Make install

stable/_downloads/00a1bbd0443a134549688a8b5402105d/plot_multiscale_parcellations.py

@@ -4,8 +4,8 @@
 
 This example shows how to download and fetch brain parcellations of
 multiple networks using
-:func:`nilearn.datasets.fetch_atlas_basc_multiscale_2015`
-and visualize them using plotting function :func:`nilearn.plotting.plot_roi`.
+:func:`~nilearn.datasets.fetch_atlas_basc_multiscale_2015`
+and visualize them using plotting function :func:`~nilearn.plotting.plot_roi`.
 
 We show here only three different networks of 'symmetric' version. For more
 details about different versions and different networks, please refer to its
@@ -17,12 +17,12 @@
 # -----------------------------------------------
 
 # import datasets module and use `fetch_atlas_basc_multiscale_2015` function
-from nilearn import datasets
+from nilearn.datasets import fetch_atlas_basc_multiscale_2015
 
 parcellations = [
-    datasets.fetch_atlas_basc_multiscale_2015(version="sym", resolution=64),
-    datasets.fetch_atlas_basc_multiscale_2015(version="sym", resolution=197),
-    datasets.fetch_atlas_basc_multiscale_2015(version="sym", resolution=444),
+    fetch_atlas_basc_multiscale_2015(version="sym", resolution=64),
+    fetch_atlas_basc_multiscale_2015(version="sym", resolution=197),
+    fetch_atlas_basc_multiscale_2015(version="sym", resolution=444),
 ]
 
 # We show here networks of 64, 197, 444
@@ -35,20 +35,14 @@
 # -------------------------------
 
 # import plotting module and use `plot_roi` function, since the maps are in 3D
-from nilearn import plotting
+from nilearn.plotting import cm, plot_roi, show
 
 # The coordinates of all plots are selected automatically by itself
 # We manually change the colormap of our choice
-plotting.plot_roi(
-    networks_64, cmap=plotting.cm.bwr, title="64 regions of brain clusters"
-)
+plot_roi(networks_64, cmap=cm.bwr, title="64 regions of brain clusters")
 
-plotting.plot_roi(
-    networks_197, cmap=plotting.cm.bwr, title="197 regions of brain clusters"
-)
+plot_roi(networks_197, cmap=cm.bwr, title="197 regions of brain clusters")
 
-plotting.plot_roi(
-    networks_444, cmap=plotting.cm.bwr_r, title="444 regions of brain clusters"
-)
+plot_roi(networks_444, cmap=cm.bwr_r, title="444 regions of brain clusters")
 
-plotting.show()
+show()

stable/_downloads/00b63a2f3c19f56521d9ac182410c025/plot_simulated_data.py

@@ -148,11 +148,9 @@ def plot_slices(data, title=None):
 # We can now run different estimators and look at their prediction score,
 # as well as the feature maps that they recover. Namely, we will use
 #
-# * A support vector regression (`SVM
-#   <https://scikit-learn.org/stable/modules/svm.html>`_)
+# * A :sklearn:`support vector regression </modules/svm.html>`
 #
-# * An `elastic-net
-#   <https://scikit-learn.org/stable/modules/linear_model.html#elastic-net>`_
+# * An :sklearn:`elastic-net <modules/linear_model.html#elastic-net>`
 #
 # * A *Bayesian* ridge estimator, i.e. a ridge estimator that sets its
 #   parameter according to a metaprior

stable/_downloads/01cfe421c270935a30bc814b91794c28/plot_haxby_mass_univariate.ipynb

@@ -94,7 +94,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.feature_selection import f_regression\n\n# f_regression implicitly adds intercept\n_, pvals_bonferroni = f_regression(\n    grouped_fmri_masked, grouped_conditions_encoded\n)\npvals_bonferroni *= fmri_masked.shape[1]\npvals_bonferroni[np.isnan(pvals_bonferroni)] = 1\npvals_bonferroni[pvals_bonferroni > 1] = 1\nneg_log_pvals_bonferroni = -np.log10(pvals_bonferroni)\nneg_log_pvals_bonferroni_unmasked = nifti_masker.inverse_transform(\n    neg_log_pvals_bonferroni\n)"
+        "from sklearn.feature_selection import f_regression\n\n# f_regression implicitly adds intercept\n_, pvals_bonferroni = f_regression(\n    grouped_fmri_masked,\n    grouped_conditions_encoded.ravel(),\n)\npvals_bonferroni *= fmri_masked.shape[1]\npvals_bonferroni[np.isnan(pvals_bonferroni)] = 1\npvals_bonferroni[pvals_bonferroni > 1] = 1\nneg_log_pvals_bonferroni = -np.log10(pvals_bonferroni)\nneg_log_pvals_bonferroni_unmasked = nifti_masker.inverse_transform(\n    neg_log_pvals_bonferroni\n)"
       ]
     },
     {

