Search in sources :

Example 1 with ContinuousTabularDataFileReader

use of edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader in project tetrad by cmu-phil.

the class DataLoaderSettings method loadDataWithSettings.

/**
 * Kevin's fast data reader
 *
 * @param file
 * @return DataModel on success
 */
public DataModel loadDataWithSettings(File file) throws IOException {
    DataModel dataModel = null;
    Delimiter delimiter = getDelimiterType();
    boolean hasHeader = isVarNamesFirstRow();
    String commentMarker = getCommentMarker();
    String missingValueMarker = getMissingValueMarker();
    if (tabularRadioButton.isSelected()) {
        TabularDataReader dataReader = null;
        // Continuous, discrete, mixed
        if (contRadioButton.isSelected()) {
            dataReader = new ContinuousTabularDataFileReader(file, delimiter);
        } else if (discRadioButton.isSelected()) {
            dataReader = new VerticalDiscreteTabularDataReader(file, delimiter);
        } else if (mixedRadioButton.isSelected()) {
            dataReader = new MixedTabularDataFileReader(getMaxNumOfDiscCategories(), file, delimiter);
        } else {
            throw new UnsupportedOperationException("Unsupported data type!");
        }
        // Header in first row or not
        dataReader.setHasHeader(hasHeader);
        // Set comment marker
        dataReader.setCommentMarker(commentMarker);
        dataReader.setMissingValueMarker(missingValueMarker);
        // Set the quote character
        if (doubleQuoteRadioButton.isSelected()) {
            dataReader.setQuoteCharacter('"');
        }
        if (singleQuoteRadioButton.isSelected()) {
            dataReader.setQuoteCharacter('\'');
        }
        Dataset dataset;
        // Handle case ID column based on different selections
        if (idNoneRadioButton.isSelected()) {
            // No column exclusion
            dataset = dataReader.readInData();
        } else if (idUnlabeledFirstColRadioButton.isSelected()) {
            // Exclude the first column
            dataset = dataReader.readInData(new int[] { 1 });
        } else if (idLabeledColRadioButton.isSelected() && !idStringField.getText().isEmpty()) {
            // Exclude the specified labled column
            dataset = dataReader.readInData(new HashSet<>(Arrays.asList(new String[] { idStringField.getText() })));
        } else {
            throw new UnsupportedOperationException("Unexpected 'Case ID column to ignore' selection.");
        }
        // Box Dataset to DataModel
        dataModel = DataConvertUtils.toDataModel(dataset);
    } else if (covarianceRadioButton.isSelected()) {
        // Covariance data can only be continuous
        CovarianceDataReader dataReader = new LowerCovarianceDataReader(file, delimiter);
        // Set comment marker
        dataReader.setCommentMarker(commentMarker);
        // Set the quote character
        if (doubleQuoteRadioButton.isSelected()) {
            dataReader.setQuoteCharacter('"');
        }
        if (singleQuoteRadioButton.isSelected()) {
            dataReader.setQuoteCharacter('\'');
        }
        Dataset dataset = dataReader.readInData();
        // Box Dataset to DataModel
        dataModel = DataConvertUtils.toDataModel(dataset);
    } else {
        throw new UnsupportedOperationException("Unsupported selection of File Type!");
    }
    return dataModel;
}
Also used : TabularDataReader(edu.pitt.dbmi.data.reader.tabular.TabularDataReader) VerticalDiscreteTabularDataReader(edu.pitt.dbmi.data.reader.tabular.VerticalDiscreteTabularDataReader) Delimiter(edu.pitt.dbmi.data.Delimiter) Dataset(edu.pitt.dbmi.data.Dataset) CovarianceDataReader(edu.pitt.dbmi.data.reader.covariance.CovarianceDataReader) LowerCovarianceDataReader(edu.pitt.dbmi.data.reader.covariance.LowerCovarianceDataReader) ContinuousTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader) LowerCovarianceDataReader(edu.pitt.dbmi.data.reader.covariance.LowerCovarianceDataReader) MixedTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.MixedTabularDataFileReader) DataModel(edu.cmu.tetrad.data.DataModel) VerticalDiscreteTabularDataReader(edu.pitt.dbmi.data.reader.tabular.VerticalDiscreteTabularDataReader) HashSet(java.util.HashSet)

Example 2 with ContinuousTabularDataFileReader

use of edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader in project tetrad by cmu-phil.

the class GdistanceApply method main.

