Feature/sept2025 update output

.github/workflows/ci.yml

@@ -0,0 +1,99 @@
+name: CI
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.8, 3.9]
+        cuda-version: ['11.8.0']
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install CUDA
+      uses: Jimver/cuda-toolkit@v0.2.11
+      with:
+        cuda: ${{ matrix.cuda-version }}
+        method: 'network'
+        sub-packages: '["nvcc", "cudart", "cublas", "curand", "cusolver", "cusparse"]'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pytest pytest-cov
+        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+        pip install -r requirements.txt
+        pip install -e .
+
+    - name: Run tests
+      run: |
+        pytest tests/ --cov=XuanjiNovo --cov-report=xml
+
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v3
+      with:
+        file: ./coverage.xml
+        flags: unittests
+        fail_ci_if_error: true
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 black isort mypy
+
+    - name: Run linters
+      run: |
+        flake8 XuanjiNovo tests
+        black --check XuanjiNovo tests
+        isort --check-only XuanjiNovo tests
+        mypy XuanjiNovo
+
+  build-extensions:
+    runs-on: ubuntu-latest
+    needs: [test, lint]
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.9'
+
+    - name: Install CUDA
+      uses: Jimver/cuda-toolkit@v0.2.11
+      with:
+        cuda: '11.8.0'
+        method: 'network'
+        sub-packages: '["nvcc", "cudart"]'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install ninja
+        pip install -r requirements.txt
+
+    - name: Build C++ extensions
+      run: |
+        python setup.py build_ext --inplace

.pre-commit-config.yaml

@@ -0,0 +1,54 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+    -   id: debug-statements
+
+-   repo: https://github.com/psf/black
+    rev: 24.1.1
+    hooks:
+    -   id: black
+        language_version: python3
+        args: [--line-length=100]
+
+-   repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+    -   id: isort
+        args: ["--profile", "black", "--line-length", "100"]
+
+-   repo: https://github.com/pycqa/flake8
+    rev: 7.0.0
+    hooks:
+    -   id: flake8
+        additional_dependencies: [
+            'flake8-docstrings',
+            'flake8-bugbear',
+            'flake8-comprehensions',
+        ]
+        args: [
+            "--max-line-length=100",
+            "--extend-ignore=E203",  # For black compatibility
+        ]
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.8.0
+    hooks:
+    -   id: mypy
+        additional_dependencies: [
+            'types-all',
+            'torch',
+            'numpy',
+        ]
+        args: [
+            "--ignore-missing-imports",
+            "--disallow-untyped-defs",
+            "--check-untyped-defs",
+            "--warn-redundant-casts",
+            "--warn-unused-ignores",
+            "--show-error-codes",
+        ]

