- Updated FastAPI /training/start endpoint to extract X-User-ID header via get_user_id() dependency
- Modified _run_training_background to accept and use user_id parameter
- Added MLflow experiment setup with user scoping: experiments are named user_{user_id}_training when user_id is provided, falling back to default experiment name otherwise
- Updated database record insertion to store scoped experiment name
- Updated training/train.py train() function to accept user_id parameter and use it for experiment naming
- Mark task 14.2 as complete in tasks.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Fix CCI indicator to use HLC prices instead of close only
- Parse datetime column when loading enriched CSV
- Strip timezone from annotation timestamps
- Fix TA-Lib pattern names (CDL3WHITESOLDIERS, CDL3BLACKCROWS)
- Exclude programmatic label columns from training features
- Fix classification report to handle missing classes
- Update MLflow tracking to use localhost:5000
- Grant PostgreSQL permissions to ml_user
Pipeline now runs successfully end-to-end:
- Feature engineering: 2543 rows, 31 columns
- Annotation ingestion: 286 samples
- Training: 89.47% test accuracy with Random Forest
- Create RandomForestModel and XGBoostModel wrappers with class weight support
- Implement temporal and random train/val/test splitting
- Add MLflow experiment tracking with full parameter and metric logging
- Create evaluation module for confusion matrix, feature importance, and classification reports
- Implement model training with sklearn/xgboost flavor logging and optional registry registration
- Store training run metadata in PostgreSQL
- Wire training stage into pipeline.py orchestrator
- Support both RandomForest and XGBoost models with configurable hyperparameters
