Machine learning for NeuroImaging in Python
Released April 2024
Use the appropriate HTML templates for nilearn.maskers.MultiNiftiMapsMasker and nilearn.maskers.MultiNiftiLabelsMasker reports that would lead to empty reports for MultiNiftiMapsMasker (#4310 by Rémi Gau).
Fix color bar handling with color map with only 1 level (#4255 by Rémi Gau).
Improve colorbar size and labels in mosaic display (#4284 by Rémi Gau).
Remove unused **kwargs from nilearn.plotting.view_img and nilearn.plotting.plot_surf (#4270 by Rémi Gau).
Fix plotting of carpet plot due to a change in the coming version of matplolib (3.9.0) (#4279 by Rémi Gau).
Fix errant warning when using stat_type in nilearn.glm.compute_contrast (#4257 by Eric Larson).
Fix when thresholding is applied to images by GLM reports (#4258 by Rémi Gau).
Use the appropriate HTML templates for nilearn.maskers.MultiNiftiMapsMasker and nilearn.maskers.MultiNiftiLabelsMasker reports that would lead to empty reports for MultiNiftiMapsMasker (#4310 by Rémi Gau).
Make masker report tables horizontally scrollable (#4308 by Rémi Gau).-
Masker reports tables do not overlap with report image (#4308 by Rémi Gau).
Fix color bar handling with color map with only 1 level (#4255 by Rémi Gau).
Ensure that region_names_ can be generated by nilearn.maskers.NiftiSpheresMasker.transform_single_imgs for deterministic atlases that use floats or non-consecutive values as region_ids whether they include background in their labels or not (#4274 by Rémi Gau).
Ensure that nilearn.interfaces.bids.save_glm_to_bids serializes numpy arrays to list used as GLM parameters before saving them to JSON (#4325 by Rémi Gau).
Check that the view parameter in surface plotting functions is a pair of int or float when it is not a string (#4297 by Rémi Gau).
Fix positions of the markers on the images on the sphere masker reports (#4285 by Rémi Gau).
Fix cut position in nifti maps maskers to match displayed map maximum (#4304 by Rémi Gau).
Make sure that nilearn.maskers.NiftiSpheresMasker reports displays properly when it contains only 1 sphere (#4269 by Rémi Gau).
Miscellaneous fixes in GLM reports (only display FIR delay if FIR is used, display color bar “Z score” legend…) (#4266 by Rémi Gau).
Fix minor typos in documentation (glossary and connectivity/parcellating) (#4343 by Florent Pollet).
Update minor information on the Code of Conduct page (#4318 and #4320 by Himanshu Aggarwal).
Add an avg_method parameter to nilearn.plotting.plot_surf_stat_map (#4298 by Rémi Gau).
Advertise nilearn’s in built globbing capability in an example (#4334 by Himanshu Aggarwal).
Throw warnings when passing parameters to surface plotting functions that are not used by the plotly engine (#4298 by Rémi Gau).
Improve colorbar size and labels in mosaic display (#4284 by Rémi Gau).
Change the colormap to gray for the background image in the nilearn.maskers.NiftiSpheresMasker (#4269 by Rémi Gau).
Remove unused **kwargs from nilearn.plotting.view_img and nilearn.plotting.plot_surf (#4270 by Rémi Gau).
Use red to blue color map in the GLM reports (#4266 by Rémi Gau).
nilearn.maskers.NiftiSpheresMasker will throw warnings if the labels passed to it is not a list of str, or if the number of items in the list of labels does not match the number of regions in the label image (#4274 by Rémi Gau).
Copy headers from user-specified image to the result of nilearn.image.math_img (#4337 by Himanshu Aggarwal).
Render the description of the templates, atlases and datasets of the nilearn.datasets as part of the documentation (#4232 by Rémi Gau).
Render examples of GLM and masker reports as part of the documentation (#4267 and #4295 by Rémi Gau).
HTML, CSS are now linted using prettier. (#4302, by Rémi Gau).
contrast_type by stat_type by @larsoner in https://github.com/nilearn/nilearn/pull/4257
two_sided parameter of binarize_img function by @NicolasGensollen in https://github.com/nilearn/nilearn/pull/4262
int or float when not a string by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4297
avg_method to plot_surf_stat_map by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4298
resampling_target = None for nifti label maskers by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4336
glm.first_level.first_level_from_bids by @michellewang in https://github.com/nilearn/nilearn/pull/4352
doc/visual_testing/reporter_visual_inspection_suite.py for older Matplotlib versions by @michellewang in https://github.com/nilearn/nilearn/pull/4353
math_img by @man-shu in https://github.com/nilearn/nilearn/pull/4337
Full Changelog: https://github.com/nilearn/nilearn/compare/0.10.3...0.10.4
Released January 2024
[!WARNING]
Support for python 3.7 has been dropped. We recommend moving to python >= 3.11.
