[DOC] update URLs with http:// to https:// (#4050)

* [DOC] http:// → htps://

Update a large part of the URLs in the documentation.

* Update examples/06_manipulating_images/plot_roi_extraction.py

---------

Co-authored-by: Remi Gau <remi_gau@hotmail.com>

AUTHORS.rst

@@ -182,7 +182,7 @@ Some other past or present contributors are:
 * `Thomas Bazeille`_: Inria, Saclay, France
 * `Tom Vanasse`_: Wisconsin Institute for Sleep and Consciousness, USA
 * `Vasco Diogo`_
-* `Vincent Michel`_: http://www.logilab.fr/
+* `Vincent Michel`_: https://www.logilab.fr/
 * `Virgile Fritsch`_: Inria, Saclay, France
 * `Yaroslav Halchenko`_: Dartmouth College, PBS, Hanover, New Hampshire, USA
 * `Yasmin Mzayek`_: Inria, Saclay, France
@@ -201,7 +201,7 @@ Funding
 `Mehdi Rahim`_, `Philippe Gervais`_ were paid by the
 :inria:`NiConnect <parietal/research/spatial_patterns/niconnect/>`.
 project, funded by the French `Investissement d'Avenir
-<http://www.gouvernement.fr/investissements-d-avenir-cgi>`_.
+<https://www.gouvernement.fr/investissements-d-avenir-cgi>`_.
 
 `Kshitij Chawla`_ was paid by `INRIA <https://www.inria.fr/en>`_.
 
@@ -220,7 +220,7 @@ There is no paper published yet about nilearn. We are waiting for the
 package to mature a bit. However, the patterns underlying the package
 have been described in: `Machine learning for neuroimaging with
 scikit-learn
-<http://journal.frontiersin.org/article/10.3389/fninf.2014.00014/abstract>`_.
+<https://doi.org/10.3389/fninf.2014.00014>`_.
 
 We suggest that you read and cite the paper. Thank you.
 

CITATION.cff

@@ -228,7 +228,7 @@ authors:
     orcid: https://orcid.org/0000-0002-8161-7699
   - given-names: Gael
     family-names: Varoquaux
-    website: http://gael-varoquaux.info/
+    website: https://gael-varoquaux.info/
     affiliation: Inria, Saclay, France
     orcid: https://orcid.org/0000-0003-1076-5122
   - given-names: Gilles de
@@ -648,7 +648,7 @@ authors:
   - given-names: Vincent
     family-names: Michel
     website: https://github.com/vmichel
-    affiliation: http://www.logilab.fr/
+    affiliation: https://www.logilab.fr/
   - given-names: Virgile
     family-names: Fritsch
     website: https://github.com/VirgileFritsch

README.rst

@@ -128,4 +128,4 @@ Development
 ===========
 
 Detailed instructions on how to contribute are available at
-http://nilearn.github.io/stable/development.html
+https://nilearn.github.io/stable/development.html

doc/README

@@ -3,8 +3,8 @@ NILEARN: neuroimaging with the scikit-learn
 ===========================================
 
 This repository contains code and documentation to use the scikit-learn
-( http://scikit-learn.org ) for neuroimaging data analysis. The only
-requirements are scikit-learn and nibabel ( http://nipy.org/nibabel ), as
+( https://scikit-learn.org ) for neuroimaging data analysis. The only
+requirements are scikit-learn and nibabel ( https://nipy.org/nibabel ), as
 well as their dependencies (numpy, scipy and matplotlib).
 
 The code comes with fully-runnable examples that download the data

doc/building_blocks/manual_pipeline.rst

@@ -32,7 +32,7 @@ which downloads a dataset and returns a bunch of paths to the dataset
 files (more details in :ref:`loading_data`). We can then proceed
 loading them as if they were just any other files on our disk. For
 example, we can download the data from the
-`Haxby 2001 paper <http://dx.doi.org/10.1126/science.1063736>`_ :
+`Haxby 2001 paper <https://doi.org/10.1126/science.1063736>`_ :
 
 .. code-block:: default
 
@@ -67,7 +67,7 @@ and the goal of this experiment is to predict which category is presented
 to the subjects from the brain activation.
 
 These conditions are presented as string into a CSV file. The `pandas
-<http://pandas.pydata.org/>`__ function
+<https://pandas.pydata.org/>`__ function
 ``read_csv`` is very useful to load this kind of data.
 
