- sklearn.covariance.shrunk_covariance(emp_cov, shrinkage=0.1)¶
Calculates a covariance matrix shrunk on the diagonal
Read more in the User Guide.
- emp_covarray-like of shape (n_features, n_features)
Covariance matrix to be shrunk
- shrinkagefloat, default=0.1
Coefficient in the convex combination used for the computation of the shrunk estimate. Range is [0, 1].
- shrunk_covndarray of shape (n_features, n_features)
The regularized (shrunk) covariance is given by:
(1 - shrinkage) * cov + shrinkage * mu * np.identity(n_features)
where mu = trace(cov) / n_features