Minimum supported versions of packages have been bumped up:
- Numpy – v1.19.0
- SciPy – v1.8.0
- Scikit-learn – v1.0.0
- Nibabel – v4.0.0
- Pandas – v1.1.5
- Joblib – v1.0.0
API Allow passing arguments to first_level_from_bids to build first level models that include specific set of confounds by relying on the strategies from load_confounds (#4103 by Rémi Gau).
Support passing t and F contrasts to compute_contrast that that have fewer columns than the number of estimated parameters. Remaining columns are padded with zero (#4067 by Rémi Gau).
NiftiSpheresMasker now has generate_report method (#3102 by Yasmin Mzayek and Nicolas Gensollen).
Update the CompCor strategy in load_confounds and load_confounds_strategy to support fmriprep 21.x series and above. (#3285 by Hao-Ting Wang).
Allow setting vmin in plot_glass_brain and plot_stat_map (#3993 by Michelle Wang).
When plotting thresholded statistical maps with a colorbar, the threshold value(s) will now be displayed as tick labels on the colorbar (##2833 by Nicolas Gensollen).
Combine GLM examples plot_fixed_effect and plot_fiac_analysis into a a single example plot_two_runs_model (#3191 by Taylor Salo and Rémi Gau).
MultiNiftiMasker can now call generate_report which will generate a report for the first subject in the list of subjects (#4001 by Yasmin Mzayek).
Make sure that all atlases and datasets fetchers return a description (#4215 Rémi Gau).
Update the CompCor strategy in load_confounds and load_confounds_strategy to support fmriprep 21.x series and above. (#3285 by Hao-Ting Wang).
Fix SimpleRegressionResults to accommodate for the lack of a model attribute (#4071 Rémi Gau)
clean_img can now use kwargs clean__sample_mask argument to correctly reshape the nifti image to the dimensions of the mask in the output (#4051 by Mia Zwally).
Fix plotting of an image with color bar when maximum value is exactly zero (#4204 by Rémi Gau).
Code Fix PSC normalisation method applied by standardize_signal in signal (#4116 by Hao-Ting Wang and Yasmin Mzayek).
Fixed inheritance of decoder classes to keep compatibility with scikit-learn>v1.3 (#4188 by Yasmin Mzayek).
Make sure that all the fetchers for atlas and func from nilearn.datasets return a sklearn.utils.Bunch. Add new behavior to fetch_language_localizer_demo_dataset to return output as Bunch. This behavior will become the default in version 0.13.0 (#4233 by Rémi Gau).
NiftiSpheresMasker now has generate_report method (#3102 by Yasmin Mzayek and Nicolas Gensollen).
Allow passing Pandas Series of image filenames to SecondLevelModel (#4070 by Rémi Gau).
Allow passing arguments to first_level_from_bids to build first level models that include specific set of confounds by relying on the strategies from load_confounds (#4103 by Rémi Gau).
Support passing t and F contrasts to compute_contrast that that have fewer columns than the number of estimated parameters. Remaining columns are padded with zero (#4067 by Rémi Gau).
Multi-subject maskers’ generate_report method no longer fails with 5D data but instead shows report of first subject. User can index input list to show report for different subjects (#3935 by Yasmin Mzayek).
Allow global_signal parameter in load_confounds_strategy in denoise_strategy='compcor' (#4225 by Hao-Ting Wang).
Add two_sided option for binarize_img (#4121 by Steven Meisler).
generate_report now uses appropriate cut coordinates when functional image is provided (#4099 by Yasmin Mzayek and Nicolas Gensollen).
Mention the classification type (all-vs-one) in Decoding of a dataset after GLM fit for signal extraction (#4122 by Tamer Gezici).
Add backslash to homogenize Parcellations documentation (#4042 by Nikhil Krish).
Specify full form of LSS in Beta-Series Modeling for Task-Based Functional Connectivity and Decoding (#4141 by Tamer Gezici).
Don’t fetch tmaps in examples if tmaps aren’t used in the example. (#4136 by Christina Roßmanith).
Describe the return value in fetch_abide_pcp documentation (#4159 by Suramya Pokharel).
Allow setting vmin in plot_glass_brain and plot_stat_map (#3993 by Michelle Wang).
When plotting thresholded statistical maps with a colorbar, the threshold value(s) will now be displayed as tick labels on the colorbar (##2833 by Nicolas Gensollen).
