Statistical::Statistical(InputSet& inputSet) : Filter(inputSet) {
// Get the number of samples and features
const unsigned int nbSamples = inputSet.nbSamples();
const unsigned int nbFeatures = inputSet.nbFeatures();
// Used to store the current sum and sum of squares of every feature
means_.resize(nbFeatures);
stds_.resize(nbFeatures);
for(unsigned int s = 0; s < nbSamples; ++s) {
std::vector<unsigned int> sample(1, s);
inputSet.pushSamples(sample);
const scalar_t* features = inputSet.features(0);
for(unsigned int f = 0; f < nbFeatures; ++f) {
means_[f] += features[f];
stds_[f] += features[f] * features[f];
}
inputSet.popSamples();
}
std::vector<unsigned int> featureStack;
for(unsigned int f = 0; f < nbFeatures; ++f) {
scalar_t mean = means_[f] / nbSamples;
scalar_t variance = (stds_[f] - means_[f] * mean) / (nbSamples - 1);
if(variance > 0) {
means_[f] = mean;
stds_[f] = std::sqrt(variance);
featureStack.push_back(f);
}
}
// There must be at least one feature
assert(!featureStack.empty());
// Push the selected features if needed
if(featureStack.size() < nbFeatures) {
featureStack_.push_back(featureStack);
}
}
void LinearSVM::distribution(InputSet& inputSet,
unsigned int sample,
scalar_t* distr) const {
// Push the selected features if required
if(!indices_.empty()) {
inputSet.pushFeatures(indices_);
}
// Get the number of features and labels
const unsigned int nbFeatures = inputSet.nbFeatures();
const unsigned int nbLabels = inputSet.nbLabels();
// Make sure that we have a model
assert(model_);
// Make sure that there is the same number of labels
assert(static_cast<unsigned int>(get_nr_class(model_)) <= nbLabels);
// Create a node
feature_node node;
node.dim = nbFeatures;
node.values = const_cast<scalar_t*>(inputSet.features(sample));
// The predicted labels
std::vector<double> predictions(nbLabels);
predict_values(model_, &node, &predictions[0]);
// Update the ditribution according to the predictions
for(unsigned int l = 0; l < nbLabels; ++l) {
distr[map_[l]] = predictions[l];
}
// Pop the selected features if required
if(!indices_.empty()) {
inputSet.popFeatures();
}
}
void C45Tree::distribution(InputSet& inputSet,
unsigned int sample,
scalar_t* distr) const {
// Get the features of the sample to classifiy
const scalar_t* features = inputSet.features(sample);
// The currently selected tree
const C45Tree* current = this;
// If the tree has children, find which one is selected
while(current->children_[0]) {
assert(current->feature_ < inputSet.nbFeatures());
if(features[current->feature_] <= current->split_) {
current = current->children_[0];
}
else {
current = current->children_[1];
}
}
// Recopy the distribution
assert(current->distr_.size() == inputSet.nbLabels());
std::copy(current->distr_.begin(), current->distr_.end(), distr);
}
