Example usage for weka.core Instance value

List of usage examples for weka.core Instance value

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Instance
  6. value

Introduction

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

Prototype

public double value(Attribute att);

Source Link

Document

Returns an instance's attribute value in internal format.

Usage

From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java

License:Open Source License

/**
 * Calculates the class membership probabilities for the given test 
 * instance./* w ww  .  ja  va 2s . co m*/
 *
 * @param instance the instance to be classified
 * @return predicted class probability distribution
 * @exception Exception if there is a problem generating the prediction
 */
public double[] distributionForInstance(Instance instance) throws Exception {

    if (m_UseDiscretization) {
        m_Disc.input(instance);
        instance = m_Disc.output();
    }
    double[] probs = new double[m_NumClasses];
    for (int j = 0; j < m_NumClasses; j++) {
        probs[j] = m_ClassDistribution.getProbability(j);
    }
    Enumeration enumAtts = instance.enumerateAttributes();
    int attIndex = 0;
    while (enumAtts.hasMoreElements()) {
        Attribute attribute = (Attribute) enumAtts.nextElement();
        if (!instance.isMissing(attribute)) {
            double temp, max = 0;
            for (int j = 0; j < m_NumClasses; j++) {
                temp = Math.max(1e-75,
                        Math.pow(m_Distributions[attIndex][j].getProbability(instance.value(attribute)),
                                m_Instances.attribute(attIndex).weight()));
                probs[j] *= temp;
                if (probs[j] > max) {
                    max = probs[j];
                }
                if (Double.isNaN(probs[j])) {
                    throw new Exception("NaN returned from estimator for attribute " + attribute.name() + ":\n"
                            + m_Distributions[attIndex][j].toString());
                }
            }
            if ((max > 0) && (max < 1e-75)) { // Danger of probability underflow
                for (int j = 0; j < m_NumClasses; j++) {
                    probs[j] *= 1e75;
                }
            }
        }
        attIndex++;
    }

    // Display probabilities
    Utils.normalize(probs);
    return probs;
}

From source file:cn.edu.xjtu.dbmine.StringToWordVector.java

License:Open Source License

/**
 * Converts the instance w/o normalization.
 * //from   w ww.j av  a2  s. com
 * @oaram instance the instance to convert
 * @param v
 * @return the conerted instance
 */
private int convertInstancewoDocNorm(Instance instance, FastVector v) {

    // Convert the instance into a sorted set of indexes
    TreeMap contained = new TreeMap();

    // Copy all non-converted attributes from input to output
    int firstCopy = 0;
    for (int i = 0; i < getInputFormat().numAttributes(); i++) {
        if (!m_SelectedRange.isInRange(i)) {
            if (getInputFormat().attribute(i).type() != Attribute.STRING) {
                // Add simple nominal and numeric attributes directly
                if (instance.value(i) != 0.0) {
                    contained.put(new Integer(firstCopy), new Double(instance.value(i)));
                }
            } else {
                if (instance.isMissing(i)) {
                    contained.put(new Integer(firstCopy), new Double(Instance.missingValue()));
                } else {

                    // If this is a string attribute, we have to first add
                    // this value to the range of possible values, then add
                    // its new internal index.
                    if (outputFormatPeek().attribute(firstCopy).numValues() == 0) {
                        // Note that the first string value in a
                        // SparseInstance doesn't get printed.
                        outputFormatPeek().attribute(firstCopy)
                                .addStringValue("Hack to defeat SparseInstance bug");
                    }
                    int newIndex = outputFormatPeek().attribute(firstCopy)
                            .addStringValue(instance.stringValue(i));
                    contained.put(new Integer(firstCopy), new Double(newIndex));
                }
            }
            firstCopy++;
        }
    }

    for (int j = 0; j < instance.numAttributes(); j++) {
        // if ((getInputFormat().attribute(j).type() == Attribute.STRING)
        if (m_SelectedRange.isInRange(j) && (instance.isMissing(j) == false)) {

            m_Tokenizer.tokenize(instance.stringValue(j));

            while (m_Tokenizer.hasMoreElements()) {
                String word = (String) m_Tokenizer.nextElement();
                if (this.m_lowerCaseTokens == true)
                    word = word.toLowerCase();
                word = m_Stemmer.stem(word);
                Integer index = (Integer) m_Dictionary.get(word);
                if (index != null) {
                    if (m_OutputCounts) { // Separate if here rather than
                        // two lines down to avoid
                        // hashtable lookup
                        Double count = (Double) contained.get(index);
                        if (count != null) {
                            contained.put(index, new Double(count.doubleValue() + 1.0));
                        } else {
                            contained.put(index, new Double(1));
                        }
                    } else {
                        contained.put(index, new Double(1));
                    }
                }
            }
        }
    }