Expose scipy CubicSpline extrapolate parameter in clean to control the interpolation of censored volumes in both ends of the BOLD signal data (#4028 by Jordi Huguet).
Make nilearn.reporting._get_clusters_table module public and move copy_img out of nilearn._utils.niimg (#4166 by Rémi Gau).
Private utility context manager write_tmp_imgs is refactored into function write_imgs_to_path (#4094 by Yasmin Mzayek).
Move user facing function concat_niimgs out of private module nilearn._utils.niimg_conversions (#4167 by Rémi Gau).
Remove leading underscore from non private functions to align with PEP8 (#4086 by Rémi Gau).
Make decoding/proximal_operator explicitly private to align with PEP8 (#4153 by Rémi Gau).
Make private functions public when used outside of their module nilearn.interface to align with PEP8 (#4168 by Rémi Gau).
img_to_signals_labels will also return masked_atlas in release 0.15. Meanwhile, use return_masked_atlas parameter to enable/disable this behavior. (#3761 by Mohammad Torabi).
cation Rename the parameter contrast_type in compute_contrast and attribute contrast_type in Contrast to stat_type (#4191 by Rémi Gau).
plot_surf_roi will raise a warning if roi_map contains negative or non-integer values; in version 0.13 this will be a ValueError (#4131 by Michelle Wang).
nilearn.datasets.fetch_bids_langloc_dataset will be deprecated in release 0.13 as it returns data simuilar to fetch_language_localizer_demo_dataset (#4219 by Rémi Gau).
the default parameter of fd_threshold and std_dvars_threshold in load_confounds with be updated to match fmriprep default in version 0.13 (#4225 by Hao-Ting Wang).
Combine GLM examples plot_fixed_effect and plot_fiac_analysis into a a single example plot_two_runs_model (#3191 by Taylor Salo and Rémi Gau).
Switch to using tox to manage environments during development and testing. All plotting python dependencies (matplotlib AND plotly) are now installed when running pip install nilearn[plotting] (#4029 by Rémi Gau).
MultiNiftiMasker to use generate_report method by @ymzayek in https://github.com/nilearn/nilearn/pull/4001
vmin in plot_glass_brain and plot_stat_map by @michellewang in https://github.com/nilearn/nilearn/pull/3993
http:// to https:// by @DimitriPapadopoulos in https://github.com/nilearn/nilearn/pull/4050
np.random.RandomState() - part 1 by @ymzayek in https://github.com/nilearn/nilearn/pull/4052
0.1.0.post1 for windows by @ymzayek in https://github.com/nilearn/nilearn/pull/4101
write_tmp_imgs function and use it with pytest's tmp_path by @ymzayek in https://github.com/nilearn/nilearn/pull/4094
find_parcellation_cut_coords function by @ymzayek in https://github.com/nilearn/nilearn/pull/4107
img_plotting by @ymzayek in https://github.com/nilearn/nilearn/pull/4115
NiftiLabelsMasker's transform output by @mtorabi59 in https://github.com/nilearn/nilearn/pull/3761
NiftiSpheresMasker reports by @NicolasGensollen in https://github.com/nilearn/nilearn/pull/3102
plot_surf_roi by @michellewang in https://github.com/nilearn/nilearn/pull/4131
nilearn.datasets._utils.fetch_file to nilearn.datasets._utils.fetch_single_file by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4156
__all__ and API doc more consistent by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4157
plot_surf by @ymzayek in https://github.com/nilearn/nilearn/pull/4164
nilearn._utils.data_gen by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4171
second_level_contrast of non_parametric_inference by @ymzayek in https://github.com/nilearn/nilearn/pull/4150
contrast_type to stat_type by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4191
nilearn.plotting used outside of their module public by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4197
test_clean_psc by @paul-reiners in https://github.com/nilearn/nilearn/pull/4208
session by run to align with BIDS terminology by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4214
Full Changelog: https://github.com/nilearn/nilearn/compare/0.10.2...0.10.3
Released September 2023
