List of usage examples for weka.core Instance numValues
public int numValues();
From source file:moa.classifiers.functions.SGD.java
License:Open Source License
/** * Trains the classifier with the given instance. * * @param instance the new training instance to include in the model */// w ww . java2 s .c o m @Override public void trainOnInstanceImpl(Instance instance) { if (m_weights == null) { m_weights = new DoubleVector(); m_bias = 0.0; } if (!instance.classIsMissing()) { double wx = dotProd(instance, m_weights, instance.classIndex()); double y; double z; if (instance.classAttribute().isNominal()) { y = (instance.classValue() == 0) ? -1 : 1; z = y * (wx + m_bias); } else { y = instance.classValue(); z = y - (wx + m_bias); y = 1; } // Compute multiplier for weight decay double multiplier = 1.0; if (m_numInstances == 0) { multiplier = 1.0 - (m_learningRate * m_lambda) / m_t; } else { multiplier = 1.0 - (m_learningRate * m_lambda) / m_numInstances; } for (int i = 0; i < m_weights.numValues(); i++) { m_weights.setValue(i, m_weights.getValue(i) * multiplier); } // Only need to do the following if the loss is non-zero if (m_loss != HINGE || (z < 1)) { // Compute Factor for updates double factor = m_learningRate * y * dloss(z); // Update coefficients for attributes int n1 = instance.numValues(); for (int p1 = 0; p1 < n1; p1++) { int indS = instance.index(p1); if (indS != instance.classIndex() && !instance.isMissingSparse(p1)) { m_weights.addToValue(indS, factor * instance.valueSparse(p1)); } } // update the bias m_bias += factor; } m_t++; } }
From source file:moa.classifiers.functions.SGDMultiClass.java
License:Open Source License
public void trainOnInstanceImpl(Instance instance, int classLabel) { if (!instance.classIsMissing()) { double wx = dotProd(instance, m_weights[classLabel], instance.classIndex()); double y; double z; if (instance.classAttribute().isNominal()) { y = (instance.classValue() != classLabel) ? -1 : 1; z = y * (wx + m_bias[classLabel]); } else {//w ww .ja va 2s. co m y = instance.classValue(); z = y - (wx + m_bias[classLabel]); y = 1; } // Compute multiplier for weight decay double multiplier = 1.0; if (m_numInstances == 0) { multiplier = 1.0 - (m_learningRate * m_lambda) / m_t; } else { multiplier = 1.0 - (m_learningRate * m_lambda) / m_numInstances; } for (int i = 0; i < m_weights[classLabel].numValues(); i++) { m_weights[classLabel].setValue(i, m_weights[classLabel].getValue(i) * multiplier); } // Only need to do the following if the loss is non-zero if (m_loss != HINGE || (z < 1)) { // Compute Factor for updates double factor = m_learningRate * y * dloss(z); // Update coefficients for attributes int n1 = instance.numValues(); for (int p1 = 0; p1 < n1; p1++) { int indS = instance.index(p1); if (indS != instance.classIndex() && !instance.isMissingSparse(p1)) { m_weights[classLabel].addToValue(indS, factor * instance.valueSparse(p1)); } } // update the bias m_bias[classLabel] += factor; } } }
From source file:moa.classifiers.functions.SGDOld.java
License:Open Source License
protected static double dotProd(Instance inst1, double[] weights, int classIndex) { double result = 0; int n1 = inst1.numValues(); int n2 = weights.length - 1; for (int p1 = 0, p2 = 0; p1 < n1 && p2 < n2;) { int ind1 = inst1.index(p1); int ind2 = p2; if (ind1 == ind2) { if (ind1 != classIndex && !inst1.isMissingSparse(p1)) { result += inst1.valueSparse(p1) * weights[p2]; }// w ww. j ava2 s . co m p1++; p2++; } else if (ind1 > ind2) { p2++; } else { p1++; } } return (result); }
From source file:moa.classifiers.functions.SGDOld.java
License:Open Source License
