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.
7.1.1. nilearn.connectome.ConnectivityMeasure¶

class
nilearn.connectome.
ConnectivityMeasure
(cov_estimator=LedoitWolf(assume_centered=False, block_size=1000, store_precision=False), kind=’covariance’, vectorize=False, discard_diagonal=False)¶ A class that computes different kinds of functional connectivity matrices.
New in version 0.2.
Parameters: cov_estimator : estimator object, optional.
The covariance estimator. By default the LedoitWolf estimator is used. This implies that correlations are slightly shrunk towards zero compared to a maximumlikelihood estimate
kind : {“correlation”, “partial correlation”, “tangent”, “covariance”, “precision”}, optional
The matrix kind.
vectorize : bool, optional
If True, connectivity matrices are reshaped into 1D arrays and only their flattened lower triangular parts are returned.
discard_diagonal : bool, optional
If True, vectorized connectivity coefficients do not include the matrices diagonal elements. Used only when vectorize is set to True.
References
For the use of “tangent”, see the paper: G. Varoquaux et al. “Detection of brain functionalconnectivity difference in poststroke patients using grouplevel covariance modeling, MICCAI 2010.
Attributes
cov_estimator_ (estimator object) A new covariance estimator with the same parameters as cov_estimator. mean_ (numpy.ndarray) The mean connectivity matrix across subjects. For ‘tangent’ kind, individual connectivity patterns from both correlation and partial correlation matrices are used to estimate a robust group covariance matrix, called the geometric mean. whitening_ (numpy.ndarray) The inverted squarerooted geometric mean of the covariance matrices. 
__init__
(cov_estimator=LedoitWolf(assume_centered=False, block_size=1000, store_precision=False), kind=’covariance’, vectorize=False, discard_diagonal=False)¶

fit
(X, y=None)¶ Fit the covariance estimator to the given time series for each subject.
Parameters: X : list of numpy.ndarray, shape for each (n_samples, n_features)
The input subjects time series. The number of samples may differ from one subject to another.
Returns: self : ConnectivityMatrix instance
The object itself. Useful for chaining operations.

fit_transform
(X, y=None, **fit_params)¶ Fit to data, then transform it.
Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.
Parameters: X : numpy array of shape [n_samples, n_features]
Training set.
y : numpy array of shape [n_samples]
Target values.
Returns: X_new : numpy array of shape [n_samples, n_features_new]
Transformed array.

get_params
(deep=True)¶ Get parameters for this estimator.
Parameters: deep : boolean, optional
If True, will return the parameters for this estimator and contained subobjects that are estimators.
Returns: params : mapping of string to any
Parameter names mapped to their values.

inverse_transform
(connectivities, diagonal=None)¶ Returns connectivity matrices from connectivities, vectorized or not.
If kind is ‘tangent’, the covariance matrices are reconstructed.
Parameters: connectivities : list of n_subjects numpy.ndarray with shapes (n_features, n_features) or (n_features * (n_features + 1) / 2,)
or ((n_features  1) * n_features / 2,) Connectivities of each subject, vectorized or not.
diagonal : numpy.ndarray, shape (n_subjects, n_features), optional
The diagonals of the connectivity matrices.
Returns: output : numpy.ndarray, shape (n_subjects, n_features, n_features)
The corresponding connectivity matrices. If kind is ‘correlation’/ ‘partial correlation’, the correlation/partial correlation matrices are returned. If kind is ‘tangent’, the covariance matrices are reconstructed.

set_params
(**params)¶ Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form
<component>__<parameter>
so that it’s possible to update each component of a nested object.Returns: self

transform
(X)¶ Apply transform to covariances matrices to get the connectivity matrices for the chosen kind.
Parameters: X : list of n_subjects numpy.ndarray with shapes (n_samples, n_features)
The input subjects time series. The number of samples may differ from one subject to another.
Returns: output : numpy.ndarray, shape (n_subjects, n_features, n_features) or (n_subjects, n_features * (n_features + 1) / 2) if vectorize is set to True.
The transformed individual connectivities, as matrices or vectors.