public static void main(String... args) {
    double xdist = 2.4;
    double ydist = 2.4;
    double zdist = 2;
    long timestart = System.nanoTime();
    System.out.println("Loading first graph");
    Graph graph1 = GraphUtils.loadGraphTxt(new File("Motion_Corrected_Graphs/singlesub_motion_graph_025_04.txt"));
    long timegraph1 = System.nanoTime();
    // System.out.println(graph1);
    System.out.println("Done loading first graph. Elapsed time: " + (timegraph1 - timestart) / 1000000000 + "s");
    System.out.println("Loading second graph");
    Graph graph2 = GraphUtils.loadGraphTxt(new File("Motion_Corrected_Graphs/singlesub_motion_graph_027_04.txt"));
    long timegraph2 = System.nanoTime();
    System.out.println("Done loading second graph. Elapsed time: " + (timegraph2 - timegraph1) / 1000000000 + "s");
    // +++++++++ these steps are specifically for the motion corrected fMRI graphs ++++++++++++
    graph1.removeNode(graph1.getNode("Motion_1"));
    graph1.removeNode(graph1.getNode("Motion_2"));
    graph1.removeNode(graph1.getNode("Motion_3"));
    graph1.removeNode(graph1.getNode("Motion_4"));
    graph1.removeNode(graph1.getNode("Motion_5"));
    graph1.removeNode(graph1.getNode("Motion_6"));
    graph2.removeNode(graph2.getNode("Motion_1"));
    graph2.removeNode(graph2.getNode("Motion_2"));
    graph2.removeNode(graph2.getNode("Motion_3"));
    graph2.removeNode(graph2.getNode("Motion_4"));
    graph2.removeNode(graph2.getNode("Motion_5"));
    graph2.removeNode(graph2.getNode("Motion_6"));
    // load the location map
    String workingDirectory = System.getProperty("user.dir");
    System.out.println(workingDirectory);
    Path mapPath = Paths.get("coords.txt");
    System.out.println(mapPath);
    TabularDataReader dataReaderMap = new ContinuousTabularDataFileReader(mapPath.toFile(), Delimiter.COMMA);
    try {
        DataSet locationMap = (DataSet) DataConvertUtils.toDataModel(dataReaderMap.readInData());
        long timegraph3 = System.nanoTime();
        System.out.println("Done loading location map. Elapsed time: " + (timegraph3 - timegraph2) / 1000000000 + "s");
        System.out.println("Running Gdistance");
        Gdistance gdist = new Gdistance(locationMap, xdist, ydist, zdist);
        List<Double> distance = gdist.distances(graph1, graph2);
        System.out.println(distance);
        System.out.println("Done running Distance. Elapsed time: " + (System.nanoTime() - timegraph3) / 1000000000 + "s");
        System.out.println("Total elapsed time: " + (System.nanoTime() - timestart) / 1000000000 + "s");
        PrintWriter writer = new PrintWriter("Gdistances.txt", "UTF-8");
        writer.println(distance);
        writer.close();
    } catch (Exception IOException) {
        IOException.printStackTrace();
    }
}
Also used : Path(java.nio.file.Path) TabularDataReader(edu.pitt.dbmi.data.reader.tabular.TabularDataReader) DataSet(edu.cmu.tetrad.data.DataSet) ContinuousTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader) Graph(edu.cmu.tetrad.graph.Graph) File(java.io.File) PrintWriter(java.io.PrintWriter)

Example 3 with ContinuousTabularDataFileReader

use of edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader in project tetrad by cmu-phil.

the class GdistanceTest method main.

public static void main(String... args) {
    // first generate a couple random graphs
    int numVars = 16;
    int numEdges = 16;
    List<Node> vars = new ArrayList<>();
    for (int i = 0; i < numVars; i++) {
        vars.add(new ContinuousVariable("X" + i));
    }
    Graph testdag1 = GraphUtils.randomGraphRandomForwardEdges(vars, 0, numEdges, 30, 15, 15, false, true);
    Graph testdag2 = GraphUtils.randomGraphRandomForwardEdges(vars, 0, numEdges, 30, 15, 15, false, true);
    // System.out.println(testdag1);
    // load the location map
    String workingDirectory = System.getProperty("user.dir");
    System.out.println(workingDirectory);
    Path mapPath = Paths.get("locationMap.txt");
    System.out.println(mapPath);
    TabularDataReader dataReaderMap = new ContinuousTabularDataFileReader(mapPath.toFile(), Delimiter.COMMA);
    try {
        DataSet locationMap = (DataSet) DataConvertUtils.toDataModel(dataReaderMap.readInData());
        // System.out.println(locationMap);
        // then compare their distance
        double xdist = 2.4;
        double ydist = 2.4;
        double zdist = 2;
        Gdistance gdist = new Gdistance(locationMap, xdist, ydist, zdist);
        List<Double> output = gdist.distances(testdag1, testdag2);
        System.out.println(output);
        PrintWriter writer = new PrintWriter("Gdistances.txt", "UTF-8");
        writer.println(output);
        writer.close();
    } catch (Exception IOException) {
        IOException.printStackTrace();
    }
}
Also used : Path(java.nio.file.Path) TabularDataReader(edu.pitt.dbmi.data.reader.tabular.TabularDataReader) DataSet(edu.cmu.tetrad.data.DataSet) Node(edu.cmu.tetrad.graph.Node) ArrayList(java.util.ArrayList) ContinuousTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader) ContinuousVariable(edu.cmu.tetrad.data.ContinuousVariable) Graph(edu.cmu.tetrad.graph.Graph) PrintWriter(java.io.PrintWriter)