 .. literalinclude:: ../../examples/00_tutorials/plot_decoding_tutorial.py
@@ -76,7 +76,7 @@ These conditions are presented as string into a CSV file. The `pandas
 
 .. seealso::
 
-   * `pandas <http://pandas.pydata.org/>`_ is a very useful Python
+   * `pandas <https://pandas.pydata.org/>`_ is a very useful Python
      library to load CSV files and process their data
 
 For example, we will now consider only the conditions *cat* and *face* from our dataset.
@@ -193,7 +193,7 @@ predict the category of picture seen by the subject:
 
 
 We will not detail it here since there is a very good documentation about it in the
-`scikit-learn documentation <http://scikit-learn.org/stable/modules/svm.html#classification>`__
+`scikit-learn documentation <https://scikit-learn.org/stable/modules/svm.html#classification>`__
 
 Unmasking (inverse_transform)
 =============================

doc/building_blocks/neurovault.rst

@@ -6,7 +6,7 @@ Downloading statistical maps from the Neurovault repository
 
 Neurovault is a public repository of unthresholded statistical maps,
 parcellations, and atlases of the human brain. You can read about it
-and browse the images it contains at http://www.neurovault.org. You
+and browse the images it contains at https://www.neurovault.org. You
 can download maps from Neurovault with Nilearn.
 
 Neurovault was introduced in [1]_.
@@ -25,7 +25,7 @@ Specific images or collections
 
 In the simplest case, you already know the "id" of the collections or
 images you want. Maybe you liked a paper and went to
-http://www.neurovault.org looking for the data. Once on the relevant
+https://www.neurovault.org looking for the data. Once on the relevant
 collection's webpage, you can click 'Details' to see its id
 (and more). You can then download it using
 :func:`nilearn.datasets.fetch_neurovault_ids` :
@@ -187,7 +187,7 @@ Neurosynth annotations
 It is also possible to ask Neurosynth to annotate the maps found on
 Neurovault. Neurosynth is a platform for large-scale, automated
 synthesis of :term:`fMRI` data. It can be used to perform decoding.  You can
-learn more about Neurosynth at http://www.neurosynth.org.
+learn more about Neurosynth at https://www.neurosynth.org.
 
 Neurosynth was introduced in [2]_.
 

doc/conf.py

@@ -332,7 +332,7 @@
         "nilearn.tex",
         "NeuroImaging with scikit-learn",
         "Gaël Varoquaux and Alexandre Abraham"
-        + r"\\\relax ~\\\relax http://nilearn.github.io",
+        + r"\\\relax ~\\\relax https://nilearn.github.io",
         "manual",
     ),
 ]

doc/connectivity/connectome_extraction.rst

@@ -15,11 +15,11 @@ Connectome extraction: inverse covariance for direct connections
 .. topic:: **References**
 
    * `Smith et al, Network modelling methods for FMRI,
-     NeuroImage 2011 <http://www.sciencedirect.com/science/article/pii/S1053811910011602>`_
+     NeuroImage 2011 <https://www.sciencedirect.com/science/article/pii/S1053811910011602>`_
 
    * `Varoquaux and Craddock, Learning and comparing functional
      connectomes across subjects, NeuroImage 2013
-     <http://www.sciencedirect.com/science/article/pii/S1053811913003340>`_
+     <https://www.sciencedirect.com/science/article/pii/S1053811913003340>`_
 
 Sparse inverse covariance for functional connectomes
 =====================================================
@@ -36,7 +36,7 @@ them only the direct connections between two regions.
 
 
 As shown in `[Smith 2011]
-<http://www.sciencedirect.com/science/article/pii/S1053811910011602>`_,
+<https://www.sciencedirect.com/science/article/pii/S1053811910011602>`_,
 `[Varoquaux 2010] <https://hal.inria.fr/inria-00512451>`_, it is more
 interesting to use the inverse covariance matrix, ie the *precision
 matrix*. It gives **only direct connections between regions**, as it
@@ -95,7 +95,7 @@ of the estimator:
 .. topic:: **Parameter selection**
 
     The parameter controlling the sparsity is set by `cross-validation
-    <http://scikit-learn.org/stable/modules/cross_validation.html>`_
+    <https://scikit-learn.org/stable/modules/cross_validation.html>`_
     scheme. If you want to specify it manually, use the estimator
     :class:`sklearn.covariance.GraphicalLasso`.
 
@@ -114,7 +114,7 @@ of the estimator:
 
 .. topic:: **Reference**
 
- * The `graph lasso [Friedman et al, Biostatistics 2007] <http://biostatistics.oxfordjournals.org/content/9/3/432.short>`_ is useful to estimate one
+ * The `graph lasso [Friedman et al, Biostatistics 2007] <https://academic.oup.com/biostatistics/article/9/3/432/224260>`_ is useful to estimate one
    inverse covariance, ie to work on single-subject data or concatenate
    multi-subject data.
 
@@ -234,7 +234,7 @@ information.
 
