ba9eb3d7c7
- 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.
2.5 KiB
2.5 KiB
Insert a new experiment run
-- Optional: remove a previous run with the same id
DELETE FROM public.experiment_run WHERE experiment_run_id = 1001;
INSERT INTO public.experiment_run
(experiment_name, run_name, username, status, error_message, created_at,
updated_at, bucket_name, file_name, request_data, orchestrator_response_data)
VALUES(
'test-experiment-name',
'test-run-name',
'test-username',
'ORCHESTRATOR_WAITING_PROC',
null,
now(),
now(),
'model-training',
'training_data.csv',
'{"experiment_run_id":1001,"variable_columns":["feature_a","feature_b"],"target_variable":"target","bucket_name":"model-training","file_name":"training_data.csv","line_separator":",","decimal_separator":".","train_size":80,"shuffle":true,"model_name":"Linear Regression","model_type":"linear_regression","data_model_kwargs":{"lag_train":{"feature_a":0,"feature_b":0},"lag_val":{"feature_a":0,"feature_b":0},"nan_treatment":"drop"},"model_kwargs":{"degree":1,"scaler_name":"Standard Scaler"},"opt_params":{}}',
null
);
Upload the input dataset to MinIO
mc cp input_dataset.csv suse/model-training/training-sample-dataset-1001.csv
Temporal input payload sample
Keys match TrainModelParams.from_dict in model_manager/utils/models/train_model_params.py: every field passed to _check_none must be present, including date_column; model_metadata must be non-empty for validate_business_rules(). You may omit date_format (defaults to yyyy-MM-dd HH:mm:ss). Omit optional keys (random_state, val_file_name, model_id) when defaults or None apply.
{
"experiment_run_id": 1001,
"variable_columns": ["feature_a", "feature_b"],
"target_variable": "target",
"bucket_name": "model-training",
"file_name": "training-sample-dataset-1001.csv",
"line_separator": ",",
"decimal_separator": ".",
"date_column": "timestamp",
"train_size": 80,
"shuffle": true,
"random_state": 42,
"model_name": "test-runtime-linear-regression-model",
"model_type": "linear_regression",
"data_model_kwargs": {
"lag_train": {
"feature_a": 0,
"feature_b": 0
},
"lag_val": {
"feature_a": 0,
"feature_b": 0
},
"nan_treatment": "drop",
"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": "Standard Scaler"
},
"opt_params": {}
}