Skip to main content

EmpiricalCovariance

#include <Skigen/Covariance>

template <typename Scalar = double>
class Skigen::EmpiricalCovariance(assume_centered=false)

Maximum likelihood covariance estimator.

Computes the sample covariance matrix from data.

Mirrors sklearn.covariance.EmpiricalCovariance.



Attributes:

  • covariance : MatrixType Estimated covariance matrix (p × p).

  • location : RowVectorType Estimated location (mean) of the data (1 × p).


Methods​

fit(X)​

Fit the empirical covariance model.

Parameters:

  • X : MatrixType Data matrix of shape (n_samples, n_features).

Returns:

  • result : EmpiricalCovariance Reference to the fitted estimator (*this).

score(X)​

Return Gaussian log-likelihood of X under the fitted model.


Example​

Skigen::EmpiricalCovariance<double> emp;
emp.fit(X);

std::cout << "=== EmpiricalCovariance ===\n"
<< "Covariance (4x4):\n" << emp.covariance() << "\n\n"
<< "Location: " << emp.location() << "\n\n";