spe.estimators.cp_smoother#
- spe.estimators.cp_smoother(model, X, y, tr_idx, Chol_y=None, Chol_ystar=None, Cov_y_ystar=None)#
Computes Generalized Mallows’s Cp for any linear model and dependent train and test set.
- Parameters:
- model: object
- Xarray-like of shape (n_samples, n_features)
- yarray-like of shape (n_samples,)
- tr_idxbool array-like of shape (n_samples,)
Boolean index of which samples to train the model on.
- Chol_yarray-like of shape (n_samples, n_samples), optional
Cholesky of covariance matrix of \(\Sigma_Y\). Default is
Nonein which caseChol_yis set tonp.eye(n).- Chol_ystararray-like of shape (n_samples, n_samples), optional
Cholesky of covariance matrix of \(\Sigma_{Y^*}\). Default is
Nonein which caseChol_ystaris set tonp.eye(n).- Cov_y_ystararray-like of shape (n_samples, n_samples), optional
Covariance matrix of \(\Sigma_{Y,Y^*}\). Default is
Nonein which case it is assumed \(\Sigma_{Y,Y^*} = 0\).
- Returns:
- err_estfloat
Cp type estimate of MSE.