Example usage for weka.core Instance weight

List of usage examples for weka.core Instance weight

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

Introduction

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

Prototype

public double weight();

Source Link

Document

Returns the instance's weight.

Usage

From source file:edu.oregonstate.eecs.mcplan.abstraction.WekaUtil.java

License:Open Source License

public static Instances powerSet(final Instances D, final int n) {
    final Attribute class_attr = D.classAttribute();

    final ImmutableSet.Builder<Integer> b = new ImmutableSet.Builder<Integer>();
    final int Nattr = class_attr != null ? D.numAttributes() - 1 : D.numAttributes();
    for (final int i : Fn.range(1, Nattr)) {
        b.add(i);// ww w .  j  a  v a2  s.  c  o m
    }
    final Set<Set<Integer>> index = Sets.powerSet(b.build());

    final ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    for (final Set<Integer> subset : index) {
        if (subset.isEmpty() || subset.size() > n) {
            continue;
        }

        final StringBuilder attr_name = new StringBuilder();
        int count = 0;
        for (final Integer i : subset) {
            if (count++ > 0) {
                attr_name.append("_x_");
            }
            attr_name.append(D.attribute(i).name());
        }

        attributes.add(new Attribute(attr_name.toString()));
    }
    if (class_attr != null) {
        assert (class_attr.isNominal());
        attributes.add(WekaUtil.createNominalAttribute(class_attr.name(), class_attr.numValues()));
    }

    final String Pname = "P" + n + "_" + D.relationName();
    final Instances P = new Instances(Pname, attributes, 0);
    if (class_attr != null) {
        P.setClassIndex(attributes.size() - 1);
    }

    for (final Instance inst : D) {
        final double[] xp = new double[attributes.size()];
        int idx = 0;
        for (final Set<Integer> subset : index) {
            if (subset.isEmpty() || subset.size() > n) {
                continue;
            }

            double p = 1.0;
            for (final Integer i : subset) {
                p *= inst.value(i);
            }
            xp[idx++] = p;
        }
        if (class_attr != null) {
            xp[idx++] = inst.classValue();
        }

        WekaUtil.addInstance(P, new DenseInstance(inst.weight(), xp));
    }

    return P;
}

From source file:edu.oregonstate.eecs.mcplan.abstraction.WekaUtil.java

License:Open Source License

public static Instances allPairwiseProducts(final Instances single, final boolean reflexive,
        final boolean symmetric) {
    final int c = single.classIndex();
    System.out.println("Class attribute = " + c);

    final ArrayList<Attribute> pair_attributes = new ArrayList<Attribute>();
    for (int i = 0; i < single.numAttributes(); ++i) {
        if (i == c) {
            continue;
        }//from  w w  w  .j a  v a2s  .com
        final Attribute ai = single.attribute(i);
        final int j0 = (symmetric ? 0 : i);
        for (int j = j0; j < single.numAttributes(); ++j) {
            if (j == c) {
                continue;
            }
            if (!reflexive && i == j) {
                continue;
            }

            final Attribute aj = single.attribute(j);

            final String name = ai.name() + "_x_" + aj.name();
            pair_attributes.add(new Attribute(name));
        }
    }

    String pair_name = single.relationName();
    pair_name += "_x";
    if (reflexive) {
        pair_name += "r";
    }
    if (symmetric) {
        pair_name += "s";
    }
    pair_name += "_";
    pair_name += single.relationName();
    final Instances result = new Instances(pair_name, pair_attributes, 0);

    for (final Instance inst : single) {
        final double[] xp = new double[pair_attributes.size()];
        int idx = 0;
        for (int i = 0; i < single.numAttributes(); ++i) {
            if (i == c) {
                continue;
            }
            final double xi = inst.value(i);
            final int j0 = (symmetric ? 0 : i);
            for (int j = j0; j < single.numAttributes(); ++j) {
                if (j == c) {
                    continue;
                }
                if (!reflexive && i == j) {
                    continue;
                }
                final double xj = inst.value(j);
                xp[idx++] = xi * xj;
            }
        }
        WekaUtil.addInstance(result, new DenseInstance(inst.weight(), xp));
    }

    return result;
}

From source file:edu.oregonstate.eecs.mcplan.domains.frogger.FroggerRepresentationConverter.java

