Example usage for weka.core Instances attribute

Introduction

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

Prototype

publicAttribute attribute(String name) 

Source Link

Document

Returns an attribute given its name.

Usage

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

License:Open Source License

/**
 * Excludes attributes from the data./*  ww  w. jav  a 2 s  . c om*/
 *
 * @param inst   the data to process
 * @return      the processed data
 */
protected Instances excludeAttributes(Instances inst) {
    Instances result;
    StringBuilder atts;
    int i;
    Remove filter;

    // determine attribute indices
    atts = new StringBuilder();
    for (i = 0; i < inst.numAttributes(); i++) {
        if (inst.attribute(i).name().matches(m_ExcludedAttributes)) {
            if (atts.length() > 0)
                atts.append(",");
            atts.append((i + 1));
        }
    }

    // filter data
    try {
        filter = new Remove();
        filter.setAttributeIndices(atts.toString());
        filter.setInvertSelection(m_InvertMatchingSense);
        filter.setInputFormat(inst);
        result = weka.filters.Filter.useFilter(inst, filter);
    } catch (Exception e) {
        result = inst;
        handleException("Error filtering data:", e);
    }

    return result;
}

---

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

License:Open Source License

/**
 * Prefixes the attributes./*from   w w  w.  j ava  2  s.  c  o m*/
 *
 * @param index   the index of the dataset
 * @param inst   the data to process
 * @return      the processed data
 */
protected Instances prefixAttributes(Instances inst, int index) {
    Instances result;
    String prefix;
    ArrayList<Attribute> atts;
    int i;

    prefix = createPrefix(inst, index);

    // header
    atts = new ArrayList<>();
    for (i = 0; i < inst.numAttributes(); i++)
        atts.add(inst.attribute(i).copy(prefix + inst.attribute(i).name()));

    // data
    result = new Instances(inst.relationName(), atts, inst.numInstances());
    result.setClassIndex(inst.classIndex());
    for (i = 0; i < inst.numInstances(); i++)
        result.add((Instance) inst.instance(i).copy());

    return result;
}

---

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

License:Open Source License

/**
 * Prepares the data, prefixing attributes, removing columns, etc, before
 * merging it.// ww  w.j ava2 s  .com
 *
 * @param inst   the data to process
 * @param index   the 0-based index of the dataset being processed
 * @return      the prepared data
 */
protected Instances prepareData(Instances inst, int index) {
    Instances result;

    result = inst;

    if (m_KeepOnlySingleUniqueID && !m_UniqueID.isEmpty() && (inst.attribute(m_UniqueID) != null)) {
        if (index > 0)
            m_UniqueIDAtts.add(createPrefix(inst, index) + m_UniqueID);
    }

    // exclude attributes
    if (m_ExcludedAttributes.length() > 0)
        result = excludeAttributes(result);

    // prefix
    if (m_UsePrefix)
        result = prefixAttributes(inst, index);

    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 2s  .c  o  m
 *
 * @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  . ja  va2  s  . c om
 * @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.WekaInstancesMerge.java

License:Open Source License

/**
 * Executes the flow item.//from   w w  w. j  a  v a 2s  . c o  m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    String[] filesStr;
    File[] files;
    int i;
    Instances output;
    Instances[] orig;
    Instances[] inst;
    Instance[] rows;
    HashSet ids;
    int max;
    TIntList uniqueList;
    Remove remove;

    result = null;

    // get filenames
    files = null;
    orig = null;
    if (m_InputToken.getPayload() instanceof String[]) {
        filesStr = (String[]) m_InputToken.getPayload();
        files = new File[filesStr.length];
        for (i = 0; i < filesStr.length; i++)
            files[i] = new PlaceholderFile(filesStr[i]);
    } else if (m_InputToken.getPayload() instanceof File[]) {
        files = (File[]) m_InputToken.getPayload();
    } else if (m_InputToken.getPayload() instanceof Instance[]) {
        rows = (Instance[]) m_InputToken.getPayload();
        orig = new Instances[rows.length];
        for (i = 0; i < rows.length; i++) {
            orig[i] = new Instances(rows[i].dataset(), 1);
            orig[i].add((Instance) rows[i].copy());
        }
    } else if (m_InputToken.getPayload() instanceof Instances[]) {
        orig = (Instances[]) m_InputToken.getPayload();
    } else {
        throw new IllegalStateException("Unhandled input type: " + m_InputToken.getPayload().getClass());
    }

    try {
        output = null;

