Marko Djordjevic 40d6d1739e fix(ml): add windowed feature flattening for inference parity ... The model was trained on 94-candle sliding windows flattened to 2820 features (94 candles x 30 features). Inference was sending raw per-candle features (27 columns). Changes: - Rewrite preprocessing to return (X, window_times) tuple - Add sliding window creation with correct feature ordering - Fill missing columns (average, barCount) with 0 for feature parity - Fill NaN from indicator warmup with 0 instead of dropping rows - Always compute all indicators (including MFI) for feature parity - Update predict and batch predict endpoints for new signature		2026-02-15 22:07:06 +01:00
..
.dvc	feat(ml): add database schema, config parser, and DVC setup	2026-02-15 12:08:53 +01:00
app	fix(ml): add windowed feature flattening for inference parity	2026-02-15 22:07:06 +01:00
candle_ml.egg-info	feat(ml): add TA-Lib annotation generation and import workflow	2026-02-15 19:18:28 +01:00
config	fix(ml): complete ML pipeline fixes and setup	2026-02-15 21:29:54 +01:00
features	fix(ml): handle missing volume data and skip volume-dependent indicators	2026-02-15 21:56:14 +01:00
migrations	feat(ml): add database schema, config parser, and DVC setup	2026-02-15 12:08:53 +01:00
mlruns	fix(frontend): update ModelInfoResponse types to match backend structure	2026-02-15 21:39:38 +01:00
models	fix(ml): complete ML pipeline fixes and setup	2026-02-15 21:29:54 +01:00
training	fix(ml): complete ML pipeline fixes and setup	2026-02-15 21:29:54 +01:00
.dvcignore	feat(ml): add database schema, config parser, and DVC setup	2026-02-15 12:08:53 +01:00
Dockerfile	feat: add ML service scaffolding with Python FastAPI, Docker, and MLflow setup	2026-02-15 11:58:31 +01:00
generate_talib_annotations.py	fix(ml): handle date strings in TA-Lib annotation generator	2026-02-15 19:30:38 +01:00
pipeline.py	feat(ml): implement training stage with MLflow tracking and model wrappers	2026-02-15 14:22:19 +01:00
pyproject.toml	feat(ml): add database schema, config parser, and DVC setup	2026-02-15 12:08:53 +01:00
talib_annotations.json	fix(scripts): add created_at timestamps to annotation import	2026-02-15 19:36:55 +01:00
uv.lock	feat(ml): add TA-Lib annotation generation and import workflow	2026-02-15 19:18:28 +01:00