    // Doing TFTransform
    if (m_TFTransform == true) {
        Iterator it = contained.keySet().iterator();
        for (int i = 0; it.hasNext(); i++) {
            Integer index = (Integer) it.next();
            if (index.intValue() >= firstCopy) {
                double val = ((Double) contained.get(index)).doubleValue();
                val = Math.log(val + 1);
                contained.put(index, new Double(val));
                Tfcontained.put(index, new Double(val));
                ;
            }
        }
    }

    // Doing IDFTransform
    if (m_IDFTransform == true) {
        Iterator it = contained.keySet().iterator();
        for (int i = 0; it.hasNext(); i++) {
            Integer index = (Integer) it.next();
            if (index.intValue() >= firstCopy) {
                double val = ((Double) contained.get(index)).doubleValue();
                val = val * Math.log(m_NumInstances / ((double) m_DocsCounts[index.intValue()] + 0.01));
                contained.put(index, new Double(val));
            }
        }
    }

    // Convert the set to structures needed to create a sparse instance.
    double[] values = new double[contained.size()];
    int[] indices = new int[contained.size()];
    Iterator it = contained.keySet().iterator();
    for (int i = 0; it.hasNext(); i++) {
        Integer index = (Integer) it.next();
        Double value = (Double) contained.get(index);
        values[i] = value.doubleValue();
        indices[i] = index.intValue();
    }

    Instance inst = new SparseInstance(instance.weight(), values, indices, outputFormatPeek().numAttributes());
    inst.setDataset(outputFormatPeek());

    v.addElement(inst);

    return firstCopy;
}

From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java

License:Open Source License

protected Instances runExp(Instances samplePoints, int round, String postfix, boolean resuming) {
    Instances retval = null;// w w  w  .  ja  va  2  s  .c  o  m
    try {
        //DataIOFile.saveDataToArffFile("data/zyqTestRange.arff", samplePoints);

        if (resuming) {
            samplePoints = manager.collectPerfs(samplePoints, perfAttName);
        }

        retval = manager.runExp(samplePoints, perfAttName);
        //we output the result set for future debugging and testing purposes
        DataIOFile.saveDataToArffFile("data/trainingBestConf" + round + "_" + postfix + ".arff", samplePoints);

        //evict all bad configurations
        Attribute perfAtt = retval.attribute(perfAttName);
        Iterator<Instance> itr = retval.iterator();
        ArrayList<Integer> toRemove = new ArrayList<Integer>();
        Instance next;
        while (itr.hasNext()) {
            next = itr.next();
            if (next.value(perfAtt) == -1)
                toRemove.add(retval.indexOf(next));
        }
        while (!toRemove.isEmpty())
            retval.remove(toRemove.remove(0));
    } catch (IOException e) {
        e.printStackTrace();
    }

    if (allInstances == null) {
        allInstances = new Instances(retval);
    } else {
        allInstances.addAll(retval);
    }

    return retval;
}

From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java

License:Open Source License

public static ArrayList<Attribute> scaleDownDetour(Instances previousSet, Instance center) {
    ArrayList<Attribute> localAtts = new ArrayList<Attribute>();
    int attNum = center.numAttributes();

    int pos = previousSet.attribute(PerformanceAttName).index();

    //traverse each dimension
    Enumeration<Instance> enu;
    double minDis;
    for (int i = 0; i < attNum; i++) {
        if (i == pos)
            continue;

        enu = previousSet.enumerateInstances();
        minDis = Double.MAX_VALUE;

        while (enu.hasMoreElements()) {
            Instance ins = enu.nextElement();
            if (!ins.equals(center))
                minDis = Math.min((double) ((int) (Math.abs(ins.value(i) - center.value(i)) * 100)) / 100.0,
                        minDis);/*  w ww  .  jav  a 2  s  .co m*/
        }

        //now we set the range
        Properties p1 = new Properties();
        double upper = center.value(i) + minDis, lower = center.value(i) - minDis;