        // simple merge
        if (m_UniqueID.length() == 0) {
            if (files != null) {
                inst = new Instances[1];
                for (i = 0; i < files.length; i++) {
                    if (isStopped())
                        break;
                    inst[0] = DataSource.read(files[i].getAbsolutePath());
                    inst[0] = prepareData(inst[0], i);
                    if (i == 0) {
                        output = inst[0];
                    } else {
                        if (isLoggingEnabled())
                            getLogger().info("Merging with file #" + (i + 1) + ": " + files[i]);
                        output = Instances.mergeInstances(output, inst[0]);
                    }
                }
            } else if (orig != null) {
                inst = new Instances[1];
                for (i = 0; i < orig.length; i++) {
                    if (isStopped())
                        break;
                    inst[0] = prepareData(orig[i], i);
                    if (i == 0) {
                        output = inst[0];
                    } else {
                        if (isLoggingEnabled())
                            getLogger()
                                    .info("Merging with dataset #" + (i + 1) + ": " + orig[i].relationName());
                        output = Instances.mergeInstances(output, inst[0]);
                    }
                }
            }
        }
        // merge based on row IDs
        else {
            m_AttType = -1;
            max = 0;
            m_UniqueIDAtts = new ArrayList<>();
            if (files != null) {
                orig = new Instances[files.length];
                for (i = 0; i < files.length; i++) {
                    if (isStopped())
                        break;
                    if (isLoggingEnabled())
                        getLogger().info("Loading file #" + (i + 1) + ": " + files[i]);
                    orig[i] = DataSource.read(files[i].getAbsolutePath());
                    max = Math.max(max, orig[i].numInstances());
                }
            } else if (orig != null) {
                for (i = 0; i < orig.length; i++)
                    max = Math.max(max, orig[i].numInstances());
            }
            inst = new Instances[orig.length];
            ids = new HashSet(max);
            for (i = 0; i < orig.length; i++) {
                if (isStopped())
                    break;
                if (isLoggingEnabled())
                    getLogger().info("Updating IDs #" + (i + 1));
                updateIDs(i, orig[i], ids);
                if (isLoggingEnabled())
                    getLogger().info("Preparing dataset #" + (i + 1));
                inst[i] = prepareData(orig[i], i);
            }
            output = merge(orig, inst, ids);
            // remove unnecessary unique ID attributes
            if (m_KeepOnlySingleUniqueID) {
                uniqueList = new TIntArrayList();
                for (String att : m_UniqueIDAtts)
                    uniqueList.add(output.attribute(att).index());
                if (uniqueList.size() > 0) {
                    if (isLoggingEnabled())
                        getLogger().info("Removing duplicate unique ID attributes: " + m_UniqueIDAtts);
                    remove = new Remove();
                    remove.setAttributeIndicesArray(uniqueList.toArray());
                    remove.setInputFormat(output);
                    output = Filter.useFilter(output, remove);
                }
            }
        }

        if (!isStopped()) {
            m_OutputToken = new Token(output);
            updateProvenance(m_OutputToken);
        }
    } catch (Exception e) {
        result = handleException("Failed to merge: ", e);
    }

    return result;
}

---

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

License:Open Source License

/**
 * Executes the flow item.//  w  w w. j av a  2  s. co m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    SpreadSheet sheet;
    Instances data;
    int i;
    int n;
    Index index;
    AbstractArrayStatistic stat;

    result = null;

    try {
        sheet = null;
        data = (Instances) m_InputToken.getPayload();
        stat = m_Statistic.shallowCopy(true);

        for (i = 0; i < m_Locations.length; i++) {
            switch (m_DataType) {
            case ROW_BY_INDEX:
                index = new Index(m_Locations[i].stringValue());
                index.setMax(data.numInstances());
                stat.add(StatUtils.toNumberArray(data.instance(index.getIntIndex()).toDoubleArray()));
                break;

