/**
* Train one of the crossvalidation bins
* @param set identification number of the bin that is processed
* @param updateDOC boolean deciding to calculate retention features
* @see DescriptionOfCorrect
* @param cposCandidates candidate soft margin parameters for positives
* @param cfracCandidates candidate soft margin parameters for fraction neg/pos
* @param bestCpos best soft margin parameter for positives
* @param bestCfrac best soft margin parameter for fraction neg/pos
* @param pWeights results vector from the SVM algorithm
* @param pOptions options for the SVM algorithm
*/
int CrossValidation::processSingleFold(unsigned int set, bool updateDOC,
const vector<double>& cposCandidates, const vector<double>& cfracCandidates,
double &bestCpos, double &bestCfrac, vector_double* pWeights,
options * pOptions) {
int bestTruePos = 0;
if (VERB > 2) {
cerr << "cross validation - fold " << set + 1 << " out of "
<< numFolds_ << endl;
}
vector<double> ww = w_[set]; // SVM weights initial guess and result holder
vector<double> bestW = w_[set]; // SVM weights with highest true pos estimate
trainScores_[set].calcScores(ww, selectionFdr_);
if (DataSet::getCalcDoc() && updateDOC) {
trainScores_[set].recalculateDescriptionOfCorrect(selectionFdr_);
}
AlgIn* svmInput = svmInputs_[set % numAlgInObjects_];
trainScores_[set].generateNegativeTrainingSet(*svmInput, 1.0);
trainScores_[set].generatePositiveTrainingSet(*svmInput, selectionFdr_, 1.0);
if (VERB > 2) {
cerr << "Calling with " << svmInput->positives << " positives and "
<< svmInput->negatives << " negatives\n";
}
// Create storage vector for SVM algorithm
struct vector_double* Outputs = new vector_double;
size_t numInputs = svmInput->positives + svmInput->negatives;
Outputs->vec = new double[numInputs];
Outputs->d = numInputs;
// Find soft margin parameters with highest estimate of true positives
std::vector<double>::const_iterator itCpos = cposCandidates.begin();
for ( ; itCpos != cposCandidates.end(); ++itCpos) {
double cpos = *itCpos;
std::vector<double>::const_iterator itCfrac = cfracCandidates.begin();
for ( ; itCfrac != cfracCandidates.end(); ++itCfrac) {
double cfrac = *itCfrac;
if (VERB > 2) cerr << "-cross validation with cpos=" << cpos
<< ", cfrac=" << cfrac << endl;
int tp = 0;
for (int ix = 0; ix < pWeights->d; ix++) {
pWeights->vec[ix] = 0;
}
for (int ix = 0; ix < Outputs->d; ix++) {
Outputs->vec[ix] = 0;
}
svmInput->setCost(cpos, cpos * cfrac);
// Call SVM algorithm (see ssl.cpp)
L2_SVM_MFN(*svmInput, pOptions, pWeights, Outputs);
for (int i = FeatureNames::getNumFeatures() + 1; i--;) {
ww[i] = pWeights->vec[i];
}
// sub-optimal cross validation (better would be to measure
// performance on a set disjoint of the training set)
tp = trainScores_[set].calcScores(ww, testFdr_);
if (VERB > 2) {
cerr << "- cross validation estimates " << tp
<< " target PSMs over " << testFdr_ * 100 << "% FDR level"
<< endl;
}
if (tp >= bestTruePos) {
if (VERB > 2) {
cerr << "Better than previous result, store this" << endl;
}
bestTruePos = tp;
bestW = ww;
bestCpos = cpos;
bestCfrac = cfrac;
}
}
if (VERB > 2) {
std::cerr << "cross validation estimates " <<
bestTruePos / (numFolds_-1) << " target PSMs with q<" << testFdr_ <<
" for hyperparameters Cpos=" << bestCpos <<
", Cneg=" << bestCfrac * bestCpos << std::endl;
}
}
w_[set] = bestW;
delete[] Outputs->vec;
delete Outputs;
return bestTruePos;
}
/**
* Train one of the crossvalidation bins
* @param set identification number of the bin that is processed
* @param w list of normal vectors (in the linear algebra sense) of the hyperplane from SVM, one for each bin
* @param updateDOC boolean deciding to calculate retention features @see DescriptionOfCorrect
* @param cpos_vec vector with soft margin parameter for positives
* @param cfrac_vec vector with soft margin parameter for fraction negatives / positives
* @param best_cpos best soft margin parameter for positives
* @param best_cfrac best soft margin parameter for fraction negatives / positives
* @param pWeights results vector from the SVM algorithm
* @param pOptions options for the SVM algorithm
*/
int CrossValidation::xv_process_one_bin(unsigned int set, bool updateDOC, vector<double>& cpos_vec,
vector<double>& cfrac_vec, double &best_cpos, double &best_cfrac, vector_double* pWeights,
options * pOptions) {
int bestTP = 0;
if (VERB > 2) {
cerr << "cross validation - fold " << set + 1 << " out of "
<< xval_fold << endl;
}
vector<double> ww = w[set]; // normal vector initial guess and result holder
vector<double> bestW = w[set]; // normal vector with highest true positive estimate
xv_train[set].calcScores(ww, selectionFdr);
if (DataSet::getCalcDoc() && updateDOC) {
xv_train[set].recalculateDescriptionOfCorrect(selectionFdr);
}
xv_train[set].generateNegativeTrainingSet(*svmInput, 1.0);
xv_train[set].generatePositiveTrainingSet(*svmInput, selectionFdr, 1.0);
if (VERB > 2) {
cerr << "Calling with " << svmInput->positives << " positives and "
<< svmInput->negatives << " negatives\n";
}
// Create storage vector for SVM algorithm
struct vector_double* Outputs = new vector_double;
Outputs->vec = new double[svmInput->positives + svmInput->negatives];
Outputs->d = svmInput->positives + svmInput->negatives;
// Find combination of soft margin parameters with highest estimate of true positives
BOOST_FOREACH (const double cpos, cpos_vec) {
BOOST_FOREACH (const double cfrac, cfrac_vec) {
if (VERB > 2) cerr << "-cross validation with cpos=" << cpos
<< ", cfrac=" << cfrac << endl;
int tp = 0;
for (int ix = 0; ix < pWeights->d; ix++) {
pWeights->vec[ix] = 0;
}
for (int ix = 0; ix < Outputs->d; ix++) {
Outputs->vec[ix] = 0;
}
svmInput->setCost(cpos, (cpos) * (cfrac));
// Call SVM algorithm (see ssl.cpp)
L2_SVM_MFN(*svmInput, pOptions, pWeights, Outputs);
for (int i = FeatureNames::getNumFeatures() + 1; i--;) {
ww[i] = pWeights->vec[i];
}
// sub-optimal cross validation (better would be to measure
// performance on a set disjoint of the training set)
tp = xv_train[set].calcScores(ww, testFdr);
if (VERB > 2) {
cerr << "- cross validation estimates " << tp
<< " target PSMs over " << testFdr * 100 << "% FDR level"
<< endl;
}
if (tp >= bestTP) {
if (VERB > 2) {
cerr << "Better than previous result, store this" << endl;
}
bestTP = tp;
bestW = ww;
best_cpos = cpos;
best_cfrac = cfrac;
}
}
if (VERB > 2) cerr << "cross validation estimates " << bestTP
/ (xval_fold - 1) << " target PSMs with q<" << testFdr
<< " for hyperparameters Cpos=" << best_cpos << ", Cneg="
<< best_cfrac * best_cpos << endl;
}