Example 4 with ContinuousTabularDataFileReader

use of edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader in project tetrad by cmu-phil.

the class HsimEvalFromData method main.

public static void main(String[] args) {
    long timestart = System.nanoTime();
    System.out.println("Beginning Evaluation");
    String nl = System.lineSeparator();
    String output = "Simulation edu.cmu.tetrad.study output comparing Fsim and Hsim on predicting graph discovery accuracy" + nl;
    int iterations = 100;
    int vars = 20;
    int cases = 500;
    int edgeratio = 3;
    List<Integer> hsimRepeat = Arrays.asList(40);
    List<Integer> fsimRepeat = Arrays.asList(40);
    List<PRAOerrors>[] fsimErrsByPars = new ArrayList[fsimRepeat.size()];
    int whichFrepeat = 0;
    for (int frepeat : fsimRepeat) {
        fsimErrsByPars[whichFrepeat] = new ArrayList<PRAOerrors>();
        whichFrepeat++;
    }
    List<PRAOerrors>[][] hsimErrsByPars = new ArrayList[1][hsimRepeat.size()];
    // System.out.println(resimSize.size()+" "+hsimRepeat.size());
    int whichHrepeat;
    whichHrepeat = 0;
    for (int hrepeat : hsimRepeat) {
        // System.out.println(whichrsize+" "+whichHrepeat);
        hsimErrsByPars[0][whichHrepeat] = new ArrayList<PRAOerrors>();
        whichHrepeat++;
    }
    // !(*%(@!*^!($%!^ START ITERATING HERE !#$%(*$#@!^(*!$*%(!$#
    try {
        for (int iterate = 0; iterate < iterations; iterate++) {
            System.out.println("iteration " + iterate);
            // @#$%@$%^@$^@$^@%$%@$#^ LOADING THE DATA AND GRAPH @$#%%*#^##*^$#@%$
            DataSet data1;
            Graph graph1 = GraphUtils.loadGraphTxt(new File("graph/graph.1.txt"));
            Dag odag = new Dag(graph1);
            Set<String> eVars = new HashSet<String>();
            eVars.add("MULT");
            Path dataFile = Paths.get("data/data.1.txt");
            TabularDataReader dataReader = new ContinuousTabularDataFileReader(dataFile.toFile(), Delimiter.TAB);
            data1 = (DataSet) DataConvertUtils.toDataModel(dataReader.readInData(eVars));
            vars = data1.getNumColumns();
            cases = data1.getNumRows();
            edgeratio = 3;
            // !#@^$@&%^!#$!&@^ CALCULATING TARGET ERRORS $%$#@^@!%!#^$!%$#%
            ICovarianceMatrix newcov = new CovarianceMatrixOnTheFly(data1);
            SemBicScore oscore = new SemBicScore(newcov);
            Fges ofgs = new Fges(oscore);
            ofgs.setVerbose(false);
            ofgs.setNumPatternsToStore(0);
            // ***********This is the original FGS output on the data
            Graph oFGSGraph = ofgs.search();
            PRAOerrors oErrors = new PRAOerrors(HsimUtils.errorEval(oFGSGraph, odag), "target errors");
            // **then step 1: full resim. iterate through the combinations of estimator parameters (just repeat num)
            for (whichFrepeat = 0; whichFrepeat < fsimRepeat.size(); whichFrepeat++) {
                ArrayList<PRAOerrors> errorsList = new ArrayList<PRAOerrors>();
                for (int r = 0; r < fsimRepeat.get(whichFrepeat); r++) {
                    PatternToDag pickdag = new PatternToDag(oFGSGraph);
                    Graph fgsDag = pickdag.patternToDagMeek();
                    Dag fgsdag2 = new Dag(fgsDag);
                    // then fit an IM to this dag and the data. GeneralizedSemEstimator seems to bug out
                    // GeneralizedSemPm simSemPm = new GeneralizedSemPm(fgsdag2);
                    // GeneralizedSemEstimator gsemEstimator = new GeneralizedSemEstimator();
                    // GeneralizedSemIm fittedIM = gsemEstimator.estimate(simSemPm, oData);
                    SemPm simSemPm = new SemPm(fgsdag2);
                    // BayesPm simBayesPm = new BayesPm(fgsdag2, bayesPm);
                    SemEstimator simSemEstimator = new SemEstimator(data1, simSemPm);
                    SemIm fittedIM = simSemEstimator.estimate();
                    DataSet simData = fittedIM.simulateData(data1.getNumRows(), false);
                    // after making the full resim data (simData), run FGS on that
                    ICovarianceMatrix simcov = new CovarianceMatrixOnTheFly(simData);
                    SemBicScore simscore = new SemBicScore(simcov);
                    Fges simfgs = new Fges(simscore);
                    simfgs.setVerbose(false);
                    simfgs.setNumPatternsToStore(0);
                    Graph simGraphOut = simfgs.search();
                    PRAOerrors simErrors = new PRAOerrors(HsimUtils.errorEval(simGraphOut, fgsdag2), "Fsim errors " + r);
                    errorsList.add(simErrors);
                }
                PRAOerrors avErrors = new PRAOerrors(errorsList, "Average errors for Fsim at repeat=" + fsimRepeat.get(whichFrepeat));
                // if (verbosity>3) System.out.println(avErrors.allToString());
                // ****calculate the squared errors of prediction, store all these errors in a list
