Example usage for weka.core Instances Instances

Introduction

In this page you can find the example usage for weka.core Instances Instances.

Prototype

public Instances(Instances dataset, int capacity) 

Source Link

Document

Constructor creating an empty set of instances.

Usage

From source file:de.tudarmstadt.ukp.similarity.experiments.coling2012.util.Evaluator.java

License:Open Source License

public static void runClassifierCV(WekaClassifier wekaClassifier, Dataset dataset) throws Exception {
    // Set parameters
    int folds = 10;
    Classifier baseClassifier = getClassifier(wekaClassifier);

    // Set up the random number generator
    long seed = new Date().getTime();
    Random random = new Random(seed);

    // Add IDs to the instances
    AddID.main(new String[] { "-i", MODELS_DIR + "/" + dataset.toString() + ".arff", "-o",
            MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff" });
    Instances data = DataSource.read(MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff");
    data.setClassIndex(data.numAttributes() - 1);

    // Instantiate the Remove filter
    Remove removeIDFilter = new Remove();
    removeIDFilter.setAttributeIndices("first");

    // Randomize the data
    data.randomize(random);// w w  w.  j a v  a 2s. com

    // Perform cross-validation
    Instances predictedData = null;
    Evaluation eval = new Evaluation(data);

    for (int n = 0; n < folds; n++) {
        Instances train = data.trainCV(folds, n, random);
        Instances test = data.testCV(folds, n);

        // Apply log filter
        //          Filter logFilter = new LogFilter();
        //           logFilter.setInputFormat(train);
        //           train = Filter.useFilter(train, logFilter);        
        //           logFilter.setInputFormat(test);
        //           test = Filter.useFilter(test, logFilter);

        // Copy the classifier
        Classifier classifier = AbstractClassifier.makeCopy(baseClassifier);

        // Instantiate the FilteredClassifier
        FilteredClassifier filteredClassifier = new FilteredClassifier();
        filteredClassifier.setFilter(removeIDFilter);
        filteredClassifier.setClassifier(classifier);

        // Build the classifier
        filteredClassifier.buildClassifier(train);

        // Evaluate
        eval.evaluateModel(filteredClassifier, test);

        // Add predictions
        AddClassification filter = new AddClassification();
        filter.setClassifier(filteredClassifier);
        filter.setOutputClassification(true);
        filter.setOutputDistribution(false);
        filter.setOutputErrorFlag(true);
        filter.setInputFormat(train);
        Filter.useFilter(train, filter); // trains the classifier

        Instances pred = Filter.useFilter(test, filter); // performs predictions on test set
        if (predictedData == null)
            predictedData = new Instances(pred, 0);
        for (int j = 0; j < pred.numInstances(); j++)
            predictedData.add(pred.instance(j));
    }

    // Prepare output classification
    String[] scores = new String[predictedData.numInstances()];

    for (Instance predInst : predictedData) {
        int id = new Double(predInst.value(predInst.attribute(0))).intValue() - 1;

        int valueIdx = predictedData.numAttributes() - 2;

        String value = predInst.stringValue(predInst.attribute(valueIdx));

        scores[id] = value;
    }

    // Output
    StringBuilder sb = new StringBuilder();
    for (String score : scores)
        sb.append(score.toString() + LF);

    FileUtils.writeStringToFile(
            new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/output.csv"),
            sb.toString());
}

---

From source file:decisiontree.MyC45.java

/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*///  w ww  .j  a v  a  2  s.c  om
private Instances[] splitData(Instances data, Attribute att) {
    Instances[] splitData = new Instances[att.numValues()];
    for (int j = 0; j < att.numValues(); j++) {
        splitData[j] = new Instances(data, data.numInstances());
    }
    Enumeration instEnum = data.enumerateInstances();
    while (instEnum.hasMoreElements()) {
        Instance inst = (Instance) instEnum.nextElement();
        splitData[(int) inst.value(att)].add(inst);
    }
    for (int i = 0; i < splitData.length; i++) {
        splitData[i].compactify();
    }
    return splitData;
}

---

From source file:decisiontree.MyC45.java

/**
* Splits a dataset according to the values of a numeric attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*//*from  w w  w.ja v a2s.c  om*/
private Instances[] splitData(Instances data, Attribute att, double threshold) {
    Instances[] splitData = new Instances[2];
    for (int i = 0; i < 2; i++) {
        splitData[i] = new Instances(data, data.numInstances());
    }

