mlenvdoctor 0.1.0__tar.gz → 0.1.2__tar.gz

mlenvdoctor-0.1.2/.github/workflows/ci.yml

@@ -0,0 +1,137 @@
+name: CI
+
+on:
+  push:
+    branches: [main, master, develop]
+  pull_request:
+    branches: [main, master, develop]
+  release:
+    types: [published]
+
+jobs:
+  test:
+    name: Test Python ${{ matrix.python-version }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Run linters
+        run: |
+          black --check src/ tests/
+          ruff check src/ tests/
+
+      - name: Run type checker
+        run: |
+          mypy src/ || true  # Optional for now
+
+      - name: Run tests
+        run: |
+          pytest --cov=mlenvdoctor --cov-report=xml --cov-report=term-missing
+
+      - name: Upload coverage
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./coverage.xml
+          flags: unittests
+          name: codecov-umbrella
+          fail_ci_if_error: false
+
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install black ruff mypy
+
+      - name: Check formatting
+        run: black --check src/ tests/
+
+      - name: Run ruff
+        run: ruff check src/ tests/
+
+      - name: Type check
+        run: mypy src/ || true
+
+  build:
+    name: Build package
+    runs-on: ubuntu-latest
+    needs: [test, lint]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Check package
+        run: |
+          pip install twine
+          twine check dist/*
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v3
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    name: Publish to PyPI
+    runs-on: ubuntu-latest
+    needs: [build]
+    if: github.event_name == 'release' && github.event.action == 'published'
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v3
+        with:
+          name: dist
+          path: dist/
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install twine
+        run: pip install twine
+
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+        run: twine upload dist/*

{mlenvdoctor-0.1.0 → mlenvdoctor-0.1.2}/.gitignore

@@ -139,3 +139,9 @@ environment-mlenvdoctor.yml
 Dockerfile.mlenvdoctor
 *.mlenvdoctor
 
+# Local docs / helper guides (not for distribution)
+QUICK_CLI_TEST.md
+CLI_TESTING_GUIDE.md
+TECHNICAL_IMPROVEMENTS.md
+TECHNICAL_IMPROVEMENTS_SUMMARY.md
+CHANGES_SUMMARY.md

mlenvdoctor-0.1.2/.pre-commit-config.yaml

@@ -0,0 +1,34 @@
+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: check-json
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: debug-statements
+      - id: mixed-line-ending
+
+  - repo: https://github.com/psf/black
+    rev: 23.12.1
+    hooks:
+      - id: black
+        language_version: python3
+        args: [--line-length=100]
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.9
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.8.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [types-all]
+        args: [--ignore-missing-imports]
+        exclude: ^tests/