/** * Trains the classifier with the given instance. * * @param instance the new training instance to include in the model *///ww w . j a va2s .c o m @Override public void trainOnInstanceImpl(Instance instance) { if (m_weights == null) { m_weights = new double[instance.numAttributes() + 1]; } if (!instance.classIsMissing()) { double wx = dotProd(instance, m_weights, instance.classIndex()); double y; double z; if (instance.classAttribute().isNominal()) { y = (instance.classValue() == 0) ? -1 : 1; z = y * (wx + m_weights[m_weights.length - 1]); } else { y = instance.classValue(); z = y - (wx + m_weights[m_weights.length - 1]); y = 1; } // Compute multiplier for weight decay double multiplier = 1.0; if (m_numInstances == 0) { multiplier = 1.0 - (m_learningRate * m_lambda) / m_t; } else { multiplier = 1.0 - (m_learningRate * m_lambda) / m_numInstances; } for (int i = 0; i < m_weights.length - 1; i++) { m_weights[i] *= multiplier; } // Only need to do the following if the loss is non-zero if (m_loss != HINGE || (z < 1)) { // Compute Factor for updates double factor = m_learningRate * y * dloss(z); // Update coefficients for attributes int n1 = instance.numValues(); for (int p1 = 0; p1 < n1; p1++) { int indS = instance.index(p1); if (indS != instance.classIndex() && !instance.isMissingSparse(p1)) { m_weights[indS] += factor * instance.valueSparse(p1); } } // update the bias m_weights[m_weights.length - 1] += factor; } m_t++; } }
From source file:moa.classifiers.functions.SPegasos.java
License:Open Source License
/** * Trains the classifier with the given instance. * * @param instance the new training instance to include in the model *///from w w w.j av a 2 s .co m @Override public void trainOnInstanceImpl(Instance instance) { if (m_weights == null) { m_weights = new double[instance.numAttributes() + 1]; } if (!instance.classIsMissing()) { double learningRate = 1.0 / (m_lambda * m_t); //double scale = 1.0 - learningRate * m_lambda; double scale = 1.0 - 1.0 / m_t; double y = (instance.classValue() == 0) ? -1 : 1; double wx = dotProd(instance, m_weights, instance.classIndex()); double z = y * (wx + m_weights[m_weights.length - 1]); for (int j = 0; j < m_weights.length - 1; j++) { if (j != instance.classIndex()) { m_weights[j] *= scale; } } if (m_loss == LOGLOSS || (z < 1)) { double loss = dloss(z); int n1 = instance.numValues(); for (int p1 = 0; p1 < n1; p1++) { int indS = instance.index(p1); if (indS != instance.classIndex() && !instance.isMissingSparse(p1)) { double m = learningRate * loss * (instance.valueSparse(p1) * y); m_weights[indS] += m; } } // update the bias m_weights[m_weights.length - 1] += learningRate * loss * y; } double norm = 0; for (int k = 0; k < m_weights.length - 1; k++) { if (k != instance.classIndex()) { norm += (m_weights[k] * m_weights[k]); } } double scale2 = Math.min(1.0, (1.0 / (m_lambda * norm))); if (scale2 < 1.0) { scale2 = Math.sqrt(scale2); for (int j = 0; j < m_weights.length - 1; j++) { if (j != instance.classIndex()) { m_weights[j] *= scale2; } } } m_t++; } }
From source file:moa.classifiers.NaiveBayesMultinomial.java
License:Open Source License
/** * Trains the classifier with the given instance. * * @param instance the new training instance to include in the model *///from ww w .j a v a2s .c om @Override public void trainOnInstanceImpl(Instance inst) { if (this.reset == true) { this.m_numClasses = inst.numClasses(); double laplace = this.laplaceCorrectionOption.getValue(); int numAttributes = inst.numAttributes(); m_probOfClass = new double[m_numClasses]; Arrays.fill(m_probOfClass, laplace); m_classTotals = new double[m_numClasses]; Arrays.fill(m_classTotals, laplace * numAttributes); m_wordTotalForClass = new double[numAttributes][m_numClasses]; for (double[] wordTotal : m_wordTotalForClass) { Arrays.fill(wordTotal, laplace); } this.reset = false; } // Update classifier int classIndex = inst.classIndex(); int classValue = (int) inst.value(classIndex); double w = inst.weight(); m_probOfClass[classValue] += w; m_classTotals[classValue] += w * totalSize(inst); double total = m_classTotals[classValue]; for (int i = 0; i < inst.numValues(); i++) { int index = inst.index(i); if (index != classIndex && !inst.isMissing(i)) { m_wordTotalForClass[index][classValue] += w * inst.valueSparse(i); } } }
From source file:moa.classifiers.NaiveBayesMultinomial.java
License:Open Source License
/** * Calculates the class membership probabilities for the given test * instance.// www . j a v a 2 s .c o m * * @param instance the instance to be classified * @return predicted class probability distribution */ @Override public double[] getVotesForInstance(Instance instance) { if (this.reset == true) { return new double[2]; } double[] probOfClassGivenDoc = new double[m_numClasses]; double totalSize = totalSize(instance); for (int i = 0; i < m_numClasses; i++) { probOfClassGivenDoc[i] = Math.log(m_probOfClass[i]) - totalSize * Math.log(m_classTotals[i]); } for (int i = 0; i < instance.numValues(); i++) { int index = instance.index(i); if (index == instance.classIndex() || instance.isMissing(i)) { continue; } double wordCount = instance.valueSparse(i); for (int c = 0; c < m_numClasses; c++) { probOfClassGivenDoc[c] += wordCount * Math.log(m_wordTotalForClass[index][c]); } } return Utils.logs2probs(probOfClassGivenDoc); }
From source file:moa.clusterers.clustream.Clustream.java
License:Apache License
@Override public void trainOnInstanceImpl(Instance instance) { int dim = instance.numValues(); timestamp++;/*from w w w . j a va 2 s .co m*/ // 0. Initialize if (!initialized) { if (buffer.size() < bufferSize) { buffer.add(new ClustreamKernel(instance, dim, timestamp, t, m)); return; } int k = kernels.length; //System.err.println("k="+k+" bufferSize="+bufferSize); assert (k <= bufferSize); ClustreamKernel[] centers = new ClustreamKernel[k]; for (int i = 0; i < k; i++) { centers[i] = buffer.get(i); // TODO: make random! } Clustering kmeans_clustering = kMeans(k, centers, buffer); // Clustering kmeans_clustering = kMeans(k, buffer); for (int i = 0; i < kmeans_clustering.size(); i++) { kernels[i] = new ClustreamKernel(new DenseInstance(1.0, centers[i].getCenter()), dim, timestamp, t, m); } buffer.clear(); initialized = true; return; } // 1. Determine closest kernel ClustreamKernel closestKernel = null; double minDistance = Double.MAX_VALUE; for (int i = 0; i < kernels.length; i++) { //System.out.println(i+" "+kernels[i].getWeight()+" "+kernels[i].getDeviation()); double distance = distance(instance.toDoubleArray(), kernels[i].getCenter()); if (distance < minDistance) { closestKernel = kernels[i]; minDistance = distance; } } // 2. Check whether instance fits into closestKernel double radius = 0.0; if (closestKernel.getWeight() == 1) { // Special case: estimate radius by determining the distance to the // next closest cluster radius = Double.MAX_VALUE; double[] center = closestKernel.getCenter(); for (int i = 0; i < kernels.length; i++) { if (kernels[i] == closestKernel) { continue; } double distance = distance(kernels[i].getCenter(), center); radius = Math.min(distance, radius); } } else { radius = closestKernel.getRadius(); } if (minDistance < radius) { // Date fits, put into kernel and be happy closestKernel.insert(instance, timestamp); return; } // 3. Date does not fit, we need to free // some space to insert a