void VJCascadeClassifier::savePosteriors(const string& dataFileName, const string& shypFileName,
const string& outFileName, int numIterations)
{
// loading data
InputData* pData = loadInputData(dataFileName, shypFileName);
const int numOfExamples = pData->getNumExamples();
//get the index of positive label
const NameMap& namemap = pData->getClassMap();
_positiveLabelIndex = namemap.getIdxFromName( _positiveLabelName );
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// open outfile
ofstream outRes(outFileName.c_str());
if (!outRes.is_open())
{
cout << "Cannot open outfile!!! " << outFileName << endl;
}
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<vector<BaseLearner*> > weakHypotheses;
// For stagewise thresholds
vector<AlphaReal> thresholds(0);
// loads them
//us.loadHypotheses(shypFileName, weakHypotheses, pData);
us.loadCascadeHypotheses(shypFileName, weakHypotheses, thresholds, pData);
// output the number of stages
outRes << "StageNum " << weakHypotheses.size() << endl;
// output original labels
outRes << "Labels";
for(int i=0; i<numOfExamples; ++i )
{
vector<Label>& labels = pData->getLabels(i);
if (labels[_positiveLabelIndex].y>0) // pos label
outRes << " 1";
else
outRes << " 0";
}
outRes << endl;
// store result
vector<CascadeOutputInformation> cascadeData(0);
vector<CascadeOutputInformation>::iterator it;
cascadeData.resize(numOfExamples);
for( it=cascadeData.begin(); it != cascadeData.end(); ++it )
{
it->active=true;
}
for(int stagei=0; stagei < weakHypotheses.size(); ++stagei )
{
// for posteriors
vector<AlphaReal> posteriors(0);
// calculate the posteriors after stage
VJCascadeLearner::calculatePosteriors( pData, weakHypotheses[stagei], posteriors, _positiveLabelIndex );
// update the data (posteriors, active element index etc.)
//VJCascadeLearner::forecastOverAllCascade( pData, posteriors, activeInstances, thresholds[stagei] );
updateCascadeData(pData, weakHypotheses, stagei, posteriors, thresholds, _positiveLabelIndex, cascadeData);
int numberOfActiveInstance = 0;
for( int i = 0; i < numOfExamples; ++i )
if (cascadeData[i].active) numberOfActiveInstance++;
if (_verbose > 0 )
cout << "Number of active instances: " << numberOfActiveInstance << "(" << numOfExamples << ")" << endl;
// output stats
outRes << "Stage " << stagei << " " << weakHypotheses[stagei].size() << endl;
outRes << "Forecast";
for(int i=0; i<numOfExamples; ++i )
{
outRes << " " << cascadeData[i].forecast;
}
outRes << endl;
outRes << "Active";
for(int i=0; i<numOfExamples; ++i )
{
if( cascadeData[i].active)
outRes << " 1";
else
outRes << " 0";
}
outRes << endl;
outRes << "Posteriors";
for(int i=0; i<numOfExamples; ++i )
{
outRes << " " << cascadeData[i].score;
}
outRes << endl;
}
outRes.close();
// free memory allocation
vector<vector<BaseLearner*> >::iterator bvIt;
for( bvIt = weakHypotheses.begin(); bvIt != weakHypotheses.end(); ++bvIt )
{
vector<BaseLearner* >::iterator bIt;
for( bIt = (*bvIt).begin(); bIt != (*bvIt).end(); ++bIt )
delete *bIt;
}
}
void VJCascadeClassifier::run(const string& dataFileName, const string& shypFileName,
int numIterations, const string& outResFileName )
{
// loading data
InputData* pData = loadInputData(dataFileName, shypFileName);
const int numOfExamples = pData->getNumExamples();
//get the index of positive label
const NameMap& namemap = pData->getClassMap();
_positiveLabelIndex = namemap.getIdxFromName( _positiveLabelName );
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<vector<BaseLearner*> > weakHypotheses;
// For stagewise thresholds
vector<AlphaReal> thresholds(0);
// loads them
//us.loadHypotheses(shypFileName, weakHypotheses, pData);
us.loadCascadeHypotheses(shypFileName, weakHypotheses, thresholds, pData);
// store result
vector<CascadeOutputInformation> cascadeData(0);
vector<CascadeOutputInformation>::iterator it;
cascadeData.resize(numOfExamples);
for( it=cascadeData.begin(); it != cascadeData.end(); ++it )
{
it->active=true;
}
if (!_outputInfoFile.empty())
{
outputHeader();
}
for(int stagei=0; stagei < weakHypotheses.size(); ++stagei )
{
// for posteriors
vector<AlphaReal> posteriors(0);
// calculate the posteriors after stage
VJCascadeLearner::calculatePosteriors( pData, weakHypotheses[stagei], posteriors, _positiveLabelIndex );
// update the data (posteriors, active element index etc.)
