Examples with Instances weka.core.Instances used on opensource projects

Example 16 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaUtils method removeInstanceId.

/**
 * Removes the instanceId attribute, iff present
 *
 * @param data
 *            data set with or without instanceId attribute
 * @param multilabel
 *            is multi label processing
 * @return the data set without instanceId attribute
 * @throws Exception
 *             an exception
 */
public static Instances removeInstanceId(Instances data, boolean multilabel) throws Exception {
    Instances filteredData;
    int classIndex = data.classIndex();
    if (data.attribute(Constants.ID_FEATURE_NAME) != null) {
        int instanceIdOffset = data.attribute(Constants.ID_FEATURE_NAME).index();
        Remove remove = new Remove();
        remove.setAttributeIndices(Integer.toString(instanceIdOffset + 1));
        remove.setInvertSelection(false);
        remove.setInputFormat(data);
        filteredData = Filter.useFilter(data, remove);
    } else {
        filteredData = new Instances(data);
    }
    // make sure the class index gets retained in multi-label
    if (multilabel) {
        filteredData.setClassIndex(classIndex);
    }
    return filteredData;
}

Example 17 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaUtils method addInstanceId.

/**
 * Copies the instanceId attribute and its values from an existing data set, iff present. It
 * will be indexed right before the class attribute
 *
 * @param newData
 *            data set without instanceId attribute
 * @param oldData
 *            data set with or without instanceId attribute
 * @param isMultilabel
 *            is multi label processing
 * @return a data set with or without instanceId attribute
 * @throws Exception
 *             an exception
 */
public static Instances addInstanceId(Instances newData, Instances oldData, boolean isMultilabel) throws Exception {
    Instances filteredData;
    if (oldData.attribute(Constants.ID_FEATURE_NAME) != null) {
        int instanceIdOffset = oldData.attribute(Constants.ID_FEATURE_NAME).index();
        Add add = new Add();
        add.setAttributeName(Constants.ID_FEATURE_NAME);
        // for single-label
        if (isMultilabel) {
            add.setAttributeIndex("last");
        } else {
            add.setAttributeIndex("first");
        }
        add.setAttributeType(new SelectedTag(Attribute.STRING, Add.TAGS_TYPE));
        add.setInputFormat(newData);
        filteredData = Filter.useFilter(newData, add);
        int j = isMultilabel ? filteredData.numAttributes() - 1 : 0;
        for (int i = 0; i < filteredData.numInstances(); i++) {
            String outcomeId = oldData.instance(i).stringValue(instanceIdOffset);
            filteredData.instance(i).setValue(j, outcomeId);
        }
    } else {
        filteredData = new Instances(newData);
    }
    return filteredData;
}

Example 18 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class MekaDataWriter method initalConfiguration.

private Instances initalConfiguration(Collection<Instance> instances) throws TextClassificationException, IOException {
    if (saver != null) {
        return masterInstance;
    }
    saver = new ArffSaver();
    saver.setRetrieval(Saver.INCREMENTAL);
    saver.setFile(arffTarget);
    saver.setCompressOutput(false);
    attributeStore = new AttributeStore();
    List<String> lines = FileUtils.readLines(new File(outputFolder, Constants.FILENAME_FEATURES_DESCRIPTION), "utf-8");
    for (String l : lines) {
        String[] split = l.split("\t");
        String featureName = split[0];
        if (!attributeStore.containsAttributeName(featureName)) {
            FeatureType type = FeatureType.valueOf(split[1]);
            String enumType = null;
            if (type == FeatureType.NOMINAL) {
                enumType = split[2];
            }
            Attribute attribute = WekaFeatureEncoder.featureToAttributeUsingFeatureDescription(featureName, type, enumType);
            attributeStore.addAttribute(featureName, attribute);
        }
    }
    // Make sure "outcome" is not the name of an attribute
    List<String> outcomeList = Arrays.asList(outcomes);
    outcomeAttributes = createOutcomeAttributes(outcomeList);
    // in Meka, class label attributes have to go on top
    for (Attribute attribute : outcomeAttributes) {
        attributeStore.addAttributeAtBegin(attribute.name(), attribute);
    }
    // for Meka-internal use
    masterInstance = new Instances(WekaUtils.RELATION_NAME + ": -C " + outcomeAttributes.size() + " ", attributeStore.getAttributes(), instances.size());
    masterInstance.setClassIndex(outcomeAttributes.size());
    saver.setInstances(masterInstance);
    return masterInstance;
}

Example 19 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class MekaDataWriter method writeClassifierFormat.

@Override
public void writeClassifierFormat(Collection<Instance> instances) throws AnalysisEngineProcessException {
    try {
        Instances masterInstance = initalConfiguration(instances);
        for (Instance instance : instances) {
            double[] featureValues = getFeatureValues(attributeStore, instance);
            // set class label values
            List<String> instanceOutcome = instance.getOutcomes();
            for (Attribute label : outcomeAttributes) {
                String labelname = label.name();
                featureValues[attributeStore.getAttributeOffset(labelname)] = instanceOutcome.contains(labelname.split(CLASS_ATTRIBUTE_PREFIX)[1]) ? 1.0d : 0.0d;
            }
            weka.core.Instance wekaInstance;
            if (useSparse) {
                wekaInstance = new SparseInstance(1.0, featureValues);
            } else {
                wekaInstance = new DenseInstance(1.0, featureValues);
            }
            wekaInstance.setDataset(masterInstance);
            Double instanceWeight = instance.getWeight();
            if (applyWeighting) {
                wekaInstance.setWeight(instanceWeight);
            }
            saver.writeIncremental(wekaInstance);
        }
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
}

Example 20 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaDataWriter method initalConfiguration.

private Instances initalConfiguration(Collection<Instance> instances) throws TextClassificationException, IOException {
    if (saver != null) {
        return masterInstance;
    }
    saver = new ArffSaver();
    saver.setRetrieval(Saver.INCREMENTAL);
    saver.setFile(arffTarget);
    saver.setCompressOutput(false);
    attributeStore = new AttributeStore();
    List<String> lines = FileUtils.readLines(new File(outputFolder, Constants.FILENAME_FEATURES_DESCRIPTION), "utf-8");
    for (String l : lines) {
        String[] split = l.split("\t");
        String featureName = split[0];
        if (!attributeStore.containsAttributeName(featureName)) {
            FeatureType type = FeatureType.valueOf(split[1]);
            String enumType = null;
            if (type == FeatureType.NOMINAL) {
                enumType = split[2];
            }
            Attribute attribute = WekaFeatureEncoder.featureToAttributeUsingFeatureDescription(featureName, type, enumType);
            attributeStore.addAttribute(featureName, attribute);
        }
    }
    // Make sure "outcome" is not the name of an attribute
    List<String> outcomeList = Arrays.asList(outcomes);
    outcomeAttribute = createOutcomeAttribute(outcomeList, isRegression);
    if (attributeStore.containsAttributeName(CLASS_ATTRIBUTE_NAME)) {
        System.err.println("A feature with name \"outcome\" was found. Renaming outcome attribute");
        outcomeAttribute = outcomeAttribute.copy(CLASS_ATTRIBUTE_PREFIX + CLASS_ATTRIBUTE_NAME);
    }
    attributeStore.addAttribute(outcomeAttribute.name(), outcomeAttribute);
    masterInstance = new Instances(WekaUtils.RELATION_NAME, attributeStore.getAttributes(), instances.size());
    masterInstance.setClass(outcomeAttribute);
    saver.setInstances(masterInstance);
    return masterInstance;
}