Merge branch 'main' into method

bids-apps · Dec 14, 2023 · 92f408d · 92f408d
2 parents d2a4fad + 321705e
commit 92f408d
Show file tree

Hide file tree

Showing 19 changed files with 235 additions and 118 deletions.
diff --git a/.github/workflows/run_precommit.yml b/.github/workflows/run_precommit.yml
@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+    - uses: pre-commit/[email protected]
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -43,6 +43,9 @@ jobs:
     - uses: actions/checkout@v4
       with:
         fetch-depth: 0
+    - uses: actions/setup-python@v5
+    - name: install tox
+      run: pip install tox
     - uses: actions/cache@v3
       id: cache
       env:
@@ -54,19 +57,7 @@ jobs:
     - if: ${{ steps.cache.outputs.cache-hit != 'true' }}
       name: Download fmriprep derivative of ds000017
       id: download
-      run: |
-        mkdir -p /home/runner/work/giga_connectome/giga_connectome/giga_connectome/data/test_data
-        cd /home/runner/work/giga_connectome/giga_connectome/giga_connectome/data/test_data
-        wget --retry-connrefused \
-          --waitretry=5 \
-          --read-timeout=20 \
-          --timeout=15 \
-          -t 0 \
-          -q \
-          -O ds000017.tar.gz \
-          "https://zenodo.org/record/8091903/files/ds000017-fmriprep22.0.1-downsampled-nosurface.tar.gz?download=1"
-        tar -xzf ds000017.tar.gz
-        rm ds000017.tar.gz
+      run: tox -e test_data
 
   build:
     runs-on: ubuntu-latest

diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,7 @@
 */_version.py
 */data/test_data/
 output/
+work/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

diff --git a/CITATION.cff b/CITATION.cff
@@ -22,8 +22,8 @@ authors:
     email: [email protected]
   - family-names: Dessain
     given-names: Quentin
-  - family-names: Natasha 
+  - family-names: Natasha
     given-names: Clarke
-     
+
 
 license: MIT
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -25,6 +25,7 @@
     "sphinx.ext.autodoc",
     "sphinx.ext.autosummary",
     "sphinx.ext.napoleon",
+    "sphinxarg.ext",
 ]
 
 templates_path = ["_templates"]
@@ -35,7 +36,6 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
 html_theme = "sphinx_rtd_theme"
-html_static_path = ["_static"]
 
 # -- Options for myst_parser -------------------------------------------------
 myst_enable_extensions = ["colon_fence"]
diff --git a/docs/source/contributing.md b/docs/source/contributing.md
@@ -27,6 +27,14 @@ pip install -e .[dev]
 pre-commit install
 ```
 
+5. Install the data required for testing from zenodo
+
+This can be done using tox by running:
+
+```bash
+tox -e test_data
+```
+
 ## Contributing to code
 
 This is a very generic workflow.
@@ -51,7 +59,7 @@ git checkout -b your_branch
 5. Run the tests locally; you can run spectfic tests to speed up the process:
 
 ```bash
-pytest -v giga_connectome/tests/tests/test_connectome.py::test_calculate_intranetwork_correlation
+pytest -v giga_connectome/tests/test_connectome.py::test_calculate_intranetwork_correlation
 ```
 
 6. push your changes to your online fork. If this is the first commit, you might want to set up the remote tracking:
@@ -75,7 +83,7 @@ The workflow is the same as code contributions, with some minor differences.
 1. Install the `[doc]` dependencies.
 