License:Open Source License

public static Instances absoluteToRelative(final FroggerParameters params, final Instances src,
        final int vision) {
    final ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    attributes.add(new Attribute("x"));
    attributes.add(new Attribute("y"));
    for (int i = vision; i >= -vision; --i) {
        for (int j = -vision; j <= vision; ++j) {
            if (i == 0 && j == 0) {
                continue;
            }//from www  .  jav a 2s .  co m

            final String name = "car_x" + (j >= 0 ? "+" : "") + j + "_y" + (i >= 0 ? "+" : "") + i;
            attributes.add(new Attribute(name));
        }
    }
    attributes.add(src.classAttribute());

    final Instances dest = new Instances(src.relationName() + "_relative", attributes, src.size());
    for (final Instance inst : src) {
        final double[] phi = new double[attributes.size()];
        int idx = 0;

        final int x = (int) inst.value(0);
        final int y = (int) inst.value(1);
        phi[idx++] = x;
        phi[idx++] = y;

        for (int i = vision; i >= -vision; --i) {
            for (int j = -vision; j <= vision; ++j) {
                if (i == 0 && j == 0) {
                    continue;
                }

                final int xoff = x + j;
                final int yoff = y + i;

                if (xoff >= 0 && xoff < params.road_length && yoff >= 1 && yoff <= params.lanes) {
                    final int car = (int) inst.value(2 + (yoff - 1) * params.road_length + xoff);
                    phi[idx] = car; // s.grid[dy][dx] == Tile.Car ? 1.0 : 0.0; // fv[2 + (dy-1)*road_length + dx]
                }
                idx += 1;
            }
        }

        phi[idx++] = inst.classValue();
        assert (idx == phi.length);

        WekaUtil.addInstance(dest, new DenseInstance(inst.weight(), phi));
    }

    return dest;
}

From source file:edu.oregonstate.eecs.mcplan.ml.GameTreeStateSimilarityDataset.java

License:Open Source License

@Override
public void run() {
    System.out.println("*** Extracting state nodes");
    final Visitor visitor = new Visitor();
    tree_.root().accept(visitor);/*from w  ww  . j a  v a2s  . c om*/

    // This extracts only the level-1 nodes.
    // TODO: Do this somewhere better.
    final HashMap<List<ActionNode<S, A>>, List<StateNode<S, A>>> tx = new HashMap<List<ActionNode<S, A>>, List<StateNode<S, A>>>();
    final ArrayList<StateNode<S, A>> depth_1 = new ArrayList<StateNode<S, A>>();
    for (final Map.Entry<List<ActionNode<S, A>>, List<StateNode<S, A>>> e : visitor.xs.entrySet()) {
        if (e.getKey() == null || e.getKey().size() != 1) {
            continue;
        } else {
            depth_1.addAll(e.getValue());
        }
    }
    tx.put(null, depth_1);

    final Comparator<Instance> weight_comp = new Comparator<Instance>() {
        @Override
        public int compare(final Instance a, final Instance b) {
            return (int) Math.signum(a.weight() - b.weight());
        }
    };
    final int max_cap = max_instances_ + 1;
    final PriorityQueue<Instance> positive = new PriorityQueue<Instance>(max_cap, weight_comp);
    final PriorityQueue<Instance> negative = new PriorityQueue<Instance>(max_cap, weight_comp);
    System.out.println("*** Building Instances");
    for (final Map.Entry<List<ActionNode<S, A>>, List<StateNode<S, A>>> e : tx.entrySet()) {
        System.out.println("***** key = " + e.getKey() + ", value.size() = " + e.getValue().size());

        final String name = (e.getKey() != null ? e.getKey().toString() : "null");
        final List<StateNode<S, A>> values = e.getValue();
        final int[] num_instances = { 0, 0 };
        int count = 0;
        for (int i = 0; i < values.size(); ++i) {
            for (int j = i + 1; j < values.size(); ++j) {
                if (count++ % 100 == 0) {
                    System.out.println("***** instance " + (count - 1));
                }

