21in7 30ddb2fef4 feat(ml): relax training thresholds for 5-10x more training samples ...

Add TRAIN_* constants (signal_threshold=2, adx=15, vol_mult=1.5, neg_ratio=3)
as dataset_builder defaults. Remove hardcoded negative_ratio=5 from all callers.
Bot entry conditions unchanged (config.py strict values).

WF 5-fold results (all symbols AUC 0.91+):
- XRPUSDT: 0.9216 ± 0.0052
- SOLUSDT:  0.9174 ± 0.0063
- DOGEUSDT: 0.9222 ± 0.0085

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-21 19:38:15 +09:00

..

__init__.py

chore: 프로젝트 초기 설정 및 의존성 추가

2026-03-01 12:48:03 +09:00

test_bot.py

fix: address critical code review issues (PnL double recording, sync HTTP, race conditions)

2026-03-19 23:03:52 +09:00

test_config.py

fix: address code review round 2 — 9 issues (2 critical, 3 important, 4 minor)

2026-03-21 17:26:15 +09:00

test_dashboard_api.py

fix(dashboard): address code review — auth, DB stability, idempotency, UI fixes

2026-03-20 00:00:16 +09:00

test_data_stream.py

feat: add position monitor logging with real-time price tracking

2026-03-03 20:36:46 +09:00

test_dataset_builder.py

chore: deprecate legacy dataset generation, remove stale comparison test

2026-03-21 18:38:07 +09:00

test_exchange.py

fix: address code review round 2 — 9 issues (2 critical, 3 important, 4 minor)

2026-03-21 17:26:15 +09:00

test_fetch_history.py

feat: add upsert_parquet to accumulate OI/funding data incrementally

2026-03-02 14:09:36 +09:00

test_indicators.py

feat: add signal score detail to bot logs for HOLD reason debugging

2026-03-07 02:20:44 +09:00

test_label_builder.py

feat: implement ML filter with LightGBM for trading signal validation

2026-03-01 17:07:18 +09:00

test_log_parser.py

feat: add multi-symbol dashboard support (parser, API, UI)

2026-03-06 16:19:16 +09:00

test_ml_features.py

fix: resolve 6 warning issues from code review

2026-03-16 22:44:40 +09:00

test_ml_filter.py

fix: resolve ML filter dtype error and missing BTC/ETH correlation features

2026-03-07 00:08:23 +09:00

test_ml_pipeline_fixes.py

feat(ml): relax training thresholds for 5-10x more training samples

2026-03-21 19:38:15 +09:00

test_mlx_filter.py

fix: test_mlx_filter _make_X를 FEATURE_COLS 기반으로 수정 — 피처 확장 후 input_dim 불일치 해소

2026-03-02 00:34:21 +09:00

test_risk_manager.py

fix: address code review round 2 — 9 issues (2 critical, 3 important, 4 minor)

2026-03-21 17:26:15 +09:00

test_weekly_report.py

fix(weekly-report): calculate combined metrics directly from trades

2026-03-17 20:12:42 +09:00