            case COLUMN_BY_INDEX:
                index = new WekaAttributeIndex(m_Locations[i].stringValue());
                ((WekaAttributeIndex) index).setData(data);
                stat.add(StatUtils.toNumberArray(data.attributeToDoubleArray(index.getIntIndex())));
                break;

            case COLUMN_BY_REGEXP:
                for (n = 0; n < data.numAttributes(); n++) {
                    if (data.attribute(n).name().matches(m_Locations[i].stringValue())) {
                        stat.add(StatUtils.toNumberArray(data.attributeToDoubleArray(n)));
                        break;
                    }
                }
                break;

            default:
                throw new IllegalStateException("Unhandled data type: " + m_DataType);
            }
        }

        sheet = stat.calculate().toSpreadSheet();
    } catch (Exception e) {
        result = handleException("Error generating the statistic: ", e);
        sheet = null;
    }

    if (sheet != null)
        m_OutputToken = new Token(sheet);

    return result;
}

---

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

License:Open Source License

/**
 * Returns the generated token.//w  w  w.  j a v a 2  s.  c om
 *
 * @return      the generated token
 */
@Override
public Token output() {
    Token result;
    int index;
    Remove remove;
    Reorder reorder;
    StringBuilder indices;
    int i;
    int newIndex;
    Instances processed;

    result = null;

    index = m_AttributesToProcess.remove(0);
    remove = new Remove();
    indices = new StringBuilder();
    for (i = 0; i < m_ClassAttributes.size(); i++) {
        if (m_ClassAttributes.get(i) == index)
            continue;
        if (indices.length() > 0)
            indices.append(",");
        indices.append("" + (m_ClassAttributes.get(i) + 1));
    }
    remove.setAttributeIndices(indices.toString());

    try {
        remove.setInputFormat(m_Dataset);
        processed = weka.filters.Filter.useFilter(m_Dataset, remove);
        if (m_UpdateRelationName)
            processed.setRelationName(m_Dataset.attribute(index).name());
        result = new Token(processed);
    } catch (Exception e) {
        processed = null;
        handleException(
                "Failed to process dataset with following filter setup:\n" + OptionUtils.getCommandLine(remove),
                e);
    }

    if (m_MakeClassLast && (processed != null)) {
        newIndex = processed.attribute(m_Dataset.attribute(index).name()).index();
        indices = new StringBuilder();
        for (i = 0; i < processed.numAttributes(); i++) {
            if (i == newIndex)
                continue;
            if (indices.length() > 0)
                indices.append(",");
            indices.append("" + (i + 1));
        }
        if (indices.length() > 0)
            indices.append(",");
        indices.append("" + (newIndex + 1));
        reorder = new Reorder();
        try {
            reorder.setAttributeIndices(indices.toString());
            reorder.setInputFormat(processed);
            processed = weka.filters.Filter.useFilter(processed, reorder);
            if (m_UpdateRelationName)
                processed.setRelationName(m_Dataset.attribute(index).name());
            result = new Token(processed);
        } catch (Exception e) {
            handleException("Failed to process dataset with following filter setup:\n"
                    + OptionUtils.getCommandLine(reorder), e);
        }
    }

    return result;
}

---

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

License:Open Source License

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

    result = null;
    range = "";

    if (m_InputToken.getPayload() instanceof Instances)
        inst = (Instances) m_InputToken.getPayload();
    else
        inst = ((Instance) m_InputToken.getPayload()).dataset();

    int firstInRange = Integer.MIN_VALUE;
    int lastInRange = Integer.MIN_VALUE;
    int last = Integer.MIN_VALUE;

    for (int i = 0; i < inst.numAttributes(); i++) {
        if (match(inst.attribute(i).name())) {
            if (i == last + 1) {
                lastInRange = i;
            } else {
                if (firstInRange != Integer.MIN_VALUE) {
                    if (!range.equals("")) {
                        range += ",";
                    }
                    if (firstInRange - lastInRange == 0) {
                        range += "" + (firstInRange + 1);
                    } else {
                        range += "" + (firstInRange + 1) + "-" + (lastInRange + 1);
                    }
                }

