Example usage for weka.core.converters CSVLoader setFile

List of usage examples for weka.core.converters CSVLoader setFile

  1. HOME
  2. Java
  3. weka
  4. weka.core.converters.*
  5. CSVLoader
  6. setFile

Introduction

In this page you can find the example usage for weka.core.converters CSVLoader setFile.

Prototype

@Override
public void setFile(File file) throws IOException

Source Link

Document

sets the source File

Usage

From source file:classif.ExperimentsLauncher.java

License:Open Source License

public static Instances[] readTrainAndTest(String name) {
    File trainFile = new File(datasetsDir + name + "/" + name + "_TRAIN");
    if (!new File(trainFile.getAbsolutePath() + ".csv").exists()) {
        UCR2CSV.run(trainFile, new File(trainFile.getAbsolutePath() + ".csv"));
    }/*w  ww.j a  v a  2s.  c  o  m*/
    trainFile = new File(trainFile.getAbsolutePath() + ".csv");
    File testFile = new File(datasetsDir + name + "/" + name + "_TEST");
    if (!new File(testFile.getAbsolutePath() + ".csv").exists()) {
        UCR2CSV.run(testFile, new File(testFile.getAbsolutePath() + ".csv"));
    }
    testFile = new File(testFile.getAbsolutePath() + ".csv");

    CSVLoader loader = new CSVLoader();
    Instances trainDataset = null;
    Instances testDataset = null;

    try {
        loader.setFile(trainFile);
        loader.setNominalAttributes("first");
        trainDataset = loader.getDataSet();
        trainDataset.setClassIndex(0);

        loader.setFile(testFile);
        loader.setNominalAttributes("first");
        testDataset = loader.getDataSet();
        testDataset.setClassIndex(0);
    } catch (Exception e) {
        e.printStackTrace();
    }
    return new Instances[] { trainDataset, testDataset };
}

From source file:demo.Demo.java

License:Open Source License

/**
 * @param args//from  w w  w  .j  a v a  2  s .  c o m
 * @throws IOException 
 */
public static void main(String[] args) throws IOException {

    CSVLoader loader = new CSVLoader();
    System.out.println("Downloading dataset...");
    URL oracle = new URL("http://repository.seasr.org/Datasets/UCI/csv/mushroom.csv");
    File csvFile = File.createTempFile("data-", ".csv");
    BufferedReader in = new BufferedReader(new InputStreamReader(oracle.openStream()));
    PrintWriter out = new PrintWriter(new BufferedOutputStream(new FileOutputStream(csvFile)));
    String inputLine;
    while ((inputLine = in.readLine()) != null) {
        out.println(inputLine);
    }
    in.close();
    out.close();
    System.out.println("Dataset written to: " + csvFile.getAbsolutePath());

    loader.setFile(csvFile);
    loader.setNominalAttributes("first-last");
    Instances instances = loader.getDataSet();
    String[] variablesNames = new String[instances.numAttributes()];
    for (int i = 0; i < variablesNames.length; i++) {
        variablesNames[i] = instances.attribute(i).name();
    }

    ChordalysisModelling modeller = new ChordalysisModelling(0.05);

    System.out.println("Learning...");
    modeller.buildModel(instances);
    DecomposableModel bestModel = modeller.getModel();
    bestModel.display(variablesNames);
    System.out.println("The model selected is:");
    System.out.println(bestModel.toString(variablesNames));
    bestModel.display(variablesNames);

}

From source file:demo.DemoInference.java

License:Open Source License

/**
 * @param args//from   ww  w  .  j  a  v  a 2 s  .com
 * @throws IOException 
 */
public static void main(String[] args) throws IOException {

