[MRG] Iter age group prediction example #2063

jeromedockes · 2019-05-17T18:59:56Z

warn about small sample size
simplify cross-val code with gridsearch
include tangent space fitting in the cross-validated pipeline
show cross-val score standard deviation on the bar plot

codecov · 2019-05-18T09:16:49Z

Codecov Report

Merging #2063 into master will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##           master    #2063   +/-   ##
=======================================
  Coverage   94.98%   94.98%           
=======================================
  Files         141      141           
  Lines       18298    18298           
=======================================
  Hits        17380    17380           
  Misses        918      918

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 2dde3f9...bf66048. Read the comment docs.

codecov · 2019-05-18T09:16:49Z

Codecov Report

Merging #2063 into master will increase coverage by 0.16%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #2063      +/-   ##
==========================================
+ Coverage   92.21%   92.38%   +0.16%     
==========================================
  Files         149      149              
  Lines       18752    18761       +9     
  Branches     2277     2279       +2     
==========================================
+ Hits        17293    17333      +40     
+ Misses        944      917      -27     
+ Partials      515      511       -4

Impacted Files	Coverage Δ
nilearn/tests/test_signal.py	`99.23% <0%> (-0.77%)`	⬇️
nilearn/plotting/tests/test_surf_plotting.py	`100% <0%> (ø)`	⬆️
nilearn/plotting/img_plotting.py	`88.19% <0%> (ø)`	⬆️
nilearn/_utils/testing.py	`78.76% <0%> (ø)`	⬆️
nilearn/plotting/surf_plotting.py	`76.25% <0%> (+0.52%)`	⬆️
nilearn/image/resampling.py	`93.75% <0%> (+0.89%)`	⬆️
nilearn/image/tests/test_image.py	`99.45% <0%> (+1.09%)`	⬆️
nilearn/regions/parcellations.py	`96.19% <0%> (+1.9%)`	⬆️
nilearn/_utils/cache_mixin.py	`83.65% <0%> (+1.92%)`	⬆️
nilearn/decoding/fista.py	`90.12% <0%> (+2.46%)`	⬆️
... and 4 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update e0ae31c...3f59840. Read the comment docs.

…ediction_example

jeromedockes · 2019-05-19T18:12:48Z

failure is related to #2056 and not this PR.

…ediction_example

jeromedockes · 2019-06-05T13:57:05Z

ping @GaelVaroquaux or @KamalakerDadi for a review

jeromedockes · 2019-06-05T13:57:40Z

ping @GaelVaroquaux or @KamalakerDadi for a review

https://4437-1235740-gh.circle-artifacts.com/0/home/circleci/project/doc/_build/html/auto_examples/03_connectivity/plot_group_level_connectivity.html

emdupre · 2019-10-02T19:07:50Z

Is this blocked by #2035 ?

jeromedockes · 2019-10-03T08:03:28Z

Is this blocked by #2035 ?

I don't think so. I think it is waiting to be either reviewed or closed.

emdupre · 2019-10-03T19:21:28Z

I can review if that's helpful ? Though I don't think it counts towards an official "approval."

GaelVaroquaux · 2019-10-03T19:28:48Z

I can review if that's helpful ?

It is.

emdupre

I think this is a big improvement, thanks @jeromedockes ! Small questions and comments.

examples/03_connectivity/plot_group_level_connectivity.py

emdupre · 2019-10-03T21:12:28Z

examples/03_connectivity/plot_group_level_connectivity.py

@@ -57,7 +39,7 @@ def plot_matrices(matrices, matrix_kind):

 masker = input_data.NiftiMapsMasker(
    msdl_data.maps, resampling_target="data", t_r=2, detrend=True,
-    low_pass=.1, high_pass=.01, memory='nilearn_cache', memory_level=1)
+    low_pass=.1, high_pass=.01, memory='nilearn_cache', memory_level=1).fit([])