                final StateNode<S, A> s_i = values.get(i);
                final StateNode<S, A> s_j = values.get(j);
                if (s_i.n() < min_samples_ || s_j.n() < min_samples_) {
                    System.out.println("! skipping under-sampled state pair");
                    continue;
                }
                final double[] phi_i = s_i.token.phi();
                final double[] phi_j = s_j.token.phi();
                assert (phi_i.length == phi_j.length);
                if (phi_i.length != attributes_.size() - 1) {
                    System.out.println("! phi_i.length = " + phi_i.length);
                    System.out.println("! attributes_.size() = " + attributes_.size());
                }
                assert (phi_i.length == attributes_.size() - 1);
                // Feature vector is absolute difference of the two state
                // feature vectors.
                final double[] phi_labeled = new double[phi_i.length + 1];
                for (int k = 0; k < phi_i.length; ++k) {
                    phi_labeled[k] = Math.abs(phi_i[k] - phi_j[k]);
                }
                final Tuple2<Integer, Double> labeled = label(e.getKey(), player_, s_i, s_j);
                final int label = labeled._1;
                final double weight = labeled._2;
                final String label_string = Integer.toString(label);
                phi_labeled[label_index] = label; //attributes.get( label_index ).indexOfValue( label_string );

                num_instances[label] += 1;

                final Instance instance = new DenseInstance(weight, phi_labeled);
                if (label == 0) {
                    negative.add(instance);
                    if (negative.size() >= max_cap) {
                        negative.poll();
                    }
                } else {
                    positive.add(instance);
                    if (positive.size() >= max_cap) {
                        positive.poll();
                    }
                }
            } // for j
        } // for i
        System.out.println("num_instances = " + Arrays.toString(num_instances));
        final Instances x = new Instances(name, attributes_, negative.size() + positive.size());
        x.setClassIndex(label_index);
        x.addAll(negative);
        x.addAll(positive);
        xs_.put(e.getKey(), x);
    }
}

From source file:en_deep.mlprocess.manipulation.featmodif.FeatureModifierFilter.java

License:Open Source License

/**
 * Convert a single instance over if the class is nominal. The converted
 * instance is added to the end of the output queue.
 *
 * @param instance the instance to convert
 *//*  www .  j  a  va 2 s . co  m*/
private void convertInstance(Instance instance) {

    double[] vals = new double[outputFormatPeek().numAttributes()];
    String[] stringVals = new String[vals.length];
    int attSoFar = 0;

    for (int j = 0; j < getInputFormat().numAttributes(); j++) {
        Attribute att = instance.attribute(j);
        if (!m_Columns.isInRange(j)) {
            vals[attSoFar] = instance.value(j);
            attSoFar++;
        } else {
            // store new string values, make double values "missing" for now (if some string
            // values are missing, the double values will remain missing)
            if (instance.value(0) == 12 && instance.value(1) == 9 && att.name().equals("sempos")) {
                attSoFar = attSoFar;
            }
            attSoFar += getAttributeOutputValue(att, instance.value(j), vals, stringVals, attSoFar);
        }
    }
    Instance inst = null;
    if (instance instanceof SparseInstance) {
        inst = new SparseInstance(instance.weight(), vals);
    } else {
        inst = new DenseInstance(instance.weight(), vals);
    }

    inst.setDataset(getOutputFormat());
    copyValues(inst, false, instance.dataset(), getOutputFormat());

    // add new string values to the output data set and to the instance
    for (int i = 0; i < stringVals.length; ++i) {
        if (stringVals[i] != null) {
            vals[i] = inst.dataset().attribute(i).addStringValue(stringVals[i]);
        }
    }
    inst.replaceMissingValues(vals);

    inst.setDataset(getOutputFormat());
    push(inst);
}

From source file:en_deep.mlprocess.manipulation.featmodif.ReplaceMissing.java

License:Open Source License

/**
 * Convert a single instance over if the class is nominal. The converted
 * instance is added to the end of the output queue.
 *
 * @param instance the instance to convert
 *///w  w  w  . jav  a2 s  .co m
private void convertInstance(Instance instance) {

    // create a copy of the input instance
    Instance inst = null;

    if (instance instanceof SparseInstance) {
        inst = new SparseInstance(instance.weight(), instance.toDoubleArray());
    } else {
        inst = new DenseInstance(instance.weight(), instance.toDoubleArray());
    }

    // copy the string values from this instance as well (only the existing ones)
    inst.setDataset(getOutputFormat());
    copyValues(inst, false, instance.dataset(), getOutputFormat()); // beware of weird behavior of this function (see source)!!
    inst.setDataset(getOutputFormat());

