arma::mat readMDS(const std::string& file_name, const std::vector<Sample>& sample_names)
{
arma::mat MDS = readHDF5(file_name);
// Check that the sample names match up
std::string sample_name_file = file_name + sample_suffix;
if (fileStat(sample_name_file))
{
std::ifstream samples_in(sample_name_file.c_str());
if (samples_in)
{
arma::uvec keep_indices(sample_names.size());
unsigned int sample_row = 0;
unsigned int file_row = 0;
while (samples_in)
{
std::string sample_name;
samples_in >> sample_name;
// Must be ordered, and lines in sample_names be a subset of what
// is in the file. Otherwise a non-compatible mds will be returned
// which will throw
if (sample_name == sample_names.at(sample_row).iid())
{
keep_indices(sample_row) = file_row;
if (++sample_row >= sample_names.size())
{
break;
}
}
++file_row;
}
// Only keep the rows where the pheno file has data
if (sample_row == sample_names.size())
{
MDS = MDS.rows(keep_indices);
}
else
{
throw std::runtime_error("Could not find all samples in input .pheno file in --struct mat. Was kmds run with all samples included?");
}
}
else
{
std::cerr << "WARNING: Could not open sample file " + sample_name_file + ". Ensure kmds and seer -p inputs were identical" << std::endl;
}
}
void cData2d::readHDF5(char* filename){
char fieldname[100];
strcpy(fieldname, "/data/data");
readHDF5(filename, fieldname);
}
