eegdash 0.0.9__tar.gz → 0.2.0__tar.gz

eegdash-0.2.0/.github/workflows/pre-commit.yaml

@@ -0,0 +1,14 @@
+name: pre-commit-codestyle
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.number }}-${{ github.event.ref }}
+  cancel-in-progress: true
+
+on: [push]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+    - uses: pre-commit/action@v3.0.1

eegdash-0.2.0/.github/workflows/tests.yml

@@ -0,0 +1,49 @@
+name: tests
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.number }}-${{ github.event.ref }}
+  cancel-in-progress: true
+on:
+  push:
+    branches:
+      - "*"
+  pull_request:
+    branches:
+      - '*' # all branches, including forks
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ "ubuntu-latest", "macos-latest", "windows-latest" ]
+        python-version: ["3.10", "3.12"] # first and last supported Python version
+    steps:
+    ## Install Braindecode
+    - name: Checking Out Repository
+      uses: actions/checkout@v4
+    # Cache MNE Data
+    # The cache key here is fixed except for os
+    # so if you download a new mne dataset in the code, best to manually increment the key below
+    - name: Create/Restore MNE Data Cache
+      id: cache-mne_data
+      uses: actions/cache@v3
+      with:
+        path: ~/mne_data
+        key: ${{ runner.os }}-v3
+
+    - name: Install uv and set the python version
+      uses: astral-sh/setup-uv@v5
+      with:
+        enable-cache: true
+        python-version: ${{ matrix.python-version }}
+    - name: Show Python Version
+      run: python --version
+    - name: Install EEGDash from Current Checkout
+      run: uv pip install -e .[tests]
+    # Show EEGDash Version
+    - name: Show EEGDash Version
+      run: python -c "import eegdash; print(eegdash.__version__)"
+    - name: Run Tests
+      run: pytest -vvv -s --tb=long --durations=0 --log-cli-level=INFO --cov=eegdash --cov-report=xml tests --verbose 
+

eegdash-0.2.0/.gitignore

@@ -0,0 +1,17 @@
+*.egg-info
+*.npy
+*/*.npy
+*/*/*.npy
+eegdash/data/
+**/__pycache__/
+.venv
+.secret
+note
+tests/.testeegdash/
+dist/
+**/.eegdash_cache/
+**/*/eegdash.egg-info/
+.env
+tests/data/
+.ruff_cache/
+.vscode/

eegdash-0.2.0/.pre-commit-config.yaml

@@ -0,0 +1,48 @@
+default_language_version:
+    python: python3
+ci:
+    autofix_commit_msg: '[pre-commit.ci] auto fixes from pre-commit.com hooks'
+    autofix_prs: true
+    autoupdate_branch: master
+    autoupdate_commit_msg: '[pre-commit.ci] pre-commit autoupdate'
+    autoupdate_schedule: weekly
+    skip: []
+    submodules: false
+repos:
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.7
+    hooks:
+    -   id: ruff
+        name: ruff lint & format
+        args:
+        - --fix
+        - --show-fixes
+        # Selects all rules from your original config (E,W,F,I,D) and enables import sorting (I)
+        # and unused import removal (F401 is part of 'F' and is no longer ignored).
+        - --select=E,W,F,D,NPY201
+        - --ignore=E402,E501,D100,D101,D102,D103,D104,D105,D107,D205,D400,D415,D417,F403,D401,E741,E722,D419
+        files: ^(eegdash|docs|examples|notebooks|scripts|tests)/
+        exclude: \.ipynb$
+    -   id: ruff-format
+        name: ruff format code
+-   repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+    -   id: codespell
+        args:
+        - --ignore-words-list=carin,splitted,meaned,wil,whats,additionals,alle,alot,bund,currenty,datas,farenheit,falsy,fo,haa,hass,iif,incomfort,ines,ist,nam,nd,pres,pullrequests,resset,rime,ser,serie,te,technik,ue,unsecure,withing,zar,mane,THIRDPARTY
+        - --skip="./.*,*.csv,*.json,*.ambr,*.toml"
+        - --quiet-level=2
+        exclude_types:
+        - csv
+        - json
+-   repo: https://github.com/asottile/blacken-docs
+    rev: 1.19.1
+    hooks:
+    -   id: blacken-docs
+        exclude: ^.github|CONTRIBUTING.md
+-   repo: https://github.com/PyCQA/isort
+    rev: 6.0.1
+    hooks:
+    -   id: isort
+        exclude: ^\.gitignore