                double FsimAR2 = (avErrors.getAdjRecall() - oErrors.getAdjRecall()) * (avErrors.getAdjRecall() - oErrors.getAdjRecall());
                double FsimAP2 = (avErrors.getAdjPrecision() - oErrors.getAdjPrecision()) * (avErrors.getAdjPrecision() - oErrors.getAdjPrecision());
                double FsimOR2 = (avErrors.getOrientRecall() - oErrors.getOrientRecall()) * (avErrors.getOrientRecall() - oErrors.getOrientRecall());
                double FsimOP2 = (avErrors.getOrientPrecision() - oErrors.getOrientPrecision()) * (avErrors.getOrientPrecision() - oErrors.getOrientPrecision());
                PRAOerrors Fsim2 = new PRAOerrors(new double[] { FsimAR2, FsimAP2, FsimOR2, FsimOP2 }, "squared errors for Fsim at repeat=" + fsimRepeat.get(whichFrepeat));
                // add the fsim squared errors to the appropriate list
                fsimErrsByPars[whichFrepeat].add(Fsim2);
            }
            // **then step 2: hybrid sim. iterate through combos of params (repeat num, resimsize)
            for (whichHrepeat = 0; whichHrepeat < hsimRepeat.size(); whichHrepeat++) {
                HsimRepeatAC study = new HsimRepeatAC(data1);
                PRAOerrors HsimErrors = new PRAOerrors(study.run(1, hsimRepeat.get(whichHrepeat)), "Hsim errors" + "at rsize=" + 1 + " repeat=" + hsimRepeat.get(whichHrepeat));
                // ****calculate the squared errors of prediction
                double HsimAR2 = (HsimErrors.getAdjRecall() - oErrors.getAdjRecall()) * (HsimErrors.getAdjRecall() - oErrors.getAdjRecall());
                double HsimAP2 = (HsimErrors.getAdjPrecision() - oErrors.getAdjPrecision()) * (HsimErrors.getAdjPrecision() - oErrors.getAdjPrecision());
                double HsimOR2 = (HsimErrors.getOrientRecall() - oErrors.getOrientRecall()) * (HsimErrors.getOrientRecall() - oErrors.getOrientRecall());
                double HsimOP2 = (HsimErrors.getOrientPrecision() - oErrors.getOrientPrecision()) * (HsimErrors.getOrientPrecision() - oErrors.getOrientPrecision());
                PRAOerrors Hsim2 = new PRAOerrors(new double[] { HsimAR2, HsimAP2, HsimOR2, HsimOP2 }, "squared errors for Hsim, rsize=" + 1 + " repeat=" + hsimRepeat.get(whichHrepeat));
                hsimErrsByPars[0][whichHrepeat].add(Hsim2);
            }
        }
        // Average the squared errors for each set of fsim/hsim params across all iterations
        PRAOerrors[] fMSE = new PRAOerrors[fsimRepeat.size()];
        PRAOerrors[][] hMSE = new PRAOerrors[1][hsimRepeat.size()];
        String[][] latexTableArray = new String[1 * hsimRepeat.size() + fsimRepeat.size()][5];
        for (int j = 0; j < fMSE.length; j++) {
            fMSE[j] = new PRAOerrors(fsimErrsByPars[j], "MSE for Fsim at vars=" + vars + " edgeratio=" + edgeratio + " cases=" + cases + " frepeat=" + fsimRepeat.get(j) + " iterations=" + iterations);
            // if(verbosity>0){System.out.println(fMSE[j].allToString());}
            output = output + fMSE[j].allToString() + nl;
            latexTableArray[j] = prelimToPRAOtable(fMSE[j]);
        }
        for (int j = 0; j < hMSE.length; j++) {
            for (int k = 0; k < hMSE[j].length; k++) {
                hMSE[j][k] = new PRAOerrors(hsimErrsByPars[j][k], "MSE for Hsim at vars=" + vars + " edgeratio=" + edgeratio + " cases=" + cases + " rsize=" + 1 + " repeat=" + hsimRepeat.get(k) + " iterations=" + iterations);
                // if(verbosity>0){System.out.println(hMSE[j][k].allToString());}
                output = output + hMSE[j][k].allToString() + nl;
                latexTableArray[fsimRepeat.size() + j * hMSE[j].length + k] = prelimToPRAOtable(hMSE[j][k]);
            }
        }
        // record all the params, the base error values, and the fsim/hsim mean squared errors
        String latexTable = HsimUtils.makeLatexTable(latexTableArray);
        PrintWriter writer = new PrintWriter("latexTable.txt", "UTF-8");
        writer.println(latexTable);
        writer.close();
        PrintWriter writer2 = new PrintWriter("HvsF-SimulationEvaluation.txt", "UTF-8");
        writer2.println(output);
        writer2.close();
        long timestop = System.nanoTime();
        System.out.println("Evaluation Concluded. Duration: " + (timestop - timestart) / 1000000000 + "s");
    } catch (Exception IOException) {
        IOException.printStackTrace();
    }
}
Also used : TabularDataReader(edu.pitt.dbmi.data.reader.tabular.TabularDataReader) DataSet(edu.cmu.tetrad.data.DataSet) ICovarianceMatrix(edu.cmu.tetrad.data.ICovarianceMatrix) SemPm(edu.cmu.tetrad.sem.SemPm) SemEstimator(edu.cmu.tetrad.sem.SemEstimator) PrintWriter(java.io.PrintWriter) Path(java.nio.file.Path) PatternToDag(edu.cmu.tetrad.search.PatternToDag) ContinuousTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader) PatternToDag(edu.cmu.tetrad.search.PatternToDag) Dag(edu.cmu.tetrad.graph.Dag) Fges(edu.cmu.tetrad.search.Fges) Graph(edu.cmu.tetrad.graph.Graph) CovarianceMatrixOnTheFly(edu.cmu.tetrad.data.CovarianceMatrixOnTheFly) File(java.io.File) SemIm(edu.cmu.tetrad.sem.SemIm) SemBicScore(edu.cmu.tetrad.search.SemBicScore)