 .. topic:: **Reference**
 
- * The `Brain covariance selection using population prior [Varoquaux et al, NIPS 2010] <http://papers.nips.cc/paper/4080-brain-covariance-selection-better-individual-functional-connectivity-models-using-population-prior>`_
+ * The `Brain covariance selection using population prior [Varoquaux et al, NIPS 2010] <https://papers.nips.cc/paper/4080-brain-covariance-selection-better-individual-functional-connectivity-models-using-population-prior>`_
 
 Linking total and direct interactions at the group level
 ========================================================
@@ -277,4 +277,4 @@ Deviations from this mean in the tangent space are provided in the connectivitie
 
 .. topic:: **Reference**
 
- * The `tangent space for connectivity [Varoquaux et al, MICCAI 2010] <http://link.springer.com/chapter/10.1007%2F978-3-642-15705-9_25>`_
+ * The `tangent space for connectivity [Varoquaux et al, MICCAI 2010] <https://link.springer.com/chapter/10.1007/978-3-642-15705-9_25>`_

doc/connectivity/functional_connectomes.rst

@@ -14,7 +14,7 @@ Extracting times series to build a functional connectome
 
    * `Varoquaux and Craddock, "Learning and comparing functional
      connectomes across subjects", NeuroImage 2013
-     <http://www.sciencedirect.com/science/article/pii/S1053811913003340>`_.
+     <https://www.sciencedirect.com/science/article/pii/S1053811913003340>`_.
 
 .. _parcellation_time_series:
 
@@ -71,7 +71,7 @@ the important parameters, but not the data::
 The Nifti data can then be turned to time-series by calling the
 :meth:`NiftiLabelsMasker.fit_transform` method, that takes either
 filenames or `NiftiImage objects
-<http://nipy.org/nibabel/nibabel_images.html>`_::
+<https://nipy.org/nibabel/nibabel_images.html>`_::
 
     time_series = masker.fit_transform(frmi_files,
                                        confounds=confounds_dataframe)
@@ -173,7 +173,7 @@ specifying the important parameters, in particular the atlas::
     masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True)
 
 The ``fit_transform`` method turns filenames or `NiftiImage objects
-<http://nipy.org/nibabel/nibabel_images.html>`_ to time series::
+<https://nipy.org/nibabel/nibabel_images.html>`_ to time series::
 
     time_series = masker.fit_transform(frmi_files, confounds=csv_file)
 
@@ -253,7 +253,7 @@ can be computed for each region on hard :term:`parcellation` or probabilistic at
 .. topic:: **References**
 
   * `Zalesky et al., NeuroImage 2012, "On the use of correlation as a measure of
-    network connectivity" <http://www.sciencedirect.com/science/article/pii/S1053811912001784>`_.
+    network connectivity" <https://www.sciencedirect.com/science/article/pii/S1053811912001784>`_.
 
   * `Varoquaux et al., NeuroImage 2013, "Learning and comparing functional
-    connectomes across subjects" <http://www.sciencedirect.com/science/article/pii/S1053811913003340>`_.
+    connectomes across subjects" <https://www.sciencedirect.com/science/article/pii/S1053811913003340>`_.

doc/connectivity/parcellating.rst

@@ -16,7 +16,7 @@ into homogeneous regions from functional imaging data.
 
     Thirion, et al. `"Which fMRI clustering gives good brain
     parcellations?."
-    <http://journal.frontiersin.org/article/10.3389/fnins.2014.00167/full>`_
+    <https://www.frontiersin.org/articles/10.3389/fnins.2014.00167/full>`_
     Frontiers in neuroscience 8.167 (2014): 13.
 
 Data loading: movie-watching data
@@ -40,7 +40,7 @@ Applying clustering
     to debate. There are many clustering methods; their computational
     cost will vary, as well as their results. A `well-cited empirical
     comparison paper, Thirion et al. 2014
-    <http://journal.frontiersin.org/article/10.3389/fnins.2014.00167/full>`_
+    <https://www.frontiersin.org/articles/10.3389/fnins.2014.00167/full>`_
     suggests that:
 
     * For a large number of clusters, it is preferable to use Ward
@@ -68,7 +68,7 @@ Applying clustering
 Before applying Ward's method, we compute a spatial neighborhood matrix,
 aka connectivity matrix. This is useful to constrain clusters to form
 contiguous parcels (see `the scikit-learn documentation
-<http://scikit-learn.org/stable/modules/clustering.html#adding-connectivity-constraints>`_)
+<https://scikit-learn.org/stable/modules/clustering.html#adding-connectivity-constraints>`_)
 
 This is done from the mask computed by the masker: a niimg from which we
 extract a numpy array and then the connectivity matrix.

