Example usage for weka.core Attribute NUMERIC

List of usage examples for weka.core Attribute NUMERIC

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Attribute
  6. NUMERIC

Introduction

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

Prototype

int NUMERIC

To view the source code for weka.core Attribute NUMERIC.

Click Source Link

Document

Constant set for numeric attributes.

Usage

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

License:Open Source License

/**
 * Matches the input instance against the header.
 *
 * @param input   the Instance to align to the header
 * @return      the aligned Instance// ww  w . j a  v a 2  s. com
 */
protected Instance match(Instance input) {
    Instance result;
    double[] values;
    int i;

    values = new double[m_Dataset.numAttributes()];
    for (i = 0; i < m_Dataset.numAttributes(); i++) {
        values[i] = Utils.missingValue();
        switch (m_Dataset.attribute(i).type()) {
        case Attribute.NUMERIC:
        case Attribute.DATE:
            values[i] = input.value(i);
            break;
        case Attribute.NOMINAL:
            if (m_Dataset.attribute(i).indexOfValue(input.stringValue(i)) != -1)
                values[i] = m_Dataset.attribute(i).indexOfValue(input.stringValue(i));
            break;
        case Attribute.STRING:
            values[i] = m_Dataset.attribute(i).addStringValue(input.stringValue(i));
            break;
        case Attribute.RELATIONAL:
            values[i] = m_Dataset.attribute(i).addRelation(input.relationalValue(i));
            break;
        default:
            throw new IllegalStateException(
                    "Unhandled attribute type: " + Attribute.typeToString(m_Dataset.attribute(i).type()));
        }
    }

    if (input instanceof SparseInstance)
        result = new SparseInstance(input.weight(), values);
    else
        result = new DenseInstance(input.weight(), values);
    result.setDataset(m_Dataset);

    // fix class index, if necessary
    if ((input.classIndex() != m_Dataset.classIndex()) && (m_Dataset.classIndex() < 0))
        m_Dataset.setClassIndex(input.classIndex());

    return result;
}

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

License:Open Source License

/**
 * Performs the actual conversion./*from   w w w. j a  va 2 s . c  om*/
 *
 * @return      the converted data
 * @throws Exception   if something goes wrong with the conversion
 */
@Override
protected Object doConvert() throws Exception {
    SpreadSheet result;
    Instances data;
    Row row;
    int i;
    int n;
    String str;

    data = (Instances) m_Input;

    // special case for InstancesViews
    if (m_SpreadSheetType instanceof InstancesView) {
        result = new InstancesView((Instances) m_Input);
        return result;
    }

    // create header
    result = m_SpreadSheetType.newInstance();
    result.setDataRowClass(m_DataRowType.getClass());
    row = result.getHeaderRow();
    for (n = 0; n < data.numAttributes(); n++)
        row.addCell("" + n).setContent(data.attribute(n).name());
    if (result instanceof Dataset) {
        if (data.classIndex() != -1)
            ((Dataset) result).setClassAttribute(data.classIndex(), true);
    }

    // fill spreadsheet
    for (i = 0; i < data.numInstances(); i++) {
        row = result.addRow("" + i);

        for (n = 0; n < data.numAttributes(); n++) {
            if (data.instance(i).isMissing(n))
                continue;
            if (data.attribute(n).type() == Attribute.DATE) {
                row.addCell("" + n).setContent(new DateTimeMsec(new Date((long) data.instance(i).value(n))));
            } else if (data.attribute(n).type() == Attribute.NUMERIC) {
                row.addCell("" + n).setContent(data.instance(i).value(n));
            } else {
                str = data.instance(i).stringValue(n);
                if (str.equals(SpreadSheet.MISSING_VALUE))
                    row.addCell("" + n).setContentAsString("'" + str + "'");
                else
                    row.addCell("" + n).setContentAsString(str);
            }
        }
    }

    return result;
}

From source file:adams.data.instances.AbstractInstanceGenerator.java

License:Open Source License

/**
 * Adds IDs, notes, additional fields to header.
 *
 * @param data   the input data/*  w w  w .  ja  v a2s.  c om*/
 */
protected void postProcessHeader(T data) {
    Add add;

