<String> childNames = getNames(_children);
if (new HashSet<String>(childNames).equals(new HashSet<String>(d))) {
g2.getNode(node.getName()).setName(latentName);
}
}
}
return g2;
}
private void calculateArrowsForward(Node x, Node y, Graph graph) {
clearArrow(x, y);
if (!knowledgeEmpty()) {
if (getKnowledge().isForbidden(x.getName(), y.getName())) {
return;
}
}
List<Node> naYX = getNaYX(x, y, graph);
List<Node> t = getTNeighbors(x, y, graph);
DepthChoiceGenerator gen = new DepthChoiceGenerator(t.size(), t.size());
int[] choice;
while ((choice = gen.next()) != null) {
List<Node> s = GraphUtils.asList(choice, t);
if (!knowledgeEmpty()) {
if (!validSetByKnowledge(y, s)) {
continue;
}
}
double bump = insertEval(x, y, s, naYX, graph);
if (bump > 0.0) {
Arrow arrow = new Arrow(bump, x, y, s, naYX);
sortedArrows.add(arrow);
addLookupArrow(x, y, arrow);
}
}
}
/**
* Use background knowledge to decide if an insert or delete operation does not orient edges in a
* forbidden direction according to prior knowledge. If some orientation is forbidden in the
* subset, the whole subset is forbidden.
*/
private boolean validSetByKnowledge(Node y, List<Node> subset) {
for (Node node : subset) {
if (getKnowledge().isForbidden(node.getName(), y.getName())) {
return false;
}
}
return true;
}
private Graph structure(Graph mim) {
List<Node> latents = new ArrayList<Node>();
for (Node node : mim.getNodes()) {
if (node.getNodeType() == NodeType.LATENT) {
latents.add(node);
}
}
return mim.subgraph(latents);
}
private String reportIfDiscrete(Graph dag, DataSet dataSet) {
List vars = dataSet.getVariables();
Map<String, DiscreteVariable> nodesToVars = new HashMap<String, DiscreteVariable>();
for (int i = 0; i < dataSet.getNumColumns(); i++) {
DiscreteVariable var = (DiscreteVariable) vars.get(i);
String name = var.getName();
Node node = new GraphNode(name);
nodesToVars.put(node.getName(), var);
}
BayesPm bayesPm = new BayesPm(new Dag(dag));
List<Node> nodes = bayesPm.getDag().getNodes();
for (Node node : nodes) {
Node var = nodesToVars.get(node.getName());
if (var instanceof DiscreteVariable) {
DiscreteVariable var2 = nodesToVars.get(node.getName());
int numCategories = var2.getNumCategories();
List<String> categories = new ArrayList<String>();
for (int j = 0; j < numCategories; j++) {
categories.add(var2.getCategory(j));
}
bayesPm.setCategories(node, categories);
}
}
BayesProperties properties = new BayesProperties(dataSet, dag);
properties.setGraph(dag);
NumberFormat nf = NumberFormat.getInstance();
nf.setMaximumFractionDigits(4);
StringBuilder buf = new StringBuilder();
buf.append("\nP-value = ").append(properties.getLikelihoodRatioP());
buf.append("\nDf = ").append(properties.getPValueDf());
buf.append("\nChi square = ").append(nf.format(properties.getPValueChisq()));
buf.append("\nBIC score = ").append(nf.format(properties.getBic()));
buf.append("\n\nH0: Completely disconnected graph.");
return buf.toString();
}
// Invalid if then nodes or graph changes.
