Vanszs
a55148f232
Add M1+M15 multi-timeframe SMC scalping training pipeline (GPU XGBoost), then fix data-leakage and non-stationarity issues found in a skeptical audit. Pipeline: - src/triple_barrier.py: TP/SL/time labeling (ATR-scaled, asymmetric RR) - src/multi_tf_dataset.py: M1 base + M15 HTF context, point-in-time join_asof (only CLOSED M15 candles visible to each M1 bar - proven no leakage) - src/economic_calendar.py: point-in-time forecast/actual/surprise provider - src/smc_polars.py: add premium/discount + displacement SMC features - scripts/train_multitf_scalper.py: GPU (device=cuda) training + walk-forward - scripts/download_training_data.py: 1y data downloader Leakage / robustness fixes (audit): - CRITICAL: order block signal was written to the ORIGIN bar (future info); now assigned at the CONFIRMATION bar -> matches live conditions - replace non-stationary absolute features (ema_9/21, macd*) with scale-free forms (ema*_dist_atr, ema_spread_atr, macd_*_bps) -> valid at any price level - drop constant-zero calendar features from defaults (recurring provider has no real values); re-add when a real calendar CSV is configured - walk-forward + train/test now embargo the max_holding label horizon and drop warmup rows (NaN->0 artifacts) - news calendar features remain point-in-time (actual only at/after release) Honest result: after fixes the spurious +2.35% edge collapses to ~random (AUC 0.49). The prior edge was caused by the order-block look-ahead. Pipeline is now leakage-free; a real edge still needs more M1 history / better features. Also: test infra (pytest.ini asyncio, hmmlearn), TRAIN_BARS, cleanup of dead modules. 14 tests pass.
116 lines
1.4 KiB
Plaintext
116 lines
1.4 KiB
Plaintext
# Environment and secrets
|
|
.env
|
|
.env.local
|
|
.env.*.local
|
|
*.pem
|
|
*.key
|
|
credentials.json
|
|
|
|
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
*$py.class
|
|
*.so
|
|
.Python
|
|
build/
|
|
develop-eggs/
|
|
dist/
|
|
downloads/
|
|
eggs/
|
|
.eggs/
|
|
lib/
|
|
lib64/
|
|
parts/
|
|
sdist/
|
|
var/
|
|
wheels/
|
|
*.egg-info/
|
|
.installed.cfg
|
|
*.egg
|
|
|
|
# Virtual environments
|
|
venv/
|
|
ENV/
|
|
env/
|
|
.venv/
|
|
|
|
# IDE
|
|
.idea/
|
|
.vscode/
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
|
|
# Logs (ignore all content)
|
|
logs/
|
|
*.log
|
|
|
|
# Data files (large)
|
|
data/market_data/
|
|
data/trade_logs/trades/*.csv
|
|
data/trade_logs/ml_data/*.csv
|
|
|
|
# Models (large binary files)
|
|
models/*.pkl
|
|
models/*.joblib
|
|
models/*.h5
|
|
|
|
# Backtest results (generated run artifacts)
|
|
backtests/results/*.csv
|
|
backtests/*_results/
|
|
backtests/**/*.xlsx
|
|
backtests/**/*.log
|
|
backtests/ml_v3/training_log*.txt
|
|
backtests/ml_v3/*.pkl
|
|
backtests/*_results/*.pkl
|
|
|
|
# Node modules (dashboard)
|
|
web-dashboard/node_modules/
|
|
web-dashboard/.next/
|
|
web-dashboard/out/
|
|
|
|
# OS files
|
|
.DS_Store
|
|
Thumbs.db
|
|
desktop.ini
|
|
|
|
# Temporary files
|
|
*.tmp
|
|
*.temp
|
|
*.bak
|
|
|
|
# Jupyter
|
|
.ipynb_checkpoints/
|
|
|
|
# Docker
|
|
docker/data/
|
|
|
|
# Archive
|
|
archive/
|
|
|
|
# Runtime files
|
|
bot.pid
|
|
bot_output.log
|
|
nul
|
|
data/bot.lock
|
|
data/bot_status.json
|
|
data/signal_persistence.json
|
|
data/model_metrics.json
|
|
|
|
# Stray analysis output dumps
|
|
*_analysis_output.txt
|
|
training_output.log
|
|
|
|
# Claude Code local settings
|
|
.claude/
|
|
backtests/.claude/
|
|
|
|
# Screenshots
|
|
*.png
|
|
|
|
# Kiro CLI local settings
|
|
.kiro/
|
|
|
|
# Generated multi-TF dataset cache
|
|
data/multitf_dataset.parquet
|