Commit Graph

4 Commits

Author SHA1 Message Date
vitor-aignosi
ba9eb3d7c7 feat: require date_column in training parameters and update documentation
- Made `date_column` a required field in `TrainModelParams`, ensuring it must be present in the input data.
- Updated related documentation in `input-sample.md`, `README.md`, and various test scenarios to reflect the change in requirement.
- Adjusted the handling of `date_format` to default to `yyyy-MM-dd HH:mm:ss` if omitted, enhancing usability.
- Refined test scenarios to include new examples and ensure compliance with the updated parameter structure.

These changes improve the robustness of the model training workflow and clarify the expectations for input data.
2026-05-05 08:35:12 -03:00
vitor-aignosi
6bd30e3328 feat: enhance test scenarios and configuration for regression models
- Updated `pyproject.toml` to include new linting rules for end-to-end tests.
- Modified `requirements-dev.txt` to add dependencies for E2E testing with `testcontainers` and `requests`.
- Refactored multiple JSON test scenario files to standardize structure, including new fields for `experiment_run_id`, `bucket_name`, and `file_name`.
- Improved model training parameters in `train_model_params.py` to use `experiment_name` directly.
- Adjusted `data_manager_repository.py` to utilize the updated `experiment_name` for logging.

These changes improve the organization and clarity of regression model tests and enhance the overall testing framework.
2026-05-04 11:11:16 -03:00
Kou Kinoshita
b6eb346a0b SIENTIAPDE-1579: Added test case scenario to test filter, also updated old scenarios 2026-02-18 14:24:17 -03:00
Bruno Domingues
06fd08dc70 SIENTIAPDE-1430: Introduce comprehensive integration testing with JSON-based scenarios and detailed README documentation. Enhance training workflow to support advanced model configurations, including polynomial regression with mandatory scaler validation. Ensure robust prediction handling by calculating training predictions (y_train_pred) before denormalization and automatically configuring datetime indices for time-series operations. 2025-12-18 17:05:10 -03:00