eegdash-0.2.0/.readthedocs.yaml

@@ -0,0 +1,24 @@
+
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.13"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/conf.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+# python:
+#    install:
+#    - requirements: docs/requirements.txt
+

eegdash-0.2.0/DevNotes.md

@@ -0,0 +1,29 @@
+## Install locally
+pip install -r requirements.txt
+
+pip uninstall eegdash -y
+python -m pip install --editable /Users/arno/Python/EEG-Dash-Data
+# Warning use the exact command above, pip install by itself might not work
+
+### check if working from different folders
+python -c "from eegdash import EEGDashDataset; print(EEGDashDataset)"
+
+## Run hooks
+pip install pre-commit
+pre-commit install
+pre-commit run --all-files
+
+## Create package and release on Pypi
+Documentation is at https://packaging.python.org/en/latest/tutorials/packaging-projects/
+- Update version in pyproject.toml
+- Run "python -m build"
+- "python -m twine upload --repository testpypi dist/*" OR "python -m twine upload dist/*"
+Look for API token in email (different for test and regular)
+
+## Populate database
+- Log on mongodb.com with sccn user sccn3709@gmail.com (see email for pass)
+- Change eegdash or eegdashstaging in main.py
+- Run script/data_ingest.py
+
+# Remount
+sudo sshfs -o allow_other,IdentityFile=/home/dung/.ssh/id_rsa arno@login.expanse.sdsc.edu:/expanse/projects/nemar /mnt/nemar/

{eegdash-0.0.9 → eegdash-0.2.0}/LICENSE

@@ -4,6 +4,7 @@ Copyright (C) 2024-2025
 
 Young Truong, UCSD, dt.young112@gmail.com
 Arnaud Delorme, UCSD, adelorme@ucsd.edu
+Bruno Aristimunha, b.aristimunha@gmail.com
 
 This program is free software; you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by

{eegdash-0.0.9/src/eegdash.egg-info → eegdash-0.2.0}/PKG-INFO

@@ -1,14 +1,15 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.0.9
+Version: 0.2.0
 Summary: EEG data for machine learning
-Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>
+Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>, Bruno Aristimunha <b.aristimunha@gmail.com>
 License: GNU General Public License
         
         Copyright (C) 2024-2025
         
         Young Truong, UCSD, dt.young112@gmail.com
         Arnaud Delorme, UCSD, adelorme@ucsd.edu
+        Bruno Aristimunha, b.aristimunha@gmail.com
         
         This program is free software; you can redistribute it and/or modify
         it under the terms of the GNU General Public License as published by
@@ -24,35 +25,69 @@ License: GNU General Public License
         along with this program; if not, write to the Free Software
         Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1.07  USA
         
-Project-URL: Homepage, https://eegdash.org
-Project-URL: Issues, https://github.com/sccn/EEGDash/issues
-Classifier: Programming Language :: Python :: 3
+Project-URL: Homepage, https://github.com/sccn/EEG-Dash-Data
+Project-URL: Issues, https://github.com/sccn/EEG-Dash-Data/issues
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python
+Classifier: Topic :: Software Development
+Classifier: Topic :: Scientific/Engineering
+Classifier: Development Status :: 3 - Alpha
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: Unix
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: xarray
+Requires-Dist: braindecode>=1.0
+Requires-Dist: mne_bids>=0.16.0
+Requires-Dist: numba
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pybids
+Requires-Dist: pymongo
 Requires-Dist: python-dotenv
 Requires-Dist: s3fs
-Requires-Dist: mne
-Requires-Dist: pynwb
-Requires-Dist: h5py
-Requires-Dist: pymongo
-Requires-Dist: joblib
-Requires-Dist: braindecode
-Requires-Dist: mne-bids
-Requires-Dist: pybids
-Requires-Dist: pymatreader
-Requires-Dist: pyarrow
+Requires-Dist: scipy
 Requires-Dist: tqdm
-Requires-Dist: numba
+Requires-Dist: xarray
+Provides-Extra: tests
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: pytest-cov; extra == "tests"
+Requires-Dist: codecov; extra == "tests"
+Requires-Dist: pytest_cases; extra == "tests"
+Provides-Extra: dev
+Requires-Dist: pre-commit; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx_gallery; extra == "docs"
+Requires-Dist: sphinx_rtd_theme; extra == "docs"
+Requires-Dist: numpydoc; extra == "docs"
+Provides-Extra: all
+Requires-Dist: pytest; extra == "all"
+Requires-Dist: pytest-cov; extra == "all"
+Requires-Dist: codecov; extra == "all"
+Requires-Dist: pytest_cases; extra == "all"
+Requires-Dist: pre-commit; extra == "all"
+Requires-Dist: sphinx; extra == "all"
+Requires-Dist: sphinx_gallery; extra == "all"
+Requires-Dist: sphinx_rtd_theme; extra == "all"
+Requires-Dist: numpydoc; extra == "all"
 Dynamic: license-file
 