DEVELOPMENT.md

@@ -0,0 +1,178 @@
+# Development Guide for MassNet-DDA
+
+This document outlines the development practices, testing procedures, and continuous integration setup for the MassNet-DDA project.
+
+## Testing Framework
+
+### Prerequisites
+
+Before running tests, ensure you have the required dependencies:
+
+```bash
+pip install pytest pytest-cov flake8 black isort mypy
+```
+
+### Running Tests
+
+We use pytest for our test suite. Here are common test commands:
+
+```bash
+# Run all tests with coverage report
+pytest tests/ --cov=XuanjiNovo
+
+# Run specific test file
+pytest tests/test_model.py
+
+# Run tests matching specific pattern
+pytest -k "test_model"
+
+# Run tests with detailed output
+pytest -v tests/
+
+# Run tests and generate HTML coverage report
+pytest tests/ --cov=XuanjiNovo --cov-report=html
+```
+
+### Test Structure
+
+- `tests/test_model.py`: Core model component tests
+- `tests/conftest.py`: Shared pytest fixtures and configurations
+
+## Code Quality Tools
+
+We maintain code quality through several automated tools:
+
+### Flake8 (Style Guide Enforcement)
+```bash
+# Check style
+flake8 XuanjiNovo tests
+
+# Common configuration in setup.cfg:
+# [flake8]
+# max-line-length = 100
+# exclude = .git,__pycache__,build,dist
+```
+
+### Black (Code Formatting)
+```bash
+# Check formatting
+black --check XuanjiNovo tests
+
+# Apply formatting
+black XuanjiNovo tests
+```
+
+### isort (Import Sorting)
+```bash
+# Check import sorting
+isort --check-only XuanjiNovo tests
+
+# Apply import sorting
+isort XuanjiNovo tests
+```
+
+### mypy (Static Type Checking)
+```bash
+# Run type checking
+mypy XuanjiNovo
+```
+
+## Continuous Integration
+
+We use GitHub Actions for automated testing and quality assurance. The CI pipeline runs on:
+- Push to main/master branches
+- Pull request to main/master branches
+
+### CI Pipeline Components
+
+1. **Test Job**
+   - Runs on Ubuntu with Python 3.8 and 3.9
+   - Tests with CUDA 11.8.0
+   - Generates coverage reports
+   - Uploads coverage to Codecov
+
+2. **Lint Job**
+   - Runs all code quality tools
+   - Ensures consistent code style
+   - Checks type annotations
+
+3. **Build Extensions Job**
+   - Builds C++ extensions
+   - Verifies CUDA compatibility
+   - Tests compiled components
+
+### CI Configuration
+
+The complete CI configuration is in `.github/workflows/ci.yml`. Key features:
+- Matrix testing across Python versions
+- CUDA toolkit installation
+- Dependency caching
+- Automated coverage reporting
+
+## Development Workflow
+
+1. **Setting Up Development Environment**
+   ```bash
+   # Clone repository
+   git clone https://github.com/your-username/MassNet-DDA.git
+   cd MassNet-DDA
+
+   # Create virtual environment
+   python -m venv venv
+   source venv/bin/activate  # or `venv\Scripts\activate` on Windows
+
+   # Install dependencies
+   pip install -r requirements.txt
+   pip install -r requirements-dev.txt  # Development dependencies
+   ```
+
+2. **Making Changes**
+   - Write tests for new features
+   - Ensure all tests pass locally
+   - Run code quality checks
+   - Update documentation as needed
+
+3. **Pre-commit Checks**
+   ```bash
+   # Run all checks
+   pytest tests/
+   flake8 XuanjiNovo tests
+   black --check XuanjiNovo tests
+   isort --check-only XuanjiNovo tests
+   mypy XuanjiNovo
+   ```
+
+## Test Coverage
+
+We aim to maintain high test coverage for critical components:
+- Model architecture and initialization
+- Training and inference pipelines
+- Data processing utilities
+- CUDA-specific functionality
+
+Current test coverage can be viewed:
+- Locally: Generate HTML report with `pytest --cov=XuanjiNovo --cov-report=html`
+- Online: Visit our Codecov dashboard
+
+## Adding New Tests
+
+When adding new features or fixing bugs:
+1. Create corresponding test file in `tests/`
+2. Use appropriate fixtures from `conftest.py`
+3. Include both positive and negative test cases
+4. Test edge cases and error conditions
+5. Add CUDA-specific tests where relevant
+
+## Debugging Tests
+
+For failing tests:
+```bash
+# Run with detailed output
+pytest -vv tests/
+
+# Run specific failing test with debug output
+pytest tests/test_model.py::test_name -vv
+
+# Drop into debugger on failure
+pytest --pdb tests/
+```

Dockerfile_cuda11

@@ -0,0 +1,19 @@
+FROM pytorch/pytorch:2.1.0-cuda11.8-cudnn8-runtime
+
+ENV CUDA_HOME=/usr/local/cuda
+ENV PATH=$CUDA_HOME/bin:$PATH
+ENV LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
+ENV GIT_PYTHON_REFRESH=quiet
+
+WORKDIR /app
+
+COPY . /app/
+
+RUN apt update && apt install -y gcc g++ ninja-build
+
+RUN cd /app/ctcdecode-master && pip install .
+
+RUN pip install -r /app/requirements-docker-cuda11.txt
+RUN cd /app/imputer-pytorch && pip install -e .
+
+ENTRYPOINT ["python", "-m", "XuanjiNovo.XuanjiNovo"]

Dockerfile_cuda12

@@ -0,0 +1,19 @@
+FROM pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime
+
+ENV CUDA_HOME=/usr/local/cuda
+ENV PATH=$CUDA_HOME/bin:$PATH
+ENV LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
+ENV GIT_PYTHON_REFRESH=quiet
+
+WORKDIR /app
+
+COPY . /app/
+
+RUN apt update && apt install -y gcc g++ ninja-build
+
+RUN cd /app/ctcdecode-master && pip install .
+
+RUN pip install -r /app/requirements-docker-cuda12.txt
+RUN cd /app/imputer-pytorch && pip install -e .
+
+ENTRYPOINT ["python", "-m", "XuanjiNovo.XuanjiNovo"]