    // find the missing values to be filled + the double values for the new "missing" label and store it
    double[] vals = instance.toDoubleArray();

    for (int j = 0; j < getInputFormat().numAttributes(); j++) {

        Attribute att = instance.attribute(j);

        if (m_Columns.isInRange(j) && instance.isMissing(j)) {
            // find the "missing" value in the output nominal attribute
            if (att.isNominal()) {
                vals[j] = inst.dataset().attribute(j).indexOfValue(m_ReplVal);
            }
            // add a string value for the new "missing" label
            else if (att.isString()) {
                vals[j] = inst.dataset().attribute(j).addStringValue(m_ReplVal);
            }
        }
    }

    // fill in the missing values found
    inst.replaceMissingValues(vals);

    push(inst);
}

From source file:en_deep.mlprocess.manipulation.SetAwareNominalToBinary.java

License:Open Source License

/**
 * Convert a single instance over if the class is nominal. The converted
 * instance is added to the end of the output queue.
 *
 * @param instance the instance to convert
 *//*from  w w w  .  j  a v  a2s .  c o  m*/
private void convertInstance(Instance instance) {

    double[] vals = new double[outputFormatPeek().numAttributes()];
    int attSoFar = 0;

    for (int j = 0; j < getInputFormat().numAttributes(); j++) {
        Attribute att = getInputFormat().attribute(j);
        if (!att.isNominal() || (j == getInputFormat().classIndex()) || !m_Columns.isInRange(j)) {
            vals[attSoFar] = instance.value(j);
            attSoFar++;
        } else {
            if ((att.numValues() <= 2) && (!m_TransformAll)) {
                vals[attSoFar] = instance.value(j);
                attSoFar++;
            } else {
                attSoFar += setConvertedAttribute(att, instance.value(j), vals, attSoFar);
            }
        }
    }
    Instance inst = null;
    if (instance instanceof SparseInstance) {
        inst = new SparseInstance(instance.weight(), vals);
    } else {
        inst = new DenseInstance(instance.weight(), vals);
    }
    inst.setDataset(getOutputFormat());
    copyValues(inst, false, instance.dataset(), getOutputFormat());
    inst.setDataset(getOutputFormat());
    push(inst);
}

From source file:etc.aloe.filters.AbstractRegexFilter.java

License:Open Source License

@Override
protected Instance process(Instance instance) throws Exception {
    if (stringAttributeIndex < 0) {
        throw new IllegalStateException("String attribute not set");
    }/*from  w ww .  j  av  a  2 s  . c  o  m*/

    String stringValue = instance.stringValue(stringAttributeIndex);
    NamedRegex[] regexFeatures = getRegexFeatures();

    int numOldValues = instance.numAttributes();
    int numNewFeatures = regexFeatures.length;
    if (countRegexLengths) {
        numNewFeatures = regexFeatures.length * 2;
    }
    double[] newValues = new double[numOldValues + numNewFeatures];

    // Copy all attributes from input to output
    for (int i = 0; i < getInputFormat().numAttributes(); i++) {
        if (getInputFormat().attribute(i).type() != Attribute.STRING) {
            // Add simple nominal and numeric attributes directly
            if (instance.value(i) != 0.0) {
                newValues[i] = instance.value(i);
            }
        } else {
            if (instance.isMissing(i)) {
                newValues[i] = Utils.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(i).numValues() == 0) {
                    // Note that the first string value in a
                    // SparseInstance doesn't get printed.
                    outputFormatPeek().attribute(i).addStringValue("Hack to defeat SparseInstance bug");
                }
                int newIndex = outputFormatPeek().attribute(i).addStringValue(instance.stringValue(i));
                newValues[i] = newIndex;
            }
        }
    }

    for (int i = 0; i < regexFeatures.length; i++) {
        Pattern pattern = regexFeatures[i].getPattern();

        Matcher matches = pattern.matcher(stringValue);
        int count = 0;
        int maxLength = 0;
        while (matches.find()) {
            count++;
            int len = matches.group().length();
            if (len > maxLength) {
                maxLength = len;
            }
        }

        int index = numOldValues + i;
        if (countRegexLengths) {
            index = numOldValues + 2 * i;
        }
        newValues[index] = count;

        if (countRegexLengths) {
            newValues[numOldValues + 2 * i + 1] = maxLength;
        }
    }

    Instance result = new SparseInstance(instance.weight(), newValues);
    return result;
}