stable/_downloads/0a08d2a6f3fe90c61fff00f683f2fa0a/plot_3d_and_4d_niimg.py

@@ -126,7 +126,7 @@
 # given in the documentation section: :ref:`loading_data`.
 #
 # Functions accept either 3D or 4D images, and we need to use on the one
-# hand :func:`nilearn.image.index_img` or :func:`nilearn.image.iter_img`
+# hand :func:`~nilearn.image.index_img` or :func:`~nilearn.image.iter_img`
 # to break down 4D images into 3D images, and on the other hand
-# :func:`nilearn.image.concat_imgs` to group a list of 3D images into a 4D
+# :func:`~nilearn.image.concat_imgs` to group a list of 3D images into a 4D
 # image.

stable/_downloads/0ddd8df13e1163e78fa0a1b381f453cd/plot_surface_projection_strategies.py

@@ -2,9 +2,9 @@
 Technical point: Illustration of the volume to surface sampling schemes
 =======================================================================
 
-In nilearn, :func:`nilearn.surface.vol_to_surf` allows us to measure values of
+In nilearn, :func:`~nilearn.surface.vol_to_surf` allows us to measure values of
 a 3d volume at the nodes of a cortical mesh, transforming it into surface data.
-This data can then be plotted with :func:`nilearn.plotting.plot_surf_stat_map`
+This data can then be plotted with :func:`~nilearn.plotting.plot_surf_stat_map`
 for example.
 
 This script shows, on a toy example, where samples are drawn around each mesh

stable/_downloads/1020ea2b51f8e38daf607e192d4bdc5d/plot_oasis.py

@@ -5,7 +5,7 @@
 This example uses voxel-based morphometry (:term:`VBM`) to study the
 relationship between aging, sex, and gray matter density.
 
-The data come from the `OASIS <https://www.oasis-brains.org/>`_ project.
+The data come from the `OASIS <https://sites.wustl.edu/oasisbrains/>`_ project.
 If you use it, you need to agree with the data usage agreement available
 on the website.
 
@@ -79,7 +79,7 @@
 )
 
 # %%
-# Analyse data
+# Analyze data
 # ------------
 # First, we create an adequate design matrix with three columns: 'age', 'sex',
 # and 'intercept'.

stable/_downloads/126eff4ec954cc958192cc36d5123433/plot_visualize_megatrawls_netmats.ipynb

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Visualizing Megatrawls Network Matrices from Human Connectome Project\n\nThis example shows how to fetch network matrices data from HCP beta-release\nof the Functional Connectivity Megatrawl project.\n\nSee :func:`nilearn.datasets.fetch_megatrawls_netmats`\ndocumentation for more details.\n"
+        "\n# Visualizing Megatrawls Network Matrices from Human Connectome Project\n\nThis example shows how to fetch network matrices data from HCP beta-release\nof the Functional Connectivity Megatrawl project.\n\nSee :func:`~nilearn.datasets.fetch_megatrawls_netmats`\ndocumentation for more details.\n"
       ]
     },
     {

stable/_downloads/14447d91ef3f4e2c67352826410cf720/plot_haxby_understand_decoder.py

@@ -1,12 +1,12 @@
-"""Understanding :class:`nilearn.decoding.Decoder`
+"""Understanding :class:`~nilearn.decoding.Decoder`
 ==================================================
 
-Nilearn's :class:`nilearn.decoding.Decoder` object is a composite estimator
+Nilearn's :class:`~nilearn.decoding.Decoder` object is a composite estimator
 that does several things under the hood and can hence be a bit difficult to
 understand at first.
 
 This example aims to provide a clear understanding of the
-:class:`nilearn.decoding.Decoder` object by demonstrating these steps via a
+:class:`~nilearn.decoding.Decoder` object by demonstrating these steps via a
 Scikit-Learn pipeline.
 