 ```bash
-pip install -e .[doc]
+pip install -e '.[doc]'
 ```
 
 2. After making changes, build the docs locally:
@@ -104,7 +112,7 @@ This tells the development team that your pull request is a "work-in-progress",
 
 One your PR is ready a member of the development team will review your changes to confirm that they can be merged into the main codebase.
 
-## Making an release
+## Making a release
 
 Currently this project is not pushed to PyPi.
 We simply tag the version on the repository so users can reference the version of installation.

diff --git a/docs/source/usage.md b/docs/source/usage.md
@@ -1,48 +1,17 @@
 # Usage Notes
 
-```bash
-usage: giga_connectome [-h] [-v] [--participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]] [-w WORK_DIR] [--atlas ATLAS]
-                       [--denoise-strategy DENOISE_STRATEGY] [--standardize {zscore,psc}] [--smoothing_fwhm SMOOTHING_FWHM] [--reindex-bids]
-                       [--bids-filter-file BIDS_FILTER_FILE]
-                       bids_dir output_dir {participant,group}
-
-Generate connectome based on denoising strategy for fmriprep processed dataset.
-
-positional arguments:
-  bids_dir              The directory with the input dataset (e.g. fMRIPrep derivative)formatted according to the BIDS standard.
-  output_dir            The directory where the output files should be stored.
-  {participant,group}   Level of the analysis that will be performed. Only group level is allowed as we need to generate a dataset inclusive brain mask.
-
-optional arguments:
-  -h, --help            show this help message and exit
-  -v, --version         show program's version number and exit
-  --participant_label PARTICIPANT_LABEL [PARTICIPANT_LABEL ...]
-                        The label(s) of the participant(s) that should be analyzed. The label corresponds to sub-<participant_label> from the BIDS spec (so it does not include 'sub-'). If this parameter is not provided all subjects should be analyzed. Multiple participants can be specified with a space separated list.
-  -w WORK_DIR, --work-dir WORK_DIR
-                        Path where intermediate results should be stored.
-  --atlas ATLAS         The choice of atlas for time series extraction. Default atlas choices are: 'Schaefer20187Networks, 'MIST', 'DiFuMo'. User can pass a path to a json file containing configuration for their own choice of atlas. The default is 'MIST'.
-  --denoise-strategy DENOISE_STRATEGY
-                        The choice of post-processing for denoising. The default choices are: 'simple', 'simple+gsr', 'scrubbing.2', 'scrubbing.2+gsr', 'scrubbing.5', 'scrubbing.5+gsr', 'acompcor50', 'icaaroma'. User can pass a path to a json file containing configuration for their own choice of denoising strategy. The defaultis 'simple'.
-  --standardize {zscore,psc}
-                        The choice of signal standardization. The choices are z score or percent signal change (psc). The default is 'zscore'.
-  --smoothing_fwhm SMOOTHING_FWHM
-                        Size of the full-width at half maximum in millimeters of the spatial smoothing to apply to the signal. The default is 5.0.
-  --reindex-bids        Reindex BIDS data set, even if layout has already been created.
-  --bids-filter-file BIDS_FILTER_FILE
-                        A JSON file describing custom BIDS input filters using PyBIDS.We use the same format as described in fMRIPrep documentation: https://fmriprep.org/en/latest/faq.html#how-do-i-select-only-certain-files-to-be-input-to-fmriprepHowever, the query filed should always be 'bold'
+## Command line interface
 
+```{eval-rst}
+.. argparse::
+   :prog: giga_connectome
+   :module: giga_connectome.run
+   :func: global_parser
 ```
 
-When performing `participant` level analysis, the output is a HDF5 file per participant that was passed to `--participant_label` or all subjects under `bids_dir`.
-The output file name is: `sub-<participant_id>_atlas-<atlas_name>_desc-<denoising_strategy>.h5`
-
-When performing `group` level analysis, the output is a HDF5 file per participant that was passed to `--participant_label` or all subjects under `bids_dir`.
-The output file name is: `atlas-<atlas_name>_desc-<denoising_strategy>.h5`
-The file will contain time series and connectomes of each subject, as well as group average connectomes.
-
 ## Writing configuration files
 
-All preset can be found in `giga_connectome/data`
+All preset can be found in [`giga_connectome/data`](https://github.com/SIMEXP/giga_connectome/tree/main/giga_connectome/data).
 