From source file:etc.aloe.filters.StringToDictionaryVector.java

License:Open Source License

/**
 * Converts the instance w/o normalization.
 *
 * @param instance the instance to convert
 *
 * @param ArrayList<Instance> the list of instances
 * @return the document length/*w ww . j  a v a2s  .  c  o  m*/
 */
private double convertInstancewoDocNorm(Instance instance, ArrayList<Instance> converted) {
    if (stringAttributeIndex < 0) {
        throw new IllegalStateException("String attribute index not valid");
    }

    int numOldValues = instance.numAttributes();
    double[] newValues = new double[numOldValues + m_selectedTerms.size()];

    // Copy all attributes from input to output
    for (int i = 0; i < getInputFormat().numAttributes(); i++) {
        if (getInputFormat().attribute(i).type() != Attribute.STRING) {
            // Add simple nominal and numeric attributes directly
            if (instance.value(i) != 0.0) {
                newValues[i] = instance.value(i);
            }
        } else {
            if (instance.isMissing(i)) {
                newValues[i] = Utils.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(i).numValues() == 0) {
                    // Note that the first string value in a
                    // SparseInstance doesn't get printed.
                    outputFormatPeek().attribute(i).addStringValue("Hack to defeat SparseInstance bug");
                }
                int newIndex = outputFormatPeek().attribute(i).addStringValue(instance.stringValue(i));
                newValues[i] = newIndex;
            }
        }
    }

    String stringValue = instance.stringValue(stringAttributeIndex);
    double docLength = 0;

    HashMap<String, Integer> termMatches = m_selectedTermsTrie.countNonoverlappingMatches(stringValue);
    for (Map.Entry<String, Integer> entry : termMatches.entrySet()) {
        String term = entry.getKey();
        int termIdx = m_selectedTermIndices.get(term);
        double matches = entry.getValue();
        if (!m_OutputCounts && matches > 0) {
            matches = 1;
        }

        if (matches > 0) {
            if (m_TFTransform == true) {
                matches = Math.log(matches + 1);
            }

            if (m_IDFTransform == true) {
                matches = matches * Math.log(m_NumInstances / (double) m_DocsCounts[termIdx]);
            }

            newValues[numOldValues + termIdx] = matches;
            docLength += matches * matches;
        }
    }

    Instance result = new SparseInstance(instance.weight(), newValues);
    converted.add(result);

    return Math.sqrt(docLength);
}

From source file:etc.aloe.filters.WordFeaturesExtractor.java

License:Open Source License

@Override
protected Instance process(Instance instance) throws Exception {
    if (selectedAttributeIndex < 0) {
        throw new IllegalStateException("String attribute not set");
    }/*from www . ja  v  a  2  s  . co  m*/

    int numOldValues = instance.numAttributes();
    int numNewFeatures = unigrams.size() + bigrams.size();
    double[] newValues = new double[numOldValues + numNewFeatures];

    // Copy all attributes from input to output
    for (int i = 0; i < getInputFormat().numAttributes(); i++) {
        if (getInputFormat().attribute(i).type() != Attribute.STRING) {
            // Add simple nominal and numeric attributes directly
            if (instance.value(i) != 0.0) {
                newValues[i] = instance.value(i);
            }
        } else {
            if (instance.isMissing(i)) {
                newValues[i] = Utils.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(i).numValues() == 0) {
                    // Note that the first string value in a
                    // SparseInstance doesn't get printed.
                    outputFormatPeek().attribute(i).addStringValue("Hack to defeat SparseInstance bug");
                }
                int newIndex = outputFormatPeek().attribute(i).addStringValue(instance.stringValue(i));
                newValues[i] = newIndex;
            }
        }
    }

    String stringValue = instance.stringValue(selectedAttributeIndex);
    if (instance.isMissing(selectedAttributeIndex) == false) {

        List<String> words = tokenizeDocument(instance);
        Set<String> wordSet = new HashSet<String>(words);

        for (int i = 0; i < unigrams.size(); i++) {
            String unigram = unigrams.get(i);
            int count = 0;
            if (wordSet.contains(unigram)) {
                //Count the times the word is in the document
                for (int w = 0; w < words.size(); w++) {
                    if (words.get(w).equals(unigram)) {
                        count += 1;
                    }
                }
            }

            int featureIndex = numOldValues + i;
            newValues[featureIndex] = count;
        }

        for (int i = 0; i < bigrams.size(); i++) {
            Bigram bigram = bigrams.get(i);
            int count = bigram.getTimesInDocument(words);
            int featureIndex = numOldValues + unigrams.size() + i;
            newValues[featureIndex] = count;
        }
    }

    Instance result = new SparseInstance(instance.weight(), newValues);
    return result;
}