ErrorStruct StrongClassifier::errorForFeatures(const TrainingData &features, bool printStats) const {
ErrorStruct e;
for (int i=0; i<features.size(); i++) {
FeatureVector feature = *(features.feature(i));
if (decide(feature)) {
feature.val() == POS ? e.true_pos++ : e.false_pos++;//it is really positive
} else {
feature.val() == NEG ? e.true_neg++ : e.false_neg++;//it is really negative
}
}
// if all 10 samples, 3 is misclassified, error is 3/10
e.error = (e.false_pos + e.false_neg) / ((float)features.size());
if (printStats) {
std::cout << e.true_pos << " true positives" << std::endl;
std::cout << e.false_pos << " false positives" << std::endl;
std::cout << e.true_neg << " true negatives" << std::endl;
std::cout << e.false_neg << " false negatives" << std::endl;
std::cout << e.error * 100 << "% error" << std::endl;
std::cout << std::endl;
}
return e;
}
/*************************************
* Function: update_feature_weight
* -------------------------------
* Given TrainingData and a WeakClassifier that has been weighted in
* get_best_classifier(), we recalculate the weights of all the features
*
* td: training data (set of features)
* wc: (weighted) weak classifier
*
* returns true if successful, false otherwise
*/
bool AdaBooster::update_feature_weight(TrainingData &td, WeakClassifier &wc){
// check that WeakClassifier has actually been weighted
if (wc.weight() < 0){
printf("Error in update_feature_weight: WeakClassifier has invalid weight\n");
return false;
}
// traverse features in feature set and adjust their weights
for (unsigned int i=0; i<num_features; i++){
FeatureVector* fv = td.feature(i);
// either 1 or -1 (used in weight below)
int is_correct = is_classifier_correct(wc, *fv) ? 1 : -1;
// calculate and update weight
// note M_E := 2.71828
float weight = pow(M_E, (double) -1 * wc.weight() * is_correct);
td.setWeight(i, td.weight(i)*weight);
}
// calculate normalization factor
float norm = 0;
for (unsigned int i=0; i<num_features; i++)
norm += td.weight(i);
// normalize feature weights
for (unsigned int i=0; i<num_features; i++)
td.setWeight(i, td.weight(i)/norm);
return true; // successful
}
/**************************************
* Function: create_feature_views
* ------------------------------
* For each dimension, we sort the feature vectors and store the result in
* *sorted*. Note that *sorted* is a little complicated -- we need the sorting to
* be fast so we sort feature vector pointers, and we have a vector of these
* for each dimension.
*
* td: training data -- set of features
*/
void AdaBooster::create_feature_views(TrainingData &td){
sorted = new vector<FeatureVector *>[dimensions];
// add a feature pointer to sorted for each dimension in the training data
for (unsigned int i=0; i<dimensions; i++){
for (unsigned int j=0; j<num_features; j++){
sorted[i].push_back(td.feature(j));
}
}
// sort each feature vector pointer in sorted
for (unsigned int i=0; i<dimensions; i++)
sort(sorted[i].begin(), sorted[i].end(), idx_cmp(i));
}