Files
sientia-dataops-model-manager/docs/test-scenarios/06-linear-regression-nan-interpolation.json
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

40 lines
1021 B
JSON

{
"_description": "Regressão linear com tratamento de NaN por interpolação linear",
"experiment_run_id": 1006,
"variable_columns": [
"303-WIT-200(Value)"
],
"target_variable": "03CV020/CORRENTE_N_M1_PV(Value)",
"bucket_name": "model-training",
"file_name": "training_data.csv",
"line_separator": ",",
"decimal_separator": ".",
"date_column": "timestamp",
"date_format": "yyyy-MM-dd HH:mm:ss",
"train_size": 80,
"shuffle": true,
"random_state": 42,
"model_name": "Linear Regression",
"model_type": "linear_regression",
"data_model_kwargs": {
"lag_train": {
"303-WIT-200(Value)": 0
},
"lag_val": {
"303-WIT-200(Value)": 0
},
"nan_treatment": "linear interpolation",
"rem_static_win": false,
"static_threshold": null,
"start_date": null,
"end_date": null,
"support_filters": {},
"removed_intervals": []
},
"model_kwargs": {
"degree": 1,
"interaction_only": false,
"scaler_name": "None"
},
"opt_params": {}
}