private void calculateArrowsBackward(Node x, Node y, Graph graph) {
if (x == y) {
return;
}
if (!graph.isAdjacentTo(x, y)) {
return;
}
if (!knowledgeEmpty()) {
if (!getKnowledge().noEdgeRequired(x.getName(), y.getName())) {
return;
}
}
List<Node> naYX = getNaYX(x, y, graph);
clearArrow(x, y);
List<Node> _naYX = new ArrayList<Node>(naYX);
DepthChoiceGenerator gen = new DepthChoiceGenerator(_naYX.size(), _naYX.size());
int[] choice;
while ((choice = gen.next()) != null) {
List<Node> H = GraphUtils.asList(choice, _naYX);
if (!knowledgeEmpty()) {
if (!validSetByKnowledge(y, H)) {
continue;
}
}
double bump = deleteEval(x, y, H, naYX, graph);
if (bump > 0.0) {
Arrow arrow = new Arrow(bump, x, y, H, naYX);
sortedArrows.add(arrow);
addLookupArrow(x, y, arrow);
}
}
}
private void initializeArrowsBackward(Graph graph) {
sortedArrows.clear();
lookupArrows.clear();
for (Edge edge : graph.getEdges()) {
Node x = edge.getNode1();
Node y = edge.getNode2();
if (!knowledgeEmpty()) {
if (!getKnowledge().noEdgeRequired(x.getName(), y.getName())) {
continue;
}
}
if (Edges.isDirectedEdge(edge)) {
calculateArrowsBackward(x, y, graph);
} else {
calculateArrowsBackward(x, y, graph);
calculateArrowsBackward(y, x, graph);
}
}
}
private void addRequiredEdges(Graph graph) {
if (true) return;
if (knowledgeEmpty()) return;
for (Iterator<KnowledgeEdge> it = getKnowledge().requiredEdgesIterator(); it.hasNext(); ) {
KnowledgeEdge next = it.next();
Node nodeA = graph.getNode(next.getFrom());
Node nodeB = graph.getNode(next.getTo());
if (!graph.isAncestorOf(nodeB, nodeA)) {
graph.removeEdges(nodeA, nodeB);
graph.addDirectedEdge(nodeA, nodeB);
TetradLogger.getInstance()
.log("insertedEdges", "Adding edge by knowledge: " + graph.getEdge(nodeA, nodeB));
}
}
for (Edge edge : graph.getEdges()) {
final String A = edge.getNode1().getName();
final String B = edge.getNode2().getName();
if (knowledge.isForbidden(A, B)) {
Node nodeA = edge.getNode1();
Node nodeB = edge.getNode2();
if (nodeA != null
&& nodeB != null
&& graph.isAdjacentTo(nodeA, nodeB)
&& !graph.isChildOf(nodeA, nodeB)) {
if (!graph.isAncestorOf(nodeA, nodeB)) {
graph.removeEdges(nodeA, nodeB);
graph.addDirectedEdge(nodeB, nodeA);
TetradLogger.getInstance()
.log("insertedEdges", "Adding edge by knowledge: " + graph.getEdge(nodeB, nodeA));
}
}
if (!graph.isChildOf(nodeA, nodeB)
&& getKnowledge().isForbidden(nodeA.getName(), nodeB.getName())) {
if (!graph.isAncestorOf(nodeA, nodeB)) {
graph.removeEdges(nodeA, nodeB);
graph.addDirectedEdge(nodeB, nodeA);
TetradLogger.getInstance()
.log("insertedEdges", "Adding edge by knowledge: " + graph.getEdge(nodeB, nodeA));
}
}
} else if (knowledge.isForbidden(B, A)) {
Node nodeA = edge.getNode2();
Node nodeB = edge.getNode1();
if (nodeA != null
&& nodeB != null
&& graph.isAdjacentTo(nodeA, nodeB)
&& !graph.isChildOf(nodeA, nodeB)) {
if (!graph.isAncestorOf(nodeA, nodeB)) {
graph.removeEdges(nodeA, nodeB);
graph.addDirectedEdge(nodeB, nodeA);
TetradLogger.getInstance()
.log("insertedEdges", "Adding edge by knowledge: " + graph.getEdge(nodeB, nodeA));
}
}
if (!graph.isChildOf(nodeA, nodeB)
&& getKnowledge().isForbidden(nodeA.getName(), nodeB.getName())) {
if (!graph.isAncestorOf(nodeA, nodeB)) {
graph.removeEdges(nodeA, nodeB);
graph.addDirectedEdge(nodeB, nodeA);
TetradLogger.getInstance()
.log("insertedEdges", "Adding edge by knowledge: " + graph.getEdge(nodeB, nodeA));
}
}
}
}
}
/** Do an actual deletion (Definition 13 from Chickering, 2002). */
private void delete(Node x, Node y, List<Node> subset, Graph graph, double bump) {
Edge trueEdge = null;
if (trueGraph != null) {
Node _x = trueGraph.getNode(x.getName());
Node _y = trueGraph.getNode(y.getName());
trueEdge = trueGraph.getEdge(_x, _y);
}
if (log && verbose) {
Edge oldEdge = graph.getEdge(x, y);
String label = trueGraph != null && trueEdge != null ? "*" : "";
TetradLogger.getInstance()
.log(
"deletedEdges",
(graph.getNumEdges() - 1)
+ ". DELETE "
+ oldEdge
+ " "
+ subset
+ " ("
+ bump
+ ") "
+ label);
out.println(
(graph.getNumEdges() - 1)
+ ". DELETE "
+ oldEdge
+ " "
+ subset
+ " ("
+ bump
+ ") "
+ label);
} else {
int numEdges = graph.getNumEdges() - 1;
if (numEdges % 50 == 0) out.println(numEdges);
}
graph.removeEdge(x, y);
for (Node h : subset) {
Edge oldEdge = graph.getEdge(y, h);
graph.removeEdge(y, h);
graph.addDirectedEdge(y, h);
if (log) {
TetradLogger.getInstance()
.log("directedEdges", "--- Directing " + oldEdge + " to " + graph.getEdge(y, h));
}
if (verbose) {
out.println("--- Directing " + oldEdge + " to " + graph.getEdge(y, h));
}
if (Edges.isUndirectedEdge(graph.getEdge(x, h))) {
if (!graph.isAdjacentTo(x, h))
throw new IllegalArgumentException("Not adjacent: " + x + ", " + h);
oldEdge = graph.getEdge(x, h);
graph.removeEdge(x, h);
graph.addDirectedEdge(x, h);
if (log) {
TetradLogger.getInstance()
.log("directedEdges", "--- Directing " + oldEdge + " to " + graph.getEdge(x, h));
}
if (verbose) {
out.println("--- Directing " + oldEdge + " to " + graph.getEdge(x, h));
}
}
}
}
// serial.