        TreeSet<Double> detourSet = new TreeSet<Double>();
        detourSet.add(upper);
        detourSet.add(lower);
        detourSet.add(previousSet.attribute(i).getUpperNumericBound());
        detourSet.add(previousSet.attribute(i).getLowerNumericBound());
        switch (detourSet.size()) {
        case 1:
            upper = lower = detourSet.first();
            break;
        case 2:
            upper = detourSet.last();
            lower = detourSet.first();
            break;
        case 3:
            upper = lower = detourSet.higher(detourSet.first());
            break;
        default://case 4:
            upper = detourSet.lower(detourSet.last());
            lower = detourSet.higher(detourSet.first());
            break;
        }

        p1.setProperty("range", "[" + String.valueOf(lower) + "," + String.valueOf(upper) + "]");
        ProtectedProperties prop1 = new ProtectedProperties(p1);

        localAtts.add(new Attribute(previousSet.attribute(i).name(), prop1));
    }

    return localAtts;
}

From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java

License:Open Source License

public static Map<Attribute, Double> instanceToMap(Instance ins) {
    HashMap<Attribute, Double> retval = new HashMap<Attribute, Double>();
    Enumeration<Attribute> enu = ins.enumerateAttributes();
    while (enu.hasMoreElements()) {
        Attribute temp = enu.nextElement();
        retval.put(temp, ins.value(temp));
    }/* w  w w  .ja  v  a2  s . co  m*/
    return retval;
}

From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java

License:Open Source License

public static void getBestPerfFrom(String path) {
    try {/*from   ww  w .j  av  a  2  s  .c  om*/
        BestConf bestconf = new BestConf();
        Instances trainingSet = DataIOFile.loadDataFromArffFile(path);
        Instance best = trainingSet.firstInstance();
        //set the best configuration to the cluster
        Map<Attribute, Double> attsmap = new HashMap<Attribute, Double>();
        for (int i = 0; i < best.numAttributes() - 1; i++) {
            attsmap.put(best.attribute(i), best.value(i));
        }

        double bestPerf = bestconf.setOptimal(attsmap, "getBestPerfFrom");
        System.out.println("=========================================");
        System.err.println("The actual performance for the best point is : " + bestPerf);
        System.out.println("=========================================");
    } catch (IOException e) {
        e.printStackTrace();
    }
}

From source file:cn.ict.zyq.bestConf.bestConf.RBSoDDSOptimization.java

License:Open Source License

@Override
public void optimize(String preLoadDatasetPath) {
    ResumeParams rParams = resumePrepareTry();
    boolean justAfterResume = rParams.isResuming;

    //detect whether we need to resume
    if (rParams.isResuming)
        preLoadDatasetPath = null;/*from  w w  w. j  a  v  a  2 s  .c  o m*/

    double tempBest;

    while (opParams.currentround < RRSMaxRounds) {
        //is it a global search
        if (samplePoints == null || rParams.propsRound < opParams.currentround) {
            props = bestconf.getAttributes();
            saveProps(props, opParams.currentround, opParams.subround);//for resumability
            opParams.saveToFile();
        }

        if (opParams.currentround != 0 || opParams.subround != 0) {
            if (!justAfterResume || (justAfterResume && (rParams.samplePointRound < opParams.currentround
                    || rParams.samplePointSubRound < opParams.subround))) {
                //let's do the sampling
                ((DDSSampler) sampler).setCurrentRound(opParams.currentround);
                samplePoints = sampler.getMultiDimContinuous(props, InitialSampleSetSize, false, bestconf);
                saveSamplePoints(samplePoints, opParams.currentround, opParams.subround);
            }

            if (!justAfterResume || (justAfterResume && rParams.trainingRound < opParams.currentround
                    || rParams.trainingSubRound < opParams.subround)) {
                //traverse the set and initiate the experiments
                trainingSet = bestconf.runExp(samplePoints, opParams.currentround,
                        "RRS" + String.valueOf(opParams.subround), justAfterResume);
                saveTrainingSet(trainingSet, opParams.currentround, opParams.subround);
            }
        } else {//(currentround==0 && subround==0)
            if (preLoadDatasetPath == null) {