What's the reasoning for adding the .fit() here distinct from .fit_transform() as previously ? It feels less explicit, as a reader.

because the masker is not fitted on the data provided to transform (or fit_transform)

examples/03_connectivity/plot_group_level_connectivity.py

emdupre · 2019-10-03T21:18:01Z

examples/03_connectivity/plot_group_level_connectivity.py

-###############################################################################
-# Finally, we can display the classification scores.
-from nilearn.plotting import show
+    print(kind)


I'm not sure what this print statement adds, other than having an output between the cells. Slight stylistic preference to drop -- feel free to ignore.

examples/05_advanced/plot_age_group_prediction_cross_val.py

emdupre · 2019-10-03T21:20:00Z

examples/05_advanced/plot_age_group_prediction_cross_val.py

+# We study only 60 subjects from the dataset, to save computation time.
+from nilearn import datasets
+
+rest_data = datasets.fetch_development_fmri(n_subjects=60)


rest_data might be misleading, here, since they're watching a movie. Maybe just func_data ?

emdupre · 2019-10-03T21:20:40Z

examples/05_advanced/plot_age_group_prediction_cross_val.py

+
+masker = NiftiMapsMasker(
+    msdl_data.maps, resampling_target="data", t_r=2, detrend=True,
+    low_pass=.1, high_pass=.01, memory='nilearn_cache', memory_level=1).fit([])


Same question as above on empty .fit as opposed to .fit_transform

examples/03_connectivity/plot_group_level_connectivity.py

Co-Authored-By: Elizabeth DuPre <emd222@cornell.edu> Co-Authored-By: bthirion <bertrand.thirion@inria.fr>

kchawla-pi · 2019-10-04T09:06:30Z

Pulling from master should resolve the CircleCI failure

jeromedockes · 2019-10-04T09:17:07Z

Pulling from master should resolve the CircleCI failure

thanks!

kchawla-pi · 2019-10-07T12:10:24Z

I am assuming no more comments. I will merge this PR on Wednesday.

KamalakerDadi

I don't have strong opinion on the advanced example. I would like to convert this advanced example into teaching material by adding them into user guide in the functional connectivity slot. AFAIK there is no guide showing supervised learning based on functional connectomes.

KamalakerDadi · 2019-10-07T09:49:04Z

examples/03_connectivity/plot_group_level_connectivity.py

@@ -1,43 +1,25 @@
 """
-Functional connectivity matrices for group analysis of connectomes
-==================================================================
+Functional connectivity predicts age group


I would write "Functional connectome-based classification of age groups". You can write predict but I am more used to listen this on a continuous range scale.

KamalakerDadi · 2019-10-07T09:49:33Z

examples/03_connectivity/plot_group_level_connectivity.py

+        development_dataset.func,
+        development_dataset.confounds,
+        development_dataset.phenotypic):
+    time_series = masker.transform(func_file, confounds=confound_file)


Using fit_transform is straight-forward. I feel.

kchawla-pi · 2019-10-08T15:07:09Z

~~Will merge once the current crop of CircleCI master builds have completed.~~

kchawla-pi · 2019-10-08T18:10:55Z

This needs a whats_new entry.

@emdupre

…s_brain_orientation * 'master' of https://github.com/nilearn/nilearn: (116 commits) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset Made Flake8 happy added whats_new ... # Conflicts: # doc/whats_new.rst

@emdupre

…lot_connectome_strength * 'master' of https://github.com/nilearn/nilearn: (272 commits) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset Made Flake8 happy ... # Conflicts: # examples/03_connectivity/plot_sphere_based_connectome.py

@emdupre

…ounds_for_connectome * 'master' of https://github.com/nilearn/nilearn: (227 commits) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset Made Flake8 happy ...

@emdupre

…_roi_contours * 'master' of https://github.com/nilearn/nilearn: (227 commits) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset Made Flake8 happy ...