private void insert(Node x, Node y, List<Node> t, Graph graph, double bump) {
if (graph.isAdjacentTo(x, y)) {
return; // The initial graph may already have put this edge in the graph.
// throw new IllegalArgumentException(x + " and " + y + " are already adjacent in
// the graph.");
}
Edge trueEdge = null;
if (trueGraph != null) {
Node _x = trueGraph.getNode(x.getName());
Node _y = trueGraph.getNode(y.getName());
trueEdge = trueGraph.getEdge(_x, _y);
}
graph.addDirectedEdge(x, y);
if (log) {
String label = trueGraph != null && trueEdge != null ? "*" : "";
TetradLogger.getInstance()
.log(
"insertedEdges",
graph.getNumEdges()
+ ". INSERT "
+ graph.getEdge(x, y)
+ " "
+ t
+ " "
+ bump
+ " "
+ label);
} else {
int numEdges = graph.getNumEdges() - 1;
if (verbose) {
if (numEdges % 50 == 0) out.println(numEdges);
}
}
if (verbose) {
String label = trueGraph != null && trueEdge != null ? "*" : "";
out.println(
graph.getNumEdges()
+ ". INSERT "
+ graph.getEdge(x, y)
+ " "
+ t
+ " "
+ bump
+ " "
+ label);
} else {
int numEdges = graph.getNumEdges() - 1;
if (verbose) {
if (numEdges % 50 == 0) out.println(numEdges);
}
}
for (Node _t : t) {
Edge oldEdge = graph.getEdge(_t, y);
if (oldEdge == null) throw new IllegalArgumentException("Not adjacent: " + _t + ", " + y);
graph.removeEdge(_t, y);
graph.addDirectedEdge(_t, y);
if (log && verbose) {
TetradLogger.getInstance()
.log("directedEdges", "--- Directing " + oldEdge + " to " + graph.getEdge(_t, y));
out.println("--- Directing " + oldEdge + " to " + graph.getEdge(_t, y));
}
}
}
public DataSet simulateDataCholesky(
int sampleSize, TetradMatrix covar, List<Node> variableNodes) {
List<Node> variables = new LinkedList<Node>();
for (Node node : variableNodes) {
variables.add(node);
}
List<Node> newVariables = new ArrayList<Node>();
for (Node node : variables) {
ContinuousVariable continuousVariable = new ContinuousVariable(node.getName());
continuousVariable.setNodeType(node.getNodeType());
newVariables.add(continuousVariable);
}
TetradMatrix impliedCovar = covar;
DataSet fullDataSet = new ColtDataSet(sampleSize, newVariables);
TetradMatrix cholesky = MatrixUtils.choleskyC(impliedCovar);
// Simulate the data by repeatedly calling the Cholesky.exogenousData
// method. Store only the data for the measured variables.
ROW:
for (int row = 0; row < sampleSize; row++) {
// Step 1. Generate normal samples.
double exoData[] = new double[cholesky.rows()];
for (int i = 0; i < exoData.length; i++) {
exoData[i] = RandomUtil.getInstance().nextNormal(0, 1);
// exoData[i] = randomUtil.nextUniform(-1, 1);
}
// Step 2. Multiply by cholesky to get correct covariance.
double point[] = new double[exoData.length];
for (int i = 0; i < exoData.length; i++) {
double sum = 0.0;
for (int j = 0; j <= i; j++) {
sum += cholesky.get(i, j) * exoData[j];
}
point[i] = sum;
}
double rowData[] = point;
for (int col = 0; col < variables.size(); col++) {
int index = variableNodes.indexOf(variables.get(col));
double value = rowData[index];
if (Double.isNaN(value) || Double.isInfinite(value)) {
throw new IllegalArgumentException("Value out of range: " + value);
}
fullDataSet.setDouble(row, col, value);
}
}
return DataUtils.restrictToMeasured(fullDataSet);
}
