Example usage for weka.core Attribute Attribute

Introduction

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

Prototype

public Attribute(String attributeName) 

Source Link

Document

Constructor for a numeric attribute.

Usage

From source file:DocClassifier.java

private FastVector createTerms(File[] files) {
    try {//from w  ww .  ja  v a2s. c o  m
        Set<String> termSet = new HashSet<String>();
        for (File file : files) {
            BufferedReader reader = new BufferedReader(new FileReader(file));
            Set<String> docTermSet = new HashSet<String>();
            while (reader.ready()) {
                String line = reader.readLine();
                String[] words = line.split(" ");
                for (String word : words) {
                    Kelime[] kelimeler = this.zemberek.kelimeCozumle(word);
                    if (kelimeler.length > 0) {
                        String kok = kelimeler[0].kok().icerik();
                        docTermSet.add(kok);
                        termSet.add(kok);
                    }
                }
            }
            // DF for a doc
            for (String t : docTermSet) {
                Double freq = this.idfMap.get(t);
                this.idfMap.put(t, ((freq != null) ? (freq + 1) : 1));
            }
            reader.close();
        }
        //Remove some words like ve,veya,de,da,in from set
        termSet = PreProcesser.filterTermSet(termSet);
        //IDF Calculation
        for (String t : termSet) {
            Double df = this.idfMap.get(t);
            if (df != null) {
                this.idfMap.put(t, Math.log(files.length / df) / Math.log(2));
            } else {
                this.idfMap.put(t, 0.0);
            }
            //System.out.println(t + ": " + df);
        }
        // Attribute creation
        //System.err.println("\nAttribute:");
        FastVector terms = new FastVector();
        for (String term : termSet) {
            terms.addElement(new Attribute(term));
            // System.err.println(term + "-");
        }
        // Class values are created
        Set<String> classSet = new HashSet<String>();
        for (File file : files) {
            classSet.add(file.getName().substring(0, 3).toLowerCase());
        }
        //System.err.println("\nClass:");
        this.classValues = new FastVector();
        for (String category : classSet) {
            this.classValues.addElement(category);
            // System.out.print(category + "-");
        }
        terms.addElement(new Attribute(CLASS_ATTR_NAME, classValues));
        return terms;
    } catch (FileNotFoundException ex) {
        Logger.getLogger(DocClassifier.class.getName()).log(Level.SEVERE, null, ex);
    } catch (IOException ex) {
        Logger.getLogger(DocClassifier.class.getName()).log(Level.SEVERE, null, ex);
    }
    return null;
}

---

From source file:PrincipalComponents.java

License:Open Source License

/**
 * Set up the header for the PC->original space dataset
 *
 * @return the output format/*  w w w  .  ja v  a2  s  .  com*/
 * @throws Exception if something goes wrong
 */
private Instances setOutputFormatOriginal() throws Exception {
    ArrayList<Attribute> attributes = new ArrayList<Attribute>();

    for (int i = 0; i < m_numAttribs; i++) {
        String att = m_trainInstances.attribute(i).name();
        attributes.add(new Attribute(att));
    }

    if (m_hasClass) {
        attributes.add((Attribute) m_trainHeader.classAttribute().copy());
    }

    Instances outputFormat = new Instances(m_trainHeader.relationName() + "->PC->original space", attributes,
            0);

    // set the class to be the last attribute if necessary
    if (m_hasClass) {
        outputFormat.setClassIndex(outputFormat.numAttributes() - 1);
    }

    return outputFormat;
}

---

From source file:PrincipalComponents.java

License:Open Source License

/**
 * Set the format for the transformed data
 *
 * @return a set of empty Instances (header only) in the new format
 * @throws Exception if the output format can't be set
 *//*from ww w.  j a v a  2 s  .  co  m*/
private Instances setOutputFormat() throws Exception {
    if (m_eigenvalues == null) {
        return null;
    }