 ### Denoising strategy
 
@@ -62,13 +31,14 @@ In a `json` file, define the customised strategy in the following format:
 }
 ```
 
-See examples in `giga_connectome/data/denoise_strategy`.
+See examples in [`giga_connectome/data/denoise_strategy`](https://github.com/SIMEXP/giga_connectome/tree/main/giga_connectome/data/denoise_strategy).
 
 ### Atlas
 
 After the atlas files are organised according to the [TemplateFlow](https://www.templateflow.org/python-client/0.7.1/naming.html) convention.
 
 A minimal set up should look like this:
+
 ```
 my_atlas/
   └──tpl-MNI152NLin2009cAsym/  # template directory of a valid template name
@@ -96,4 +66,4 @@ In a `json` file, define the customised atlas. We will use the atlas above as an
 }
 ```
 
-See examples in `giga_connectome/data/atlas`.
+See examples in [`giga_connectome/data`](https://github.com/SIMEXP/giga_connectome/tree/main/giga_connectome/data).
diff --git a/giga_connectome/atlas.py b/giga_connectome/atlas.py
@@ -9,6 +9,10 @@
 from nibabel import Nifti1Image
 from pkg_resources import resource_filename
 
+from giga_connectome.logger import gc_logger
+
+gc_log = gc_logger()
+
 
 PRESET_ATLAS = ["DiFuMo", "MIST", "Schaefer20187Networks"]
 
@@ -42,7 +46,7 @@ def load_atlas_setting(atlas: Union[str, Path, dict]):
         Path to the atlas files.
     """
     atlas_config = _check_altas_config(atlas)
-    print(atlas_config)
+    gc_log.info(atlas_config)
 
     # load template flow
     templateflow_dir = atlas_config.get("templateflow_dir")
@@ -104,7 +108,7 @@ def resample_atlas_collection(
     List of pathlib.Path
         Paths to atlases sampled to group level grey matter mask.
     """
-    print("Resample atlas to group grey matter mask.")
+    gc_log.info("Resample atlas to group grey matter mask.")
     resampled_atlases = []
     for desc in tqdm(atlas_config["file_paths"]):
         parcellation = atlas_config["file_paths"][desc]

diff --git a/giga_connectome/logger.py b/giga_connectome/logger.py
@@ -0,0 +1,20 @@
+"""General logger for the cohort_creator package."""
+from __future__ import annotations
+
+import logging
+
+from rich.logging import RichHandler
+
+
+def gc_logger(log_level: str = "INFO") -> logging.Logger:
+    # FORMAT = '\n%(asctime)s - %(name)s - %(levelname)s\n\t%(message)s\n'
+    FORMAT = "%(message)s"
+
+    logging.basicConfig(
+        level=log_level,
+        format=FORMAT,
+        datefmt="[%X]",
+        handlers=[RichHandler()],
+    )
+
+    return logging.getLogger("giga_connectome")
diff --git a/giga_connectome/mask.py b/giga_connectome/mask.py
@@ -19,6 +19,10 @@
 
 from giga_connectome.atlas import resample_atlas_collection
 
+from giga_connectome.logger import gc_logger
+
+gc_log = gc_logger()
+
 
 def generate_gm_mask_atlas(
     working_dir: Path,
@@ -63,7 +67,6 @@ def generate_group_mask(
     template: str = "MNI152NLin2009cAsym",
     templateflow_dir: Optional[Path] = None,
     n_iter: int = 2,
-    verbose: int = 1,
 ) -> Nifti1Image:
     """
     Generate a group EPI grey matter mask, and overlaid with a MNI grey
@@ -88,9 +91,6 @@ def generate_group_mask(
         Number of repetitions of dilation and erosion steps performed in
         scipy.ndimage.binary_closing function.
 
-    verbose :
-        Level of verbosity.
-
     Keyword Arguments
     -----------------
     Used to filter the cirret
@@ -102,12 +102,10 @@ def generate_group_mask(
     nibabel.nifti1.Nifti1Image
         EPI (grey matter) mask for the current group of subjects.
     """
-    if verbose > 1:
-        print(f"Found {len(imgs)} masks")
-    if exclude := _check_mask_affine(imgs, verbose):
+    gc_log.debug(f"Found {len(imgs)} masks")
+    if exclude := _check_mask_affine(imgs):