    // add the database ID to the output?
    if (m_AddDatabaseID) {
        try {
            add = new Add();
            add.setAttributeIndex("1");
            add.setAttributeName(ArffUtils.getDBIDName());
            add.setAttributeType(new SelectedTag(Attribute.NUMERIC, Add.TAGS_TYPE));
            add.setInputFormat(m_OutputHeader);
            m_OutputHeader = Filter.useFilter(m_OutputHeader, add);
        } catch (Exception e) {
            getLogger().log(Level.SEVERE, "Error initializing the Add filter for database ID!", e);
        }
    }
}

From source file:adams.flow.transformer.WekaGetInstancesValue.java

License:Open Source License

/**
 * Executes the flow item./*w ww.ja  va2 s  . c o  m*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances inst;
    int index;
    int row;

    result = null;

    inst = (Instances) m_InputToken.getPayload();
    m_Column.setData(inst);
    m_Row.setMax(inst.numInstances());
    index = m_Column.getIntIndex();
    row = m_Row.getIntIndex();

    if (row == -1)
        result = "Failed to retrieve row: " + m_Row.getIndex();
    else if (index == -1)
        result = "Failed to retrieve column: " + m_Column.getIndex();

    if (result == null) {
        try {
            if (inst.instance(row).isMissing(index)) {
                m_OutputToken = new Token("?");
            } else {
                switch (inst.attribute(index).type()) {
                case Attribute.NUMERIC:
                    m_OutputToken = new Token(inst.instance(row).value(index));
                    break;

                case Attribute.DATE:
                case Attribute.NOMINAL:
                case Attribute.STRING:
                case Attribute.RELATIONAL:
                    m_OutputToken = new Token(inst.instance(row).stringValue(index));
                    break;

                default:
                    result = "Unhandled attribute type: " + inst.attribute(index).type();
                }
            }
        } catch (Exception e) {
            result = handleException("Failed to obtain value from dataset:", e);
        }
    }

    return result;
}

From source file:adams.flow.transformer.WekaGetInstanceValue.java

License:Open Source License

/**
 * Executes the flow item.//from   www.  jav a 2s  .  c om
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instance inst;
    int index;

    result = null;

    inst = (Instance) m_InputToken.getPayload();

    try {
        if (m_AttributeName.length() > 0) {
            index = inst.dataset().attribute(m_AttributeName).index();
        } else {
            m_Index.setMax(inst.numAttributes());
            index = m_Index.getIntIndex();
        }
        if (inst.isMissing(index)) {
            m_OutputToken = new Token("?");
        } else {
            switch (inst.attribute(index).type()) {
            case Attribute.NUMERIC:
                m_OutputToken = new Token(inst.value(index));
                break;

            case Attribute.DATE:
            case Attribute.NOMINAL:
            case Attribute.STRING:
            case Attribute.RELATIONAL:
                m_OutputToken = new Token(inst.stringValue(index));
                break;

            default:
                result = "Unhandled attribute type: " + inst.attribute(index).type();
            }
        }
    } catch (Exception e) {
        result = handleException("Failed to obtain value from instance:\n" + inst, e);
    }

    return result;
}

From source file:adams.flow.transformer.WekaInstanceEvaluator.java

License:Open Source License

/**
 * Generates the new header for the data.
 *
 * @param inst   the instance to get the original data format from
 * @return      null if everything is fine, otherwise error message
 * @see      #m_Header/*  ww w.j a v  a  2s  . c  o m*/
 * @see      #m_Filter
 */
protected String generateHeader(Instance inst) {
    String result;

    result = null;

    m_Filter = new Add();
    m_Filter.setAttributeName(determineAttributeName(inst.dataset()));
    m_Filter.setAttributeType(new SelectedTag(Attribute.NUMERIC, Add.TAGS_TYPE));
    if (inst.dataset().classIndex() == inst.dataset().numAttributes() - 1)
        m_Filter.setAttributeIndex("" + inst.dataset().numAttributes());
    else
        m_Filter.setAttributeIndex("" + (inst.dataset().numAttributes() + 1));
    try {
        m_Filter.setInputFormat(inst.dataset());
        m_Header = weka.filters.Filter.useFilter(inst.dataset(), m_Filter);
    } catch (Exception e) {
        result = handleException("Failed to generate header:", e);
    }

    return result;
}

From source file:adams.flow.transformer.WekaInstancesMerge.java

License:Open Source License

/**
 * Updates the IDs in the hashset with the ones stored in the ID attribute
 * of the provided dataset.//from   w w w  .  j a  va  2  s .c om
 *
 * @param instIndex    the dataset index
 * @param inst   the dataset to obtain the IDs from
 * @param ids      the hashset to store the IDs in
 */
protected void updateIDs(int instIndex, Instances inst, HashSet ids) {
    Attribute att;
    int i;
    boolean numeric;
    HashSet current;
    Object id;

    att = inst.attribute(m_UniqueID);
    if (att == null)
        throw new IllegalStateException("Attribute '" + m_UniqueID + "' not found in relation '"
                + inst.relationName() + "' (#" + (instIndex + 1) + ")!");