mlenvdoctor-0.1.2/IMPROVEMENTS.md

@@ -0,0 +1,265 @@
+# 🚀 ML Environment Doctor - Improvement Recommendations
+
+This document outlines potential improvements for the ML Environment Doctor project, organized by priority and category.
+
+## 🔴 Critical Issues (Fix Immediately)
+
+### 1. Version Mismatch
+- **Issue**: `src/mlenvdoctor/__init__.py` has version `0.1.0` but `pyproject.toml` has `0.1.1`
+- **Fix**: Synchronize versions across all files
+- **Impact**: Version inconsistency can cause confusion and packaging issues
+
+### 2. Missing CI/CD Pipeline
+- **Issue**: No GitHub Actions workflow despite being mentioned in CHANGELOG
+- **Fix**: Create `.github/workflows/ci.yml` with:
+  - Automated testing on multiple Python versions (3.8, 3.9, 3.10, 3.11)
+  - Linting (black, ruff, mypy)
+  - Test coverage reporting
+  - Automated PyPI publishing on tags
+- **Impact**: No automated quality checks, harder to maintain
+
+### 3. Missing Pre-commit Configuration
+- **Issue**: Pre-commit hooks mentioned in CONTRIBUTING.md but no `.pre-commit-config.yaml`
+- **Fix**: Add pre-commit config with black, ruff, and other hooks
+- **Impact**: Inconsistent code quality, manual checks required
+
+## 🟠 High Priority Improvements
+
+### 4. Enhanced Logging System
+- **Current**: Only console output via Rich
+- **Improvement**: Add proper logging with levels (DEBUG, INFO, WARNING, ERROR)
+  - File logging option (`--log-file`)
+  - Structured logging for programmatic access
+  - Log rotation
+- **Benefits**: Better debugging, audit trails, production readiness
+
+### 5. Export/Report Functionality
+- **Current**: Only console output
+- **Improvement**: Add export options:
+  - `--json` flag for JSON output
+  - `--csv` flag for CSV export
+  - `--html` flag for HTML report
+  - `--output` flag to specify file path
+- **Benefits**: Integration with CI/CD, documentation, tracking over time
+
+### 6. Better Error Handling
+- **Current**: Basic try-except blocks, some errors not caught
+- **Improvement**:
+  - Custom exception classes (`MLEnvDoctorError`, `DiagnosticError`, etc.)
+  - Better error messages with actionable suggestions
+  - Error recovery where possible
+  - Stack traces in debug mode
+- **Benefits**: Better user experience, easier debugging
+
+### 7. Configuration File Support
+- **Current**: All settings are CLI flags
+- **Improvement**: Add `mlenvdoctor.toml` or `.mlenvdoctorrc` config file:
+  ```toml
+  [diagnostics]
+  full_scan = false
+  skip_checks = ["docker_gpu"]
+  
+  [fix]
+  default_stack = "trl-peft"
+  auto_install = false
+  
+  [docker]
+  default_base_image = "nvidia/cuda:12.4.0-devel-ubuntu22.04"
+  ```
+- **Benefits**: Better UX, repeatable configurations
+
+### 8. Requirements Locking
+- **Current**: Generates requirements with `>=` version constraints
+- **Improvement**: 
+  - Add `--lock` flag to generate exact versions using `pip-compile`
+  - Support for `requirements-lock.txt` with hashes
+  - Verify lock file integrity
+- **Benefits**: Reproducible environments, security
+
+## 🟡 Medium Priority Improvements
+
+### 9. Test Coverage Expansion
+- **Current**: Minimal tests, mostly smoke tests
+- **Improvement**:
+  - Unit tests for each diagnostic check
+  - Mock external dependencies (nvidia-smi, docker, etc.)
+  - Integration tests with test fixtures
+  - Test coverage target: >80%
+- **Benefits**: Confidence in changes, catch regressions
+
+### 10. Progress Indicators
+- **Current**: Basic spinners for some operations
+- **Improvement**:
+  - Progress bars for long operations (model downloads, installations)
+  - Estimated time remaining
+  - Download progress for model files
+  - Better visual feedback
+- **Benefits**: Better UX, users know what's happening
+
+### 11. Caching System
+- **Current**: No caching, re-runs all checks every time
+- **Improvement**:
+  - Cache diagnostic results (with TTL)
+  - Cache model downloads
+  - Cache version checks
+  - `--no-cache` flag to bypass
+- **Benefits**: Faster subsequent runs, reduced network usage
+
+### 12. Interactive Mode
+- **Current**: CLI flags only
+- **Improvement**: Add `--interactive` mode:
+  - Prompt for missing information
+  - Confirm before auto-fixing
+  - Step-by-step fix wizard
+  - Guided setup for beginners
+- **Benefits**: Better for new users, more control
+
+### 13. Multi-GPU Support
+- **Current**: Only checks first GPU
+- **Improvement**:
+  - Detect all GPUs
+  - Show per-GPU diagnostics
+  - Multi-GPU memory checks
+  - GPU topology detection
+- **Benefits**: Better for multi-GPU setups
+
+### 14. Windows-Specific Improvements
+- **Current**: Some paths may not work well on Windows
+- **Improvement**:
+  - Better Windows path handling
+  - Windows-specific CUDA detection
+  - PowerShell vs CMD compatibility
+  - Windows service detection
+- **Benefits**: Better Windows support
+
+### 15. Model Registry System
+- **Current**: Hardcoded models in `dockerize.py`
+- **Improvement**:
+  - External model registry (JSON/YAML)
+  - User-defined model templates
+  - Model discovery from Hugging Face
+  - Model recommendations based on GPU
+- **Benefits**: Extensibility, easier updates
+
+## 🟢 Nice-to-Have Features
+
+### 16. Plugin System
+- **Current**: Monolithic codebase
+- **Improvement**:
+  - Plugin architecture for custom checks
+  - Plugin registry
+  - Community plugins
+- **Benefits**: Extensibility, community contributions
+
+### 17. Telemetry (Opt-in)
+- **Current**: No usage tracking
+- **Improvement**:
+  - Opt-in anonymous usage statistics
+  - Error reporting (with user consent)
+  - Feature usage analytics
+- **Benefits**: Understand user needs, prioritize features
+
+### 18. Documentation Improvements
+- **Current**: Basic README
+- **Improvement**:
+  - API documentation (Sphinx/MkDocs)
+  - Video tutorials
+  - Example workflows
+  - Troubleshooting guide
+  - FAQ section
+- **Benefits**: Better onboarding, reduced support burden
+
+### 19. Performance Optimizations
+- **Current**: Sequential checks
+- **Improvement**:
+  - Parallel execution of independent checks
+  - Async I/O for network checks
+  - Faster version detection
+- **Benefits**: Faster diagnostics
+
+### 20. Additional Diagnostic Checks
+- **Current**: Basic checks
+- **Improvement**:
+  - Python version compatibility
+  - Virtual environment detection
+  - Conda environment detection
+  - Jupyter notebook compatibility
+  - VS Code / PyCharm integration
+  - WSL2 GPU support
+  - Cloud GPU detection (AWS, GCP, Azure)
+- **Benefits**: More comprehensive diagnostics
+
+### 21. Docker Improvements
+- **Current**: Basic Dockerfile generation
+- **Improvement**:
+  - Docker Compose templates
+  - Multi-stage builds
+  - BuildKit optimizations
+  - Health checks
+  - Volume management
+- **Benefits**: Production-ready containers
+
+### 22. Integration with ML Frameworks
+- **Current**: PyTorch-focused
+- **Improvement**:
+  - TensorFlow support
+  - JAX support
+  - ONNX Runtime checks
+  - MLflow integration
+- **Benefits**: Broader framework support
+
+### 23. Benchmark Suite
+- **Current**: Basic GPU benchmark
+- **Improvement**:
+  - Comprehensive benchmark suite
+  - Compare against baseline
+  - Performance regression detection
+  - Benchmark history
+- **Benefits**: Performance monitoring
+
+### 24. Environment Comparison
+- **Current**: Single environment diagnostics
+- **Improvement**:
+  - Compare two environments
+  - Diff diagnostics
+  - Environment migration guide
+- **Benefits**: Easier environment management
+
+### 25. Automated Fixes
+- **Current**: Generates files, user installs
+- **Improvement**:
+  - Automatic installation with confirmation
+  - Rollback on failure
+  - Dry-run mode
+  - Fix verification
+- **Benefits**: True auto-fix capability
+
+## 📊 Implementation Priority Matrix
+
+| Priority | Effort | Impact | Recommendation |
+|----------|--------|--------|----------------|
+| Critical | Low | High | Fix version mismatch, add CI/CD |
+| High | Medium | High | Add logging, export, config files |
+| Medium | Medium | Medium | Expand tests, add caching, interactive mode |
+| Low | High | Medium | Plugin system, telemetry, framework support |
+
+## 🎯 Quick Wins (Low Effort, High Impact)
+
+1. **Fix version mismatch** (5 min)
+2. **Add CI/CD pipeline** (1-2 hours)
+3. **Add pre-commit config** (30 min)
+4. **Add JSON export** (1-2 hours)
+5. **Improve error messages** (2-3 hours)
+6. **Add progress bars** (2-3 hours)
+
+## 📝 Notes
+
+- Consider breaking into phases: Phase 1 (Critical + High Priority), Phase 2 (Medium), Phase 3 (Nice-to-have)
+- Community feedback should guide priority
+- Some features may require breaking changes (version 0.2.0+)
+- Consider backward compatibility when adding features
+
+---
+
+**Last Updated**: 2024
+**Status**: Recommendations for project improvement