@emdupre

…nt_modify_fetch_dev * 'master' of https://github.com/nilearn/nilearn: (228 commits) [MRG] Nans in view connectome (nilearn#2166) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset ... # Conflicts: # nilearn/datasets/func.py

@emdupre

…ecomposition * 'master' of https://github.com/nilearn/nilearn: (348 commits) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) Update Schaefer parcelation to v0.14.3 (nilearn#2138) MAINT: Future-compatible cmap reversal (nilearn#2131) fix openmp crash (nilearn#2140) change nose to pytest on appveyor (nilearn#2130) adding fix to whatsnew fix wrong urls in nki dataset Made Flake8 happy ... # Conflicts: # doc/connectivity/resting_state_networks.rst # doc/whats_new.rst # examples/03_connectivity/plot_canica_analysis.py

@emdupre

…smooth-image * 'master' of https://github.com/nilearn/nilearn: (114 commits) [DOC] Update whats_new to reference nilearn#2013 (Merging of several examples) (nilearn#2183) Removed sub-example due to unfit for lasso dataset - unstable float values (nilearn#2177) Fix Flake8 errors overlooked when merging PR nilearn#2028 (Plot connectome strength) (nilearn#2174) ENH: add connectome strength plot (nilearn#2028) Fix cache mixin tests (nilearn#2161) Do not fail if metadata cannot be updated for an image (nilearn#2167) [MRG] Nans in view connectome (nilearn#2166) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) Renamed test to deduplicate name (nilearn#2144) Fixes nilearn#2029 Handle gzip files without extensions (nilearn#2126) ...

@emdupre

…te-req-dev * 'master' of https://github.com/nilearn/nilearn: (336 commits) Release Nilearn 0.6.0 alpha (nilearn#2164) Making fetch_localizer_button_task backwards compatibile (nilearn#2182) [DOC] Update whats_new to reference nilearn#2013 (Merging of several examples) (nilearn#2183) Removed sub-example due to unfit for lasso dataset - unstable float values (nilearn#2177) Fix Flake8 errors overlooked when merging PR nilearn#2028 (Plot connectome strength) (nilearn#2174) ENH: add connectome strength plot (nilearn#2028) Fix cache mixin tests (nilearn#2161) Do not fail if metadata cannot be updated for an image (nilearn#2167) [MRG] Nans in view connectome (nilearn#2166) [MRG] FIX: orientation problem with plot_glass_brain (nilearn#1888) Import HTMLDocument in its original module to preserve backwards compatibility (nilearn#2162) Fixing malfunctioning allowed-failure section in Travis (nilearn#2160) Update Brainomics fetcher (nilearn#2097) Remove inplace modification in signal.clean (nilearn#2125) Iter age group prediction example (nilearn#2063) Expose bg_img, vmin and vmax in plot_img signature (nilearn#2157) Replac conda with pip in TravisCI setup (nilearn#2141) Core devs doc and add @emdupre (nilearn#2151) Add check for vmin, vmax in plot_surf_roi (nilearn#2052) [ENH] Initial visual reports (nilearn#2019) ...

jeromedockes added 2 commits May 17, 2019 20:52

simplify cv + include transformer in cv

6f8de61

note about dataset size

2b94c75

jeromedockes mentioned this pull request May 17, 2019

[MRG+1] 3 fold cv -> 100 fold shuffle split in group-level connectivity example #2059

Merged

don't use "passthrough"

bf66048

jeromedockes added 3 commits May 18, 2019 11:22

Merge remote-tracking branch 'upstream/master' into iter_age_group_pr…

d01aee8

…ediction_example

iter

1f2eaf2

simplify matrix plotting

65bfa2c

jeromedockes added 4 commits June 3, 2019 14:33

Merge remote-tracking branch 'upstream/master' into iter_age_group_pr…

b75cc2e

…ediction_example

don't use GridSearch or Pipeline (move to advanced example)