                if (samplePoints == null) {
                    //let's do the sampling
                    ((DDSSampler) sampler).setCurrentRound(opParams.currentround);
                    samplePoints = sampler.getMultiDimContinuous(props, InitialSampleSetSize, false, bestconf);
                    samplePoints.add(0, bestconf.defltSettings.firstInstance());
                    saveSamplePoints(samplePoints, opParams.currentround, opParams.subround);
                }
                if (trainingSet == null) {
                    //traverse the set and initiate the experiments
                    trainingSet = bestconf.runExp(samplePoints, opParams.currentround,
                            "RRS" + String.valueOf(opParams.subround), justAfterResume);
                    saveTrainingSet(trainingSet, opParams.currentround, opParams.subround);
                }
            } else {
                try {
                    bestconf.allInstances = DataIOFile.loadDataFromArffFile(preLoadDatasetPath);
                    bestconf.allInstances.setClassIndex(bestconf.allInstances.numAttributes() - 1);
                    samplePoints = trainingSet = new Instances(bestconf.allInstances);

                    saveSamplePoints(samplePoints, opParams.currentround, opParams.subround);
                    saveTrainingSet(trainingSet, opParams.currentround, opParams.subround);
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }

        //get the point with the best performance
        Instance tempIns = BestConf.findBestPerf(trainingSet);
        tempBest = tempIns.value(trainingSet.numAttributes() - 1);
        if (tempBest > opParams.currentBest || (justAfterResume && tempBest == opParams.currentBest
                && (rParams.propsRound < opParams.currentround || rParams.propsSubRound < opParams.subround))) {
            System.err.println("Previous best is " + opParams.currentBest + "; Current best is " + tempBest);

            opParams.currentBest = tempBest;
            opParams.currentIns = tempIns;
            opParams.saveToFile();

            try {
                //output the best instance of this round
                Instances bestInstances = new Instances(samplePoints, 1);
                bestInstances.add(opParams.currentIns);
                DataIOFile.saveDataToArffFile("data/trainingBestConf_RRS_" + opParams.currentround + "_"
                        + opParams.subround + "_" + opParams.currentBest + ".arff", bestInstances);
            } catch (IOException e) {
                e.printStackTrace();
            }

            //let's search locally
            if (!justAfterResume || (justAfterResume && rParams.propsRound < opParams.currentround
                    || rParams.propsSubRound < opParams.subround)) {
                props = ConfigSampler.scaleDownDetour(trainingSet, tempIns);
                saveProps(props, opParams.currentround, opParams.subround);//for resumability
            }

            opParams.subround++;
            opParams.saveToFile();
        } else {//let's do the restart
            samplePoints = null;

            opParams.currentround++;
            opParams.subround = 0;
            opParams.saveToFile();

            System.err.println("Entering into round " + opParams.currentround);
            /*if(opParams.currentround>=RRSMaxRounds)
               break;*/
        }

        justAfterResume = false;
    } //RRS search

    System.err.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
    System.err.println("We are ending the optimization experiments!");
    System.err.println("Please wait and don't shutdown!");
    System.err.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
    System.err.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");

    //output the best
    Map<Attribute, Double> attsmap = BestConf.instanceToMap(opParams.currentIns);
    System.out.println(attsmap.toString());

    //set the best configuration to the cluster
    System.err.println("The best performance is : " + opParams.currentBest);

    System.out.println("=========================================");
    TxtFileOperation.writeToFile("bestConfOutput_RRS", attsmap.toString() + "\n");

    System.out.println("=========================================");

    //output the whole trainings dataset
    try {
        DataIOFile.saveDataToArffFile("data/trainingAllRSS.arff", bestconf.allInstances);
    } catch (IOException e) {
        e.printStackTrace();
    }
}

From source file:cn.ict.zyq.bestConf.bestConf.sampler.ConfigSampler.java

License:Open Source License

private static ArrayList<Attribute> scaleDownNeighbordists(Instances previousSet, Instance center) {
    ArrayList<Attribute> localAtts = new ArrayList<Attribute>();
    int attNum = center.numAttributes();

    int pos = -1;
    if (previousSet.attribute(PerformanceAttName) != null)
        pos = previousSet.attribute(PerformanceAttName).index();

