fix(ml): complete ML pipeline fixes and setup

Browse source

- Fix CCI indicator to use HLC prices instead of close only
- Parse datetime column when loading enriched CSV
- Strip timezone from annotation timestamps
- Fix TA-Lib pattern names (CDL3WHITESOLDIERS, CDL3BLACKCROWS)
- Exclude programmatic label columns from training features
- Fix classification report to handle missing classes
- Update MLflow tracking to use localhost:5000
- Grant PostgreSQL permissions to ml_user

Pipeline now runs successfully end-to-end:
- Feature engineering: 2543 rows, 31 columns
- Annotation ingestion: 286 samples
- Training: 89.47% test accuracy with Random Forest

...

This commit is contained in:

Marko Djordjevic 2026-02-15 21:29:54 +01:00

parent ceb4103ec4

commit aa81d4f3d0

348 changed files with 1327 additions and 11 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

BIN

services/ml/models/best_model.pkl Normal file

View file

Binary file not shown.