Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the user guide for the big picture.

nilearn.datasets.fetch_atlas_craddock_2012#

nilearn.datasets.fetch_atlas_craddock_2012(data_dir=None, url=None, resume=True, verbose=1, homogeneity=None, grp_mean=True)[source]#

Download and return file names for the Craddock 2012 parcellation.

This function returns a probabilistic atlas. The provided images are in MNI152 space. All images are 4D with shapes equal to (47, 56, 46, 43).

See [1] for the licence.

See [2] and [3] for more information on this parcellation.

Parameters:
data_dirpathlib.Path or str, optional

Path where data should be downloaded. By default, files are downloaded in home directory.

urlstr, default=None

URL of file to download. Override download URL. Used for test only (or if you setup a mirror of the data).

resumebool, default=True

Whether to resume download of a partly-downloaded file.

verboseint, default=1

Verbosity level (0 means no message).

homogeneity: :obj:`str`, optional

The choice of the homogeneity (‘spatial’ or ‘temporal’ or ‘random’)

grp_mean: :obj:`bool`, optional

The choice of the parcellation (with group_mean or without) Default=True.

Returns:
datasklearn.utils.Bunch

Dictionary-like object, keys are:

  • ‘scorr_mean’: obj:str, path to nifti file containing the group-mean parcellation when emphasizing spatial homogeneity.

  • ‘tcorr_mean’: obj:str, path to nifti file containing the group-mean parcellation when emphasizing temporal homogeneity.

  • ‘scorr_2level’: obj:str, path to nifti file containing the parcellation obtained when emphasizing spatial homogeneity.

  • ‘tcorr_2level’: obj:str, path to nifti file containing the parcellation obtained when emphasizing temporal homogeneity.

  • ‘random’: obj:str, path to nifti file containing the parcellation obtained with random clustering.

  • ‘description’: str, general description of the dataset.

Warns:
DeprecationWarning

If an homogeneity input is provided, the current behavior (returning multiple maps) is deprecated. Starting in version 0.13, one map will be returned in a ‘maps’ dict key depending on the homogeneity and grp_mean value.

References