 # EEG-Dash
+
 To leverage recent and ongoing advancements in large-scale computational methods and to ensure the preservation of scientific data generated from publicly funded research, the EEG-DaSh data archive will create a data-sharing resource for MEEG (EEG, MEG) data contributed by collaborators for machine learning (ML) and deep learning (DL) applications. 
 
 ## Data source
+
 The data in EEG-DaSh originates from a collaboration involving 25 laboratories, encompassing 27,053 participants. This extensive collection includes MEEG data, which is a combination of EEG and MEG signals. The data is sourced from various studies conducted by these labs, involving both healthy subjects and clinical populations with conditions such as ADHD, depression, schizophrenia, dementia, autism, and psychosis. Additionally, data spans different mental states like sleep, meditation, and cognitive tasks. In addition, EEG-DaSh will incorporate a subset of the data converted from NEMAR, which includes 330 MEEG BIDS-formatted datasets, further expanding the archive with well-curated, standardized neuroelectromagnetic data.
 
 ## Featured data
@@ -72,9 +107,11 @@ The following HBN datasets are currently featured on EEGDash. Documentation abou
 A total of [246 other datasets](datasets.md) are also available through EEGDash. 
 
 ## Data format
+
 EEGDash queries return a **Pytorch Dataset** formatted to facilitate machine learning (ML) and deep learning (DL) applications. PyTorch Datasets are the best format for EEGDash queries because they provide an efficient, scalable, and flexible structure for machine learning (ML) and deep learning (DL) applications. They allow seamless integration with PyTorch’s DataLoader, enabling efficient batching, shuffling, and parallel data loading, which is essential for training deep learning models on large EEG datasets.
 
 ## Data preprocessing
+
 EEGDash datasets are processed using the popular [BrainDecode](https://braindecode.org/stable/index.html) library. In fact, EEGDash datasets are BrainDecode datasets, which are themselves PyTorch datasets. This means that any preprocessing possible on BrainDecode datasets is also possible on EEGDash datasets. Refer to [BrainDecode](https://braindecode.org/stable/index.html) tutorials for guidance on preprocessing EEG data.
 
 ## EEG-Dash usage
@@ -90,7 +127,10 @@ To use the data from a single subject, enter:
 
 ```python
 from eegdash import EEGDashDataset
-ds_NDARDB033FW5 = EEGDashDataset({'dataset': 'ds005514', 'task': 'RestingState', 'subject': 'NDARDB033FW5'})
+
+ds_NDARDB033FW5 = EEGDashDataset(
+    {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
+)
 ```
 
 This will search and download the metadata for the task **RestingState** for subject **NDARDB033FW5** in BIDS dataset **ds005514**. The actual data will not be downloaded at this stage. Following standard practice, data is only downloaded once it is processed. The **ds_NDARDB033FW5** object is a fully functional BrainDecode dataset, which is itself a PyTorch dataset. This [tutorial](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_eoec.ipynb) shows how to preprocess the EEG data, extracting portions of the data containing eyes-open and eyes-closed segments, then perform eyes-open vs. eyes-closed classification using a (shallow) deep-learning model. 
@@ -99,7 +139,10 @@ To use the data from multiple subjects, enter:
 
 ```python
 from eegdash import EEGDashDataset
-ds_ds005505rest = EEGDashDataset({'dataset': 'ds005505', 'task': 'RestingState'}, target_name='sex')
+
+ds_ds005505rest = EEGDashDataset(
+    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
+)
 ```
 
 This will search and download the metadata for the task 'RestingState' for all subjects in BIDS dataset 'ds005505' (a total of 136). As above, the actual data will not be downloaded at this stage so this command is quick to execute. Also, the target class for each subject is assigned using the target_name parameter. This means that this object is ready to be directly fed to a deep learning model, although the [tutorial script](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_sex_classification.ipynb) performs minimal processing on it, prior to training a deep-learning model. Because 14 gigabytes of data are downloaded, this tutorial takes about 10 minutes to execute.
@@ -121,3 +164,7 @@ EEG-DaSh is a collaborative initiative between the United States and Israel, sup
 
 
 
+python3 -m pip install --upgrade build
+python3 -m build
+python3 -m pip install --upgrade twine
+python3 -m twine upload --repository eegdash dist/*

{eegdash-0.0.9 → eegdash-0.2.0}/README.md

@@ -1,7 +1,9 @@
 # EEG-Dash
+
 To leverage recent and ongoing advancements in large-scale computational methods and to ensure the preservation of scientific data generated from publicly funded research, the EEG-DaSh data archive will create a data-sharing resource for MEEG (EEG, MEG) data contributed by collaborators for machine learning (ML) and deep learning (DL) applications. 
 