    Enumeration instEnum = data.enumerateInstances();
    while (instEnum.hasMoreElements()) {
        Instance inst = (Instance) instEnum.nextElement();
        if (inst.value(att) >= threshold) {
            inst.setValue(att, threshold);
            splitData[1].add(inst);
        } else {
            inst.setValue(att, 0);
            splitData[0].add(inst);
        }
    }
    for (int i = 0; i < splitData.length; i++) {
        splitData[i].compactify();
    }
    return splitData;
}

---

From source file:decisiontree.MyID3.java

private Instances[] splitData(Instances data, Attribute att) {
    Instances[] splitData = new Instances[att.numValues()];
    for (int j = 0; j < att.numValues(); j++) {
        splitData[j] = new Instances(data, data.numInstances());
    }/*from   w  w w  .  ja v  a2 s  .  c  o  m*/

    Enumeration instEnum = data.enumerateInstances();
    while (instEnum.hasMoreElements()) {
        Instance inst = (Instance) instEnum.nextElement();
        splitData[(int) inst.value(att)].add(inst);
    }
    for (Instances split : splitData) {
        split.compactify();
    }
    return splitData;
}

---

From source file:development.CrossValidateShapelets.java

public static Instances randomise(Instances train, int[] pos) {
    //Generate a random permutation into pos
    Random r = new Random();
    for (int i = 0; i < pos.length; i++)
        pos[i] = i;//from  w  ww . j  av a 2 s.com
    for (int i = 0; i < pos.length; i++) {
        int p1 = r.nextInt(pos.length);
        int p2 = r.nextInt(pos.length);
        int temp = pos[p1];
        pos[p1] = pos[p2];
        pos[p2] = temp;
    }
    Instances newD = new Instances(train, 0);
    for (int i = 0; i < pos.length; i++)
        newD.add(train.instance(pos[i]));
    return newD;
}

---

From source file:development.SpectralTransformComparison.java

public void run() {
    //   Set up the       
    int nosCases = 400;
    int[] nosCasesPerClass = { nosCases / 2, nosCases / 2 };
    int runs = 50;
    int minParas = 2;
    int maxParas = 10;
    ArrayList<String> names = new ArrayList<>();
    Random rand = new Random();
    c = ACFDomainClassification.setSingleClassifiers(names);

    int length = m;
    try {/*www .jav  a  2 s . com*/
        int nosTrans = 3;
        Instances[] train = new Instances[nosTrans];
        Instances[] test = new Instances[nosTrans];
        double[][] sum = new double[train.length][c.length];
        double[][] sumSq = new double[train.length][c.length];
        PowerSpectrum ps = new PowerSpectrum();
        PowerCepstrum pc = new PowerCepstrum();
        pc.useFFT();
        FFT fft = new FFT();

        OutFile of = new OutFile(path + "mean_" + m + ".csv");
        OutFile of2 = new OutFile(path + "sd_" + m + ".csv");
        System.out.println(" Running length =" + m);
        of.writeLine("classifier,PS,PC,FFT");
        of2.writeLine("classifier,PS,PC,FFT");

        for (int i = 0; i < runs; i++) {
            //Generate data AND SET NOISE LEVEL
            c = ACFDomainClassification.setSingleClassifiers(names);
            if (i % 10 == 0)
                System.out.println(" m =" + m + " performing run =" + i);
            train = new Instances[nosTrans];
            test = new Instances[nosTrans];
            //Change to simulate sin waves.
            Instances rawTrain = SimulatePowerSpectrum.generateFFTDataSet(minParas, maxParas, length,
                    nosCasesPerClass, true);
            rawTrain.randomize(rand);
            Instances rawTest = new Instances(rawTrain, 0);
            for (int k = 0; k < nosCases / 2; k++) {
                Instance r = rawTrain.remove(0);
                rawTest.add(r);
            }
            //Generate transforms                        
            train[0] = ps.process(rawTrain);
            train[1] = pc.process(rawTrain);
            train[2] = fft.process(rawTrain);

