Note
This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the user guide for the big picture.
nilearn.connectome.GroupSparseCovariance#
- class nilearn.connectome.GroupSparseCovariance(alpha=0.1, tol=0.001, max_iter=10, verbose=0, memory=Memory(location=None), memory_level=0)[source]#
Covariance and precision matrix estimator.
The model used has been introduced in 1, and the algorithm used is based on what is described in 2.
- Parameters
- alphafloat, optional
regularization parameter. With normalized covariances matrices and number of samples, sensible values lie in the [0, 1] range(zero is no regularization: output is not sparse). Default=0.1.
- tolpositive float, optional
The tolerance to declare convergence: if the dual gap goes below this value, iterations are stopped. Default=1e-3.
- max_iterint, optional
maximum number of iterations. The default value is rather conservative. Default=10.
- verboseint, optional
verbosity level. Zero means “no message”. Default=0.
- memoryinstance of joblib.Memory or string, optional
Used to cache the masking process. By default, no caching is done. If a string is given, it is the path to the caching directory.
- memory_levelint, optional
Caching aggressiveness. Higher values mean more caching. Default=0.
References
- 1
Gael Varoquaux, Alexandre Gramfort, Jean Baptiste Poline, and Bertrand Thirion. Brain covariance selection: better individual functional connectivity models using population prior. arXiv:1008.5071 [q-bio, stat], 11 2010. URL: https://arxiv.org/abs/1008.5071, arXiv:1008.5071.
- 2
Jean Honorio, Tommi Jaakkola, and Dimitris Samaras. On the statistical efficiency of l1,p multi-task learning of gaussian graphical models. arXiv:1207.4255 [cs, stat], 10 2015. URL: https://arxiv.org/abs/1207.4255, arXiv:1207.4255.
- Attributes
- `covariances_`numpy.ndarray, shape (n_features, n_features, n_subjects)
empirical covariance matrices.
- `precisions_`numpy.ndarraye, shape (n_features, n_features, n_subjects)
precisions matrices estimated using the group-sparse algorithm.
- __init__(alpha=0.1, tol=0.001, max_iter=10, verbose=0, memory=Memory(location=None), memory_level=0)[source]#
- fit(subjects, y=None)[source]#
Fits the group sparse precision model according to the given training data and parameters.
- Parameters
- subjectslist of numpy.ndarray with shapes (n_samples, n_features)
input subjects. Each subject is a 2D array, whose columns contain signals. Sample number can vary from subject to subject, but all subjects must have the same number of features (i.e. of columns).
- Returns
- selfGroupSparseCovariance instance
the object itself. Useful for chaining operations.
- get_params(deep=True)#
Get parameters for this estimator.
- Parameters
- deepbool, default=True
If True, will return the parameters for this estimator and contained subobjects that are estimators.
- Returns
- paramsdict
Parameter names mapped to their values.
- set_params(**params)#
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as
Pipeline). The latter have parameters of the form<component>__<parameter>so that it’s possible to update each component of a nested object.- Parameters
- **paramsdict
Estimator parameters.
- Returns
- selfestimator instance
Estimator instance.