    double cumulative = 0.0;
    ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    for (int i = m_numAttribs - 1; i >= 0; i--) {
        StringBuffer attName = new StringBuffer();
        // build array of coefficients
        double[] coeff_mags = new double[m_numAttribs];
        for (int j = 0; j < m_numAttribs; j++) {
            coeff_mags[j] = -Math.abs(m_eigenvectors[j][m_sortedEigens[i]]);
        }
        int num_attrs = (m_maxAttrsInName > 0) ? Math.min(m_numAttribs, m_maxAttrsInName) : m_numAttribs;
        // this array contains the sorted indices of the coefficients
        int[] coeff_inds;
        if (m_numAttribs > 0) {
            // if m_maxAttrsInName > 0, sort coefficients by decreasing
            // magnitude
            coeff_inds = Utils.sort(coeff_mags);
        } else {
            // if m_maxAttrsInName <= 0, use all coeffs in original order
            coeff_inds = new int[m_numAttribs];
            for (int j = 0; j < m_numAttribs; j++) {
                coeff_inds[j] = j;
            }
        }
        // build final attName string
        for (int j = 0; j < num_attrs; j++) {
            double coeff_value = m_eigenvectors[coeff_inds[j]][m_sortedEigens[i]];
            if (j > 0 && coeff_value >= 0) {
                attName.append("+");
            }
            attName.append(
                    Utils.doubleToString(coeff_value, 5, 3) + m_trainInstances.attribute(coeff_inds[j]).name());
        }
        if (num_attrs < m_numAttribs) {
            attName.append("...");
        }

        attributes.add(new Attribute(attName.toString()));
        cumulative += m_eigenvalues[m_sortedEigens[i]];

        if ((cumulative / m_sumOfEigenValues) >= m_coverVariance) {
            break;
        }
    }

    if (m_hasClass) {
        attributes.add((Attribute) m_trainHeader.classAttribute().copy());
    }

    Instances outputFormat = new Instances(m_trainInstances.relationName() + "_principal components",
            attributes, 0);

    // set the class to be the last attribute if necessary
    if (m_hasClass) {
        outputFormat.setClassIndex(outputFormat.numAttributes() - 1);
    }

    m_outputNumAtts = outputFormat.numAttributes();
    return outputFormat;
}

---

From source file:ArrayLoader.java

License:Open Source License

/**
 * Return the full data set. If the structure hasn't yet been determined
 * by a call to getStructure then method should do so before processing
 * the rest of the data set./* www. j  av  a 2s  .c o m*/
 *
 * @return the structure of the data set as an empty set of Instances
 * @exception IOException if there is no source or parsing fails
 */
public Instances getDataSet() throws IOException {
    if (m_data == null) {
        throw new IOException("No source has been specified");
    }

    if (m_structure == null) {
        getStructure();
    }

    m_cumulativeStructure = new FastVector(m_structure.numAttributes());
    for (int i = 0; i < m_structure.numAttributes(); i++) {
        m_cumulativeStructure.addElement(new Hashtable());
    }

    m_cumulativeInstances = new FastVector();
    FastVector current;

    for (int i = 0; i < m_data.length; i++) {
        current = getInstance(m_data[i]);

        m_cumulativeInstances.addElement(current);
    }

    FastVector atts = new FastVector(m_structure.numAttributes());
    for (int i = 0; i < m_structure.numAttributes(); i++) {
        String attname = m_structure.attribute(i).name();
        Hashtable tempHash = ((Hashtable) m_cumulativeStructure.elementAt(i));
        if (tempHash.size() == 0) {
            atts.addElement(new Attribute(attname));
        } else {
            if (m_StringAttributes.isInRange(i)) {
                atts.addElement(new Attribute(attname, (FastVector) null));
            } else {
                FastVector values = new FastVector(tempHash.size());
                // add dummy objects in order to make the FastVector's size == capacity
                for (int z = 0; z < tempHash.size(); z++) {
                    values.addElement("dummy");
                }
                Enumeration e = tempHash.keys();
                while (e.hasMoreElements()) {
                    Object ob = e.nextElement();
                    //     if (ob instanceof Double) {
                    int index = ((Integer) tempHash.get(ob)).intValue();
                    String s = ob.toString();
                    if (s.startsWith("'") || s.startsWith("\""))
                        s = s.substring(1, s.length() - 1);
                    values.setElementAt(new String(s), index);
                    //     }
                }
                atts.addElement(new Attribute(attname, values));
            }
        }
    }