                firstInRange = i;
                lastInRange = i;
            }
            last = i;
        }
    }
    if (!range.equals("")) {
        range += ",";
    }
    if (firstInRange < 0) {
        range = "";
    } else if (lastInRange < 0 || lastInRange == firstInRange) {
        range += "" + (firstInRange + 1);
    } else {
        range += "" + (firstInRange + 1) + "-" + (lastInRange + 1);
    }

    m_OutputToken = new Token(range);

    return result;
}

---

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

License:Open Source License

/**
 * Executes the flow item./*from   w  w w .ja v a 2 s  .  co m*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances dataOld;
    Instance instOld;
    Instances dataNew;
    Instance instNew;
    Attribute att;
    int i;
    StringBuilder order;
    List<Add> adds;
    Add add;
    int index;
    StringBuilder labels;
    int n;
    List<Filter> filters;
    Reorder reorder;

    result = null;

    if (m_OnTheFly && (m_Reference == null)) {
        result = setUpReference();
        if (result != null)
            return result;
    }

    dataNew = null;
    instNew = null;

    // get input data
    if (m_InputToken.getPayload() instanceof Instance) {
        instOld = (Instance) m_InputToken.getPayload();
        dataOld = instOld.dataset();
    } else {
        instOld = null;
        dataOld = (Instances) m_InputToken.getPayload();
    }

    // do we need to initialize filter?
    if (m_InitializeOnce || (m_Reorder == null)) {
        // check incoming data
        if (!m_Lenient) {
            for (i = 0; i < m_Reference.numAttributes(); i++) {
                att = m_Reference.attribute(i);
                if (dataOld.attribute(att.name()) == null) {
                    if (result == null)
                        result = "Missing attribute(s) in incoming data: " + att.name();
                    else
                        result += ", " + att.name();
                }
            }
            if (result != null)
                getLogger().severe(result);
        }

        if (result == null) {
            try {
                // determine indices
                order = new StringBuilder();
                adds = new ArrayList<Add>();
                for (i = 0; i < m_Reference.numAttributes(); i++) {
                    att = m_Reference.attribute(i);
                    if (dataOld.attribute(att.name()) == null) {
                        index = dataOld.numAttributes() + adds.size();
                        add = new Add();
                        add.setAttributeIndex("last");
                        add.setAttributeName(att.name());
                        add.setAttributeType(new SelectedTag(att.type(), Add.TAGS_TYPE));
                        if (att.isNominal()) {
                            labels = new StringBuilder();
                            for (n = 0; n < att.numValues(); n++) {
                                if (labels.length() > 0)
                                    labels.append(",");
                                labels.append(att.value(n));
                            }
                            add.setNominalLabels(labels.toString());
                        }
                        adds.add(add);
                    } else {
                        index = dataOld.attribute(att.name()).index();
                    }
                    if (order.length() > 0)
                        order.append(",");
                    order.append((index + 1));
                }

                // build reorder filter
                reorder = new Reorder();
                reorder.setAttributeIndices(order.toString());

                // build multifilter
                filters = new ArrayList<Filter>();
                filters.addAll(adds);
                filters.add(reorder);
                m_Reorder = new MultiFilter();
                m_Reorder.setFilters(filters.toArray(new Filter[filters.size()]));

                // initialize filter
                m_Reorder.setInputFormat(dataOld);
            } catch (Exception e) {
                result = handleException("Failed to initialize reorder filter!", e);
            }
        }
    }

    // reorder data
    if (result == null) {
        try {
            if (instOld != null) {
                m_Reorder.input(instOld);
                m_Reorder.batchFinished();
                instNew = m_Reorder.output();
                if (m_KeepRelationName)
                    instNew.dataset().setRelationName(dataOld.relationName());
            } else {
                dataNew = Filter.useFilter(dataOld, m_Reorder);
                if (m_KeepRelationName)
                    dataNew.setRelationName(dataOld.relationName());
            }
        } catch (Exception e) {
            result = handleException("Failed to reorder data!", e);
            instNew = null;
            dataNew = null;
        }
    }

    if (instNew != null)
        m_OutputToken = new Token(instNew);
    else if (dataNew != null)
        m_OutputToken = new Token(dataNew);

    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
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »