use of edu.cmu.tetrad.algcomparison.independence.IndependenceWrapper in project tetrad by cmu-phil.
the class TestFges method test9.
public void test9() {
Parameters parameters = new Parameters();
parameters.set("numMeasures", 50);
parameters.set("numLatents", 0);
parameters.set("avgDegree", 2);
parameters.set("maxDegree", 20);
parameters.set("maxIndegree", 20);
parameters.set("maxOutdegree", 20);
parameters.set("connected", false);
parameters.set("coefLow", 0.2);
parameters.set("coefHigh", 0.9);
parameters.set("varLow", 1);
parameters.set("varHigh", 3);
parameters.set("verbose", false);
parameters.set("coefSymmetric", true);
parameters.set("numRuns", 1);
parameters.set("percentDiscrete", 0);
parameters.set("numCategories", 3);
parameters.set("differentGraphs", true);
parameters.set("sampleSize", 500);
parameters.set("intervalBetweenShocks", 10);
parameters.set("intervalBetweenRecordings", 10);
parameters.set("fisherEpsilon", 0.001);
parameters.set("randomizeColumns", true);
RandomGraph graph = new RandomForward();
LinearFisherModel sim = new LinearFisherModel(graph);
sim.createData(parameters);
Graph previous = null;
int prevDiff = Integer.MAX_VALUE;
// for (int l = 7; l >= 1; l--) {
for (int i = 2; i <= 20; i++) {
parameters.set("penaltyDiscount", i / (double) 10);
// parameters.set("alpha", Double.parseDouble("1E-" + l));
// ScoreWrapper score = new edu.cmu.tetrad.algcomparison.score.SemBicScore();
// Algorithm alg = new edu.cmu.tetrad.algcomparison.algorithm.oracle.pattern.Fges(score);
IndependenceWrapper test = new SemBicTest();
// IndependenceWrapper test = new FisherZ();
Algorithm alg = new edu.cmu.tetrad.algcomparison.algorithm.oracle.pattern.Cpc(test);
Graph out = alg.search(sim.getDataModel(0), parameters);
// Graph out = GraphUtils.undirectedGraph(alg.search(sim.getDataModel(0), parameters));
Set<Edge> edges1 = out.getEdges();
int numEdges = edges1.size();
if (previous != null) {
Set<Edge> edges2 = previous.getEdges();
edges2.removeAll(edges1);
int diff = edges2.size();
//
System.out.println("Penalty discount =" + parameters.getDouble("penaltyDiscount") + " # edges = " + numEdges + " # additional = " + diff);
previous = out;
if (diff > prevDiff)
break;
prevDiff = diff;
} else {
previous = out;
}
}
Graph estGraph = previous;
Graph trueGraph = sim.getTrueGraph(0);
estGraph = GraphUtils.replaceNodes(estGraph, trueGraph.getNodes());
Statistic ap = new AdjacencyPrecision();
Statistic ar = new AdjacencyRecall();
Statistic ahp = new ArrowheadPrecision();
Statistic ahr = new ArrowheadRecall();
System.out.println("AP = " + ap.getValue(trueGraph, estGraph));
System.out.println("AR = " + ar.getValue(trueGraph, estGraph));
System.out.println("AHP = " + ahp.getValue(trueGraph, estGraph));
System.out.println("AHR = " + ahr.getValue(trueGraph, estGraph));
}
use of edu.cmu.tetrad.algcomparison.independence.IndependenceWrapper in project tetrad by cmu-phil.
the class TestGeneralBootstrapTest method testFCId.