 ## Data source
+
 The data in EEG-DaSh originates from a collaboration involving 25 laboratories, encompassing 27,053 participants. This extensive collection includes MEEG data, which is a combination of EEG and MEG signals. The data is sourced from various studies conducted by these labs, involving both healthy subjects and clinical populations with conditions such as ADHD, depression, schizophrenia, dementia, autism, and psychosis. Additionally, data spans different mental states like sleep, meditation, and cognitive tasks. In addition, EEG-DaSh will incorporate a subset of the data converted from NEMAR, which includes 330 MEEG BIDS-formatted datasets, further expanding the archive with well-curated, standardized neuroelectromagnetic data.
 
 ## Featured data
@@ -21,9 +23,11 @@ The following HBN datasets are currently featured on EEGDash. Documentation abou
 A total of [246 other datasets](datasets.md) are also available through EEGDash. 
 
 ## Data format
+
 EEGDash queries return a **Pytorch Dataset** formatted to facilitate machine learning (ML) and deep learning (DL) applications. PyTorch Datasets are the best format for EEGDash queries because they provide an efficient, scalable, and flexible structure for machine learning (ML) and deep learning (DL) applications. They allow seamless integration with PyTorch’s DataLoader, enabling efficient batching, shuffling, and parallel data loading, which is essential for training deep learning models on large EEG datasets.
 
 ## Data preprocessing
+
 EEGDash datasets are processed using the popular [BrainDecode](https://braindecode.org/stable/index.html) library. In fact, EEGDash datasets are BrainDecode datasets, which are themselves PyTorch datasets. This means that any preprocessing possible on BrainDecode datasets is also possible on EEGDash datasets. Refer to [BrainDecode](https://braindecode.org/stable/index.html) tutorials for guidance on preprocessing EEG data.
 
 ## EEG-Dash usage
@@ -39,7 +43,10 @@ To use the data from a single subject, enter:
 
 ```python
 from eegdash import EEGDashDataset
-ds_NDARDB033FW5 = EEGDashDataset({'dataset': 'ds005514', 'task': 'RestingState', 'subject': 'NDARDB033FW5'})
+
+ds_NDARDB033FW5 = EEGDashDataset(
+    {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
+)
 ```
 
 This will search and download the metadata for the task **RestingState** for subject **NDARDB033FW5** in BIDS dataset **ds005514**. The actual data will not be downloaded at this stage. Following standard practice, data is only downloaded once it is processed. The **ds_NDARDB033FW5** object is a fully functional BrainDecode dataset, which is itself a PyTorch dataset. This [tutorial](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_eoec.ipynb) shows how to preprocess the EEG data, extracting portions of the data containing eyes-open and eyes-closed segments, then perform eyes-open vs. eyes-closed classification using a (shallow) deep-learning model. 
@@ -48,7 +55,10 @@ To use the data from multiple subjects, enter:
 
 ```python
 from eegdash import EEGDashDataset
-ds_ds005505rest = EEGDashDataset({'dataset': 'ds005505', 'task': 'RestingState'}, target_name='sex')
+
+ds_ds005505rest = EEGDashDataset(
+    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
+)
 ```
 
 This will search and download the metadata for the task 'RestingState' for all subjects in BIDS dataset 'ds005505' (a total of 136). As above, the actual data will not be downloaded at this stage so this command is quick to execute. Also, the target class for each subject is assigned using the target_name parameter. This means that this object is ready to be directly fed to a deep learning model, although the [tutorial script](https://github.com/sccn/EEGDash/blob/develop/notebooks/tutorial_sex_classification.ipynb) performs minimal processing on it, prior to training a deep-learning model. Because 14 gigabytes of data are downloaded, this tutorial takes about 10 minutes to execute.
@@ -70,3 +80,7 @@ EEG-DaSh is a collaborative initiative between the United States and Israel, sup
 
 
 
+python3 -m pip install --upgrade build
+python3 -m build
+python3 -m pip install --upgrade twine
+python3 -m twine upload --repository eegdash dist/*