plotting.plot_img now have an optional radiological parameter, defaulting to False. If True, this will invert the x-axis and L and R annotations to confirm to radiological conventional view..LogisticRegressionCV.LassoCV as a new estimator option for Decoder objectsvmin and symmetric_cbar arguments to nilearn.plotting.plot_img_on_surf.contrasts allowing fixed effects on F contrastsplotting.plot_img now have an optional radiological parameter, defaulting to False. If True, this will invert the x-axis and L and R annotations to confirm to radiological conventional view..transform_imgs of maskers.MultiNiftiMapsMasker and maskers.MultiNiftiLabelsMasker that would raise an error if a list of sample_mask was specified to fit_transform.nilearn.plotting.surf_plotting._plot_surf_matplotlib that would make vertices transparent when saving in PDF or SVG format.symmetric_cmap=True or the avg_method argument with plotting.plot_surf_roi.glm.first_level.first_level_from_bids that returned no confound files if the corresponding bold files contained derivatives BIDS entities.glm.first_level.first_level_from_bids that would throw a warning about slice_time_ref not being provided even when it was.cv_params_ attribute of fitter Decoder objects sometimes had missing entries if grid_param is a sequence of dicts with different keys.nilearn.interfaces.fmriprep.load_confounds confounds file selection more generic.nilearn.interfaces.fmriprep.load_confounds confounds selection on cosine as not all confound files contained the variables.pathlib.Path not being counted as Niimg-like object in image.new_img_like.fit_transform behavior to match when fit method is passed image dataplotting.plot_surf_contours so that ROI contours are rendered clearlydatasets.fetch_atlas_craddock_2012, datasets.fetch_atlas_smith_2009 and datasets.fetch_atlas_basc_multiscale_2015 fetchers including using API consistent maps keyLogisticRegressionCV.glm.first_level.first_level_from_bids when using event.tsv files with no trial type column.datasets.fetch_atlas_surf_destrieux.LassoCV as a new estimator option for Decoder objectsvmin and symmetric_cbar arguments to nilearn.plotting.plot_img_on_surf.generate_report method of maskers by allowing users to pass a cmap argument for plotting imagecontrasts allowing fixed effects on F contrastsnilearn.glm.first_level.experimental_paradigm.check_events will now throw a warning if some events have a 0 second duration and will throw an error if an event has NaN onset or duration.mask_img in maskers.NiftiLabelsMasker will no longer be kept in release 0.15. Meanwhile, use keep_masked_labels parameter when initializing the maskers.NiftiLabelsMasker object to enable/disable this behavior..mask_img in maskers.NiftiMapsMasker will no longer be kept in release 0.15. Meanwhile, use keep_masked_maps parameter when initializing the maskers.NiftiMapsMasker object to enable/disable this behavior..darkness in surf_plotting._compute_facecolors_matplotlib and html_surface._get_vertexcolor
~nilearn.plotting.html_surface._mix_colormaps to cm.py in nilearn.plotting
~nilearn.glm.regression
standardize in plotting.plot_carpet and connectome.ConnectivityMeasure to handle "zscore" deprecation.sphx_glr_auto_examples_01_plotting_plot_prob_atlas.py is shortened to speed up build timeDecoder.cv_params_ when param_grid is a list of dicts with different keys by @michellewang in https://github.com/nilearn/nilearn/pull/3733
cobre, nyu) by @michellewang in https://github.com/nilearn/nilearn/pull/3743
_sanitize_reorder to match regex in test by @Remi-Gau in https://github.com/nilearn/nilearn/pull/3751
InvalidParameterError message by @ymzayek in https://github.com/nilearn/nilearn/pull/3763
surf_plotting function by @mathdugre in https://github.com/nilearn/nilearn/pull/3860
load_confounds. by @htwangtw in https://github.com/nilearn/nilearn/pull/3863
LassoCV to nilearn.decoding.DecoderRegressor by @michellewang in https://github.com/nilearn/nilearn/pull/3781
plot_matrix function by @ymzayek in https://github.com/nilearn/nilearn/pull/3899
vmin argument to plotting.plot_img_on_surf by @michellewang in https://github.com/nilearn/nilearn/pull/3873
plot_glass_brain by @ymzayek in https://github.com/nilearn/nilearn/pull/3924
standardize parameter in function signatures to allow handling of deprecation by @ymzayek in https://github.com/nilearn/nilearn/pull/3927
colorscale by @ymzayek in https://github.com/nilearn/nilearn/pull/3945
sample_mask in MultiNiftiMapsMasker.fit_transform by @acionca in https://github.com/nilearn/nilearn/pull/3971
event_type instead of trial_type by @Remi-Gau in https://github.com/nilearn/nilearn/pull/3986
maps key for API consistency and improve deprecation for new behavior of some atlas fetchers by @ymzayek in https://github.com/nilearn/nilearn/pull/3987
alltrue deprecation by @ymzayek in https://github.com/nilearn/nilearn/pull/3996
compute_fixed_effects by @bthirion in https://github.com/nilearn/nilearn/pull/3203
dev in sphinx directives related to version by @Remi-Gau in https://github.com/nilearn/nilearn/pull/4013
Full Changelog: https://github.com/nilearn/nilearn/compare/0.10.1...0.10.2