            test[0] = ps.process(rawTest);
            test[1] = pc.process(rawTest);
            test[2] = fft.process(rawTest);
            //Measure classification accuracy
            for (int j = 0; j < test.length; j++) {
                for (int k = 0; k < c.length; k++) {
                    double a = ClassifierTools.singleTrainTestSplitAccuracy(c[k], train[j], test[j]);
                    sum[j][k] += a;
                    sumSq[j][k] += a * a;
                }
            }
        }
        DecimalFormat df = new DecimalFormat("###.###");
        System.out.print("\n m=" + length);
        for (int j = 0; j < c.length; j++) {
            of.writeString(names.get(j) + ",");
            of2.writeString(names.get(j) + ",");
            for (int i = 0; i < test.length; i++) {
                sum[i][j] /= runs;
                sumSq[i][j] = sumSq[i][j] / runs - sum[i][j] * sum[i][j];
                System.out.print("," + df.format(sum[i][j]) + " (" + df.format(sumSq[i][j]) + ")");
                of.writeString(df.format(sum[i][j]) + ",");
                of2.writeString(df.format(sumSq[i][j]) + ",");
            }
            of.writeString("\n");
            of2.writeString("\n");
        }
    } catch (Exception e) {
        System.out.println(" Error =" + e);
        e.printStackTrace();
        System.exit(0);
    }

}

---

From source file:dewaweebtreeclassifier.Sujeong.java

public Instances[] splitInstancesOnAttribute(Instances data, Attribute attr) {
    Instances[] splitInstances = new Instances[attr.numValues()];

    for (int i = 0; i < attr.numValues(); i++) {
        splitInstances[i] = new Instances(data, data.numInstances());
    }// w w w  .  j av  a  2 s .  com

    Enumeration enumInstance = data.enumerateInstances();
    while (enumInstance.hasMoreElements()) {
        Instance instance = (Instance) enumInstance.nextElement();
        splitInstances[(int) instance.value(attr)].add(instance);
    }

    for (int i = 0; i < attr.numValues(); i++) {
        splitInstances[i].compactify();
    }

    return splitInstances;
}

---

From source file:dewaweebtreeclassifier.veranda.VerandaTree.java

/**
 * /*  w ww. j  ava 2s  .  co m*/
 * @param data
 * @param attr
 * @return 
 */
public Instances[] splitInstancesOnAttribute(Instances data, Attribute attr) {
    Instances[] splitInstances = new Instances[attr.numValues()];

    for (int i = 0; i < attr.numValues(); i++) {
        splitInstances[i] = new Instances(data, data.numInstances());
    }

    Enumeration enumInstance = data.enumerateInstances();
    while (enumInstance.hasMoreElements()) {
        Instance instance = (Instance) enumInstance.nextElement();
        splitInstances[(int) instance.value(attr)].add(instance);
    }

    for (int i = 0; i < attr.numValues(); i++) {
        splitInstances[i].compactify();
    }

    return splitInstances;
}

---

From source file:distributed.core.DistributedUtils.java

License:Open Source License

public static Instances makeHeaderWithSummaryAtts(Instances denormalized, boolean treatZerosAsMissing) {
    Instances header = new Instances(denormalized, 0);

    for (int i = 0; i < denormalized.numAttributes(); i++) {
        AttributeStats stats = denormalized.attributeStats(i);
        if (denormalized.attribute(i).isNumeric()) {
            NumericStats ns = new NumericStats(denormalized.attribute(i).name());
            if (!treatZerosAsMissing) {
                ns.getStats()[ArffSummaryNumericMetric.MIN.ordinal()] = stats.numericStats.min;
                ns.getStats()[ArffSummaryNumericMetric.MAX.ordinal()] = stats.numericStats.max;
                ns.getStats()[ArffSummaryNumericMetric.COUNT.ordinal()] = stats.numericStats.count;
                ns.getStats()[ArffSummaryNumericMetric.SUM.ordinal()] = stats.numericStats.sum;
                ns.getStats()[ArffSummaryNumericMetric.SUMSQ.ordinal()] = stats.numericStats.sumSq;
                ns.getStats()[ArffSummaryNumericMetric.MISSING.ordinal()] = stats.missingCount;

                ns.computeDerived();/*from  w  ww.  j ava2s.c o m*/
            } else {
                ns = getNumericAttributeStatsSparse(denormalized, i);
            }