Example 5 with ContinuousTabularDataFileReader

use of edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader in project tetrad by cmu-phil.

the class Comparison2 method compare.

/**
 * Simulates data from model parameterizing the given DAG, and runs the
 * algorithm on that data, printing out error statistics.
 */
public static ComparisonResult compare(ComparisonParameters params) {
    DataSet dataSet = null;
    Graph trueDag = null;
    IndependenceTest test = null;
    Score score = null;
    ComparisonResult result = new ComparisonResult(params);
    if (params.isDataFromFile()) {
        /**
         * Set path to the data directory *
         */
        String path = "/Users/dmalinsky/Documents/research/data/danexamples";
        File dir = new File(path);
        File[] files = dir.listFiles();
        if (files == null) {
            throw new NullPointerException("No files in " + path);
        }
        for (File file : files) {
            if (file.getName().startsWith("graph") && file.getName().contains(String.valueOf(params.getGraphNum())) && file.getName().endsWith(".g.txt")) {
                params.setGraphFile(file.getName());
                trueDag = GraphUtils.loadGraphTxt(file);
                break;
            }
        }
        String trialGraph = String.valueOf(params.getGraphNum()).concat("-").concat(String.valueOf(params.getTrial())).concat(".dat.txt");
        for (File file : files) {
            if (file.getName().startsWith("graph") && file.getName().endsWith(trialGraph)) {
                Path dataFile = Paths.get(path.concat("/").concat(file.getName()));
                Delimiter delimiter = Delimiter.TAB;
                if (params.getDataType() == ComparisonParameters.DataType.Continuous) {
                    try {
                        TabularDataReader dataReader = new ContinuousTabularDataFileReader(dataFile.toFile(), delimiter);
                        dataSet = (DataSet) DataConvertUtils.toDataModel(dataReader.readInData());
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                    params.setDataFile(file.getName());
                    break;
                } else {
                    try {
                        TabularDataReader dataReader = new VerticalDiscreteTabularDataReader(dataFile.toFile(), delimiter);
                        dataSet = (DataSet) DataConvertUtils.toDataModel(dataReader.readInData());
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                    params.setDataFile(file.getName());
                    break;
                }
            }
        }
        System.out.println("current graph file = " + params.getGraphFile());
        System.out.println("current data set file = " + params.getDataFile());
    }
    if (params.isNoData()) {
        List<Node> nodes = new ArrayList<>();
        for (int i = 0; i < params.getNumVars(); i++) {
            nodes.add(new ContinuousVariable("X" + (i + 1)));
        }
        trueDag = GraphUtils.randomGraphRandomForwardEdges(nodes, 0, params.getNumEdges(), 10, 10, 10, false, true);
        /**
         * added 5.25.16 for tsFCI *
         */
        if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
            trueDag = GraphUtils.randomGraphRandomForwardEdges(nodes, 0, params.getNumEdges(), 10, 10, 10, false, true);
            trueDag = TimeSeriesUtils.graphToLagGraph(trueDag, 2);
            System.out.println("Creating Time Lag Graph : " + trueDag);
        }
        /**
         * ************************
         */
        test = new IndTestDSep(trueDag);
        score = new GraphScore(trueDag);
        if (params.getAlgorithm() == null) {
            throw new IllegalArgumentException("Algorithm not set.");
        }
        long time1 = System.currentTimeMillis();
        if (params.getAlgorithm() == ComparisonParameters.Algorithm.PC) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            Pc search = new Pc(test);
            result.setResultGraph(search.search());
            result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.CPC) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            Cpc search = new Cpc(test);
            result.setResultGraph(search.search());
            result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.PCLocal) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            PcLocal search = new PcLocal(test);
            result.setResultGraph(search.search());
            result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.PCStableMax) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            PcStableMax search = new PcStableMax(test);
            result.setResultGraph(search.search());
            result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.FGES) {
            if (score == null) {
                throw new IllegalArgumentException("Score not set.");
            }
            Fges search = new Fges(score);
            // search.setFaithfulnessAssumed(params.isOneEdgeFaithfulnessAssumed());
            result.setResultGraph(search.search());
            result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.FCI) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            Fci search = new Fci(test);
            result.setResultGraph(search.search());
            result.setCorrectResult(new DagToPag(trueDag).convert());
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.GFCI) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            GFci search = new GFci(test, score);
            result.setResultGraph(search.search());
            result.setCorrectResult(new DagToPag(trueDag).convert());
        } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
            if (test == null) {
                throw new IllegalArgumentException("Test not set.");
            }
            TsFci search = new TsFci(test);
            IKnowledge knowledge = getKnowledge(trueDag);
            search.setKnowledge(knowledge);
            result.setResultGraph(search.search());
            result.setCorrectResult(new TsDagToPag(trueDag).convert());
            System.out.println("Correct result for trial = " + result.getCorrectResult());
            System.out.println("Search result for trial = " + result.getResultGraph());
        } else {
            throw new IllegalArgumentException("Unrecognized algorithm.");
        }
        long time2 = System.currentTimeMillis();
        long elapsed = time2 - time1;
        result.setElapsed(elapsed);
        result.setTrueDag(trueDag);