 We will use the :footcite:t:`Haxby2001` dataset where the participants were
@@ -65,23 +65,24 @@
 # of brain volumes acquired while visual stimuli were presented, each
 # corresponding to one of the 8 labels we selected above.
 #
-# :class:`nilearn.decoding.Decoder` can convert this 4D image to a 2D numpy
+# :class:`~nilearn.decoding.Decoder` can convert this 4D image to a 2D numpy
 # array where each row corresponds to a trial and each column corresponds to a
 # voxel. In addition, it can also do several other things like masking,
 # smoothing, standardizing the data etc. depending on your requirements.
 #
-# Under the hood, :class:`nilearn.decoding.Decoder` uses
-# :class:`nilearn.maskers.NiftiMasker` to do all these operations. So here we
+# Under the hood, :class:`~nilearn.decoding.Decoder` uses
+# :class:`~nilearn.maskers.NiftiMasker` to do all these operations. So here we
 # will demonstrate this by directly using the
-# :class:`nilearn.maskers.NiftiMasker`. Specifically, we will use it to:
+# :class:`~nilearn.maskers.NiftiMasker`. Specifically, we will use it to:
 #
 # 1. only keep the data from the Ventral Temporal cortex by providing the
-# mask image (in :class:`nilearn.decoding.Decoder` this is done by
+# mask image (in :class:`~nilearn.decoding.Decoder` this is done by
 # providing the mask image in the ``mask`` parameter).
 #
 # 2. standardize the data by z-scoring it such that the data is scaled to
 # have zero mean and unit variance across trials (in
-# :class:`nilearn.decoding.Decoder` this is done by setting the ``standardize``
+# :class:`~nilearn.decoding.Decoder`
+# this is done by setting the ``standardize``
 # parameter to ``"zscore_sample"``).
 
 from nilearn.maskers import NiftiMasker
@@ -92,7 +93,7 @@
 # Convert the multi-class labels to binary labels
 # -----------------------------------------------
 #
-# The :class:`nilearn.decoding.Decoder` converts multi-class classification
+# The :class:`~nilearn.decoding.Decoder` converts multi-class classification
 # problem to N one-vs-others binary classification problems by default (where N
 # is the number of unique labels)
 #
@@ -129,7 +130,7 @@
 fig, (ax_binary, ax_multi) = plt.subplots(
     2, gridspec_kw={"height_ratios": [10, 1.5]}, figsize=(12, 2)
 )
-cmap = ListedColormap(["white"] + list(plt.cm.tab10.colors)[0:n_labels])
+cmap = ListedColormap(["white"] + list(plt.cm.tab10.colors)[:n_labels])
 binary_plt = ax_binary.imshow(
     y_binary_.T,
     aspect="auto",
@@ -145,7 +146,7 @@
 label_multi = LabelEncoder()
 y_multi = label_multi.fit_transform(y)
 y_multi = y_multi.reshape(1, -1)
-cmap = ListedColormap(list(plt.cm.tab10.colors)[0:n_labels])
+cmap = ListedColormap(list(plt.cm.tab10.colors)[:n_labels])
 multi_plt = ax_multi.imshow(
     y_multi,
     aspect="auto",
@@ -175,7 +176,7 @@
 # -----------------
 #
 # After preprocessing the provided fMRI data, the
-# :class:`nilearn.decoding.Decoder` performs a univariate feature selection on
+# :class:`~nilearn.decoding.Decoder` performs a univariate feature selection on
 # the voxels of the brain volume. It uses Scikit-Learn's
 # :class:`~sklearn.feature_selection.SelectPercentile` with
 # :func:`~sklearn.feature_selection.f_classif` to calculate ANOVA F-scores for
@@ -210,7 +211,7 @@
 # Hyperparameter optimization
 # ---------------------------
 #
-# The :class:`nilearn.decoding.Decoder` also performs hyperparameter tuning.
+# The :class:`~nilearn.decoding.Decoder` also performs hyperparameter tuning.
 # How this is done depends on the estimator used.
 #
 # For the support vector classifiers (known as SVC, and used by setting
@@ -224,14 +225,14 @@
 # the training data.
 #
 # In addition, the parameter grids that are used for hyperparameter tuning
-# by :class:`nilearn.decoding.Decoder` are also different from the default
+# by :class:`~nilearn.decoding.Decoder` are also different from the default
 # Scikit-Learn parameter grids for the corresponding ``<estimator_name>CV``
 # objects.
 #
 # For simplicity, let's use Scikit-Learn's
 # :class:`~sklearn.linear_model.LogisticRegressionCV` with custom parameter
 # grid (via ``Cs`` parameter) as used in Nilearn's
-# :class:`nilearn.decoding.Decoder`.
+# :class:`~nilearn.decoding.Decoder`.
 