    // make the instances
    String relationName;
    relationName = "ArrayData";
    Instances dataSet = new Instances(relationName, atts, m_cumulativeInstances.size());

    for (int i = 0; i < m_cumulativeInstances.size(); i++) {
        current = ((FastVector) m_cumulativeInstances.elementAt(i));
        double[] vals = new double[dataSet.numAttributes()];
        for (int j = 0; j < current.size(); j++) {
            Object cval = current.elementAt(j);
            if (cval instanceof String) {
                if (((String) cval).compareTo(m_MissingValue) == 0) {
                    vals[j] = Instance.missingValue();
                } else {
                    if (dataSet.attribute(j).isString()) {
                        vals[j] = dataSet.attribute(j).addStringValue((String) cval);
                    } else if (dataSet.attribute(j).isNominal()) {
                        // find correct index
                        Hashtable lookup = (Hashtable) m_cumulativeStructure.elementAt(j);
                        int index = ((Integer) lookup.get(cval)).intValue();
                        vals[j] = index;
                    } else {
                        throw new IllegalStateException("Wrong attribute type at position " + (i + 1) + "!!!");
                    }
                }
            } else if (dataSet.attribute(j).isNominal()) {
                // find correct index
                Hashtable lookup = (Hashtable) m_cumulativeStructure.elementAt(j);
                int index = ((Integer) lookup.get(cval)).intValue();
                vals[j] = index;
            } else if (dataSet.attribute(j).isString()) {
                vals[j] = dataSet.attribute(j).addStringValue("" + cval);
            } else {
                vals[j] = ((Double) cval).doubleValue();
            }
        }
        dataSet.add(new Instance(1.0, vals));
    }
    m_structure = new Instances(dataSet, 0);
    m_cumulativeStructure = null; // conserve memory

    return dataSet;
}

---

From source file:ArrayLoader.java

License:Open Source License

/**
 * Assumes the first line of the file contains the attribute names.
 * Assumes all attributes are real (Reading the full data set with
 * getDataSet will establish the true structure).
 *
 *///from  w  w  w  .  ja  va 2 s.c o  m
private void readHeader(String[] column) throws IOException {

    FastVector attribNames = new FastVector();

    // Assume first row of data are the column titles
    for (int i = 0; i < column.length; i++) {
        attribNames.addElement(new Attribute(column[i]));
    }

    m_structure = new Instances("DataArray", attribNames, 0);
}

---

From source file:CJWeka.java

License:Open Source License

public Object addInstance(Object args) throws Exception {
    if (!(args instanceof String)) {
        throw new RuntimeException("Invalid type for execute");
    }/*  w  ww  .j a  v a2 s.  co  m*/

    StringBuffer retbuf = new StringBuffer("");

    // function code goes in here

    String floatstring = (String) args;

    // convert floatstring to float/double array to instance
    String[] flostr = floatstring.split(" ");
    int nvalues = flostr.length;

    // add instance to ii

    if (my_attributes.isEmpty()) {
        // create attributes for all instances
        for (int j = 0; j < nvalues - 1; j++) {
            Attribute a = new Attribute(Integer.toString(j));
            my_attributes.add(a);
        }

        classvals.add("0");
        classvals.add("1");
        /*     classvals.add("2");
        classvals.add("3");
        classvals.add("4");
        classvals.add("5");
        classvals.add("6");
        classvals.add("7");*/

        Attribute cls = new Attribute("class", classvals);

        my_attributes.add(cls);

        ii = new Instances("my_instances", my_attributes, 0);
    }

    ii.setClassIndex(nvalues - 1);

    Instance inst = this.floatstringToInst(floatstring, ii, true);
    ii.add(inst);

    retbuf.append(ii.numInstances()); // return number of Instances in ii
    return retbuf.toString();
}

---

From source file:aaa.util.test.CreateArff.java

License:Open Source License

/**
 * Generates the Instances object and outputs it in ARFF format to stdout.
 *
 * @param args   ignored/*from   w  w  w .  ja v a 2  s . c o m*/
 * @throws Exception   if generation of instances fails
 */
public static void main(String[] args) throws Exception {
    ArrayList<Attribute> atts;
    ArrayList<Attribute> attsRel;
    ArrayList<String> attVals;
    ArrayList<String> attValsRel;
    Instances data;
    Instances dataRel;
    double[] vals;
    double[] valsRel;
    int i;