@Test
public void testFCId() {
double structurePrior = 1, samplePrior = 1;
int depth = -1;
int maxPathLength = -1;
int numVars = 20;
int edgesPerNode = 2;
int numLatentConfounders = 4;
int numCases = 50;
int numBootstrapSamples = 5;
boolean verbose = true;
long seed = 123;
Graph dag = makeDiscreteDAG(numVars, numLatentConfounders, edgesPerNode);
DagToPag dagToPag = new DagToPag(dag);
Graph truePag = dagToPag.convert();
System.out.println("Truth PAG_of_the_true_DAG Graph:");
System.out.println(truePag.toString());
BayesPm pm = new BayesPm(dag, 2, 3);
BayesIm im = new MlBayesIm(pm, MlBayesIm.RANDOM);
DataSet data = im.simulateData(numCases, seed, false);
Parameters parameters = new Parameters();
parameters.set("structurePrior", structurePrior);
parameters.set("samplePrior", samplePrior);
parameters.set("depth", depth);
parameters.set("maxPathLength", maxPathLength);
parameters.set("numPatternsToStore", 0);
parameters.set("verbose", verbose);
IndependenceWrapper test = new ChiSquare();
Algorithm algorithm = new Fci(test);
GeneralBootstrapTest bootstrapTest = new GeneralBootstrapTest(data, algorithm, numBootstrapSamples);
bootstrapTest.setVerbose(verbose);
bootstrapTest.setParameters(parameters);
bootstrapTest.setEdgeEnsemble(BootstrapEdgeEnsemble.Highest);
Graph resultGraph = bootstrapTest.search();
System.out.println("Estimated Bootstrapped PAG_of_the_true_DAG Graph:");
System.out.println(resultGraph.toString());
// Adjacency Confusion Matrix
int[][] adjAr = GeneralBootstrapTest.getAdjConfusionMatrix(truePag, resultGraph);
printAdjConfusionMatrix(adjAr);
// Edge Type Confusion Matrix
int[][] edgeAr = GeneralBootstrapTest.getEdgeTypeConfusionMatrix(truePag, resultGraph);
printEdgeTypeConfusionMatrix(edgeAr);
}
use of edu.cmu.tetrad.algcomparison.independence.IndependenceWrapper in project tetrad by cmu-phil.
the class TestGeneralBootstrapTest method testGFCId.
@Test
public void testGFCId() {
double structurePrior = 1, samplePrior = 1;
boolean faithfulnessAssumed = false;
int maxDegree = -1;
int numVars = 20;
int edgesPerNode = 2;
int numLatentConfounders = 4;
int numCases = 50;
int numBootstrapSamples = 5;
boolean verbose = true;
long seed = 123;
Graph dag = makeDiscreteDAG(numVars, numLatentConfounders, edgesPerNode);
DagToPag dagToPag = new DagToPag(dag);
Graph truePag = dagToPag.convert();
System.out.println("Truth PAG_of_the_true_DAG Graph:");
System.out.println(truePag.toString());
BayesPm pm = new BayesPm(dag, 2, 3);
BayesIm im = new MlBayesIm(pm, MlBayesIm.RANDOM);
DataSet data = im.simulateData(numCases, seed, false);
Parameters parameters = new Parameters();
parameters.set("structurePrior", structurePrior);
parameters.set("samplePrior", samplePrior);
parameters.set("faithfulnessAssumed", faithfulnessAssumed);
parameters.set("maxDegree", maxDegree);
parameters.set("numPatternsToStore", 0);
parameters.set("verbose", verbose);
ScoreWrapper score = new BdeuScore();
IndependenceWrapper test = new ChiSquare();
Algorithm algorithm = new Gfci(test, score);
GeneralBootstrapTest bootstrapTest = new GeneralBootstrapTest(data, algorithm, numBootstrapSamples);
bootstrapTest.setVerbose(verbose);
bootstrapTest.setParameters(parameters);
bootstrapTest.setEdgeEnsemble(BootstrapEdgeEnsemble.Highest);
Graph resultGraph = bootstrapTest.search();
System.out.println("Estimated Bootstrapped PAG_of_the_true_DAG Graph:");
System.out.println(resultGraph.toString());
// Adjacency Confusion Matrix
int[][] adjAr = GeneralBootstrapTest.getAdjConfusionMatrix(truePag, resultGraph);
printAdjConfusionMatrix(adjAr);
// Edge Type Confusion Matrix
int[][] edgeAr = GeneralBootstrapTest.getEdgeTypeConfusionMatrix(truePag, resultGraph);
printEdgeTypeConfusionMatrix(edgeAr);
}
use of edu.cmu.tetrad.algcomparison.independence.IndependenceWrapper in project tetrad by cmu-phil.
the class TestGeneralBootstrapTest method testFCIc.