    CSVLoader loader = new CSVLoader();
    System.out.println("Downloading dataset...");
    URL oracle = new URL("http://repository.seasr.org/Datasets/UCI/csv/mushroom.csv");
    File csvFile = File.createTempFile("data-", ".csv");
    BufferedReader in = new BufferedReader(new InputStreamReader(oracle.openStream()));
    PrintWriter out = new PrintWriter(new BufferedOutputStream(new FileOutputStream(csvFile)));
    String inputLine;
    while ((inputLine = in.readLine()) != null) {
        out.println(inputLine);
    }
    in.close();
    out.close();
    System.out.println("Dataset written to: " + csvFile.getAbsolutePath());

    loader.setFile(csvFile);
    loader.setNominalAttributes("first-last");
    Instances instances = loader.getDataSet();
    String[] variablesNames = new String[instances.numAttributes()];
    String[][] outcomes = new String[instances.numAttributes()][];
    for (int i = 0; i < variablesNames.length; i++) {
        variablesNames[i] = instances.attribute(i).name();
        outcomes[i] = new String[instances.attribute(i).numValues() + 1];//+1 for missing
        for (int j = 0; j < outcomes[i].length - 1; j++) {
            outcomes[i][j] = instances.attribute(i).value(j);
        }
        outcomes[i][outcomes[i].length - 1] = "missing";
        System.out.println("Dom(" + variablesNames[i] + ") = " + Arrays.toString(outcomes[i]));

    }

    ChordalysisModelling modeller = new ChordalysisModelling(0.05);

    System.out.println("Learning...");
    modeller.buildModel(instances);
    DecomposableModel bestModel = modeller.getModel();
    //      bestModel.display(variablesNames);
    System.out.println("The model selected is:");
    System.out.println(bestModel.toString(variablesNames));

    Inference inference = new Inference(bestModel, variablesNames, outcomes);
    inference.setProbabilities(modeller.getLattice());
    String targetVariable = "population";
    System.out.println("initial beliefs on " + targetVariable + " "
            + Arrays.toString(inference.getBelief(targetVariable)));

    System.out.println("adding evidence poisonous and convex shape");
    inference.addEvidence("class", "e");
    inference.addEvidence("cap-shape", "x");
    inference.recordEvidence();

    System.out.println(
            "beliefs on " + targetVariable + " " + Arrays.toString(inference.getBelief(targetVariable)));

    inference.clearEvidences();
    System.out.println("reset beliefs");
    System.out.println(
            "reset beliefs on " + targetVariable + " " + Arrays.toString(inference.getBelief(targetVariable)));

}

From source file:demo.Run.java

License:Open Source License

/**
 * @param args/*from  w ww. j a  v  a 2 s .  c  o  m*/
 */
public static void main(String[] args) {
    if (args.length != 4) {
        System.out.println("Usage:\tjava -Xmx1g -jar Chordalysis.jar dataFile pvalue imageOutputFile useGUI?");
        System.out.println("Example:\tjava -Xmx1g -jar Chordalysis.jar dataset.csv 0.05 graph.png false");
        System.out.println("\nNote:\t'1g' means that you authorize 1GB of memory. "
                + "\nNote:\tIt should be adjusted depending upon the size of your data set (mostly required to load the data set).");
        return;
    }
    System.out.println();
    CSVLoader loader = new CSVLoader();
    File csvFile = new File(args[0]);
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    } else {
        System.out.println("Info:\tUsing the dataset file " + csvFile.getAbsolutePath());
    }

    double pValue = Double.valueOf(args[1]);
    if (pValue <= 0 || 1 <= pValue) {
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    } else {
        System.out.println("Info:\tUsing p=" + pValue);
    }

    File outPutFile = new File(args[2]);
    String[] splitted = outPutFile.getName().split("\\.");
    if (splitted.length < 2) {
        System.out.println(
                "The image output file should declare an extension among \".jpg\", \".png\" or \".gif\"");
        return;
    }
    String extension = splitted[splitted.length - 1];
    if (!extension.equals("jpg") && !extension.equals("png") && !extension.equals("gif")) {
        System.out.println(
                "The format for the graphical representation of the model should be either jpg, png or gif. ");
        return;
    } else {
        System.out.println("Info:\tExporting result as a " + extension + " file");
    }

    boolean gui = Boolean.parseBoolean(args[3]);

    if (gui) {
        System.out.println("Info:\tUsing a graphical user interface");
    } else {
        System.out.println("Info:\tNot using a graphical user interface");
    }

    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }
        long start = System.currentTimeMillis();

        ChordalysisModelling modeller = new ChordalysisModelling(pValue);
        modeller.buildModel(instances);
        DecomposableModel bestModel = modeller.getModel();

        if (gui)
            bestModel.display(variablesNames);
        System.out
                .println("The model selected is: (selected in " + (System.currentTimeMillis() - start) + "ms)");
        System.out.println(bestModel.toString(variablesNames));
        ImageIO.write(bestModel.getImage(variablesNames), extension, outPutFile);
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    }
}

