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.

fetch_atlas_craddock_2012

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

Download and return file names for the Craddock 2012 parcellation.

For more information, see the dataset description.

Parameters:
data_dirpathlib.Path or str or None, optional

Path where data should be downloaded. By default, files are downloaded in a nilearn_data folder in the home directory of the user. See also nilearn.datasets.utils.get_data_dirs.

urlstr or None, 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.

verbosebool or int, default=1

Verbosity level (0 or False means no message).

homogeneitystr, default=’spatial’

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

grp_meanbool, default=True

The choice of the parcellation (with group_mean or without)

Returns:
datasklearn.utils.Bunch

Dictionary-like object, contains:

  • atlas_type: str. Type of atlas. See Probabilistic atlas and Deterministic atlas.

  • random: str. Full path to 4D nifti file (with shape (47, 56, 46, 43)) containing the parcellation obtained with random clustering (for comparison).

  • scorr_2level: str. Full path to 4D nifti file (with shape (47, 56, 46, 43)) containing the parcellation results when emphasizing spatial homogeneity

  • scorr_mean: str. Full path to 4D nifti file (with shape (47, 56, 46, 43)) containing the group-mean parcellation results when emphasizing spatial homogeneity

  • tcorr_2level: str. Full path to 4D nifti file (with shape (47, 56, 46, 43)) containing the parcellation results when emphasizing temporal homogeneity

  • tcorr_mean: str. Full path to 4D nifti file (with shape (47, 56, 46, 43)) containing the group-mean parcellation results when emphasizing temporal homogeneity

  • template: str. The standardized space of analysis in which the data is provided.

Notes

If the dataset files are already present in the user’s Nilearn data directory, this fetcher will not re-download them. To force a fresh download, you can remove the existing dataset folder from your local Nilearn data directory.

For more details on how Nilearn stores datasets.