merge with origin

Author: dungscout96

.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: [pull_request]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+    - uses: pre-commit/[email protected]

.github/workflows/tests.yml

@@ -0,0 +1,45 @@
+name: tests
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.number }}-${{ github.event.ref }}
+  cancel-in-progress: true
+on:
+  push:
+    branches:
+      - "master"
+  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: ["3.9", "3.10", "3.11"]
+    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
+    - uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Show Python Version
+      run: python --version
+    # Update pip
+    - name: Update pip
+      run: python -m pip install --upgrade pip
+    - name: Install EEGDash from Current Checkout
+      run: pip install -e .
+    # Show Braindecode Version
+    - run: python -c "import eegdash; print(eegdash.__version__)"

.gitignore

@@ -1,5 +1,5 @@
 old
-src/EEGDash.egg-info
+*.egg-info
 *.npy
 */*.npy
 */*/*.npy

.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+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: quarterly
+    skip: []
+    submodules: false
+repos:
+-   repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.11.7
+    hooks:
+    -   id: ruff
+        name: ruff lint docs & examples
+        args:
+        - --fix
+        - --select=E,W,F,I,D
+        - --ignore=E402,E501,F401,D103,D400,D100,D101,D102,D105,D107,D415,D417,D205
+        files: ^(docs|examples)/
+    -   id: ruff
+        name: ruff lint eegdash preview
+        args:
+        - --fix
+        - --preview
+        - --select=NPY201
+        - --ignore=D100,D101,D102,D105,D107,D415,D417,D205
+        files: ^eegdash/
+    -   id: ruff
+        name: ruff lint docs & examples
+        args:
+        - --fix
+        - --select=D
+        - --ignore=D103,D400,E402,D100,D101,D102,D105,D107,D415,D417,D205
+        files: ^(docs|examples)/
+    -   id: ruff-format
+        name: ruff format code
+        files: ^(eegdash|docs|examples)/
+-   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
+        exclude: ^tests/|generated/^.github
+-   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

DevNotes.md

@@ -5,5 +5,5 @@ pip install -r requirements.txt
 ## signalstore mongodb
 - Check args functions to double check input to db query
 - Create_index to the collection once its created to speed up querying
-- `find` has deserialization to convert timestamp to correct milisecond format and json_schema from bytes to dict
+- `find` has deserialization to convert timestamp to correct millisecond format and json_schema from bytes to dict
 - `add` has serialization before insert into db

README.md

@@ -39,7 +39,10 @@ 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 +51,10 @@ 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.

documents/architecture2.pptx renamed to docs/architecture2.pptx

@@ -6,26 +6,26 @@
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
-project = 'EEGDash'
-copyright = '2025, Arnaud Delorme, Dung Truong'
-author = 'Arnaud Delorme, Dung Truong'
+project = "EEGDash"
+copyright = "2025, Arnaud Delorme, Dung Truong"
+author = "Arnaud Delorme, Dung Truong"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-extensions = ['sphinx.ext.autodoc']
-
-templates_path = ['_templates']
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+extensions = ["sphinx.ext.autodoc"]
 
+templates_path = ["_templates"]
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 
 # -- Options for HTML output -------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
-html_theme = 'alabaster'
-html_static_path = ['_static']
+html_theme = "alabaster"
+html_static_path = ["_static"]
 
 import os
 import sys
-sys.path.insert(0, os.path.abspath('..'))
+
+sys.path.insert(0, os.path.abspath(".."))

docs/conf.py

@@ -1,29 +1,34 @@
 #!/usr/bin/env python3
 import sys
+
 import pandas as pd
 
+
 def excel_to_markdown(filename, sheet_name=0):
     # Read the specified sheet from the Excel file
     df = pd.read_excel(filename, sheet_name=sheet_name)
-    
+
     # Convert dataset IDs into Markdown links
     # Format: [dataset_id](https://nemar.org/dataexplorer/detail?dataset_id=dataset_id)
-    df['DatasetID'] = df['DatasetID'].astype(str).apply(
-        lambda x: f"[{x}](https://nemar.org/dataexplorer/detail?dataset_id={x})"
+    df["DatasetID"] = (
+        df["DatasetID"]
+        .astype(str)
+        .apply(lambda x: f"[{x}](https://nemar.org/dataexplorer/detail?dataset_id={x})")
     )
-    
+
     # Replace "Schizophrenia/Psychosis" with "Psychosis" in the entire DataFrame
     df = df.replace("Schizophrenia/Psychosis", "Psychosis")
-    
+
     # Convert the DataFrame to a Markdown table (excluding the index)
     markdown = df.to_markdown(index=False)
     return markdown
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     if len(sys.argv) < 2:
         print("Usage: python script.py <excel_filename> [sheet_name]")
         sys.exit(1)
-    
+
     excel_filename = sys.argv[1]
     sheet = sys.argv[2] if len(sys.argv) > 2 else 0