            Attribute newAtt = ns.makeAttribute();
            header.insertAttributeAt(newAtt, header.numAttributes());
        } else if (denormalized.attribute(i).isNominal()) {
            NominalStats nom = new NominalStats(denormalized.attribute(i).name());
            nom.setNumMissing(stats.missingCount);

            double[] labelFreqs = stats.nominalWeights;
            for (int j = 0; j < denormalized.attribute(i).numValues(); j++) {
                nom.add(denormalized.attribute(i).value(j), labelFreqs[j]);
            }

            Attribute newAtt = nom.makeAttribute();
            header.insertAttributeAt(newAtt, header.numAttributes());
        }
    }

    return header;
}

---

From source file:dkpro.similarity.experiments.rte.util.Evaluator.java

License:Open Source License

public static void runClassifierCV(WekaClassifier wekaClassifier, Dataset dataset) throws Exception {
    // Set parameters
    int folds = 10;
    Classifier baseClassifier = ClassifierSimilarityMeasure.getClassifier(wekaClassifier);

    // Set up the random number generator
    long seed = new Date().getTime();
    Random random = new Random(seed);

    // Add IDs to the instances
    AddID.main(new String[] { "-i", MODELS_DIR + "/" + dataset.toString() + ".arff", "-o",
            MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff" });
    Instances data = DataSource.read(MODELS_DIR + "/" + dataset.toString() + "-plusIDs.arff");
    data.setClassIndex(data.numAttributes() - 1);

    // Instantiate the Remove filter
    Remove removeIDFilter = new Remove();
    removeIDFilter.setAttributeIndices("first");

    // Randomize the data
    data.randomize(random);//  w w  w  .j ava  2s.c o  m

    // Perform cross-validation
    Instances predictedData = null;
    Evaluation eval = new Evaluation(data);

    for (int n = 0; n < folds; n++) {
        Instances train = data.trainCV(folds, n, random);
        Instances test = data.testCV(folds, n);

        // Apply log filter
        //          Filter logFilter = new LogFilter();
        //           logFilter.setInputFormat(train);
        //           train = Filter.useFilter(train, logFilter);        
        //           logFilter.setInputFormat(test);
        //           test = Filter.useFilter(test, logFilter);

        // Copy the classifier
        Classifier classifier = AbstractClassifier.makeCopy(baseClassifier);

        // Instantiate the FilteredClassifier
        FilteredClassifier filteredClassifier = new FilteredClassifier();
        filteredClassifier.setFilter(removeIDFilter);
        filteredClassifier.setClassifier(classifier);

        // Build the classifier
        filteredClassifier.buildClassifier(train);

        // Evaluate
        eval.evaluateModel(filteredClassifier, test);

        // Add predictions
        AddClassification filter = new AddClassification();
        filter.setClassifier(classifier);
        filter.setOutputClassification(true);
        filter.setOutputDistribution(false);
        filter.setOutputErrorFlag(true);
        filter.setInputFormat(train);
        Filter.useFilter(train, filter); // trains the classifier

        Instances pred = Filter.useFilter(test, filter); // performs predictions on test set
        if (predictedData == null)
            predictedData = new Instances(pred, 0);
        for (int j = 0; j < pred.numInstances(); j++)
            predictedData.add(pred.instance(j));
    }

    System.out.println(eval.toSummaryString());
    System.out.println(eval.toMatrixString());

    // Prepare output scores
    String[] scores = new String[predictedData.numInstances()];

    for (Instance predInst : predictedData) {
        int id = new Double(predInst.value(predInst.attribute(0))).intValue() - 1;

        int valueIdx = predictedData.numAttributes() - 2;

        String value = predInst.stringValue(predInst.attribute(valueIdx));

        scores[id] = value;
    }

    // Output classifications
    StringBuilder sb = new StringBuilder();
    for (String score : scores)
        sb.append(score.toString() + LF);

    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString()
            + "/" + dataset.toString() + ".csv"), sb.toString());

    // Output prediction arff
    DataSink.write(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString() + "/"
            + dataset.toString() + ".predicted.arff", predictedData);

    // Output meta information
    sb = new StringBuilder();
    sb.append(baseClassifier.toString() + LF);
    sb.append(eval.toSummaryString() + LF);
    sb.append(eval.toMatrixString() + LF);

    FileUtils.writeStringToFile(new File(OUTPUT_DIR + "/" + dataset.toString() + "/" + wekaClassifier.toString()
            + "/" + dataset.toString() + ".meta.txt"), sb.toString());
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• »