33259e1

Merge remote-tracking branch 'upstream/master' into iter_age_group_pr…

33e855a

…ediction_example

rename example

e5c59db

emdupre reviewed Oct 3, 2019

View reviewed changes

bthirion reviewed Oct 3, 2019

View reviewed changes

examples/03_connectivity/plot_group_level_connectivity.py Outdated Show resolved Hide resolved

jeromedockes and others added 2 commits October 4, 2019 10:38

Apply suggestions from code review

ab76a4b

Co-Authored-By: Elizabeth DuPre <emd222@cornell.edu> Co-Authored-By: bthirion <bertrand.thirion@inria.fr>

address review

1622652

Merge branch 'master' into iter_age_group_prediction_example

d1db841

KamalakerDadi reviewed Oct 7, 2019

View reviewed changes

address review

3872097

jeromedockes changed the title ~~Iter age group prediction example~~ [MRG] Iter age group prediction example Oct 8, 2019

whatsnew

3f59840

kchawla-pi merged commit eedc39e into nilearn:master Oct 8, 2019

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[MRG] Iter age group prediction example #2063

[MRG] Iter age group prediction example #2063

jeromedockes commented May 17, 2019 •

edited

Loading

codecov bot commented May 18, 2019

codecov bot commented May 18, 2019 •

edited

Loading

jeromedockes commented May 19, 2019

jeromedockes commented Jun 5, 2019

jeromedockes commented Jun 5, 2019

emdupre commented Oct 2, 2019

jeromedockes commented Oct 3, 2019 via email

emdupre commented Oct 3, 2019

GaelVaroquaux commented Oct 3, 2019 via email

emdupre left a comment

emdupre Oct 3, 2019

jeromedockes Oct 4, 2019

emdupre Oct 3, 2019

emdupre Oct 3, 2019

emdupre Oct 3, 2019

kchawla-pi commented Oct 4, 2019

jeromedockes commented Oct 4, 2019 via email

kchawla-pi commented Oct 7, 2019

KamalakerDadi left a comment

KamalakerDadi Oct 7, 2019

KamalakerDadi Oct 7, 2019

kchawla-pi commented Oct 8, 2019 •

edited

Loading

kchawla-pi commented Oct 8, 2019

[MRG] Iter age group prediction example #2063

[MRG] Iter age group prediction example #2063

Conversation

jeromedockes commented May 17, 2019 • edited Loading

codecov bot commented May 18, 2019

Codecov Report

codecov bot commented May 18, 2019 • edited Loading

Codecov Report

jeromedockes commented May 19, 2019

jeromedockes commented Jun 5, 2019

jeromedockes commented Jun 5, 2019

emdupre commented Oct 2, 2019

jeromedockes commented Oct 3, 2019 via email

emdupre commented Oct 3, 2019

GaelVaroquaux commented Oct 3, 2019 via email

emdupre left a comment

Choose a reason for hiding this comment

emdupre Oct 3, 2019

Choose a reason for hiding this comment

jeromedockes Oct 4, 2019

Choose a reason for hiding this comment

emdupre Oct 3, 2019

Choose a reason for hiding this comment

emdupre Oct 3, 2019

Choose a reason for hiding this comment

emdupre Oct 3, 2019

Choose a reason for hiding this comment

kchawla-pi commented Oct 4, 2019

jeromedockes commented Oct 4, 2019 via email

kchawla-pi commented Oct 7, 2019

KamalakerDadi left a comment

Choose a reason for hiding this comment

KamalakerDadi Oct 7, 2019

Choose a reason for hiding this comment

KamalakerDadi Oct 7, 2019

Choose a reason for hiding this comment

kchawla-pi commented Oct 8, 2019 • edited Loading

kchawla-pi commented Oct 8, 2019

jeromedockes commented May 17, 2019 •

edited

Loading

codecov bot commented May 18, 2019 •

edited

Loading

kchawla-pi commented Oct 8, 2019 •

edited

Loading