From source file:demo.RunDot.java

License:Open Source License

/**
 * @param args// ww w.ja  v a2  s  .  c om
 */
public static void main(String[] args) {
    if (args.length != 3) {
        System.out.println("Usage:\tjava -Xmx1g -jar Chordalysis.jar dataFile pvalue dotOutputFile");
        System.out.println("Example:\tjava -Xmx1g -jar Chordalysis.jar dataset.csv 0.05 graph.dot");
        System.out.println("\nNote:\t'1g' means that you authorize 1GB of memory. "
                + "\nNote:\tIt should be adjusted depending upon the size of your data set (mostly required to load the data set).");
        return;
    }
    System.out.println();
    CSVLoader loader = new CSVLoader();
    File csvFile = new File(args[0]);
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    } else {
        System.out.println("Info:\tUsing the dataset file " + csvFile.getAbsolutePath());
    }

    double pValue = Double.valueOf(args[1]);
    if (pValue <= 0 || 1 <= pValue) {
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    } else {
        System.out.println("Info:\tUsing p=" + pValue);
    }

    File outPutFile = new File(args[2]);
    String[] splitted = outPutFile.getName().split("\\.");
    if (splitted.length < 2) {
        System.out.println("The image output file should declare a \".dot\" extension");
        return;
    }

    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }
        long start = System.currentTimeMillis();

        ChordalysisModelling modeller = new ChordalysisModelling(pValue);
        modeller.buildModel(instances);
        DecomposableModel bestModel = modeller.getModel();

        System.out
                .println("The model selected is: (selected in " + (System.currentTimeMillis() - start) + "ms)");
        System.out.println(bestModel.toString(variablesNames));
        bestModel.exportDOT(outPutFile, variablesNames);
        System.out.println(
                "DOT file exported - note that the variables with no neighbors won't be included in the graph");
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    }
}

From source file:demo.RunGUI.java

License:Open Source License

/**
 * @param args// w w w. ja  va 2s  .c om
 */
public static void main(String[] args) {
    JFileChooser chooser = new JFileChooser();
    FileNameExtensionFilter filter = new FileNameExtensionFilter("CSV file", "csv");
    chooser.setFileFilter(filter);
    int returnVal = chooser.showOpenDialog(null);
    if (returnVal == JFileChooser.APPROVE_OPTION) {
        System.out.println("You chose to open this file: " + chooser.getSelectedFile().getName());
    }
    CSVLoader loader = new CSVLoader();
    File csvFile = chooser.getSelectedFile();
    if (!csvFile.exists()) {
        System.out.println("The file doesn't exist");
        return;
    }

    double pValue = Double.valueOf(JOptionPane.showInputDialog("Desired p-value ]0,1[", 0.05));
    if (pValue <= 0 || 1 <= pValue) {
        System.out.println("The p-value should be between 0 and 1 excluded. ");
        return;
    }
    try {
        loader.setFile(csvFile);
        loader.setNominalAttributes("first-last");
        Instances instances = loader.getDataSet();
        String[] variablesNames = new String[instances.numAttributes()];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
        }

        ChordalysisModelling modeller = new ChordalysisModelling(pValue);
        modeller.buildModel(instances);
        DecomposableModel bestModel = modeller.getModel();
        System.out.println("The model selected is:");
        System.out.println(bestModel.toString(variablesNames));
        bestModel.display(variablesNames);
    } catch (IOException e) {
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    }

}

From source file:demo.RunGUIProof.java

License:Open Source License

/**
 * @param args//from   w w w  .  j a  v  a 2  s  .c  om
 */
public static void main(String[] args) {
    JOptionPane.showMessageDialog(null, introductionMessage, "Chordalysis", JOptionPane.INFORMATION_MESSAGE);

    int result = JOptionPane.showOptionDialog(null, new JTextArea(agreeCitation), "Reference",
            JOptionPane.YES_NO_OPTION, JOptionPane.QUESTION_MESSAGE, null, null, null);
    if (result == JOptionPane.NO_OPTION || result == JOptionPane.CLOSED_OPTION) {
        JOptionPane.showMessageDialog(null,
                "Chordalysis will now stop, because you do not want to reference its source. ", "Chordalysis",
                JOptionPane.WARNING_MESSAGE);
        System.exit(0);
    }

