UExpression Vector::create(Reader *r) {
r->pop_token();
auto without_square_close = without(closeTypes, TokenType::SquareClose);
std::list<UExpression> l;
read_until(r, TokenType::SquareClose, without_square_close, l);
return make_unique<Vector>(l);
}
UExpression Set::create(Reader *r) {
r->pop_token();
auto without_curly_close = without(closeTypes, TokenType::CurlyClose);
std::list<UExpression> l;
read_until(r, TokenType::CurlyClose, without_curly_close, l);
return make_unique<Set>(l);
}
UExpression List::create(Reader *r) {
r->pop_token();
auto without_round_close = without(closeTypes, TokenType::RoundClose);
std::list<UExpression> l;
read_until(r, TokenType::RoundClose, without_round_close, l);
return make_unique<List>(l);
}
static FILE * withAndWithout( std::string filename, std::string time_of_day_hint )
{
string with( filename+"_"+time_of_day_hint+BASE_EXTENSION );
FILE *fp = VSFileSystem::vs_open( with.c_str(), "r" );
if (!fp) {
string without( filename+BASE_EXTENSION );
fp = VSFileSystem::vs_open( without.c_str(), "r" );
}
return fp;
}
UExpression Map::create(Reader *r) {
r->pop_token();
auto without_curly_close = without(closeTypes, TokenType::CurlyClose);
std::list<UExpression> l;
read_until(r, TokenType::CurlyClose, without_curly_close, l);
if (l.size() % 2 == 1) {
throw ReaderException("Map entries should be even");
}
return make_unique<Map>(l);
}
/**
* Run the global analysis. Put all data and covariates in a logistic regression model.
*
* Compute likelihood ratio statistic.
* This uses a likelihood statistic where n-1 haplotypes are tested.
*
* @return pvalue.
*/
ZaykinGlobalStatsResults Zaykin::runGlobal(){
ZaykinGlobalStatsResults stats;
vector<vector<double> > haps;
vector<double> ones;
prepHaplotypes(ones, haps);
#if DEBUG_ZAY_PROGRESS
cout << "Zaykin start LR portion" << endl;
#endif
LogisticRegression with(params->getRegressionConditionNumberThreshold()), without(params->getRegressionConditionNumberThreshold());
/*
* Run without the haplotypes:
*/
vector<vector<double> > inv_infmatrixWithOut;
vector<double> betasWithOut;
vector<vector<double> > inWithout;
inWithout = cov;
inWithout.push_back(ones);
inv_infmatrixWithOut = vecops::getDblVec(inWithout.size() , inWithout.size());
int retry = 0;
double startVal = 0; // value to start betas with.
while(retry < 3){
try{
betasWithOut = without.newtonRaphson(inWithout, phenotype, inv_infmatrixWithOut, startVal);
break;
}catch(NewtonRaphsonFailureEx){
handleException(stats, startVal, retry, "Unable to compute reduced model: Newton-Raphson setup failure.");
}catch(NewtonRaphsonIterationEx){
handleException(stats, startVal, retry, "Unable to compute reduced model: max iterations hit.");
}catch(SingularMatrixEx){
handleException(stats, startVal, retry, "Unable to compute reduced model: information matrix was singular.");
}catch(ConditionNumberEx err){
LogisticRegression lr;
int separableVariable = lr.dataIsSeparable(inWithout, phenotype);
string message;
if (separableVariable < 0){
// Error: poor conditioning.
stringstream ss;
ss << "Unable to compute reduced model: Poor conditioning in information matrix. ";
ss << "Condition number (1-norm) is " << err.conditionNumber;
message = ss.str();
}else{
stringstream ss;
ss << "Unable to compute reduced model: Separable data matrix.";
ss << "Condition number (1-norm) is " << err.conditionNumber;
message = ss.str();
}
handleException(stats, startVal, retry, message);
if (retry >= 3) return stats;
}catch(ADTException e){
// This one is generic.
string message = "Unable to compute reduced model: Newton-Raphson error.";
handleException(stats, startVal, retry, message);
if (retry >= 3) return stats;
}catch(alglib::ap_error err){
stringstream ss;
ss << "Unable to compute reduced model due to linalg exception: " << err.msg;
handleException(stats, startVal, retry, ss.str());
if (retry >= 3) return stats;
}
}
/*
* Run with the haplotypes:
*/
vector<vector<double> > inv_infmatrixWith, inWith;
vector<double> betasWith;
inWith = inWithout;
for (unsigned int i=0; i < haps.size()-1; i++){ // NOTE: Don't push the very last haplotype.
inWith.push_back(haps.at(i));
}
inv_infmatrixWith = vecops::getDblVec(inWith.size() , inWith.size());
retry = 0;
startVal = 0; // value to start betas with.
while(retry < 3){
try{
betasWith = with.newtonRaphson(inWith, phenotype, inv_infmatrixWith, startVal);
break;
}catch(NewtonRaphsonFailureEx){
handleException(stats, startVal, retry, "Unable to compute full model: Newton-Raphson setup failure.");
}catch(NewtonRaphsonIterationEx){
handleException(stats, startVal, retry, "Unable to compute full model: max iterations hit.");
}catch(SingularMatrixEx){
handleException(stats, startVal, retry, "Unable to compute full model: information matrix was singular.");
}catch(ConditionNumberEx err){
LogisticRegression lr;
int separableVariable = lr.dataIsSeparable(inWith, phenotype);
stringstream ss;
if (separableVariable < 0){
// Error: poor conditioning.
ss << "Unable to compute reduced model: Poor conditioning in information matrix. ";
ss << "Condition number (1-norm) is " << err.conditionNumber;
}else{
ss << "Unable to compute reduced model: Separable data matrix.";
ss << "Condition number (1-norm) is " << err.conditionNumber;
}
string message = ss.str();
handleException(stats, startVal, retry, message);
if (retry >= 3) return stats;
}catch(ADTException e){
string message = "Unable to compute full model: Newton-Raphson error.";
handleException(stats, startVal, retry, message);
if (retry >= 3) return stats;
}catch(alglib::ap_error err){
stringstream ss;
ss << "Unable to compute full model due to linalg exception: " << err.msg;
handleException(stats, startVal, retry,ss.str());
if (retry >= 3) return stats;
}
}
double likeRatio = with.likelihoodRatio(betasWithOut, inWithout, betasWith, inWith, phenotype);
try{
stats.pvalue = Statistics::chi2prob(likeRatio, betasWith.size() - betasWithOut.size());
stats.testStat = likeRatio;
stats.degFreedom = betasWith.size() - betasWithOut.size();
}catch(...){
stringstream ss;
ss << "Zaykin's method: unable to compute chi square: " << likeRatio << " " << betasWith.size() - betasWithOut.size() << endl;
Logger::Instance()->writeLine(ss.str());
stats.fillDefault();
return stats;
}
return stats;
}
