df43dd90cb
FASE 0 - Preparación y Purga: - Archived 21 completed tasks to _archive/2026-01/ - Marked 4 docs as DEPRECATED - Created 3 baseline coherence reports FASE 1 - DDL-Backend Coherence: - audit.types.ts: +4 types (SystemEvent, TradingAudit, ApiRequestLog, DataAccessLog) - investment.types.ts: +4 types (RiskQuestionnaire, WithdrawalRequest, DailyPerformance, DistributionHistory) - entity.types.ts: +5 types (Symbol, TradingBot, TradingSignal, TradingMetrics, PaperBalance) FASE 2 - Backend-Frontend Coherence: - investmentStore.ts: New Zustand store with 20+ actions - mlStore.ts: New Zustand store with signal caching - alerts.service.ts: New service with 15 functions FASE 3 - Documentation: - OQI-009: Updated to 100% coverage, added ET-MKT-004-productos.md - OQI-010: Created full structure (STATUS.md, ROADMAP-MT4.md, ET-MT4-001-gateway.md) Coherence Baseline Established: - DDL-Backend: 31% (target 95%) - Backend-Frontend: 72% (target 85%) - Global: 39.6% (target 90%) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1.6 KiB
1.6 KiB
03-PLANEACION - ML Data Migration & Model Training
Fecha: 2026-01-25
Fase: PLANEACION (P)
Estado: COMPLETADA
1. Plan de Ejecucion
Fase 1: Preparacion Ambiente Python
- Crear venv en WSL:
~/venvs/data-service/ - Instalar dependencias: aiohttp, asyncpg, pandas, numpy, python-dotenv
Fase 2: Carga de Datos
- Crear script
fetch_polygon_data.py - Configurar API key de Polygon
- Ejecutar carga para 6 tickers x 365 dias
- Validar datos insertados
Fase 3: Migracion ML Engine
- Crear
apps/ml-engine/src/data/database.py - Implementar PostgreSQLConnection con metodos:
get_ticker_data()execute_query()con traduccion MySQL→PostgreSQL
- Actualizar
config/database.yaml - Crear
.envcon credenciales
Fase 4: Entrenamiento Modelos
- Instalar dependencias ML: xgboost, scikit-learn, joblib
- Ejecutar
train_attention_models.py - Validar metricas de modelos
- Generar reporte de entrenamiento
Fase 5: Documentacion
- Actualizar DATABASE_INVENTORY.yml
- Actualizar ML_INVENTORY.yml
- Crear carpeta TASK con CAPVED
2. Estimacion de Entregables
| Entregable | Complejidad | Archivos |
|---|---|---|
| fetch_polygon_data.py | MEDIA | 1 |
| database.py | ALTA | 1 |
| Config files | BAJA | 3 |
| 12 modelos | ALTA | 36 |
| Documentacion | MEDIA | 4 |
3. Orden de Ejecucion
[1] Ambiente Python → [2] Datos → [3] Migration → [4] Training → [5] Docs
↓ ↓ ↓ ↓ ↓
venv OK 469K bars database.py 12 modelos TASK folder