Observations
MultivariateModel
::SimulateData(io::DataSettings &DS)
{
/// This function simulates observations (Patients and their measurements y_ij at different time points t_ij)
/// according to the model, with a given noise level e_ij, such that y_ij = f(t_ij) + e_ij
/// Their is two option:
/// 1) The model is not initialized (neither random variables of number of realizations) and it has to be
/// This case corresponds to simulated data used to test the model, meaning if it can recover the random variables
/// used to simulate the data
/// 2) The model is already initialized, thus it should rely on its current state (random variables, realizations, ...)
/// This case corresponds to new data, for a dataset augmentation for instance
// TODO :
/// PITFALL : As for now, only the first option is implemented
/// PITFALL2 : Take a closer look at / merge with InitializeFakeRandomVariables
/// Initialize the model
m_ManifoldDimension = DS.GetCognitiveScoresDimension();
m_NumberOfSubjects = DS.GetNumberOfSimulatedSubjects();
m_RealizationsPerRandomVariable["G"] = 1;
for(size_t i = 1; i < m_ManifoldDimension; ++i)
m_RealizationsPerRandomVariable["Delta#" + std::to_string(i)] = 1;
for(size_t i = 0; i < m_NbIndependentSources*(m_ManifoldDimension - 1); ++i)
m_RealizationsPerRandomVariable["Beta#" + std::to_string(i)] = 1;
m_RealizationsPerRandomVariable["Ksi"] = m_NumberOfSubjects;
m_RealizationsPerRandomVariable["Tau"] = m_NumberOfSubjects;
for(int i = 0; i < m_NbIndependentSources; ++i)
m_RealizationsPerRandomVariable["S#" + std::to_string(i)] = m_NumberOfSubjects;
auto R = SimulateRealizations();
/// Update the model
m_G = exp(R.at("G", 0));
ComputeDeltas(R);
ComputeOrthonormalBasis();
ComputeAMatrix(R);
ComputeSpaceShifts(R);
ComputeBlock(R);
/// Simulate the data
std::random_device RD;
std::mt19937 RNG(RD());
std::uniform_int_distribution<int> Uni(DS.GetMinimumNumberOfObservations(), DS.GetMaximumNumberOfObservations());
UniformRandomVariable NumberOfTimePoints(60, 95);
GaussianRandomVariable Noise(0, m_Noise->GetVariance());
/// Simulate the data
Observations Obs;
for(int i = 0; i < m_NumberOfSubjects; ++i)
{
/// Get a random number of timepoints and sort them
VectorType T = NumberOfTimePoints.Samples(Uni(RNG));
T.sort();
m_SubjectTimePoints.push_back(T);
/// Simulate the data base on the time-points
IndividualObservations IO(T);
std::vector<VectorType> Landmarks;
for(size_t j = 0; j < T.size(); ++j)
{
Landmarks.push_back(ComputeParallelCurve(i, j) + Noise.Samples(m_ManifoldDimension));
}
IO.AddLandmarks(Landmarks);
Obs.AddIndividualData(IO);
}
/// Initialize the observation and model attributes
Obs.InitializeGlobalAttributes();
m_IndividualObservationDate = Obs.GetObservations();
m_SumObservations = Obs.GetTotalSumOfLandmarks();
m_NbTotalOfObservations = Obs.GetTotalNumberOfObservations();
return Obs;
}
Observations
ReadData
::ReadObservations(DataSettings &DS)
{
Observations Obs;
std::ifstream IndivID(DS.GetPathToGroup());
std::ifstream TimePointsFile(DS.GetPathToTimepoints());
std::ifstream LandmarksFile(DS.GetPathToLandmarks());
std::ifstream CognitiveScoresFile(DS.GetPathToCognitiveScores());
std::string GroupLine, TimePointsLine, LandmarksLine, CognitiveScoresLine;
unsigned int CurrentSubjectID = -1;
VectorType TimePoints;
std::vector<VectorType> Landmarks;
std::vector<VectorType> CognitiveScores;
while(getline(IndivID, GroupLine))
{
if(CurrentSubjectID == -1) CurrentSubjectID = std::stoi(GroupLine);
unsigned int NewSubjectID = std::stoi(GroupLine);
getline(TimePointsFile, TimePointsLine);
if(DS.LandmarkPresence()) getline(LandmarksFile, LandmarksLine);
if(DS.CognitiveScoresPresence()) getline(CognitiveScoresFile, CognitiveScoresLine);
/// New subject
if(NewSubjectID != CurrentSubjectID)
{
IndividualObservations Individual(TimePoints);
if(DS.LandmarkPresence()) Individual.AddLandmarks(Landmarks);
if(DS.CognitiveScoresPresence()) Individual.AddCognitiveScores(CognitiveScores);
Obs.AddIndividualData(Individual);
CurrentSubjectID = NewSubjectID;
TimePoints.clear();
Landmarks.clear();
CognitiveScores.clear();
}
TimePoints.push_back(stod(TimePointsLine));
if(DS.LandmarkPresence())
{
VectorType NewObs(DS.GetLandmarksDimension());
int i = 0;
std::stringstream LineStream(LandmarksLine);
std::string cell;
while(std::getline(LineStream, cell, ','))
{
NewObs(i) = std::stod(cell);
++i;
}
Landmarks.push_back(NewObs);
}
if(DS.CognitiveScoresPresence())
{
VectorType NewObs(DS.GetCognitiveScoresDimension());
int i = 0;
std::stringstream LineStream(CognitiveScoresLine);
std::string cell;
while(std::getline(LineStream, cell, ','))
{
NewObs(i) = std::stod(cell);
++i;
}
CognitiveScores.push_back(NewObs);
}
}
IndividualObservations Individual(TimePoints);
if(DS.LandmarkPresence()) Individual.AddLandmarks(Landmarks);
if(DS.CognitiveScoresPresence()) Individual.AddCognitiveScores(CognitiveScores);
Obs.AddIndividualData(Individual);
return Obs;
}