    // 1. set up attributes
    atts = new ArrayList<Attribute>();
    // - numeric
    atts.add(new Attribute("att1"));
    // - nominal
    attVals = new ArrayList<String>();
    for (i = 0; i < 5; i++)
        attVals.add("val" + (i + 1));
    atts.add(new Attribute("att2", attVals));
    // - string
    atts.add(new Attribute("att3", (ArrayList<String>) null));
    // - date
    atts.add(new Attribute("att4", "yyyy-MM-dd"));
    // - relational
    attsRel = new ArrayList<Attribute>();
    // -- numeric
    attsRel.add(new Attribute("att5.1"));
    // -- nominal
    attValsRel = new ArrayList<String>();
    for (i = 0; i < 5; i++)
        attValsRel.add("val5." + (i + 1));
    attsRel.add(new Attribute("att5.2", attValsRel));
    dataRel = new Instances("att5", attsRel, 0);
    atts.add(new Attribute("att5", dataRel, 0));

    // 2. create Instances object
    data = new Instances("MyRelation", atts, 0);

    // 3. fill with data
    // first instance
    vals = new double[data.numAttributes()];
    // - numeric
    vals[0] = Math.PI;
    // - nominal
    vals[1] = attVals.indexOf("val3");
    // - string
    vals[2] = data.attribute(2).addStringValue("This is a string!");
    // - date
    vals[3] = data.attribute(3).parseDate("2001-11-09");
    // - relational
    dataRel = new Instances(data.attribute(4).relation(), 0);
    // -- first instance
    valsRel = new double[2];
    valsRel[0] = Math.PI + 1;
    valsRel[1] = attValsRel.indexOf("val5.3");
    dataRel.add(new DenseInstance(1.0, valsRel));
    // -- second instance
    valsRel = new double[2];
    valsRel[0] = Math.PI + 2;
    valsRel[1] = attValsRel.indexOf("val5.2");
    dataRel.add(new DenseInstance(1.0, valsRel));
    vals[4] = data.attribute(4).addRelation(dataRel);
    // add
    data.add(new DenseInstance(1.0, vals));

    // second instance
    vals = new double[data.numAttributes()]; // important: needs NEW array!
    // - numeric
    vals[0] = Math.E;
    // - nominal
    vals[1] = attVals.indexOf("val1");
    // - string
    vals[2] = data.attribute(2).addStringValue("And another one!");
    // - date
    vals[3] = data.attribute(3).parseDate("2000-12-01");
    // - relational
    dataRel = new Instances(data.attribute(4).relation(), 0);
    // -- first instance
    valsRel = new double[2];
    valsRel[0] = Math.E + 1;
    valsRel[1] = attValsRel.indexOf("val5.4");
    dataRel.add(new DenseInstance(1.0, valsRel));
    // -- second instance
    valsRel = new double[2];
    valsRel[0] = Math.E + 2;
    valsRel[1] = attValsRel.indexOf("val5.1");
    dataRel.add(new DenseInstance(1.0, valsRel));
    vals[4] = data.attribute(4).addRelation(dataRel);
    // add
    data.add(new DenseInstance(1.0, vals));

    // 4. output data
    System.out.println(data);
}

---

From source file:activeSegmentation.feature.FeatureExtraction.java

License:Open Source License

private ArrayList<Attribute> createFeatureHeader() {
    ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    for (int i = 1; i <= filterManager.getNumOfFeatures(); i++) {
        String attString = filterManager.getLabel(i);
        attributes.add(new Attribute(attString));
    }/*from ww  w. ja v  a2  s. co m*/

    return attributes;
}

---

From source file:adams.data.conversion.ReportToWekaInstance.java

License:Open Source License

/**
 * Performs the actual conversion./*from   w w w .  j a va2  s . co m*/
 *
 * @return      the converted data
 * @throws Exception   if something goes wrong with the conversion
 */
protected Object doConvert() throws Exception {
    Report report;
    Instance result;
    ArrayList atts;
    ArrayList attValues;
    int i;
    double[] values;

    report = (Report) m_Input;

    // generate header
    if (m_Header == null) {
        atts = new ArrayList();
        for (i = 0; i < m_Fields.length; i++) {
            switch (m_Fields[i].getDataType()) {
            case NUMERIC:
                atts.add(new Attribute(m_Fields[i].getName()));
                break;
            case BOOLEAN:
                attValues = new ArrayList();
                attValues.add("false");
                attValues.add("true");
                atts.add(new Attribute(m_Fields[i].getName(), attValues));
                break;
            default:
                atts.add(new Attribute(m_Fields[i].getName(), (List) null));
                break;
            }
        }
        m_Header = new Instances(getClass().getName(), atts, 0);
    }