    // determine/check type
    if (m_AttType == -1) {
        if ((att.type() == Attribute.NUMERIC) || (att.type() == Attribute.STRING))
            m_AttType = att.type();
        else
            throw new IllegalStateException("Attribute '" + m_UniqueID + "' must be either NUMERIC or STRING (#"
                    + (instIndex + 1) + ")!");
    } else {
        if (m_AttType != att.type())
            throw new IllegalStateException("Attribute '" + m_UniqueID
                    + "' must have same attribute type in all the datasets (#" + (instIndex + 1) + ")!");
    }

    // get IDs
    numeric = m_AttType == Attribute.NUMERIC;
    current = new HashSet();
    for (i = 0; i < inst.numInstances(); i++) {
        if (numeric)
            id = inst.instance(i).value(att);
        else
            id = inst.instance(i).stringValue(att);
        if (m_Strict && current.contains(id))
            throw new IllegalStateException(
                    "ID '" + id + "' is not unique in dataset #" + (instIndex + 1) + "!");
        current.add(id);
    }
    ids.addAll(current);
}

From source file:adams.flow.transformer.WekaInstancesMerge.java

License:Open Source License

/**
 * Merges the datasets based on the collected IDs.
 *
 * @param orig   the original datasets//from   w  w  w.  j  a  v  a2s . co  m
 * @param inst   the processed datasets to merge into one
 * @param ids      the IDs for identifying the rows
 * @return      the merged dataset
 */
protected Instances merge(Instances[] orig, Instances[] inst, HashSet ids) {
    Instances result;
    ArrayList<Attribute> atts;
    int i;
    int n;
    int m;
    int index;
    String relation;
    List sortedIDs;
    Attribute att;
    int[] indexStart;
    double value;
    double[] values;
    HashMap<Integer, Integer> hashmap;
    HashSet<Instance> hs;

    // create header
    if (isLoggingEnabled())
        getLogger().info("Creating merged header...");
    atts = new ArrayList<>();
    relation = "";
    indexStart = new int[inst.length];
    for (i = 0; i < inst.length; i++) {
        indexStart[i] = atts.size();
        for (n = 0; n < inst[i].numAttributes(); n++)
            atts.add((Attribute) inst[i].attribute(n).copy());
        // assemble relation name
        if (i > 0)
            relation += "_";
        relation += inst[i].relationName();
    }
    result = new Instances(relation, atts, ids.size());

    // fill with missing values
    if (isLoggingEnabled())
        getLogger().info("Filling with missing values...");
    for (i = 0; i < ids.size(); i++) {
        if (isStopped())
            return null;
        // progress
        if (isLoggingEnabled() && ((i + 1) % 1000 == 0))
            getLogger().info("" + (i + 1));
        result.add(new DenseInstance(result.numAttributes()));
    }

    // sort IDs
    if (isLoggingEnabled())
        getLogger().info("Sorting indices...");
    sortedIDs = new ArrayList(ids);
    Collections.sort(sortedIDs);

    // generate rows
    hashmap = new HashMap<>();
    for (i = 0; i < inst.length; i++) {
        if (isStopped())
            return null;
        if (isLoggingEnabled())
            getLogger().info("Adding file #" + (i + 1));
        att = orig[i].attribute(m_UniqueID);
        for (n = 0; n < inst[i].numInstances(); n++) {
            // progress
            if (isLoggingEnabled() && ((n + 1) % 1000 == 0))
                getLogger().info("" + (n + 1));

            // determine index of row
            if (m_AttType == Attribute.NUMERIC)
                index = Collections.binarySearch(sortedIDs, inst[i].instance(n).value(att));
            else
                index = Collections.binarySearch(sortedIDs, inst[i].instance(n).stringValue(att));
            if (index < 0)
                throw new IllegalStateException(
                        "Failed to determine index for row #" + (n + 1) + " of dataset #" + (i + 1) + "!");

            if (!hashmap.containsKey(index))
                hashmap.put(index, 0);
            hashmap.put(index, hashmap.get(index) + 1);