 from sklearn.linear_model import LogisticRegressionCV
 
@@ -247,7 +248,7 @@
 # -----------------------------------------------------
 #
 # Now let's put all the pieces together to train and cross-validate. The
-# :class:`nilearn.decoding.Decoder` uses a leave-one-group-out
+# :class:`~nilearn.decoding.Decoder` uses a leave-one-group-out
 # cross-validation scheme by default in cases where groups are defined. In our
 # example a group is a run, so we will use Scikit-Learn's
 # :class:`~sklearn.model_selection.LeaveOneGroupOut`
@@ -290,12 +291,12 @@
         scores_sklearn.append(score)
 
 # %%
-# Decode via the :class:`nilearn.decoding.Decoder`
-# ------------------------------------------------
+# Decode via the :class:`~nilearn.decoding.Decoder`
+# -------------------------------------------------
 #
 # All these steps can be done in a few lines and made faster via parallel
 # processing using the ``n_jobs`` parameter in
-# :class:`nilearn.decoding.Decoder`.
+# :class:`~nilearn.decoding.Decoder`.
 
 from nilearn.decoding import Decoder
 
@@ -323,10 +324,10 @@
 
 # %%
 # As we can see, the mean AU-ROC scores from the Scikit-Learn pipeline and
-# Nilearn's :class:`nilearn.decoding.Decoder` are identical.
+# Nilearn's :class:`~nilearn.decoding.Decoder` are identical.
 #
-# The advantage of using Nilearn's :class:`nilearn.decoding.Decoder` is
+# The advantage of using Nilearn's :class:`~nilearn.decoding.Decoder` is
 # that it does all these steps under the hood and provides a simple interface
 # to train, cross-validate and predict on new data, while also parallelizing
-# the computations to make the cross-validation faster. It also organises the
-# results in a structured way that can be easily accessed and analysed.
+# the computations to make the cross-validation faster. It also organizes the
+# results in a structured way that can be easily accessed and analyzed.

stable/_downloads/15bf7d6d499dfe919be74278af66d069/plot_simulated_data.ipynb

@@ -76,7 +76,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Run different estimators\n\nWe can now run different estimators and look at their prediction score,\nas well as the feature maps that they recover. Namely, we will use\n\n* A support vector regression ([SVM](https://scikit-learn.org/stable/modules/svm.html))\n\n* An [elastic-net](https://scikit-learn.org/stable/modules/linear_model.html#elastic-net)\n\n* A *Bayesian* ridge estimator, i.e. a ridge estimator that sets its\n  parameter according to a metaprior\n\n* A ridge estimator that set its parameter by cross-validation\n\nNote that the `RidgeCV` and the `ElasticNetCV` have names ending in `CV`\nthat stands for `cross-validation`: in the list of possible `alpha`\nvalues that they are given, they choose the best by cross-validation.\n\n"
+        "## Run different estimators\n\nWe can now run different estimators and look at their prediction score,\nas well as the feature maps that they recover. Namely, we will use\n\n* A :sklearn:`support vector regression </modules/svm.html>`\n\n* An :sklearn:`elastic-net <modules/linear_model.html#elastic-net>`\n\n* A *Bayesian* ridge estimator, i.e. a ridge estimator that sets its\n  parameter according to a metaprior\n\n* A ridge estimator that set its parameter by cross-validation\n\nNote that the `RidgeCV` and the `ElasticNetCV` have names ending in `CV`\nthat stands for `cross-validation`: in the list of possible `alpha`\nvalues that they are given, they choose the best by cross-validation.\n\n"
       ]
     },
     {

stable/_downloads/1762b321e2d54728de2d7ecfc8d506f2/plot_oasis_vbm.py

@@ -5,7 +5,7 @@
 This example uses Voxel-Based Morphometry (:term:`VBM`)
 to study the relationship between aging and gray matter density.
 
-The data come from the `OASIS <https://www.oasis-brains.org/>`_ project.
+The data come from the `OASIS <https://sites.wustl.edu/oasisbrains/>`_ project.
 If you use it, you need to agree with the data usage agreement available
 on the website.
 