    JFileChooser chooser = new JFileChooser();
    FileNameExtensionFilter filter = new FileNameExtensionFilter("CSV file", "csv");
    chooser.setFileFilter(filter);
    int returnVal = chooser.showOpenDialog(null);
    File csvFile = null;
    if (returnVal == JFileChooser.APPROVE_OPTION) {
        csvFile = chooser.getSelectedFile();
        System.out.println("You chose to open: " + csvFile);
    } else {
        JOptionPane.showMessageDialog(null, noFileSelectedMessage, "Chordalysis", JOptionPane.ERROR_MESSAGE);
        return;
    }
    CSVLoader loader = new CSVLoader();
    if (!csvFile.exists()) {
        JOptionPane.showMessageDialog(null, noFileMessage, "Chordalysis", JOptionPane.INFORMATION_MESSAGE);
        return;
    }
    double pValue = -1;
    while (pValue <= 0 || 1 <= pValue) {
        pValue = Double.valueOf(JOptionPane.showInputDialog("Desired p-value (between 0 and 1)", 0.05));
        if (pValue <= 0 || 1 <= pValue) {
            JOptionPane.showMessageDialog(null, incorrectPValueMessage, "Chordalysis",
                    JOptionPane.WARNING_MESSAGE);
        }
    }

    filter = new FileNameExtensionFilter("PNG or DOT or CSV file or DNE file", "png", "dot", "csv", "dne");
    chooser = new JFileChooser();
    chooser.setFileFilter(filter);
    chooser.setDialogTitle("Where to save the graph?");
    chooser.setSelectedFile(new File(csvFile.getAbsolutePath() + ".png"));
    returnVal = chooser.showSaveDialog(null);
    File graphFile = null;
    if (returnVal == JFileChooser.APPROVE_OPTION) {
        graphFile = chooser.getSelectedFile();
        System.out.println("You chose to save the graph to: " + graphFile.getAbsolutePath());
    } else {
        JOptionPane.showMessageDialog(null, noFileSelectedMessage, "Chordalysis", JOptionPane.ERROR_MESSAGE);
        return;
    }

    try {
        loader.setFile(csvFile);

        returnVal = JOptionPane.showConfirmDialog(null, "Are all of your attribute nominal?", "Chordalysis",
                JOptionPane.YES_NO_OPTION);
        if (returnVal == JOptionPane.YES_OPTION) {
            loader.setNominalAttributes("first-last");
        }

        Instances instances = loader.getDataSet();

        String cols = "";
        for (int i = 0; i < instances.numAttributes(); i++) {
            Attribute att = instances.attribute(i);
            if (!att.isNominal()) {
                cols += (i + 1) + ",";
            }
        }
        if (!cols.isEmpty()) {
            cols = cols.substring(0, cols.length() - 1);
            String message = "Some atributes are not nominal (number " + cols
                    + "), please wait during discretization. ";
            JOptionPane.showMessageDialog(null, message, "Chordalysis", JOptionPane.INFORMATION_MESSAGE);
            Discretize discretizer = new Discretize(cols);
            discretizer.setUseEqualFrequency(true);
            discretizer.setBins(3);
            discretizer.setIgnoreClass(true);
            discretizer.setInputFormat(instances);
            instances = Filter.useFilter(instances, discretizer);
            JOptionPane.showMessageDialog(null, "Discretization is now finished.", "Chordalysis",
                    JOptionPane.INFORMATION_MESSAGE);
        }

        String[] variablesNames = new String[instances.numAttributes()];
        String[][] outcomes = new String[instances.numAttributes()][];
        for (int i = 0; i < variablesNames.length; i++) {
            variablesNames[i] = instances.attribute(i).name();
            outcomes[i] = new String[instances.attribute(i).numValues()];
            for (int j = 0; j < outcomes[i].length; j++) {
                outcomes[i][j] = instances.attribute(i).value(j);
            }
        }