new kernel long threshold = timestamp - timeWindow; // Kernels before this can be forgotten // 3.1 Try to forget old kernels for (int i = 0; i < kernels.length; i++) { if (kernels[i].getRelevanceStamp() < threshold) { kernels[i] = new ClustreamKernel(instance, dim, timestamp, t, m); return; } } // 3.2 Merge closest two kernels int closestA = 0; int closestB = 0; minDistance = Double.MAX_VALUE; for (int i = 0; i < kernels.length; i++) { double[] centerA = kernels[i].getCenter(); for (int j = i + 1; j < kernels.length; j++) { double dist = distance(centerA, kernels[j].getCenter()); if (dist < minDistance) { minDistance = dist; closestA = i; closestB = j; } } } assert (closestA != closestB); kernels[closestA].add(kernels[closestB]); kernels[closestB] = new ClustreamKernel(instance, dim, timestamp, t, m); }
From source file:moa.clusterers.clustream.ClustreamKernel.java
License:Apache License
public void insert(Instance instance, long timestamp) { N++;//from www . jav a 2s . com LST += timestamp; SST += timestamp * timestamp; for (int i = 0; i < instance.numValues(); i++) { LS[i] += instance.value(i); SS[i] += instance.value(i) * instance.value(i); } }
From source file:moa.clusterers.clustream.WithKmeans.java
License:Apache License
@Override public void trainOnInstanceImpl(Instance instance) { int dim = instance.numValues(); timestamp++;/*from w ww . ja va 2 s . c o m*/ // 0. Initialize if (!initialized) { if (buffer.size() < bufferSize) { buffer.add(new ClustreamKernel(instance, dim, timestamp, t, m)); return; } else { for (int i = 0; i < buffer.size(); i++) { kernels[i] = new ClustreamKernel(new DenseInstance(1.0, buffer.get(i).getCenter()), dim, timestamp, t, m); } buffer.clear(); initialized = true; return; } } // 1. Determine closest kernel ClustreamKernel closestKernel = null; double minDistance = Double.MAX_VALUE; for (int i = 0; i < kernels.length; i++) { //System.out.println(i+" "+kernels[i].getWeight()+" "+kernels[i].getDeviation()); double distance = distance(instance.toDoubleArray(), kernels[i].getCenter()); if (distance < minDistance) { closestKernel = kernels[i]; minDistance = distance; } } // 2. Check whether instance fits into closestKernel double radius = 0.0; if (closestKernel.getWeight() == 1) { // Special case: estimate radius by determining the distance to the // next closest cluster radius = Double.MAX_VALUE; double[] center = closestKernel.getCenter(); for (int i = 0; i < kernels.length; i++) { if (kernels[i] == closestKernel) { continue; } double distance = distance(kernels[i].getCenter(), center); radius = Math.min(distance, radius); } } else { radius = closestKernel.getRadius(); } if (minDistance < radius) { // Date fits, put into kernel and be happy closestKernel.insert(instance, timestamp); return; } // 3. Date does not fit, we need to free // some space to insert a new kernel long threshold = timestamp - timeWindow; // Kernels before this can be forgotten // 3.1 Try to forget old kernels for (int i = 0; i < kernels.length; i++) { if (kernels[i].getRelevanceStamp() < threshold) { kernels[i] = new ClustreamKernel(instance, dim, timestamp, t, m); return; } } // 3.2 Merge closest two kernels int closestA = 0; int closestB = 0; minDistance = Double.MAX_VALUE; for (int i = 0; i < kernels.length; i++) { double[] centerA = kernels[i].getCenter(); for (int j = i + 1; j < kernels.length; j++) { double dist = distance(centerA, kernels[j].getCenter()); if (dist < minDistance) { minDistance = dist; closestA = i; closestB = j; } } } assert (closestA != closestB); kernels[closestA].add(kernels[closestB]); kernels[closestB] = new ClustreamKernel(instance, dim, timestamp, t, m); }