         imgs, __annotations__ = _get_consistent_masks(imgs, exclude)
-        if verbose > 1:
-            print(f"Remaining: {len(imgs)} masks")
+        gc_log.debug(f"Remaining: {len(imgs)} masks")
 
     # templateflow environment setting to get around network issue
     if templateflow_dir and templateflow_dir.exists():
@@ -129,7 +127,7 @@ def generate_group_mask(
         memory=None,
         verbose=0,
     )
-    print(
+    gc_log.info(
         f"Group EPI mask affine:\n{group_epi_mask.affine}"
         f"\nshape: {group_epi_mask.shape}"
     )
@@ -204,7 +202,7 @@ def _get_consistent_masks(
 
 
 def _check_mask_affine(
-    mask_imgs: List[Union[Path, str, Nifti1Image]], verbose: int = 1
+    mask_imgs: List[Union[Path, str, Nifti1Image]]
 ) -> Union[list, None]:
     """Given a list of input mask images, show the most common affine matrix
     and subjects with different values.
@@ -215,9 +213,6 @@ def _check_mask_affine(
         See :ref:`extracting_data`.
         3D or 4D EPI image with same affine.
 
-    verbose :
-        Level of verbosity.
-
     Returns
     -------
 
@@ -244,12 +239,11 @@ def _check_mask_affine(
     common_affine = max(
         set(header_info["affine"]), key=header_info["affine"].count
     )
-    if verbose > 0:
-        print(
-            f"We found {len(set(header_info['affine']))} unique affine "
-            f"matrices. The most common one is "
-            f"{key_to_header[common_affine]}"
-        )
+    gc_log.info(
+        f"We found {len(set(header_info['affine']))} unique affine "
+        f"matrices. The most common one is "
+        f"{key_to_header[common_affine]}"
+    )
     odd_balls = set(header_info["affine"]) - {common_affine}
     if not odd_balls:
         return None
@@ -259,18 +253,16 @@ def _check_mask_affine(
         ob_index = [
             i for i, aff in enumerate(header_info["affine"]) if aff == ob
         ]
-        if verbose > 1:
-            print(
-                "The following subjects has a different affine matrix "
-                f"({key_to_header[ob]}) comparing to the most common value: "
-                f"{mask_imgs[ob_index]}."
-            )
-        exclude += ob_index
-    if verbose > 0:
-        print(
-            f"{len(exclude)} out of {len(mask_imgs)} has "
-            "different affine matrix. Ignore when creating group mask."
+        gc_log.debug(
+            "The following subjects has a different affine matrix "
+            f"({key_to_header[ob]}) comparing to the most common value: "
+            f"{mask_imgs[ob_index]}."
         )
+        exclude += ob_index
+    gc_log.info(
+        f"{len(exclude)} out of {len(mask_imgs)} has "
+        "different affine matrix. Ignore when creating group mask."
+    )
     return sorted(exclude)
 
 
@@ -284,7 +276,9 @@ def _check_pregenerated_masks(template, working_dir, atlas):
     if not group_mask.exists():
         group_mask = None
     else:
-        print(f"Found pregenerated group level grey matter mask: {group_mask}")
+        gc_log.info(
+            f"Found pregenerated group level grey matter mask: {group_mask}"
+        )
 
     # atlas
     resampled_atlases = []
@@ -301,8 +295,8 @@ def _check_pregenerated_masks(template, working_dir, atlas):
     if not all(all_exist):
         resampled_atlases = None
     else:
-        print(
-            f"Found resampled atlases: {resampled_atlases}. Skipping group "
-            "level mask generation step."
+        gc_log.info(
+            f"Found resampled atlases:\n{[str(x) for x in resampled_atlases]}."
+            "\nSkipping group level mask generation step."
         )
     return group_mask, resampled_atlases