        ChordalysisModelling modeller = new ChordalysisModelling(pValue);
        modeller.buildModel(instances);
        DecomposableModel bestModel = modeller.getModel();
        JOptionPane.showMessageDialog(null, new JTextArea("Chordalysis has now finished analysing your data. "
                + "\nIf you found something useful, please reference Chordalysis as"
                + "\n\t- F. Petitjean, G.I. Webb and A. Nicholson, Scaling log-linear analysis to high-dimensional data, ICDM 2013"
                + "\n\t- F. Petitjean and G.I. Webb, Scaling log-linear analysis to datasets with thousands of variables, SDM 2015"
                + "\n\nYou can find the output file at: '" + graphFile.getAbsolutePath() + "'"), "Citation",
                JOptionPane.INFORMATION_MESSAGE);
        System.out.println("The model selected is:");
        System.out.println(bestModel.toString(variablesNames));
        if (graphFile.getName().endsWith("dot")) {
            bestModel.exportDOT(graphFile, variablesNames);
        } else if (graphFile.getName().endsWith("png")) {
            ImageIO.write(bestModel.getImage(variablesNames), "png", graphFile);
        } else if (graphFile.getName().endsWith("dne")) {
            bestModel.exportBNNetica(graphFile, variablesNames, outcomes);
            bestModel.exportDOT(new File(graphFile.getAbsolutePath() + ".dot"), variablesNames);
            ImageIO.write(bestModel.getImage(variablesNames), "png",
                    new File(graphFile.getAbsolutePath() + ".png"));
            bestModel.saveAssociations(variablesNames, new File(graphFile.getAbsolutePath() + ".csv"));
        } else {
            bestModel.saveAssociations(variablesNames, graphFile);
        }

    } catch (IOException e) {
        JOptionPane.showMessageDialog(null,
                "The file '" + csvFile.getAbsolutePath() + "'\ncannot be read properly.",
                "Error while reading file", JOptionPane.ERROR_MESSAGE);
        System.out.println("I/O error while loading csv file");
        e.printStackTrace();
    } catch (Exception e) {
        JOptionPane.showMessageDialog(null, "Error:" + e.getMessage(), "Chordalysis",
                JOptionPane.ERROR_MESSAGE);
        e.printStackTrace();
    }

}

From source file:general.Util.java

/**
 * load dataset from CSV format//from w ww .j ava  2s.  co  m
 * @param filename 
 */
public static void loadCSV(String filename) {
    try {
        CSVLoader csv = new CSVLoader();
        csv.setFile(new File(filename));
        data = csv.getDataSet();

        // setting class attribute
        data.setClassIndex(data.numAttributes() - 1);
    } catch (IOException ex) {
        Logger.getLogger(Util.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:general.Util.java

/**
 * show learning statistic result by using test sets
 * @param testPath test path file//from  w  ww  .  j a v a2s .c o  m
 * @param typeTestFile test file
 */
public static void TestSchema(String testPath, String typeTestFile) {
    Instances testsets = null;
    // Load test instances based on file type and path
    if (typeTestFile.equals("arff")) {
        FileReader file = null;
        try {
            file = new FileReader(testPath);
            try (BufferedReader reader = new BufferedReader(file)) {
                testsets = new Instances(reader);
            }
            // setting class attribute
            testsets.setClassIndex(data.numAttributes() - 1);
        } catch (IOException ex) {
            Logger.getLogger(Util.class.getName()).log(Level.SEVERE, null, ex);
        } finally {
            try {
                if (file != null) {
                    file.close();
                }
            } catch (IOException ex) {
                Logger.getLogger(Util.class.getName()).log(Level.SEVERE, null, ex);
            }
        }
    } else if (typeTestFile.equals("csv")) {
        try {
            CSVLoader csv = new CSVLoader();
            csv.setFile(new File(testPath));
            data = csv.getDataSet();

            // setting class attribute
            data.setClassIndex(data.numAttributes() - 1);
        } catch (IOException ex) {
            Logger.getLogger(Util.class.getName()).log(Level.SEVERE, null, ex);
        }
    }

    // Start evaluate model using instances test and print results
    try {
        Evaluation eval = new Evaluation(Util.getData());
        eval.evaluateModel(Util.getClassifier(), testsets);
        System.out.println(eval.toSummaryString("\nResults\n\n", false));
    } catch (Exception e) {
        e.printStackTrace();
    }
}