int KinshipHolder::loadDecomposed() {
LineReader lr(this->eigenFileName);
int lineNo = 0;
int fieldLen = 0;
std::vector<std::string> fd;
std::vector<int> columnToExtract;
std::vector<std::string> header; // header line of the kinship eigen file
Eigen::MatrixXf& matK = this->matK->mat;
Eigen::MatrixXf& matS = this->matS->mat;
Eigen::MatrixXf& matU = this->matU->mat;
const std::vector<std::string>& names = *this->pSample;
const int NumSample = (int)names.size();
std::map<std::string, int> nameMap;
makeMap(names, &nameMap);
std::map<std::string, int> headerMap;
while (lr.readLineBySep(&fd, "\t ")) {
++lineNo;
if (lineNo == 1) { // check header
header = fd;
fieldLen = fd.size();
if (fieldLen < 3) { // at least three columns: IID, Lambda, U1
logger->error(
"Insufficient column number (<3) in the first line of kinsihp "
"file!");
return -1;
};
for (size_t i = 0; i != fd.size(); ++i) {
fd[i] = tolower(fd[i]);
}
makeMap(fd, &headerMap);
if (fd.size() != headerMap.size()) {
logger->error("Kinship file have duplicated headers!");
return -1;
}
// check IID, Lambda, U1, U2, ... U(N) where (N) is the sample size
if (headerMap.count("iid") == 0) {
logger->error("Missing 'IID' column!");
return -1;
}
columnToExtract.push_back(headerMap["iid"]);
if (headerMap.count("lambda") == 0) {
logger->error("Missing 'Lambda' column!");
return -1;
}
columnToExtract.push_back(headerMap["lambda"]);
std::string s;
for (int i = 0; i < NumSample; ++i) {
s = "u";
s += toString(i + 1);
if (headerMap.count(s) == 0) {
logger->error("Missing '%s' column!", s.c_str());
return -1;
}
columnToExtract.push_back(headerMap[s]);
}
s = "u";
s += toString(NumSample + 1);
if (headerMap.count(s) != 0) {
logger->error("Unexpected column '%s'!", s.c_str());
return -1;
}
matS.resize(NumSample, 1);
matU.resize(NumSample, NumSample);
continue;
}
// body lines
if ((int)fd.size() != fieldLen) {
logger->error(
"Inconsistent column number [ %zu ] (used to be [ %d ])in kinship "
"file line [ %d ] - skip this file!",
fd.size(), fieldLen, lineNo);
return -1;
}
const int iidColumn = columnToExtract[0];
const std::string& iid = fd[iidColumn];
if (nameMap.count(iid) == 0) {
logger->error("Unexpected sample [ %s ]!", iid.c_str());
return -1;
}
const int row = nameMap[iid];
const int lambdaColumn = columnToExtract[1];
double temp = 0.0;
if (!str2double(fd[lambdaColumn], &temp)) {
logger->warn("Invalid numeric value [ %s ] treated as zero!",
fd[lambdaColumn].c_str());
}
matS(lineNo - 2, 0) = temp;
for (int i = 0; i < NumSample; ++i) {
int uColumn = columnToExtract[i + 2];
if (!str2double(fd[uColumn], &temp)) {
logger->warn("Invalid numeric value [ %s ] treated as zero!",
fd[lambdaColumn].c_str());
}
matU(row, i) = temp;
}
}
// verify eigen decomposition results make senses
// check largest eigen vector and eigen value
Eigen::MatrixXf v1 = matK * matU.col(0);
Eigen::MatrixXf v2 = matS(0, 0) * matU.col(0);
if (matS(0, 0) > 0.5 && v1.col(0).norm() > .5 && v2.col(0).norm() > 0.5 &&
corr(v1, v2) < 0.8) {
logger->warn("Cannot verify spectral decompose results!");
return -1;
}
// check the min(10, NumSample) random eigen vector and eigen value
int randomCol = 10;
if (randomCol > NumSample - 1) {
randomCol = NumSample - 1;
}
v1 = matK * matU.col(randomCol);
v2 = matS(randomCol, 0) * matU.col(randomCol);
if (matS(randomCol, 0) > 0.5 && v1.col(0).norm() > 0.5 &&