    // generate instance
    values = new double[m_Header.numAttributes()];
    for (i = 0; i < m_Fields.length; i++) {
        if (report.hasValue(m_Fields[i])) {
            switch (m_Fields[i].getDataType()) {
            case NUMERIC:
                values[i] = report.getDoubleValue(m_Fields[i]);
                break;
            case BOOLEAN:
                if (report.getBooleanValue(m_Fields[i]))
                    values[i] = 1;
                else
                    values[i] = 0;
                break;
            default:
                values[i] = m_Header.attribute(i).addStringValue("" + report.getValue(m_Fields[i]));
                break;
            }
        } else {
            values[i] = weka.core.Utils.missingValue();
        }
    }
    result = new DenseInstance(1.0, values);
    result.setDataset(m_Header);

    return result;
}

---

From source file:adams.data.conversion.SpreadSheetToWekaInstances.java

License:Open Source License

/**
 * Performs the actual conversion.//from   www  . ja va  2 s  .c  o m
 *
 * @return      the converted data
 * @throws Exception   if something goes wrong with the conversion
 */
@Override
protected Object doConvert() throws Exception {
    Instances result;
    SpreadSheet sheet;
    DenseInstance inst;
    ArrayList<Attribute> atts;
    HashSet<String> unique;
    ArrayList<String> labels;
    Row row;
    Cell cell;
    int i;
    int n;
    double[] values;
    Collection<ContentType> types;
    ContentType type;
    boolean added;
    int[] classIndices;

    sheet = (SpreadSheet) m_Input;

    // create header
    atts = new ArrayList<>();
    for (i = 0; i < sheet.getColumnCount(); i++) {
        added = false;
        types = sheet.getContentTypes(i);
        if (types.contains(ContentType.DOUBLE))
            types.remove(ContentType.LONG);
        if (types.contains(ContentType.LONG)) {
            types.add(ContentType.DOUBLE);
            types.remove(ContentType.LONG);
        }

        if (types.size() == 1) {
            type = (ContentType) types.toArray()[0];
            if (type == ContentType.DOUBLE) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent()));
                added = true;
            } else if (type == ContentType.DATE) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(),
                        Constants.TIMESTAMP_FORMAT));
                added = true;
            } else if (type == ContentType.TIME) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), Constants.TIME_FORMAT));
                added = true;
            }
        }

        if (!added) {
            unique = new HashSet<>();
            for (n = 0; n < sheet.getRowCount(); n++) {
                row = sheet.getRow(n);
                cell = row.getCell(i);
                if ((cell != null) && !cell.isMissing())
                    unique.add(cell.getContent());
            }
            if ((unique.size() > m_MaxLabels) || (m_MaxLabels < 1)) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), (FastVector) null));
            } else {
                labels = new ArrayList<>(unique);
                Collections.sort(labels);
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), labels));
            }
        }
    }
    result = new Instances(Environment.getInstance().getProject(), atts, sheet.getRowCount());
    if (sheet.hasName())
        result.setRelationName(sheet.getName());

    // add data
    for (n = 0; n < sheet.getRowCount(); n++) {
        row = sheet.getRow(n);
        values = new double[result.numAttributes()];
        for (i = 0; i < result.numAttributes(); i++) {
            cell = row.getCell(i);
            values[i] = weka.core.Utils.missingValue();
            if ((cell != null) && !cell.isMissing()) {
                if (result.attribute(i).type() == Attribute.DATE) {
                    if (cell.isTime())
                        values[i] = cell.toTime().getTime();
                    else
                        values[i] = cell.toDate().getTime();
                } else if (result.attribute(i).isNumeric()) {
                    values[i] = Utils.toDouble(cell.getContent());
                } else if (result.attribute(i).isString()) {
                    values[i] = result.attribute(i).addStringValue(cell.getContent());
                } else {
                    values[i] = result.attribute(i).indexOfValue(cell.getContent());
                }
            }
        }
        inst = new DenseInstance(1.0, values);
        result.add(inst);
    }

    if (sheet instanceof Dataset) {
        classIndices = ((Dataset) sheet).getClassAttributeIndices();
        if (classIndices.length > 0)
            result.setClassIndex(classIndices[0]);
    }

    return result;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• »