        return result;
    } else if (params.getDataFile() != null) {
        // dataSet = loadDataFile(params.getDataFile());
        System.out.println("Using data from file... ");
        if (params.getGraphFile() == null) {
            throw new IllegalArgumentException("True graph file not set.");
        } else {
            System.out.println("Using graph from file... ");
        // trueDag = GraphUtils.loadGraph(File params.getGraphFile());
        }
    } else {
        if (params.getNumVars() == -1) {
            throw new IllegalArgumentException("Number of variables not set.");
        }
        if (params.getNumEdges() == -1) {
            throw new IllegalArgumentException("Number of edges not set.");
        }
        if (params.getDataType() == ComparisonParameters.DataType.Continuous) {
            List<Node> nodes = new ArrayList<>();
            for (int i = 0; i < params.getNumVars(); i++) {
                nodes.add(new ContinuousVariable("X" + (i + 1)));
            }
            trueDag = GraphUtils.randomGraphRandomForwardEdges(nodes, 0, params.getNumEdges(), 10, 10, 10, false, true);
            /**
             * added 6.08.16 for tsFCI *
             */
            if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
                trueDag = GraphUtils.randomGraphRandomForwardEdges(nodes, 0, params.getNumEdges(), 10, 10, 10, false, true);
                trueDag = TimeSeriesUtils.graphToLagGraph(trueDag, 2);
                System.out.println("Creating Time Lag Graph : " + trueDag);
            }
            if (params.getDataType() == null) {
                throw new IllegalArgumentException("Data type not set or inferred.");
            }
            if (params.getSampleSize() == -1) {
                throw new IllegalArgumentException("Sample size not set.");
            }
            LargeScaleSimulation sim = new LargeScaleSimulation(trueDag);
            /**
             * added 6.08.16 for tsFCI *
             */
            if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
                sim.setCoefRange(0.20, 0.50);
            }
            /**
             * added 6.08.16 for tsFCI *
             */
            if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
                // //                    System.out.println("Coefs matrix : " + sim.getCoefs());
                // System.out.println(MatrixUtils.toString(sim.getCoefficientMatrix()));
                // //                    System.out.println("dim = " + sim.getCoefs()[1][1]);
                // boolean isStableTetradMatrix = allEigenvaluesAreSmallerThanOneInModulus(new TetradMatrix(sim.getCoefficientMatrix()));
                // //this TetradMatrix needs to be the matrix of coefficients from the SEM!
                // if (!isStableTetradMatrix) {
                // System.out.println("%%%%%%%%%% WARNING %%%%%%%%% not a stable set of eigenvalues for data generation");
                // System.out.println("Skipping this attempt!");
                // sim.setCoefRange(0.2, 0.5);
                // dataSet = sim.simulateDataAcyclic(params.getSampleSize());
                // }
                // 
                // /***************************/
                boolean isStableTetradMatrix;
                int attempt = 1;
                int tierSize = params.getNumVars();
                int[] sub = new int[tierSize];
                int[] sub2 = new int[tierSize];
                for (int i = 0; i < tierSize; i++) {
                    sub[i] = i;
                    sub2[i] = tierSize + i;
                }
                do {
                    dataSet = sim.simulateDataFisher(params.getSampleSize());
                    // System.out.println("Variable Nodes : " + sim.getVariableNodes());
                    // System.out.println(MatrixUtils.toString(sim.getCoefficientMatrix()));
                    TetradMatrix coefMat = new TetradMatrix(sim.getCoefficientMatrix());
                    TetradMatrix B = coefMat.getSelection(sub, sub);
                    TetradMatrix Gamma1 = coefMat.getSelection(sub2, sub);
                    TetradMatrix Gamma0 = TetradMatrix.identity(tierSize).minus(B);
                    TetradMatrix A1 = Gamma0.inverse().times(Gamma1);
                    // TetradMatrix B2 = coefMat.getSelection(sub2, sub2);
                    // System.out.println("B matrix : " + B);
                    // System.out.println("B2 matrix : " + B2);
                    // System.out.println("Gamma1 matrix : " + Gamma1);
                    // isStableTetradMatrix = allEigenvaluesAreSmallerThanOneInModulus(new TetradMatrix(sim.getCoefficientMatrix()));
                    isStableTetradMatrix = TimeSeriesUtils.allEigenvaluesAreSmallerThanOneInModulus(A1);
                    System.out.println("isStableTetradMatrix? : " + isStableTetradMatrix);
                    attempt++;
                } while ((!isStableTetradMatrix) && attempt <= 5);
                if (!isStableTetradMatrix) {
                    System.out.println("%%%%%%%%%% WARNING %%%%%%%% not a stable coefficient matrix, forcing coefs to [0.15,0.3]");
                    System.out.println("Made " + (attempt - 1) + " attempts to get stable matrix.");
                    sim.setCoefRange(0.15, 0.3);
                    dataSet = sim.simulateDataFisher(params.getSampleSize());
                } else {
                    System.out.println("Coefficient matrix is stable.");
                }
            }
        } else if (params.getDataType() == ComparisonParameters.DataType.Discrete) {
            List<Node> nodes = new ArrayList<>();
            for (int i = 0; i < params.getNumVars(); i++) {
                nodes.add(new DiscreteVariable("X" + (i + 1), 3));
            }
            trueDag = GraphUtils.randomGraphRandomForwardEdges(nodes, 0, params.getNumEdges(), 10, 10, 10, false, true);
            if (params.getDataType() == null) {
                throw new IllegalArgumentException("Data type not set or inferred.");
            }
            if (params.getSampleSize() == -1) {
                throw new IllegalArgumentException("Sample size not set.");
            }
            int[] tiers = new int[nodes.size()];
            for (int i = 0; i < nodes.size(); i++) {
                tiers[i] = i;
            }
            BayesPm pm = new BayesPm(trueDag, 3, 3);
            MlBayesIm im = new MlBayesIm(pm, MlBayesIm.RANDOM);
            dataSet = im.simulateData(params.getSampleSize(), false, tiers);