@Test
public void testFCIc() {
int penaltyDiscount = 2;
int depth = 3;
int maxPathLength = -1;
int numVars = 20;
int edgesPerNode = 2;
int numLatentConfounders = 2;
int numCases = 50;
int numBootstrapSamples = 5;
boolean verbose = true;
Graph dag = makeContinuousDAG(numVars, numLatentConfounders, edgesPerNode);
DagToPag dagToPag = new DagToPag(dag);
Graph truePag = dagToPag.convert();
System.out.println("Truth PAG_of_the_true_DAG Graph:");
System.out.println(truePag.toString());
int[] causalOrdering = new int[numVars];
for (int i = 0; i < numVars; i++) {
causalOrdering[i] = i;
}
LargeScaleSimulation simulator = new LargeScaleSimulation(dag, dag.getNodes(), causalOrdering);
DataSet data = simulator.simulateDataFisher(numCases);
Parameters parameters = new Parameters();
parameters.set("penaltyDiscount", penaltyDiscount);
parameters.set("depth", depth);
parameters.set("maxPathLength", maxPathLength);
parameters.set("numPatternsToStore", 0);
parameters.set("verbose", verbose);
IndependenceWrapper test = new FisherZ();
Fci algorithm = new Fci(test);
GeneralBootstrapTest bootstrapTest = new GeneralBootstrapTest(data, algorithm, numBootstrapSamples);
bootstrapTest.setVerbose(verbose);
bootstrapTest.setParameters(parameters);
bootstrapTest.setEdgeEnsemble(BootstrapEdgeEnsemble.Preserved);
// bootstrapTest.setParallelMode(false);
Graph resultGraph = bootstrapTest.search();
System.out.println("Estimated PAG_of_the_true_DAG Graph:");
System.out.println(resultGraph.toString());
// Adjacency Confusion Matrix
int[][] adjAr = GeneralBootstrapTest.getAdjConfusionMatrix(truePag, resultGraph);
printAdjConfusionMatrix(adjAr);
// Edge Type Confusion Matrix
int[][] edgeAr = GeneralBootstrapTest.getEdgeTypeConfusionMatrix(truePag, resultGraph);
printEdgeTypeConfusionMatrix(edgeAr);
}
use of edu.cmu.tetrad.algcomparison.independence.IndependenceWrapper in project tetrad by cmu-phil.
the class TestGeneralBootstrapTest method testGFCIc.
@Test
public void testGFCIc() {
int penaltyDiscount = 2;
boolean faithfulnessAssumed = false;
int maxDegree = -1;
int numVars = 20;
int edgesPerNode = 2;
int numLatentConfounders = 2;
int numCases = 50;
int numBootstrapSamples = 5;
boolean verbose = true;
Graph dag = makeContinuousDAG(numVars, numLatentConfounders, edgesPerNode);
DagToPag dagToPag = new DagToPag(dag);
Graph truePag = dagToPag.convert();
System.out.println("Truth PAG_of_the_true_DAG Graph:");
System.out.println(truePag.toString());
int[] causalOrdering = new int[numVars];
for (int i = 0; i < numVars; i++) {
causalOrdering[i] = i;
}
LargeScaleSimulation simulator = new LargeScaleSimulation(dag, dag.getNodes(), causalOrdering);
DataSet data = simulator.simulateDataFisher(numCases);
Parameters parameters = new Parameters();
parameters.set("penaltyDiscount", penaltyDiscount);
parameters.set("faithfulnessAssumed", faithfulnessAssumed);
parameters.set("maxDegree", maxDegree);
parameters.set("numPatternsToStore", 0);
parameters.set("verbose", verbose);
ScoreWrapper score = new SemBicScore();
IndependenceWrapper test = new FisherZ();
Algorithm algorithm = new Gfci(test, score);
GeneralBootstrapTest bootstrapTest = new GeneralBootstrapTest(data, algorithm, numBootstrapSamples);
bootstrapTest.setVerbose(verbose);
bootstrapTest.setParameters(parameters);
bootstrapTest.setEdgeEnsemble(BootstrapEdgeEnsemble.Highest);
Graph resultGraph = bootstrapTest.search();
System.out.println("Estimated PAG_of_the_true_DAG Graph:");
System.out.println(resultGraph.toString());
// Adjacency Confusion Matrix
int[][] adjAr = GeneralBootstrapTest.getAdjConfusionMatrix(truePag, resultGraph);
printAdjConfusionMatrix(adjAr);
// Edge Type Confusion Matrix
int[][] edgeAr = GeneralBootstrapTest.getEdgeTypeConfusionMatrix(truePag, resultGraph);
printEdgeTypeConfusionMatrix(edgeAr);
}
Aggregations