v2.col(0).norm() > 0.5 && corr(v1, v2) < 0.8) {
logger->warn("Cannot verify spectral decompose results!");
return -1;
}
#ifdef DEBUG
std::string tmp = fn;
tmp += ".tmp";
std::ofstream ofs(tmp.c_str(), std::ofstream::out);
ofs << mat;
ofs.close();
#endif
// fprintf(stderr, "Kinship matrix [ %d x %d ] loaded", (int)mat.rows(),
// (int)mat.cols());
if (this->matK) {
delete this->matK;
this->matK = NULL;
}
return 0;
}
GcmZTildeInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>::GcmZTildeInfo(
const GpmsaComputerModelOptions& gcmOptionsObj,
const GcmJointInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>& jj,
const GcmZInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>& z)
:
m_env (jj.m_env),
m_Cmat_tilde (m_env,jj.m_omega_space.map(),z.m_Cmat_rank),
m_z_tilde_space (m_env, "z_tilde_", z.m_Cmat_rank, NULL),
m_Lmat (m_env,m_z_tilde_space.map(),z.m_Cmat->numCols()),
m_Lmat_t (m_env,z.m_z_space.map(),z.m_Cmat_rank),
m_Zvec_tilde_hat (m_z_tilde_space.zeroVector()),
m_tmp_Smat_z_tilde (m_z_tilde_space.zeroVector()),
m_tmp_Smat_extra_tilde (m_z_tilde_space.zeroVector()),
m_tmp_Smat_z_tilde_hat (m_z_tilde_space.zeroVector()),
m_tmp_Smat_z_tilde_hat_inv(m_z_tilde_space.zeroVector())
{
if (m_env.subDisplayFile()) {
*m_env.subDisplayFile() << "Entering GcmZTildeInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>::constructor(1)"
<< std::endl;
}
std::set<unsigned int> tmpSet;
tmpSet.insert(m_env.subId());
// Naive formation of 'm_Cmat_tilde'
D_M matU(z.m_Cmat->svdMatU());
unsigned int uMatRank = matU.rank(0.,1.e-8 ); // todo: should be an option
unsigned int uMatRank14 = matU.rank(0.,1.e-14);
if (m_env.subDisplayFile()) {
*m_env.subDisplayFile() << "In GcmZTildeInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>::constructor(1)"
<< ": matU.numRowsLocal() = " << matU.numRowsLocal()
<< ", matU.numCols() = " << matU.numCols()
<< ", matU.rank(0.,1.e-8) = " << uMatRank
<< ", matU.rank(0.,1.e-14) = " << uMatRank14
<< std::endl;
}
if (m_env.checkingLevel() >= 1) {
D_M matUcheck(z.m_z_space.zeroVector());
D_V vecI(jj.m_omega_space.zeroVector());
D_V vecJ(jj.m_omega_space.zeroVector());
for (unsigned int i = 0; i < matU.numCols(); ++i) {
matU.getColumn(i,vecI);
for (unsigned int j = i; j < matU.numCols(); ++j) {
matU.getColumn(j,vecJ);
matUcheck(i,j) = scalarProduct(vecI,vecJ);
}
}
matUcheck.setPrintHorizontally(false);
if (m_env.subDisplayFile()) {
*m_env.subDisplayFile() << "In GcmZTildeInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>::constructor(1)"
<< ": m_Cmat_rank = " << z.m_Cmat_rank
<< ", matUcheck.numRowsLocal() = " << matUcheck.numRowsLocal()
<< ", matUcheck.numCols() = " << matUcheck.numCols()
<< ", matUcheck =\n" << matUcheck
<< std::endl;
}
}
D_V vecJ(jj.m_omega_space.zeroVector());
for (unsigned int j = 0; j < z.m_Cmat_rank; ++j) {
matU.getColumn(j,vecJ);
m_Cmat_tilde.setColumn(j,vecJ);
}
if (gcmOptionsObj.m_ov.m_dataOutputAllowedSet.find(m_env.subId()) != gcmOptionsObj.m_ov.m_dataOutputAllowedSet.end()) {
m_Cmat_tilde.subWriteContents("Ctilde",
"Ctilde2",
"m",
tmpSet);
}
if (m_env.subDisplayFile()) {
*m_env.subDisplayFile() << "In GcmZTildeInfo<S_V,S_M,D_V,D_M,P_V,P_M,Q_V,Q_M>::constructor(1)"
<< ": m_Cmat_tilde formed (2)"
<< std::endl;
}
// Naive formation of 'm_Lmat'
m_Cmat_tilde.svdSolve(*(z.m_Cmat),m_Lmat);
commonConstructor(z);
}