        } else {
            throw new IllegalArgumentException("Unrecognized data type.");
        }
        if (dataSet == null) {
            throw new IllegalArgumentException("No data set.");
        }
    }
    if (params.getIndependenceTest() == ComparisonParameters.IndependenceTestType.FisherZ) {
        if (params.getDataType() != null && params.getDataType() != ComparisonParameters.DataType.Continuous) {
            throw new IllegalArgumentException("Data type previously set to something other than continuous.");
        }
        if (Double.isNaN(params.getAlpha())) {
            throw new IllegalArgumentException("Alpha not set.");
        }
        test = new IndTestFisherZ(dataSet, params.getAlpha());
        params.setDataType(ComparisonParameters.DataType.Continuous);
    } else if (params.getIndependenceTest() == ComparisonParameters.IndependenceTestType.ChiSquare) {
        if (params.getDataType() != null && params.getDataType() != ComparisonParameters.DataType.Discrete) {
            throw new IllegalArgumentException("Data type previously set to something other than discrete.");
        }
        if (Double.isNaN(params.getAlpha())) {
            throw new IllegalArgumentException("Alpha not set.");
        }
        test = new IndTestChiSquare(dataSet, params.getAlpha());
        params.setDataType(ComparisonParameters.DataType.Discrete);
    }
    if (params.getScore() == ScoreType.SemBic) {
        if (params.getDataType() != null && params.getDataType() != ComparisonParameters.DataType.Continuous) {
            throw new IllegalArgumentException("Data type previously set to something other than continuous.");
        }
        if (Double.isNaN(params.getPenaltyDiscount())) {
            throw new IllegalArgumentException("Penalty discount not set.");
        }
        SemBicScore semBicScore = new SemBicScore(new CovarianceMatrixOnTheFly(dataSet));
        semBicScore.setPenaltyDiscount(params.getPenaltyDiscount());
        score = semBicScore;
        params.setDataType(ComparisonParameters.DataType.Continuous);
    } else if (params.getScore() == ScoreType.BDeu) {
        if (params.getDataType() != null && params.getDataType() != ComparisonParameters.DataType.Discrete) {
            throw new IllegalArgumentException("Data type previously set to something other than discrete.");
        }
        if (Double.isNaN(params.getSamplePrior())) {
            throw new IllegalArgumentException("Sample prior not set.");
        }
        if (Double.isNaN(params.getStructurePrior())) {
            throw new IllegalArgumentException("Structure prior not set.");
        }
        score = new BDeuScore(dataSet);
        ((BDeuScore) score).setSamplePrior(params.getSamplePrior());
        ((BDeuScore) score).setStructurePrior(params.getStructurePrior());
        params.setDataType(ComparisonParameters.DataType.Discrete);
        params.setDataType(ComparisonParameters.DataType.Discrete);
    }
    if (params.getAlgorithm() == null) {
        throw new IllegalArgumentException("Algorithm not set.");
    }
    long time1 = System.currentTimeMillis();
    if (params.getAlgorithm() == ComparisonParameters.Algorithm.PC) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        Pc search = new Pc(test);
        result.setResultGraph(search.search());
        result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.CPC) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        Cpc search = new Cpc(test);
        result.setResultGraph(search.search());
        result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.PCLocal) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        PcLocal search = new PcLocal(test);
        result.setResultGraph(search.search());
        result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.PCStableMax) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        PcStableMax search = new PcStableMax(test);
        result.setResultGraph(search.search());
        result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.FGES) {
        if (score == null) {
            throw new IllegalArgumentException("Score not set.");
        }
        Fges search = new Fges(score);
        // search.setFaithfulnessAssumed(params.isOneEdgeFaithfulnessAssumed());
        result.setResultGraph(search.search());
        result.setCorrectResult(SearchGraphUtils.patternForDag(new EdgeListGraph(trueDag)));
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.FCI) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        Fci search = new Fci(test);
        result.setResultGraph(search.search());
        result.setCorrectResult(new DagToPag(trueDag).convert());
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.GFCI) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        GFci search = new GFci(test, score);
        result.setResultGraph(search.search());
        result.setCorrectResult(new DagToPag(trueDag).convert());
    } else if (params.getAlgorithm() == ComparisonParameters.Algorithm.TsFCI) {
        if (test == null) {
            throw new IllegalArgumentException("Test not set.");
        }
        TsFci search = new TsFci(test);
        IKnowledge knowledge = getKnowledge(trueDag);
        search.setKnowledge(knowledge);
        result.setResultGraph(search.search());
        result.setCorrectResult(new TsDagToPag(trueDag).convert());
    } else {
        throw new IllegalArgumentException("Unrecognized algorithm.");
    }
    long time2 = System.currentTimeMillis();
    long elapsed = time2 - time1;
    result.setElapsed(elapsed);
    result.setTrueDag(trueDag);
    return result;
}
Also used : MlBayesIm(edu.cmu.tetrad.bayes.MlBayesIm) Node(edu.cmu.tetrad.graph.Node) ArrayList(java.util.ArrayList) ArrayList(java.util.ArrayList) List(java.util.List) EdgeListGraph(edu.cmu.tetrad.graph.EdgeListGraph) EdgeListGraph(edu.cmu.tetrad.graph.EdgeListGraph) Graph(edu.cmu.tetrad.graph.Graph) TabularDataReader(edu.pitt.dbmi.data.reader.tabular.TabularDataReader) VerticalDiscreteTabularDataReader(edu.pitt.dbmi.data.reader.tabular.VerticalDiscreteTabularDataReader) LargeScaleSimulation(edu.cmu.tetrad.sem.LargeScaleSimulation) VerticalDiscreteTabularDataReader(edu.pitt.dbmi.data.reader.tabular.VerticalDiscreteTabularDataReader) Path(java.nio.file.Path) Delimiter(edu.pitt.dbmi.data.Delimiter) ContinuousTabularDataFileReader(edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader) TetradMatrix(edu.cmu.tetrad.util.TetradMatrix) BayesPm(edu.cmu.tetrad.bayes.BayesPm)