{mlenvdoctor-0.1.0 → mlenvdoctor-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlenvdoctor
-Version: 0.1.0
+Version: 0.1.2
 Summary: Diagnose & fix ML environments for LLM fine-tuning
 Author: ML Environment Doctor Contributors
 License: MIT
@@ -20,6 +20,7 @@ Requires-Python: >=3.8
 Requires-Dist: packaging>=23.0
 Requires-Dist: psutil>=5.9.0
 Requires-Dist: rich>=13.0.0
+Requires-Dist: tomli>=2.0.0; python_version < '3.11'
 Requires-Dist: typer>=0.9.0
 Provides-Extra: dev
 Requires-Dist: black>=23.0.0; extra == 'dev'
@@ -34,7 +35,7 @@ Description-Content-Type: text/markdown
 
 [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![PyPI version](https://badge.fury.io/py/mlenvdoctor.svg)](https://badge.fury.io/py/mlenvdoctor)
+[![PyPI](https://img.shields.io/pypi/v/mlenvdoctor.svg)]([https://pypi.org/project/mlenvdoctor/])
 
 > **Single command fixes 90% of "my torch.cuda.is_available() is False" issues.**
 

{mlenvdoctor-0.1.0 → mlenvdoctor-0.1.2}/README.md

@@ -2,7 +2,7 @@
 
 [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![PyPI version](https://badge.fury.io/py/mlenvdoctor.svg)](https://badge.fury.io/py/mlenvdoctor)
+[![PyPI](https://img.shields.io/pypi/v/mlenvdoctor.svg)]([https://pypi.org/project/mlenvdoctor/])
 
 > **Single command fixes 90% of "my torch.cuda.is_available() is False" issues.**