@@ -56,7 +56,7 @@
 # %%
 import numpy as np
 
-from nilearn import datasets
+from nilearn.datasets import fetch_oasis_vbm
 from nilearn.image import get_data
 from nilearn.maskers import NiftiMasker
 
@@ -65,9 +65,7 @@
 # %%
 # Load Oasis dataset
 # ------------------
-oasis_dataset = datasets.fetch_oasis_vbm(
-    n_subjects=n_subjects, legacy_format=False
-)
+oasis_dataset = fetch_oasis_vbm(n_subjects=n_subjects, legacy_format=False)
 gray_matter_map_filenames = oasis_dataset.gray_matter_maps
 age = oasis_dataset.ext_vars["age"].to_numpy()
 
@@ -109,7 +107,7 @@
 
 # %%
 # Prediction pipeline with :term:`ANOVA` and SVR using
-# :class:`nilearn.decoding.DecoderRegressor` Object
+# :class:`~nilearn.decoding.DecoderRegressor` Object
 #
 # In nilearn we can benefit from the built-in DecoderRegressor object to
 # do :term:`ANOVA` with SVR instead of manually defining the whole pipeline.

stable/_downloads/1dd3df3becba1a00730b344507d5bdd4/plot_ica_neurovault.ipynb

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# NeuroVault cross-study ICA maps\n\nThis example shows how to download statistical maps from\nNeuroVault, label them with NeuroSynth terms,\nand compute :term:`ICA` components across all the maps.\n\nSee :func:`nilearn.datasets.fetch_neurovault`\ndocumentation for more details.\n\n.. include:: ../../../examples/masker_note.rst\n\n..\n    Original authors:\n\n    - Ben Cipollini\n\n    Ported from code authored by Chris Filo Gorgolewski, Gael Varoquaux\n    https://github.com/NeuroVault/neurovault_analysis\n"
+        "\n# NeuroVault cross-study ICA maps\n\nThis example shows how to download statistical maps from\nNeuroVault, label them with NeuroSynth terms,\nand compute :term:`ICA` components across all the maps.\n\nSee :func:`~nilearn.datasets.fetch_neurovault`\ndocumentation for more details.\n\n.. include:: ../../../examples/masker_note.rst\n\n..\n    Original authors:\n\n    - Ben Cipollini\n\n    Ported from code authored by Chris Filo Gorgolewski, Gael Varoquaux\n    https://github.com/NeuroVault/neurovault_analysis\n"
       ]
     },
     {

stable/_downloads/1df527f29be7e15097f801df2ab4e0a9/plot_resample_to_template.py

@@ -3,9 +3,10 @@
 ===============================
 
 The goal of this example is to illustrate the use of the function
-:func:`nilearn.image.resample_to_img` to resample an image to a template.
+:func:`~nilearn.image.resample_to_img` to resample an image to a template.
 We use the MNI152 template as the reference for resampling a t-map image.
-Function :func:`nilearn.image.resample_img` could also be used to achieve this.
+Function :func:`~nilearn.image.resample_img`
+could also be used to achieve this.
 """
 
 # %%

stable/_downloads/2002f5d0c70b1223f14a1b2bac383088/plot_extract_regions_dictlearning_maps.py

@@ -2,24 +2,24 @@
 Regions extraction using dictionary learning and functional connectomes
 =======================================================================
 
-This example shows how to use :class:`nilearn.regions.RegionExtractor`
+This example shows how to use :class:`~nilearn.regions.RegionExtractor`
 to extract spatially constrained brain regions from whole brain maps decomposed
 using :term:`Dictionary learning` and use them to build
 a :term:`functional connectome`.
 
 We used 20 movie-watching functional datasets from
-:func:`nilearn.datasets.fetch_development_fmri` and
-:class:`nilearn.decomposition.DictLearning` for set of brain atlas maps.
+:func:`~nilearn.datasets.fetch_development_fmri` and
+:class:`~nilearn.decomposition.DictLearning` for set of brain atlas maps.
 
 This example can also be inspired to apply the same steps
 to even regions extraction
 using :term:`ICA` maps.
 In that case, idea would be to replace
 :term:`Dictionary learning` to canonical :term:`ICA` decomposition
-using :class:`nilearn.decomposition.CanICA`
+using :class:`~nilearn.decomposition.CanICA`
 
 Please see the related documentation
-of :class:`nilearn.regions.RegionExtractor` for more details.
+of :class:`~nilearn.regions.RegionExtractor` for more details.
 
 """