updateCascadeData(pData, weakHypotheses, stagei, posteriors, thresholds, _positiveLabelIndex, cascadeData);
if (!_outputInfoFile.empty())
{
_output << stagei + 1 << "\t";
_output << weakHypotheses[stagei].size() << "\t";
outputCascadeResult( pData, cascadeData );
}
int numberOfActiveInstance = 0;
for( int i = 0; i < numOfExamples; ++i )
if (cascadeData[i].active) numberOfActiveInstance++;
if (_verbose > 0 )
cout << "Number of active instances: " << numberOfActiveInstance << "(" << numOfExamples << ")" << endl;
}
vector<vector<int> > confMatrix(2);
confMatrix[0].resize(2);
fill( confMatrix[0].begin(), confMatrix[0].end(), 0 );
confMatrix[1].resize(2);
fill( confMatrix[1].begin(), confMatrix[1].end(), 0 );
// print accuracy
for(int i=0; i<numOfExamples; ++i )
{
vector<Label>& labels = pData->getLabels(i);
if (labels[_positiveLabelIndex].y>0) // pos label
if (cascadeData[i].forecast==1)
confMatrix[1][1]++;
else
confMatrix[1][0]++;
else // negative label
if (cascadeData[i].forecast==0)
confMatrix[0][0]++;
else
confMatrix[0][1]++;
}
double acc = 100.0 * (confMatrix[0][0] + confMatrix[1][1]) / ((double) numOfExamples);
// output it
cout << endl;
cout << "Error Summary" << endl;
cout << "=============" << endl;
cout << "Accuracy: " << setprecision(4) << acc << endl;
cout << setw(10) << "\t" << setw(10) << namemap.getNameFromIdx(1-_positiveLabelIndex) << setw(10) << namemap.getNameFromIdx(_positiveLabelIndex) << endl;
cout << setw(10) << namemap.getNameFromIdx(1-_positiveLabelIndex) << setw(10) << confMatrix[0][0] << setw(10) << confMatrix[0][1] << endl;
cout << setw(10) << namemap.getNameFromIdx(_positiveLabelIndex) << setw(10) << confMatrix[1][0] << setw(10) << confMatrix[1][1] << endl;
// output forecast
if (!outResFileName.empty() ) outputForecast(pData, outResFileName, cascadeData );
// free memory allocation
vector<vector<BaseLearner*> >::iterator bvIt;
for( bvIt = weakHypotheses.begin(); bvIt != weakHypotheses.end(); ++bvIt )
{
vector<BaseLearner* >::iterator bIt;
for( bIt = (*bvIt).begin(); bIt != (*bvIt).end(); ++bIt )
delete *bIt;
}
}
string KmerTree::getTaxonomy(Sequence* thisSeq, string& simpleTax, bool& flipped){
try {
simpleTax = "";
string seqName = thisSeq->getName(); string querySequence = thisSeq->getAligned(); string taxonProbabilityString = "";
string unalignedSeq = thisSeq->getUnaligned();
double logPOutlier = (querySequence.length() - kmerSize + 1) * log(1.0/(double)tree[0]->getNumUniqueKmers());
vector<int> queryProfile = ripKmerProfile(unalignedSeq); //convert to kmer vector
vector<vector<double> > pXgivenKj_D_j(numLevels);
vector<vector<int> > indices(numLevels);
for(int i=0;i<numLevels;i++){
if (m->getControl_pressed()) { return taxonProbabilityString; }
pXgivenKj_D_j[i].push_back(logPOutlier);
indices[i].push_back(-1);
}
for(int i=0;i<numTaxa;i++){
if (m->getControl_pressed()) { return taxonProbabilityString; }
pXgivenKj_D_j[tree[i]->getLevel()].push_back(tree[i]->getPxGivenkj_D_j(queryProfile));
indices[tree[i]->getLevel()].push_back(i);
}
vector<double> sumLikelihood(numLevels, 0);
vector<double> bestPosterior(numLevels, 0);
vector<int> maxIndex(numLevels, 0);
int maxPosteriorIndex;
//let's find the best level and taxa within that level
for(int i=0;i<numLevels;i++){ //go across all j's - from the root to genus
if (m->getControl_pressed()) { return taxonProbabilityString; }
int numTaxaInLevel = (int)indices[i].size();
vector<double> posteriors(numTaxaInLevel, 0);
sumLikelihood[i] = getLogExpSum(pXgivenKj_D_j[i], maxPosteriorIndex);
maxPosteriorIndex = 0;
for(int j=0;j<numTaxaInLevel;j++){
posteriors[j] = exp(pXgivenKj_D_j[i][j] - sumLikelihood[i]);
if(posteriors[j] > posteriors[maxPosteriorIndex]){
maxPosteriorIndex = j;
}
}
maxIndex[i] = getMinRiskIndexKmer(queryProfile, indices[i], posteriors);
maxIndex[i] = maxPosteriorIndex;
bestPosterior[i] = posteriors[maxIndex[i]];
}
int saneDepth = sanityCheck(indices, maxIndex);
simpleTax = "";
int savedspot = 1;
taxonProbabilityString = "";
for(int i=1;i<=saneDepth;i++){
if (m->getControl_pressed()) { return taxonProbabilityString; }
int confidenceScore = (int) (bestPosterior[i] * 100);
if (confidenceScore >= confidenceThreshold) {
if(indices[i][maxIndex[i]] != -1){
taxonProbabilityString += tree[indices[i][maxIndex[i]]]->getName() + "(" + toString(confidenceScore) + ");";
simpleTax += tree[indices[i][maxIndex[i]]]->getName() + ";";
}
else{
taxonProbabilityString += "unclassified(" + toString(confidenceScore) + ");";
simpleTax += "unclassified;";
}
}else { break; }
savedspot = i;
}
for(int i=savedspot+1;i<numLevels;i++){
if (m->getControl_pressed()) { return taxonProbabilityString; }
taxonProbabilityString += "unclassified(0);";
simpleTax += "unclassified;";
}
return taxonProbabilityString;
}
catch(exception& e) {
m->errorOut(e, "KmerTree", "getTaxonomy");
exit(1);
}
}