doc/connectivity/resting_state_networks.rst

@@ -22,7 +22,7 @@ Multi-subject ICA: CanICA
 
     * G. Varoquaux et al. "A group model for stable multi-subject ICA on
       fMRI datasets", `NeuroImage Vol 51 (2010)
-      <http://www.sciencedirect.com/science/article/pii/S1053811910001618>`_, p. 288-299
+      <https://www.sciencedirect.com/science/article/pii/S1053811910001618>`_, p. 288-299
 
 Objective
 ----------

doc/decoding/decoding_intro.rst

@@ -115,7 +115,7 @@ Loading the data into nilearn
 
 * **Loading the behavioral labels**: Behavioral information is often stored
   in a text file such as a CSV, and must be load with
-  **numpy.recfromcsv** or `pandas <http://pandas.pydata.org/>`_
+  **numpy.recfromcsv** or `pandas <https://pandas.pydata.org/>`_
 
 * **Sample mask**: Masking some of the time points
   may be useful to
@@ -168,14 +168,14 @@ A first estimator
 To perform decoding, we need a model that can learn some relations
 between **X** (the imaging data) and **y** the condition label. As a default,
 Nilearn uses `Support Vector Classifier
-<http://scikit-learn.org/stable/modules/svm.html>`_ (or SVC) with a
+<https://scikit-learn.org/stable/modules/svm.html>`_ (or SVC) with a
 linear kernel. This is a simple yet performant choice that works in a wide
 variety of problems.
 
 .. seealso::
 
    `The scikit-learn documentation on SVMs
-   <http://scikit-learn.org/stable/modules/svm.html>`_
+   <https://scikit-learn.org/stable/modules/svm.html>`_
 
 Decoding made easy
 -------------------
@@ -286,7 +286,7 @@ Other metrics, such as the :term:`AUC` (Area Under the Curve, for the
 
 .. seealso::
   the `list of scoring options
-  <http://scikit-learn.org/stable/modules/model_evaluation.html#common-cases-predefined-values>`_
+  <https://scikit-learn.org/stable/modules/model_evaluation.html#common-cases-predefined-values>`_
 
 Prediction accuracy at chance using simple strategies
 .....................................................
@@ -357,7 +357,7 @@ Dimension reduction with feature selection
 If we do not start from a mask of the relevant regions, there is a very
 large number of voxels and not all are useful for
 face vs cat prediction. We thus add a `feature selection
-<http://scikit-learn.org/stable/modules/feature_selection.html>`_
+<https://scikit-learn.org/stable/modules/feature_selection.html>`_
 procedure. The idea is to select the ``k`` voxels most correlated to the
 task through a simple F-score based feature selection (a.k.a.
 `Anova <https://en.wikipedia.org/wiki/Analysis_of_variance#The_F-test>`_)

doc/decoding/estimator_choice.rst

@@ -80,7 +80,7 @@ whereas the latter is linear with the number of classes.
     :ref:`userguide <frem>`, yielding state-of-the art decoding performance.
 
 **Confusion matrix** `The confusion matrix
-<http://en.wikipedia.org/wiki/Confusion_matrix>`_,
+<https://en.wikipedia.org/wiki/Confusion_matrix>`_,
 :func:`sklearn.metrics.confusion_matrix` is a useful tool to
 understand the classifier's errors in a multiclass problem.
 
@@ -153,7 +153,7 @@ In :class:`nilearn.decoding.DecoderRegressor` you can use some of these objects
 
    * Many more estimators are available in scikit-learn (see the
      `scikit-learn documentation on supervised learning
-     <http://scikit-learn.org/stable/supervised_learning.html>`_). To learn to
+     <https://scikit-learn.org/stable/supervised_learning.html>`_). To learn to
      do decoding with any of these, see : :ref:`going_further`
 
 .. figure:: ../auto_examples/02_decoding/images/sphx_glr_plot_haxby_different_estimators_001.png
@@ -215,7 +215,7 @@ due to this noise.
 .. seealso::
 
    `The scikit-learn documentation on parameter selection
-   <http://scikit-learn.org/stable/modules/grid_search.html>`_
+   <https://scikit-learn.org/stable/modules/grid_search.html>`_
 
 Bagging several models
 ============================
@@ -234,7 +234,7 @@ models is then used to make predictions.
 
 .. seealso::
 
-  * The `scikit-learn documentation <http://scikit-learn.org>`_
+  * The `scikit-learn documentation <https://scikit-learn.org>`_
     has very detailed explanations on a large variety of estimators and
     machine learning techniques. To become better at decoding, you need
     to study it.

doc/decoding/frem.rst

@@ -62,7 +62,7 @@ Spatial regularization of decoding maps on mixed gambles study
 
 .. seealso::
 
-    * The `scikit-learn documentation <http://scikit-learn.org>`_
+    * The `scikit-learn documentation <https://scikit-learn.org>`_
       has very detailed explanations on a large variety of estimators and
       machine learning techniques. To become better at decoding, you need
       to study it.