Examples with Dag edu.cmu.tetrad.graph.Dag used on opensource projects

Example 41 with Dag

use of edu.cmu.tetrad.graph.Dag in project tetrad by cmu-phil.

the class TestDiscreteProbs method testCreateUsingBayesIm.

public void testCreateUsingBayesIm() {
    Graph graph = GraphConverter.convert("X1-->X2,X1-->X3,X2-->X4,X3-->X4");
    Dag dag = new Dag(graph);
    BayesPm bayesPm = new BayesPm(dag);
    BayesIm bayesIm = new MlBayesIm(bayesPm, MlBayesIm.RANDOM);
    StoredCellProbs cellProbs = StoredCellProbs.createCellTable(bayesIm);
    Proposition assertion = Proposition.tautology(bayesIm);
    assertion.setCategory(0, 1);
    assertion.removeCategory(2, 0);
    Proposition condition = Proposition.tautology(bayesIm);
    condition.setCategory(0, 1);
    cellProbs.getConditionalProb(assertion, condition);
}

Example 42 with Dag

use of edu.cmu.tetrad.graph.Dag in project tetrad by cmu-phil.

the class TestHistogram method testHistogram.

@Test
public void testHistogram() {
    RandomUtil.getInstance().setSeed(4829384L);
    List<Node> nodes = new ArrayList<>();
    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]);
}

Example 43 with Dag

use of edu.cmu.tetrad.graph.Dag in project tetrad by cmu-phil.

the class DirichletBayesIm method constructSample.

// /**
// * Constructs a random sample using the given already allocated data set, to
// * avoid allocating more memory.
// */
// private DataSet simulateDataHelper(DataSet dataSet,
// RandomUtil randomUtil,
// boolean latentDataSaved) {
// if (dataSet.getNumColumns() != nodes.length) {
// throw new IllegalArgumentException("When rewriting the old data set, " +
// "number of variables in data set must equal number of variables " +
// "in Bayes net.");
// }
// 
// int sampleSize = dataSet.getNumRows();
// 
// int numMeasured = 0;
// int[] map = new int[nodes.length];
// List<Node> variables = new LinkedList<>();
// 
// for (int j = 0; j < nodes.length; j++) {
// if (!latentDataSaved && nodes[j].getNodeType() != NodeType.MEASURED) {
// continue;
// }
// 
// int numCategories = bayesPm.getNumCategories(nodes[j]);
// List<String> categories = new LinkedList<>();
// 
// for (int k = 0; k < numCategories; k++) {
// categories.add(bayesPm.getCategory(nodes[j], k));
// }
// 
// DiscreteVariable var =
// new DiscreteVariable(nodes[j].getNode(), categories);
// variables.add(var);
// int index = ++numMeasured - 1;
// map[index] = j;
// }
// 
// for (int i = 0; i < variables.size(); i++) {
// Node node = dataSet.getVariable(i);
// Node _node = variables.get(i);
// dataSet.changeVariable(node, _node);
// }
// 
// constructSample(sampleSize, randomUtil, numMeasured, dataSet, map);
// return dataSet;
// }
private void constructSample(int sampleSize, RandomUtil randomUtil, int numMeasured, DataSet dataSet, int[] map) {
    // Get a tier ordering and convert it to an int array.
    Graph graph = getBayesPm().getDag();
    Dag dag = new Dag(graph);
    List<Node> tierOrdering = dag.getCausalOrdering();
    int[] tiers = new int[tierOrdering.size()];
    for (int i = 0; i < tierOrdering.size(); i++) {
        tiers[i] = getNodeIndex(tierOrdering.get(i));
    }
    // Construct the sample.
    int[] combination = new int[nodes.length];
    for (int i = 0; i < sampleSize; i++) {
        int[] point = new int[nodes.length];
        for (int nodeIndex : tiers) {
            double cutoff = randomUtil.nextDouble();
            for (int k = 0; k < getNumParents(nodeIndex); k++) {
                combination[k] = point[getParent(nodeIndex, k)];
            }
            int rowIndex = getRowIndex(nodeIndex, combination);
            double sum = 0.0;
            for (int k = 0; k < getNumColumns(nodeIndex); k++) {
                double probability = getProbability(nodeIndex, rowIndex, k);
                if (Double.isNaN(probability)) {
                    throw new IllegalStateException("Some probability " + "values in the BayesIm are not filled in; " + "cannot simulate data.");
                }
                sum += probability;
                if (sum >= cutoff) {
                    point[nodeIndex] = k;
                    break;
                }
            }
        }
        for (int j = 0; j < numMeasured; j++) {
            dataSet.setInt(i, j, point[map[j]]);
        }
    }
}

Example 44 with Dag

use of edu.cmu.tetrad.graph.Dag in project tetrad by cmu-phil.

the class Identifiability method createManipulatedGraph.

private Dag createManipulatedGraph(Graph graph) {
    Dag updatedGraph = new Dag(graph);
    // alters graph for manipulated evidenceItems
    for (int i = 0; i < evidence.getNumNodes(); ++i) {
        if (evidence.isManipulated(i)) {
            Node node = updatedGraph.getNode(evidence.getNode(i).getName());
            List<Node> parents = updatedGraph.getParents(node);
            for (Object parent1 : parents) {
                Node parent = (Node) parent1;
                updatedGraph.removeEdge(node, parent);
            }
        }
    }
    return updatedGraph;
}

Example 45 with Dag

use of edu.cmu.tetrad.graph.Dag in project tetrad by cmu-phil.

the class Identifiability method setEvidence.

// ///////////////////////////////////////////////////////////////
public final void setEvidence(Evidence evidence) {
    if (evidence == null) {
        throw new NullPointerException();
    }
    if (evidence.isIncompatibleWith(bayesIm)) {
        throw new IllegalArgumentException("The variable list for the " + "given bayesIm must be compatible with the variable list " + "for this evidence.");
    }
    this.evidence = evidence;
    Graph graph = bayesIm.getBayesPm().getDag();
    Dag manipulatedGraph = createManipulatedGraph(graph);
    BayesPm manipulatedPm = createUpdatedBayesPm(manipulatedGraph);
    this.manipulatedBayesIm = createdUpdatedBayesIm(manipulatedPm);
/*
        this.manipulatedBayesIm = bayesIm;
		this.bayesImProbs = new BayesImProbs(manipulatedBayesIm);
		 */
/*
      The BayesIm after update, if this was calculated.

      */
}