Aggregations

ContinuousTabularDataFileReader (edu.pitt.dbmi.data.reader.tabular.ContinuousTabularDataFileReader)7 TabularDataReader (edu.pitt.dbmi.data.reader.tabular.TabularDataReader)7 DataSet (edu.cmu.tetrad.data.DataSet)5 Path (java.nio.file.Path)5 Graph (edu.cmu.tetrad.graph.Graph)4 File (java.io.File)3 PrintWriter (java.io.PrintWriter)3 Node (edu.cmu.tetrad.graph.Node)2 Delimiter (edu.pitt.dbmi.data.Delimiter)2 VerticalDiscreteTabularDataReader (edu.pitt.dbmi.data.reader.tabular.VerticalDiscreteTabularDataReader)2 ArrayList (java.util.ArrayList)2 List (java.util.List)2 BayesPm (edu.cmu.tetrad.bayes.BayesPm)1 MlBayesIm (edu.cmu.tetrad.bayes.MlBayesIm)1 ContinuousVariable (edu.cmu.tetrad.data.ContinuousVariable)1 CovarianceMatrixOnTheFly (edu.cmu.tetrad.data.CovarianceMatrixOnTheFly)1 DataModel (edu.cmu.tetrad.data.DataModel)1 ICovarianceMatrix (edu.cmu.tetrad.data.ICovarianceMatrix)1 Dag (edu.cmu.tetrad.graph.Dag)1 EdgeListGraph (edu.cmu.tetrad.graph.EdgeListGraph)1