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_haxby¶

nilearn.datasets.fetch_haxby(data_dir=None, n_subjects=(2,), fetch_stimuli=False, url=None, resume=True, verbose=1)[source]¶

Download and loads complete the Haxby dataset.

See Haxby et al.[1].

Changed in Nilearn 0.15.0: The subjects parameter was renamed to n_subjects.

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.
n_subjectsint, list or tuple of int, or None: Number of subjects to load, or their one-based indices. If None is given, all available subjects are loaded. An empty list or tuple is not allowed. By default, 2nd subject will be loaded.
fetch_stimulibool, default=False: Indicate if stimuli images must be downloaded. They will be presented as a dictionary of categories.
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).

Returns:

datasklearn.utils.Bunch

Dictionary-like object, contains:

‘anat’: list of str.
Paths to anatomic images.
‘func’: list of str.
Paths to nifti file with BOLD data.
‘session_target’: list of str.
Paths to text file containing run and target data.
‘mask’: str. Path to fullbrain mask file.
‘mask_vt’: list of str.
Paths to nifti ventral temporal mask file.
‘mask_face’: list of str.
Paths to nifti with face-responsive brain regions.
‘mask_face_little’: list of str.
Paths to nifti with face-responsive brain regions. Spatially more constrained version of mask_face.
‘mask_house’: list of str.
Paths to nifti with house-responsive brain regions.
‘mask_house_little’: list of str.
Paths to nifti with house-responsive brain regions. Spatially more constrained version of mask_house.
‘t_r’: float
Repetition time of the functional data.

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.

PyMVPA provides a tutorial making use of this dataset: http://www.pymvpa.org/tutorial.html

More information about its structure: http://dev.pymvpa.org/datadb/haxby2001.html

See additional information <https://www.science.org/doi/10.1126/science.1063736>

Run 8 in subject 5 does not contain any task labels. The anatomical image for subject 6 is unavailable.

References

Examples using `nilearn.datasets.fetch_haxby`¶

An introduction tutorial to fMRI decoding

Basic nilearn example: manipulating and looking at data

More plotting tools from nilearn

NeuroImaging volumes visualization

Plot Haxby masks

Plotting tools in nilearn

Comparing classifiers in decoding

Cortical surface-based searchlight decoding

Decoding of a dataset after GLM fit for signal extraction

Decoding with ANOVA + SVM

Decoding with fast ensembling of regularized models

Effect of standardization on decoding performance

Multi-class strategies

ROI-based decoding analysis

Searchlight analysis

Show stimuli of Haxby dataset

Tuning a parameter with cross-validation

Understanding Decoder

Computing a Region of Interest (ROI) mask manually

Advanced decoding using scikit-learn

Massively univariate analysis of a visual task

SearchLight with a custom correlation estimator

fetch_haxby¶

Examples using nilearn.datasets.fetch_haxby¶

Examples using `nilearn.datasets.fetch_haxby`¶