da30ef19ed
Architecture Docker (8 services), FastAPI, TimescaleDB, Redis, Streamlit. Stratégies : scalping, intraday, swing. MLEngine + RegimeDetector (HMM). BacktestEngine + WalkForwardAnalyzer + Optuna optimizer. Routes API complètes dont /optimize async. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
25 lines
495 B
Plaintext
25 lines
495 B
Plaintext
# ============================================================
|
|
# ML - Container trading-ml (Machine Learning engine)
|
|
# ============================================================
|
|
|
|
# Serveur ASGI
|
|
uvicorn[standard]==0.24.0
|
|
|
|
# Machine Learning
|
|
scikit-learn==1.3.2
|
|
xgboost==2.0.3
|
|
lightgbm==4.1.0
|
|
hmmlearn==0.3.0
|
|
|
|
# Optimisation
|
|
optuna==3.5.0
|
|
|
|
# Time Series
|
|
statsmodels==0.14.1
|
|
|
|
# Technical Analysis (feature engineering, pandas-based)
|
|
ta==0.11.0
|
|
|
|
# Market Data (pour entraînement)
|
|
yfinance>=1.0.0
|