    //traverse each dimension
    Enumeration<Instance> enu;
    double[] minDists = new double[2];
    double val;
    for (int i = 0; i < attNum; i++) {
        if (i == pos)
            continue;

        enu = previousSet.enumerateInstances();
        minDists[0] = 1 - Double.MAX_VALUE;
        minDists[1] = Double.MAX_VALUE;

        while (enu.hasMoreElements()) {
            Instance ins = enu.nextElement();
            if (!ins.equals(center)) {
                val = ins.value(i) - center.value(i);
                if (val < 0)
                    minDists[0] = Math.max((double) ((int) ((ins.value(i) - center.value(i)) * 1000)) / 1000.0,
                            minDists[0]);
                else
                    minDists[1] = Math.min((double) ((int) ((ins.value(i) - center.value(i)) * 1000)) / 1000.0,
                            minDists[1]);
            }//from  w  w w.j av  a2s  .  c om
        }

        //now we set the range
        Properties p1 = new Properties();
        double upper = center.value(i) + minDists[1], lower = center.value(i) + minDists[0];

        TreeSet<Double> detourSet = new TreeSet<Double>();
        detourSet.add(upper);
        detourSet.add(lower);
        detourSet.add(previousSet.attribute(i).getUpperNumericBound());
        detourSet.add(previousSet.attribute(i).getLowerNumericBound());
        switch (detourSet.size()) {
        case 1:
            upper = lower = detourSet.first();
            break;
        case 2:
            upper = detourSet.last();
            lower = detourSet.first();
            break;
        case 3:
            upper = lower = detourSet.higher(detourSet.first());
            break;
        default://case 4:
            upper = detourSet.lower(detourSet.last());
            lower = detourSet.higher(detourSet.first());
            break;
        }

        p1.setProperty("range", "[" + String.valueOf(lower) + "," + String.valueOf(upper) + "]");
        ProtectedProperties prop1 = new ProtectedProperties(p1);

        localAtts.add(new Attribute(previousSet.attribute(i).name(), prop1));
    }

    return localAtts;
}

From source file:cn.ict.zyq.bestConf.bestConf.sampler.ConfigSampler.java

License:Open Source License

private static ArrayList<Attribute> scaleDownMindists(Instances previousSet, Instance center) {
    ArrayList<Attribute> localAtts = new ArrayList<Attribute>();
    int attNum = center.numAttributes();

    int pos = previousSet.attribute(PerformanceAttName).index();

    //traverse each dimension
    Enumeration<Instance> enu;
    double minDis;
    for (int i = 0; i < attNum; i++) {
        if (i == pos)
            continue;

        enu = previousSet.enumerateInstances();
        minDis = Double.MAX_VALUE;

        while (enu.hasMoreElements()) {
            Instance ins = enu.nextElement();
            if (!ins.equals(center))
                minDis = Math.min((double) ((int) (Math.abs(ins.value(i) - center.value(i)) * 1000)) / 1000.0,
                        minDis);//from  www .j  a  v a 2s  .  c o  m
        }

        //now we set the range
        Properties p1 = new Properties();
        double upper = center.value(i) + minDis, lower = center.value(i) - minDis;

        TreeSet<Double> detourSet = new TreeSet<Double>();
        detourSet.add(upper);
        detourSet.add(lower);
        detourSet.add(previousSet.attribute(i).getUpperNumericBound());
        detourSet.add(previousSet.attribute(i).getLowerNumericBound());
        switch (detourSet.size()) {
        case 1:
            upper = lower = detourSet.first();
            break;
        case 2:
            upper = detourSet.last();
            lower = detourSet.first();
            break;
        case 3:
            upper = lower = detourSet.higher(detourSet.first());
            break;
        default://case 4:
            upper = detourSet.lower(detourSet.last());
            lower = detourSet.higher(detourSet.first());
            break;
        }

        p1.setProperty("range", "[" + String.valueOf(lower) + "," + String.valueOf(upper) + "]");
        ProtectedProperties prop1 = new ProtectedProperties(p1);

        localAtts.add(new Attribute(previousSet.attribute(i).name(), prop1));
    }

    return localAtts;
}

From source file:cn.ict.zyq.bestConf.cluster.Main.AutoTestAdjust.java

License:Open Source License

public static String getMD5(Instance ins) {
    StringBuffer name = new StringBuffer("");
    for (int i = 0; i < ins.numAttributes() - 2; i++) {
        name.append(Math.round(ins.value(ins.attribute(i))) + ",");
    }/*from   w  ww.  j  a  va2s  .  c om*/
    return getMD5(name.toString());
}