            // use internal representation for faster access
            values = result.instance(index).toDoubleArray();

            // add attribute values
            for (m = 0; m < inst[i].numAttributes(); m++) {
                // missing value?
                if (inst[i].instance(n).isMissing(m))
                    continue;

                switch (inst[i].attribute(m).type()) {
                case Attribute.NUMERIC:
                case Attribute.DATE:
                case Attribute.NOMINAL:
                    values[indexStart[i] + m] = inst[i].instance(n).value(m);
                    break;

                case Attribute.STRING:
                    value = result.attribute(indexStart[i] + m)
                            .addStringValue(inst[i].instance(n).stringValue(m));
                    values[indexStart[i] + m] = value;
                    break;

                case Attribute.RELATIONAL:
                    value = result.attribute(indexStart[i] + m)
                            .addRelation(inst[i].instance(n).relationalValue(m));
                    values[indexStart[i] + m] = value;
                    break;

                default:
                    throw new IllegalStateException("Unhandled attribute type: " + inst[i].attribute(m).type());
                }
            }

            // update row
            result.set(index, new DenseInstance(1.0, values));
        }
    }

    if (getRemove()) {
        hs = new HashSet<>();
        for (Integer x : hashmap.keySet()) {
            if (hashmap.get(x) != inst.length)
                hs.add(result.get(x));
        }
        result.removeAll(hs);
    }

    return result;
}

From source file:adams.flow.transformer.WekaSetInstancesValue.java

License:Open Source License

/**
 * Executes the flow item./*from   ww  w  . jav  a  2s  .c  o  m*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances inst;
    int row;
    int index;

    result = null;

    inst = (Instances) m_InputToken.getPayload();
    inst = new Instances(inst);
    m_Row.setMax(inst.numInstances());
    m_Column.setData(inst);
    row = m_Row.getIntIndex();
    index = m_Column.getIntIndex();

    if (row == -1)
        result = "Failed to retrieve row: " + m_Row.getIndex();
    else if (index == -1)
        result = "Failed to retrieve column: " + m_Column.getIndex();

    if (result == null) {
        try {
            if (m_Value.equals("?")) {
                inst.instance(row).setMissing(index);
            } else {
                switch (inst.attribute(index).type()) {
                case Attribute.NUMERIC:
                    inst.instance(row).setValue(index, Utils.toDouble(m_Value));
                    break;

                case Attribute.DATE:
                    inst.instance(row).setValue(index, inst.attribute(index).parseDate(m_Value));
                    break;

                case Attribute.NOMINAL:
                case Attribute.STRING:
                    inst.instance(row).setValue(index, m_Value);
                    break;

                case Attribute.RELATIONAL:
                    result = "Relational attributes cannot be set!";
                    break;

                default:
                    result = "Unhandled attribute type: " + inst.attribute(index).type();
                }
            }
        } catch (Exception e) {
            result = handleException("Failed to set value: " + m_Column.getIndex() + " -> " + m_Value, e);
        }
    }

    // broadcast data
    if (result == null)
        m_OutputToken = new Token(inst);

    return result;
}

From source file:adams.flow.transformer.WekaSetInstanceValue.java

License:Open Source License

/**
 * Executes the flow item.//from ww  w  . j  a  va 2s.c  o m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instance inst;
    int index;

    result = null;

    inst = (Instance) m_InputToken.getPayload();
    inst = (Instance) inst.copy();
    m_Index.setData(inst.dataset());
    index = m_Index.getIntIndex();

    try {
        if (m_Value.equals("?")) {
            inst.setMissing(index);
        } else {
            switch (inst.attribute(index).type()) {
            case Attribute.NUMERIC:
                inst.setValue(index, Utils.toDouble(m_Value));
                break;

            case Attribute.DATE:
                inst.setValue(index, inst.attribute(index).parseDate(m_Value));
                break;

            case Attribute.NOMINAL:
            case Attribute.STRING:
                inst.setValue(index, m_Value);
                break;

            case Attribute.RELATIONAL:
                result = "Relational attributes cannot be set!";
                break;

            default:
                result = "Unhandled attribute type: " + inst.attribute(index).type();
            }
        }
    } catch (Exception e) {
        result = handleException("Failed to set value: " + m_Index.getIndex() + " -> " + m_Value, e);
    }

    // broadcast data
    if (result == null)
        m_OutputToken = new Token(inst);

    return result;
}